Merge 956ec96d51 into 0031544e14

Merge pull request #6552 from hyiip/main
Migrate to claude 4
2025-10-08 19:16:37 +08:00 · 2025-07-11 14:57:35 +03:00 · 2025-07-08 23:35:22 +08:00 · 2025-07-08 23:34:38 +08:00 · 2025-07-07 18:20:04 +08:00 · 2025-07-07 18:18:46 +08:00
53 changed files with 16834 additions and 1950 deletions
--- a/.env.template
+++ b/.env.template
@ -81,3 +81,9 @@ SILICONFLOW_API_KEY=

 ### siliconflow Api url (optional)
 SILICONFLOW_URL=
+
+### 302.AI Api key (optional)
+AI302_API_KEY=
+
+### 302.AI Api url (optional)
+AI302_URL=
--- a/README.md
+++ b/README.md
@ -4,16 +4,12 @@
  <img src="https://github.com/user-attachments/assets/83bdcc07-ae5e-4954-a53a-ac151ba6ccf3" width="1000" alt="icon"/>
 </a>

-
-
-
 <h1 align="center">NextChat</h1>

 English / [简体中文](./README_CN.md)

 <a href="https://trendshift.io/repositories/5973" target="_blank"><img src="https://trendshift.io/api/badge/repositories/5973" alt="ChatGPTNextWeb%2FChatGPT-Next-Web | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>

-
 ✨ Light and Fast AI Assistant,with Claude, DeepSeek, GPT4 & Gemini Pro support.

 [![Saas][Saas-image]][saas-url]
@ -24,7 +20,6 @@ English / [简体中文](./README_CN.md)

 [NextChatAI](https://nextchat.club?utm_source=readme) / [iOS APP](https://apps.apple.com/us/app/nextchat-ai/id6743085599) / [Web App Demo](https://app.nextchat.club) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [Enterprise Edition](#enterprise-edition)

-
 [saas-url]: https://nextchat.club?utm_source=readme
 [saas-image]: https://img.shields.io/badge/NextChat-Saas-green?logo=microsoftedge
 [web-url]: https://app.nextchat.club/
@ -40,23 +35,32 @@ English / [简体中文](./README_CN.md)

 </div>

+## ❤️ Sponsor AI API
+
+<a href='https://302.ai/'>
+  <img src="https://github.com/user-attachments/assets/a03edf82-2031-4f23-bdb8-bfc0bfd168a4" width="100%" alt="icon"/>
+</a>
+
+[302.AI](https://302.ai/) is a pay-as-you-go AI application platform that offers the most comprehensive AI APIs and online applications available.
+
 ## 🥳 Cheer for NextChat iOS Version Online!
+
 > [👉 Click Here to Install Now](https://apps.apple.com/us/app/nextchat-ai/id6743085599)

 > [❤️ Source Code Coming Soon](https://github.com/ChatGPTNextWeb/NextChat-iOS)

 ![Github iOS Image](https://github.com/user-attachments/assets/e0aa334f-4c13-4dc9-8310-e3b09fa4b9f3)

- 
 ## 🫣 NextChat Support MCP !
+
 > Before build, please set env ENABLE_MCP=true

 <img src="https://github.com/user-attachments/assets/d8851f40-4e36-4335-b1a4-ec1e11488c7e"/>

-
 ## Enterprise Edition

 Meeting Your Company's Privatization and Customization Deployment Requirements:
+
 - **Brand Customization**: Tailored VI/UI to seamlessly align with your corporate brand image.
 - **Resource Integration**: Unified configuration and management of dozens of AI resources by company administrators, ready for use by team members.
 - **Permission Control**: Clearly defined member permissions, resource permissions, and knowledge base permissions, all controlled via a corporate-grade Admin Panel.
@ -73,7 +77,6 @@ For enterprise inquiries, please contact: **business@nextchat.dev**

 ![More](./docs/images/more.png)

-
 ## Features

 - **Deploy for free with one-click** on Vercel in under 1 minute
@ -109,6 +112,7 @@ For enterprise inquiries, please contact: **business@nextchat.dev**
 - [ ] local knowledge base

 ## What's New
+
 - 🚀 v2.15.8 Now supports Realtime Chat [#5672](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5672)
 - 🚀 v2.15.4 The Application supports using Tauri fetch LLM API, MORE SECURITY! [#5379](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5379)
 - 🚀 v2.15.0 Now supports Plugins! Read this: [NextChat-Awesome-Plugins](https://github.com/ChatGPTNextWeb/NextChat-Awesome-Plugins)
@ -312,10 +316,12 @@ To control custom models, use `+` to add a custom model, use `-` to hide a model
 User `-all` to disable all default models, `+all` to enable all default models.

 For Azure: use `modelName@Azure=deploymentName` to customize model name and deployment name.
+
 > Example: `+gpt-3.5-turbo@Azure=gpt35` will show option `gpt35(Azure)` in model list.
 > If you only can use Azure model, `-all,+gpt-3.5-turbo@Azure=gpt35` will `gpt35(Azure)` the only option in model list.

 For ByteDance: use `modelName@bytedance=deploymentName` to customize model name and deployment name.
+
 > Example: `+Doubao-lite-4k@bytedance=ep-xxxxx-xxx` will show option `Doubao-lite-4k(ByteDance)` in model list.

 ### `DEFAULT_MODEL` （optional）
@ -332,6 +338,7 @@ Add additional models to have vision capabilities, beyond the default pattern ma
 ### `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：
+
 - Each address must be a complete endpoint
  > `https://xxxx/yyy`
 - Multiple addresses are connected by ', '
@ -348,7 +355,6 @@ Stability API key.

 Customize Stability API url.

-
 ### `ENABLE_MCP` (optional)

 Enable MCP（Model Context Protocol）Feature
@ -361,13 +367,20 @@ SiliconFlow API Key.

 SiliconFlow API URL.

+### `AI302_API_KEY` (optional)
+
+302.AI API Key.
+
+### `AI302_URL` (optional)
+
+302.AI API URL.
+
 ## Requirements

 NodeJS >= 18, Docker >= 20

 ## Development

-
 [![Open in Gitpod](https://gitpod.io/button/open-in-gitpod.svg)](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web)

 Before starting development, you must create a new `.env.local` file at project root, and place your api key into it:
@ -391,7 +404,6 @@ yarn dev

 ## Deployment

-
 ### Docker (Recommended)

 ```shell
@ -449,8 +461,6 @@ bash <(curl -s https://raw.githubusercontent.com/Yidadaa/ChatGPT-Next-Web/main/s
 - [How to use Vercel (No English)](./docs/vercel-cn.md)
 - [User Manual (Only Chinese, WIP)](./docs/user-manual-cn.md)

-
-
 ## Translation

 If you want to add a new translation, read this [document](./docs/translation.md).
@ -461,8 +471,6 @@ If you want to add a new translation, read this [document](./docs/translation.md

 ## Special Thanks

-
-
 ### Contributors

 <a href="https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/graphs/contributors">
--- a/README_CN.md
+++ b/README_CN.md
@ -14,9 +14,18 @@

 </div>

+## Sponsor AI API
+
+<a href='https://302.ai/'>
+  <img src="https://github.com/user-attachments/assets/d8c0c513-1e18-4d3b-a2a9-ff3696aec0d4" width="100%" alt="icon"/>
+</a>
+
+[302.AI](https://302.ai/) 是一个按需付费的AI应用平台，提供市面上最全的AI API和AI在线应用。
+
 ## 企业版

 满足您公司私有化部署和定制需求
+
 - **品牌定制**：企业量身定制 VI/UI，与企业品牌形象无缝契合
 - **资源集成**：由企业管理人员统一配置和管理数十种 AI 资源，团队成员开箱即用
 - **权限管理**：成员权限、资源权限、知识库权限层级分明，企业级 Admin Panel 统一控制
@ -29,7 +38,6 @@

 <img width="300" src="https://github.com/user-attachments/assets/bb29a11d-ff75-48a8-b1f8-d2d7238cf987">

-
 ## 开始使用

 1. 准备好你的 [OpenAI API Key](https://platform.openai.com/account/api-keys);
@ -201,7 +209,6 @@ DeepSeek Api Key.

 DeepSeek Api Url.

-
 ### `HIDE_USER_API_KEY` （可选）

 如果你不想让用户自行填入 API Key，将此环境变量设置为 1 即可。
@ -221,6 +228,7 @@ DeepSeek Api Url.
 ### `WHITE_WEBDAV_ENDPOINTS` (可选)

 如果你想增加允许访问的webdav服务地址，可以使用该选项，格式要求：
+
 - 每一个地址必须是一个完整的 endpoint
  > `https://xxxx/xxx`
 - 多个地址以`,`相连
@ -233,12 +241,13 @@ DeepSeek Api Url.
 用来控制模型列表，使用 `+` 增加一个模型，使用 `-` 来隐藏一个模型，使用 `模型名=展示名` 来自定义模型的展示名，用英文逗号隔开。

 在Azure的模式下，支持使用`modelName@Azure=deploymentName`的方式配置模型名称和部署名称(deploy-name)
+
 > 示例：`+gpt-3.5-turbo@Azure=gpt35`这个配置会在模型列表显示一个`gpt35(Azure)`的选项。
 > 如果你只能使用Azure模式，那么设置 `-all,+gpt-3.5-turbo@Azure=gpt35` 则可以让对话的默认使用 `gpt35(Azure)`

 在ByteDance的模式下，支持使用`modelName@bytedance=deploymentName`的方式配置模型名称和部署名称(deploy-name)
-> 示例: `+Doubao-lite-4k@bytedance=ep-xxxxx-xxx`这个配置会在模型列表显示一个`Doubao-lite-4k(ByteDance)`的选项

+> 示例: `+Doubao-lite-4k@bytedance=ep-xxxxx-xxx`这个配置会在模型列表显示一个`Doubao-lite-4k(ByteDance)`的选项

 ### `DEFAULT_MODEL` （可选）

@ -275,6 +284,14 @@ SiliconFlow API Key.

 SiliconFlow API URL.

+### `AI302_API_KEY` (optional)
+
+302.AI API Key.
+
+### `AI302_URL` (optional)
+
+302.AI API URL.
+
 ## 开发

 点击下方按钮，开始二次开发：
@ -299,6 +316,7 @@ BASE_URL=https://b.nextweb.fun/api/proxy
 ## 部署

 ### 宝塔面板部署
+
 > [简体中文 > 如何通过宝塔一键部署](./docs/bt-cn.md)

 ### 容器部署 （推荐）
--- a/README_JA.md
+++ b/README_JA.md
@ -9,12 +9,20 @@

 [<img src="https://vercel.com/button" alt="Zeaburでデプロイ" 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="Zeaburでデプロイ" height="30">](https://zeabur.com/templates/ZBUEFA) [<img src="https://gitpod.io/button/open-in-gitpod.svg" alt="Gitpodで開く" height="30">](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web)

-
 </div>

+## Sponsor AI API
+
+<a href='https://302.ai/'>
+  <img src="https://github.com/user-attachments/assets/6cf24233-1010-43e0-9a83-a11159866175" width="100%" alt="icon"/>
+</a>
+
+[302.AI](https://302.ai/) は、オンデマンドで支払うAIアプリケーションプラットフォームで、最も安全なAI APIとAIオンラインアプリケーションを提供します。
+
 ## 企業版

 あなたの会社のプライベートデプロイとカスタマイズのニーズに応える
+
 - **ブランドカスタマイズ**：企業向けに特別に設計された VI/UI、企業ブランドイメージとシームレスにマッチ
 - **リソース統合**：企業管理者が数十種類のAIリソースを統一管理、チームメンバーはすぐに使用可能
 - **権限管理**：メンバーの権限、リソースの権限、ナレッジベースの権限を明確にし、企業レベルのAdmin Panelで統一管理
@ -25,7 +33,6 @@

 企業版のお問い合わせ: **business@nextchat.dev**

-
 ## 始めに

 1. [OpenAI API Key](https://platform.openai.com/account/api-keys)を準備する;
@ -40,7 +47,6 @@

 </div>

-
 ## 更新を維持する

 もし上記の手順に従ってワンクリックでプロジェクトをデプロイした場合、「更新があります」というメッセージが常に表示されることがあります。これは、Vercel がデフォルトで新しいプロジェクトを作成するためで、本プロジェクトを fork していないことが原因です。そのため、正しく更新を検出できません。
@ -51,7 +57,6 @@
 - ページ右上の fork ボタンを使って、本プロジェクトを fork する
 - Vercel で再度選択してデプロイする、[詳細な手順はこちらを参照してください](./docs/vercel-ja.md)。

-
 ### 自動更新を開く

 > Upstream Sync の実行エラーが発生した場合は、[手動で Sync Fork](./README_JA.md#手動でコードを更新する) してください！
@ -62,15 +67,12 @@

 ![自動更新を有効にする](./docs/images/enable-actions-sync.jpg)

-
 ### 手動でコードを更新する

 手動で即座に更新したい場合は、[GitHub のドキュメント](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork)を参照して、fork したプロジェクトを上流のコードと同期する方法を確認してください。

 このプロジェクトをスターまたはウォッチしたり、作者をフォローすることで、新機能の更新通知をすぐに受け取ることができます。

-
-
 ## ページアクセスパスワードを設定する

 > パスワードを設定すると、ユーザーは設定ページでアクセスコードを手動で入力しない限り、通常のチャットができず、未承認の状態であることを示すメッセージが表示されます。
@ -85,7 +87,6 @@ code1,code2,code3

 この環境変数を追加または変更した後、**プロジェクトを再デプロイ**して変更を有効にしてください。

-
 ## 環境変数

 > 本プロジェクトのほとんどの設定は環境変数で行います。チュートリアル：[Vercel の環境変数を変更する方法](./docs/vercel-ja.md)。
@ -196,6 +197,7 @@ ByteDance API の URL。
 ### `WHITE_WEBDAV_ENDPOINTS` (オプション)

 アクセス許可を与える WebDAV サービスのアドレスを追加したい場合、このオプションを使用します。フォーマット要件：
+
 - 各アドレスは完全なエンドポイントでなければなりません。
  > `https://xxxx/xxx`
 - 複数のアドレスは `,` で接続します。
@ -208,9 +210,11 @@ ByteDance API の URL。
 モデルリストを管理します。`+` でモデルを追加し、`-` でモデルを非表示にし、`モデル名=表示名` でモデルの表示名をカスタマイズし、カンマで区切ります。

 Azure モードでは、`modelName@Azure=deploymentName` 形式でモデル名とデプロイ名（deploy-name）を設定できます。
+
 > 例：`+gpt-3.5-turbo@Azure=gpt35` この設定でモデルリストに `gpt35(Azure)` のオプションが表示されます。

 ByteDance モードでは、`modelName@bytedance=deploymentName` 形式でモデル名とデプロイ名（deploy-name）を設定できます。
+
 > 例: `+Doubao-lite-4k@bytedance=ep-xxxxx-xxx` この設定でモデルリストに `Doubao-lite-4k(ByteDance)` のオプションが表示されます。

 ### `DEFAULT_MODEL` （オプション）
@ -228,6 +232,13 @@ ByteDance モードでは、`modelName@bytedance=deploymentName` 形式でモデ

 『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。

+### `AI302_API_KEY` （オプション）
+
+302.AI API キー.
+
+### `AI302_URL` （オプション）
+
+302.AI API の URL.

 ## 開発

@ -241,14 +252,12 @@ ByteDance モードでは、`modelName@bytedance=deploymentName` 形式でモデ
 OPENAI_API_KEY=<your api key here>
 ```

-
 ### ローカル開発

 1. Node.js 18 と Yarn をインストールします。具体的な方法は ChatGPT にお尋ねください。
 2. `yarn install && yarn dev` を実行します。⚠️ 注意：このコマンドはローカル開発用であり、デプロイには使用しないでください。
 3. ローカルでデプロイしたい場合は、`yarn install && yarn build && yarn start` コマンドを使用してください。プロセスを守るために pm2 を使用することもできます。詳細は ChatGPT にお尋ねください。

-
 ## デプロイ

 ### コンテナデプロイ（推奨）
@ -285,7 +294,6 @@ docker run -d -p 3000:3000 \

 他の環境変数を指定する必要がある場合は、上記のコマンドに `-e 環境変数=環境変数値` を追加して指定してください。

-
 ### ローカルデプロイ

 コンソールで以下のコマンドを実行します：
@ -296,7 +304,6 @@ bash <(curl -s https://raw.githubusercontent.com/Yidadaa/ChatGPT-Next-Web/main/s

 ⚠️ 注意：インストール中に問題が発生した場合は、Docker を使用してデプロイしてください。

-
 ## 謝辞

 ### 寄付者
@ -311,7 +318,6 @@ bash <(curl -s https://raw.githubusercontent.com/Yidadaa/ChatGPT-Next-Web/main/s

 - [one-api](https://github.com/songquanpeng/one-api): 一つのプラットフォームで大規模モデルのクォータ管理を提供し、市場に出回っているすべての主要な大規模言語モデルをサポートします。

-
 ## オープンソースライセンス

 [MIT](https://opensource.org/license/mit/)
--- a/app/api/302ai.ts
+++ b/app/api/302ai.ts
@ -0,0 +1,128 @@
+import { getServerSideConfig } from "@/app/config/server";
+import {
+  AI302_BASE_URL,
+  ApiPath,
+  ModelProvider,
+  ServiceProvider,
+} from "@/app/constant";
+import { prettyObject } from "@/app/utils/format";
+import { NextRequest, NextResponse } from "next/server";
+import { auth } from "@/app/api/auth";
+import { isModelNotavailableInServer } from "@/app/utils/model";
+
+const serverConfig = getServerSideConfig();
+
+export async function handle(
+  req: NextRequest,
+  { params }: { params: { path: string[] } },
+) {
+  console.log("[302.AI Route] params ", params);
+
+  if (req.method === "OPTIONS") {
+    return NextResponse.json({ body: "OK" }, { status: 200 });
+  }
+
+  const authResult = auth(req, ModelProvider["302.AI"]);
+  if (authResult.error) {
+    return NextResponse.json(authResult, {
+      status: 401,
+    });
+  }
+
+  try {
+    const response = await request(req);
+    return response;
+  } catch (e) {
+    console.error("[302.AI] ", e);
+    return NextResponse.json(prettyObject(e));
+  }
+}
+
+async function request(req: NextRequest) {
+  const controller = new AbortController();
+
+  // alibaba use base url or just remove the path
+  let path = `${req.nextUrl.pathname}`.replaceAll(ApiPath["302.AI"], "");
+
+  let baseUrl = serverConfig.ai302Url || AI302_BASE_URL;
+
+  if (!baseUrl.startsWith("http")) {
+    baseUrl = `https://${baseUrl}`;
+  }
+
+  if (baseUrl.endsWith("/")) {
+    baseUrl = baseUrl.slice(0, -1);
+  }
+
+  console.log("[Proxy] ", path);
+  console.log("[Base Url]", baseUrl);
+
+  const timeoutId = setTimeout(
+    () => {
+      controller.abort();
+    },
+    10 * 60 * 1000,
+  );
+
+  const fetchUrl = `${baseUrl}${path}`;
+  const fetchOptions: RequestInit = {
+    headers: {
+      "Content-Type": "application/json",
+      Authorization: req.headers.get("Authorization") ?? "",
+    },
+    method: req.method,
+    body: req.body,
+    redirect: "manual",
+    // @ts-ignore
+    duplex: "half",
+    signal: controller.signal,
+  };
+
+  // #1815 try to refuse some request to some models
+  if (serverConfig.customModels && req.body) {
+    try {
+      const clonedBody = await req.text();
+      fetchOptions.body = clonedBody;
+
+      const jsonBody = JSON.parse(clonedBody) as { model?: string };
+
+      // not undefined and is false
+      if (
+        isModelNotavailableInServer(
+          serverConfig.customModels,
+          jsonBody?.model as string,
+          ServiceProvider["302.AI"] as string,
+        )
+      ) {
+        return NextResponse.json(
+          {
+            error: true,
+            message: `you are not allowed to use ${jsonBody?.model} model`,
+          },
+          {
+            status: 403,
+          },
+        );
+      }
+    } catch (e) {
+      console.error(`[302.AI] filter`, e);
+    }
+  }
+  try {
+    const res = await fetch(fetchUrl, fetchOptions);
+
+    // to prevent browser prompt for credentials
+    const newHeaders = new Headers(res.headers);
+    newHeaders.delete("www-authenticate");
+    // to disable nginx buffering
+    newHeaders.set("X-Accel-Buffering", "no");
+
+    return new Response(res.body, {
+      status: res.status,
+      statusText: res.statusText,
+      headers: newHeaders,
+    });
+  } finally {
+    clearTimeout(timeoutId);
+  }
+}
--- a/app/api/[provider]/[...path]/route.ts
+++ b/app/api/[provider]/[...path]/route.ts
@ -15,6 +15,7 @@ import { handle as siliconflowHandler } from "../../siliconflow";
 import { handle as xaiHandler } from "../../xai";
 import { handle as chatglmHandler } from "../../glm";
 import { handle as proxyHandler } from "../../proxy";
+import { handle as ai302Handler } from "../../302ai";

 async function handle(
  req: NextRequest,
@ -52,6 +53,8 @@ async function handle(
      return siliconflowHandler(req, { params });
    case ApiPath.OpenAI:
      return openaiHandler(req, { params });
+    case ApiPath["302.AI"]:
+      return ai302Handler(req, { params });
    default:
      return proxyHandler(req, { params });
  }
--- a/app/client/api.ts
+++ b/app/client/api.ts
@ -24,6 +24,7 @@ import { DeepSeekApi } from "./platforms/deepseek";
 import { XAIApi } from "./platforms/xai";
 import { ChatGLMApi } from "./platforms/glm";
 import { SiliconflowApi } from "./platforms/siliconflow";
+import { Ai302Api } from "./platforms/ai302";

 export const ROLES = ["system", "user", "assistant"] as const;
 export type MessageRole = (typeof ROLES)[number];
@ -173,6 +174,9 @@ export class ClientApi {
      case ModelProvider.SiliconFlow:
        this.llm = new SiliconflowApi();
        break;
+      case ModelProvider["302.AI"]:
+        this.llm = new Ai302Api();
+        break;
      default:
        this.llm = new ChatGPTApi();
    }
@ -265,6 +269,7 @@ export function getHeaders(ignoreHeaders: boolean = false) {
    const isChatGLM = modelConfig.providerName === ServiceProvider.ChatGLM;
    const isSiliconFlow =
      modelConfig.providerName === ServiceProvider.SiliconFlow;
+    const isAI302 = modelConfig.providerName === ServiceProvider["302.AI"];
    const isEnabledAccessControl = accessStore.enabledAccessControl();
    const apiKey = isGoogle
      ? accessStore.googleApiKey
@ -290,6 +295,8 @@ export function getHeaders(ignoreHeaders: boolean = false) {
      ? accessStore.iflytekApiKey && accessStore.iflytekApiSecret
        ? accessStore.iflytekApiKey + ":" + accessStore.iflytekApiSecret
        : ""
+      : isAI302
+      ? accessStore.ai302ApiKey
      : accessStore.openaiApiKey;
    return {
      isGoogle,
@ -304,6 +311,7 @@ export function getHeaders(ignoreHeaders: boolean = false) {
      isXAI,
      isChatGLM,
      isSiliconFlow,
+      isAI302,
      apiKey,
      isEnabledAccessControl,
    };
@ -332,6 +340,7 @@ export function getHeaders(ignoreHeaders: boolean = false) {
    isXAI,
    isChatGLM,
    isSiliconFlow,
+    isAI302,
    apiKey,
    isEnabledAccessControl,
  } = getConfig();
@ -382,6 +391,8 @@ export function getClientApi(provider: ServiceProvider): ClientApi {
      return new ClientApi(ModelProvider.ChatGLM);
    case ServiceProvider.SiliconFlow:
      return new ClientApi(ModelProvider.SiliconFlow);
+    case ServiceProvider["302.AI"]:
+      return new ClientApi(ModelProvider["302.AI"]);
    default:
      return new ClientApi(ModelProvider.GPT);
  }
--- a/app/client/platforms/ai302.ts
+++ b/app/client/platforms/ai302.ts
@ -0,0 +1,287 @@
+"use client";
+
+import {
+  ApiPath,
+  AI302_BASE_URL,
+  DEFAULT_MODELS,
+  AI302,
+} from "@/app/constant";
+import {
+  useAccessStore,
+  useAppConfig,
+  useChatStore,
+  ChatMessageTool,
+  usePluginStore,
+} from "@/app/store";
+import { preProcessImageContent, streamWithThink } from "@/app/utils/chat";
+import {
+  ChatOptions,
+  getHeaders,
+  LLMApi,
+  LLMModel,
+  SpeechOptions,
+} from "../api";
+import { getClientConfig } from "@/app/config/client";
+import {
+  getMessageTextContent,
+  getMessageTextContentWithoutThinking,
+  isVisionModel,
+  getTimeoutMSByModel,
+} from "@/app/utils";
+import { RequestPayload } from "./openai";
+
+import { fetch } from "@/app/utils/stream";
+export interface Ai302ListModelResponse {
+  object: string;
+  data: Array<{
+    id: string;
+    object: string;
+    root: string;
+  }>;
+}
+
+export class Ai302Api implements LLMApi {
+  private disableListModels = false;
+
+  path(path: string): string {
+    const accessStore = useAccessStore.getState();
+
+    let baseUrl = "";
+
+    if (accessStore.useCustomConfig) {
+      baseUrl = accessStore.ai302Url;
+    }
+
+    if (baseUrl.length === 0) {
+      const isApp = !!getClientConfig()?.isApp;
+      const apiPath = ApiPath["302.AI"];
+      baseUrl = isApp ? AI302_BASE_URL : apiPath;
+    }
+
+    if (baseUrl.endsWith("/")) {
+      baseUrl = baseUrl.slice(0, baseUrl.length - 1);
+    }
+    if (
+      !baseUrl.startsWith("http") &&
+      !baseUrl.startsWith(ApiPath["302.AI"])
+    ) {
+      baseUrl = "https://" + baseUrl;
+    }
+
+    console.log("[Proxy Endpoint] ", baseUrl, path);
+
+    return [baseUrl, path].join("/");
+  }
+
+  extractMessage(res: any) {
+    return res.choices?.at(0)?.message?.content ?? "";
+  }
+
+  speech(options: SpeechOptions): Promise<ArrayBuffer> {
+    throw new Error("Method not implemented.");
+  }
+
+  async chat(options: ChatOptions) {
+    const visionModel = isVisionModel(options.config.model);
+    const messages: ChatOptions["messages"] = [];
+    for (const v of options.messages) {
+      if (v.role === "assistant") {
+        const content = getMessageTextContentWithoutThinking(v);
+        messages.push({ role: v.role, content });
+      } else {
+        const content = visionModel
+          ? await preProcessImageContent(v.content)
+          : getMessageTextContent(v);
+        messages.push({ role: v.role, content });
+      }
+    }
+
+    const modelConfig = {
+      ...useAppConfig.getState().modelConfig,
+      ...useChatStore.getState().currentSession().mask.modelConfig,
+      ...{
+        model: options.config.model,
+        providerName: options.config.providerName,
+      },
+    };
+
+    const requestPayload: RequestPayload = {
+      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,
+      // max_tokens: Math.max(modelConfig.max_tokens, 1024),
+      // Please do not ask me why not send max_tokens, no reason, this param is just shit, I dont want to explain anymore.
+    };
+
+    console.log("[Request] openai payload: ", requestPayload);
+
+    const shouldStream = !!options.config.stream;
+    const controller = new AbortController();
+    options.onController?.(controller);
+
+    try {
+      const chatPath = this.path(AI302.ChatPath);
+      const chatPayload = {
+        method: "POST",
+        body: JSON.stringify(requestPayload),
+        signal: controller.signal,
+        headers: getHeaders(),
+      };
+
+      // console.log(chatPayload);
+
+      // Use extended timeout for thinking models as they typically require more processing time
+      const requestTimeoutId = setTimeout(
+        () => controller.abort(),
+        getTimeoutMSByModel(options.config.model),
+      );
+
+      if (shouldStream) {
+        const [tools, funcs] = usePluginStore
+          .getState()
+          .getAsTools(
+            useChatStore.getState().currentSession().mask?.plugin || [],
+          );
+        return streamWithThink(
+          chatPath,
+          requestPayload,
+          getHeaders(),
+          tools as any,
+          funcs,
+          controller,
+          // parseSSE
+          (text: string, runTools: ChatMessageTool[]) => {
+            // console.log("parseSSE", text, runTools);
+            const json = JSON.parse(text);
+            const choices = json.choices as Array<{
+              delta: {
+                content: string | null;
+                tool_calls: ChatMessageTool[];
+                reasoning_content: string | null;
+              };
+            }>;
+            const tool_calls = choices[0]?.delta?.tool_calls;
+            if (tool_calls?.length > 0) {
+              const index = tool_calls[0]?.index;
+              const id = tool_calls[0]?.id;
+              const args = tool_calls[0]?.function?.arguments;
+              if (id) {
+                runTools.push({
+                  id,
+                  type: tool_calls[0]?.type,
+                  function: {
+                    name: tool_calls[0]?.function?.name as string,
+                    arguments: args,
+                  },
+                });
+              } else {
+                // @ts-ignore
+                runTools[index]["function"]["arguments"] += args;
+              }
+            }
+            const reasoning = choices[0]?.delta?.reasoning_content;
+            const content = choices[0]?.delta?.content;
+
+            // Skip if both content and reasoning_content are empty or null
+            if (
+              (!reasoning || reasoning.length === 0) &&
+              (!content || content.length === 0)
+            ) {
+              return {
+                isThinking: false,
+                content: "",
+              };
+            }
+
+            if (reasoning && reasoning.length > 0) {
+              return {
+                isThinking: true,
+                content: reasoning,
+              };
+            } else if (content && content.length > 0) {
+              return {
+                isThinking: false,
+                content: content,
+              };
+            }
+
+            return {
+              isThinking: false,
+              content: "",
+            };
+          },
+          // processToolMessage, include tool_calls message and tool call results
+          (
+            requestPayload: RequestPayload,
+            toolCallMessage: any,
+            toolCallResult: any[],
+          ) => {
+            // @ts-ignore
+            requestPayload?.messages?.splice(
+              // @ts-ignore
+              requestPayload?.messages?.length,
+              0,
+              toolCallMessage,
+              ...toolCallResult,
+            );
+          },
+          options,
+        );
+      } else {
+        const res = await fetch(chatPath, chatPayload);
+        clearTimeout(requestTimeoutId);
+
+        const resJson = await res.json();
+        const message = this.extractMessage(resJson);
+        options.onFinish(message, res);
+      }
+    } catch (e) {
+      console.log("[Request] failed to make a chat request", e);
+      options.onError?.(e as Error);
+    }
+  }
+  async usage() {
+    return {
+      used: 0,
+      total: 0,
+    };
+  }
+
+  async models(): Promise<LLMModel[]> {
+    if (this.disableListModels) {
+      return DEFAULT_MODELS.slice();
+    }
+
+    const res = await fetch(this.path(AI302.ListModelPath), {
+      method: "GET",
+      headers: {
+        ...getHeaders(),
+      },
+    });
+
+    const resJson = (await res.json()) as Ai302ListModelResponse;
+    const chatModels = resJson.data;
+    console.log("[Models]", chatModels);
+
+    if (!chatModels) {
+      return [];
+    }
+
+    let seq = 1000; //同 Constant.ts 中的排序保持一致
+    return chatModels.map((m) => ({
+      name: m.id,
+      available: true,
+      sorted: seq++,
+      provider: {
+        id: "ai302",
+        providerName: "302.AI",
+        providerType: "ai302",
+        sorted: 15,
+      },
+    }));
+  }
+}
--- a/app/client/platforms/anthropic.ts
+++ b/app/client/platforms/anthropic.ts
@ -224,7 +224,7 @@ export class ClaudeApi implements LLMApi {
          let chunkJson:
            | undefined
            | {
-                type: "content_block_delta" | "content_block_stop";
+                type: "content_block_delta" | "content_block_stop" | "message_delta" | "message_stop";
                content_block?: {
                  type: "tool_use";
                  id: string;
@ -234,11 +234,20 @@ export class ClaudeApi implements LLMApi {
                  type: "text_delta" | "input_json_delta";
                  text?: string;
                  partial_json?: string;
+                  stop_reason?: string;
                };
                index: number;
              };
          chunkJson = JSON.parse(text);

+          // Handle refusal stop reason in message_delta
+          if (chunkJson?.delta?.stop_reason === "refusal") {
+            // Return a message to display to the user
+            const refusalMessage = "\n\n[Assistant refused to respond. Please modify your request and try again.]";
+            options.onError?.(new Error("Content policy violation: " + refusalMessage));
+            return refusalMessage;
+          }
+
          if (chunkJson?.content_block?.type == "tool_use") {
            index += 1;
            const id = chunkJson?.content_block.id;
--- a/app/components/exporter.tsx
+++ b/app/components/exporter.tsx
@ -40,6 +40,8 @@ import { type ClientApi, getClientApi } from "../client/api";
 import { getMessageTextContent } from "../utils";
 import { MaskAvatar } from "./mask";
 import clsx from "clsx";
+import { save } from "@tauri-apps/plugin-dialog";
+import { writeFile } from "@tauri-apps/plugin-fs";

 const Markdown = dynamic(async () => (await import("./markdown")).Markdown, {
  loading: () => <LoadingIcon />,
@ -456,7 +458,7 @@ export function ImagePreviewer(props: {

      if (isMobile || (isApp && window.__TAURI__)) {
        if (isApp && window.__TAURI__) {
-          const result = await window.__TAURI__.dialog.save({
+          const result = await save({
            defaultPath: `${props.topic}.png`,
            filters: [
              {
@ -474,7 +476,7 @@ export function ImagePreviewer(props: {
            const response = await fetch(blob);
            const buffer = await response.arrayBuffer();
            const uint8Array = new Uint8Array(buffer);
-            await window.__TAURI__.fs.writeBinaryFile(result, uint8Array);
+            await writeFile(result, uint8Array);
            showToast(Locale.Download.Success);
          } else {
            showToast(Locale.Download.Failed);
--- a/app/components/settings.tsx
+++ b/app/components/settings.tsx
@ -75,6 +75,7 @@ import {
  ChatGLM,
  DeepSeek,
  SiliconFlow,
+  AI302,
 } from "../constant";
 import { Prompt, SearchService, usePromptStore } from "../store/prompt";
 import { ErrorBoundary } from "./error";
@ -1458,6 +1459,46 @@ export function Settings() {
    </>
  );

+  const ai302ConfigComponent = accessStore.provider === ServiceProvider["302.AI"] && (
+    <>
+      <ListItem
+          title={Locale.Settings.Access.AI302.Endpoint.Title}
+          subTitle={
+            Locale.Settings.Access.AI302.Endpoint.SubTitle +
+            AI302.ExampleEndpoint
+          }
+        >
+          <input
+            aria-label={Locale.Settings.Access.AI302.Endpoint.Title}
+            type="text"
+            value={accessStore.ai302Url}
+            placeholder={AI302.ExampleEndpoint}
+            onChange={(e) =>
+              accessStore.update(
+                (access) => (access.ai302Url = e.currentTarget.value),
+              )
+            }
+          ></input>
+        </ListItem>
+        <ListItem
+          title={Locale.Settings.Access.AI302.ApiKey.Title}
+          subTitle={Locale.Settings.Access.AI302.ApiKey.SubTitle}
+        >
+          <PasswordInput
+            aria-label={Locale.Settings.Access.AI302.ApiKey.Title}
+            value={accessStore.ai302ApiKey}
+            type="text"
+            placeholder={Locale.Settings.Access.AI302.ApiKey.Placeholder}
+            onChange={(e) => {
+              accessStore.update(
+                (access) => (access.ai302ApiKey = e.currentTarget.value),
+              );
+            }}
+          />
+        </ListItem>
+      </>
+  );
+
  return (
    <ErrorBoundary>
      <div className="window-header" data-tauri-drag-region>
@ -1822,6 +1863,7 @@ export function Settings() {
                  {XAIConfigComponent}
                  {chatglmConfigComponent}
                  {siliconflowConfigComponent}
+                  {ai302ConfigComponent}
                </>
              )}
            </>
--- a/app/config/build.ts
+++ b/app/config/build.ts
@ -10,7 +10,7 @@ export const getBuildConfig = () => {

  const buildMode = process.env.BUILD_MODE ?? "standalone";
  const isApp = !!process.env.BUILD_APP;
-  const version = "v" + tauriConfig.package.version;
+  const version = "v" + tauriConfig.version;

  const commitInfo = (() => {
    try {
--- a/app/config/server.ts
+++ b/app/config/server.ts
@ -88,6 +88,10 @@ declare global {
      SILICONFLOW_URL?: string;
      SILICONFLOW_API_KEY?: string;

+      // 302.AI only
+      AI302_URL?: string;
+      AI302_API_KEY?: string;
+
      // custom template for preprocessing user input
      DEFAULT_INPUT_TEMPLATE?: string;

@ -163,6 +167,7 @@ export const getServerSideConfig = () => {
  const isXAI = !!process.env.XAI_API_KEY;
  const isChatGLM = !!process.env.CHATGLM_API_KEY;
  const isSiliconFlow = !!process.env.SILICONFLOW_API_KEY;
+  const isAI302 = !!process.env.AI302_API_KEY;
  // const apiKeyEnvVar = process.env.OPENAI_API_KEY ?? "";
  // const apiKeys = apiKeyEnvVar.split(",").map((v) => v.trim());
  // const randomIndex = Math.floor(Math.random() * apiKeys.length);
@ -246,6 +251,10 @@ export const getServerSideConfig = () => {
    siliconFlowUrl: process.env.SILICONFLOW_URL,
    siliconFlowApiKey: getApiKey(process.env.SILICONFLOW_API_KEY),

+    isAI302,
+    ai302Url: process.env.AI302_URL,
+    ai302ApiKey: getApiKey(process.env.AI302_API_KEY),
+
    gtmId: process.env.GTM_ID,
    gaId: process.env.GA_ID || DEFAULT_GA_ID,

--- a/app/constant.ts
+++ b/app/constant.ts
@ -36,6 +36,8 @@ export const CHATGLM_BASE_URL = "https://open.bigmodel.cn";

 export const SILICONFLOW_BASE_URL = "https://api.siliconflow.cn";

+export const AI302_BASE_URL = "https://api.302.ai";
+
 export const CACHE_URL_PREFIX = "/api/cache";
 export const UPLOAD_URL = `${CACHE_URL_PREFIX}/upload`;

@ -72,6 +74,7 @@ export enum ApiPath {
  ChatGLM = "/api/chatglm",
  DeepSeek = "/api/deepseek",
  SiliconFlow = "/api/siliconflow",
+  "302.AI" = "/api/302ai",
 }

 export enum SlotID {
@ -130,6 +133,7 @@ export enum ServiceProvider {
  ChatGLM = "ChatGLM",
  DeepSeek = "DeepSeek",
  SiliconFlow = "SiliconFlow",
+  "302.AI" = "302.AI",
 }

 // Google API safety settings, see https://ai.google.dev/gemini-api/docs/safety-settings
@ -156,6 +160,7 @@ export enum ModelProvider {
  ChatGLM = "ChatGLM",
  DeepSeek = "DeepSeek",
  SiliconFlow = "SiliconFlow",
+  "302.AI" = "302.AI",
 }

 export const Stability = {
@ -266,6 +271,13 @@ export const SiliconFlow = {
  ListModelPath: "v1/models?&sub_type=chat",
 };

+export const AI302 = {
+  ExampleEndpoint: AI302_BASE_URL,
+  ChatPath: "v1/chat/completions",
+  EmbeddingsPath: "jina/v1/embeddings",
+  ListModelPath: "v1/models?llm=1",
+};
+
 export const DEFAULT_INPUT_TEMPLATE = `{{input}}`; // input / time / model / lang
 // export const DEFAULT_SYSTEM_TEMPLATE = `
 // You are ChatGPT, a large language model trained by {{ServiceProvider}}.
@ -559,6 +571,8 @@ const anthropicModels = [
  "claude-3-5-sonnet-latest",
  "claude-3-7-sonnet-20250219",
  "claude-3-7-sonnet-latest",
+  "claude-sonnet-4-20250514",
+  "claude-opus-4-20250514",
 ];

 const baiduModels = [
@ -679,6 +693,31 @@ const siliconflowModels = [
  "Pro/deepseek-ai/DeepSeek-V3",
 ];

+const ai302Models = [
+  "deepseek-chat",
+  "gpt-4o",
+  "chatgpt-4o-latest",
+  "llama3.3-70b",
+  "deepseek-reasoner",
+  "gemini-2.0-flash",
+  "claude-3-7-sonnet-20250219",
+  "claude-3-7-sonnet-latest",
+  "grok-3-beta",
+  "grok-3-mini-beta",
+  "gpt-4.1",
+  "gpt-4.1-mini",
+  "o3",
+  "o4-mini",
+  "qwen3-235b-a22b",
+  "qwen3-32b",
+  "gemini-2.5-pro-preview-05-06",
+  "llama-4-maverick",
+  "gemini-2.5-flash",
+  "claude-sonnet-4-20250514",
+  "claude-opus-4-20250514",
+  "gemini-2.5-pro",
+];
+
 let seq = 1000; // 内置的模型序号生成器从1000开始
 export const DEFAULT_MODELS = [
  ...openaiModels.map((name) => ({
@ -835,6 +874,17 @@ export const DEFAULT_MODELS = [
      sorted: 14,
    },
  })),
+  ...ai302Models.map((name) => ({
+    name,
+    available: true,
+    sorted: seq++,
+    provider: {
+      id: "ai302",
+      providerName: "302.AI",
+      providerType: "ai302",
+      sorted: 15,
+    },
+  })),
 ] as const;

 export const CHAT_PAGE_SIZE = 15;
--- a/app/locales/ar.ts
+++ b/app/locales/ar.ts
@ -416,6 +416,17 @@ const ar: PartialLocaleType = {
          SubTitle: "مثال:",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "مفتاح 302.AI API",
+          SubTitle: "استخدم مفتاح 302.AI API مخصص",
+          Placeholder: "مفتاح 302.AI API",
+        },
+        Endpoint: {
+          Title: "عنوان الواجهة",
+          SubTitle: "مثال:",
+        },
+      },
      CustomModel: {
        Title: "اسم النموذج المخصص",
        SubTitle: "أضف خيارات نموذج مخصص، مفصولة بفواصل إنجليزية",
--- a/app/locales/bn.ts
+++ b/app/locales/bn.ts
@ -423,6 +423,17 @@ const bn: PartialLocaleType = {
          SubTitle: "উদাহরণ:",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "ইন্টারফেস কী",
+          SubTitle: "স্বনির্ধারিত 302.AI API কী ব্যবহার করুন",
+          Placeholder: "302.AI API কী",
+        },
+        Endpoint: {
+          Title: "ইন্টারফেস ঠিকানা",
+          SubTitle: "উদাহরণ:",
+        },
+      },
      CustomModel: {
        Title: "স্বনির্ধারিত মডেল নাম",
        SubTitle:
--- a/app/locales/cn.ts
+++ b/app/locales/cn.ts
@ -538,6 +538,17 @@ const cn = {
        Title: "自定义模型名",
        SubTitle: "增加自定义模型可选项，使用英文逗号隔开",
      },
+      AI302: {
+        ApiKey: {
+          Title: "接口密钥",
+          SubTitle: "使用自定义302.AI API Key",
+          Placeholder: "302.AI API Key",
+        },
+        Endpoint: {
+          Title: "接口地址",
+          SubTitle: "样例：",
+        },
+      },
    },

    Model: "模型 (model)",
--- a/app/locales/cs.ts
+++ b/app/locales/cs.ts
@ -423,6 +423,17 @@ const cs: PartialLocaleType = {
          SubTitle: "Příklad:",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "Rozhraní klíč",
+          SubTitle: "Použijte vlastní 302.AI API Key",
+          Placeholder: "302.AI API Key",
+        },
+        Endpoint: {
+          Title: "Adresa rozhraní",
+          SubTitle: "Příklad:",
+        },
+      },
      CustomModel: {
        Title: "Vlastní názvy modelů",
        SubTitle: "Přidejte možnosti vlastních modelů, oddělené čárkami",
--- a/app/locales/da.ts
+++ b/app/locales/da.ts
@ -517,6 +517,17 @@ const da: PartialLocaleType = {
          SubTitle: "Vælg et niveau for indholdskontrol",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "302.AI API Key",
+          SubTitle: "Brug en custom 302.AI API Key",
+          Placeholder: "302.AI API Key",
+        },
+        Endpoint: {
+          Title: "Endpoint-adresse",
+          SubTitle: "Eksempel: ",
+        },
+      },
    },
    Model: "Model",
    CompressModel: {
--- a/app/locales/de.ts
+++ b/app/locales/de.ts
@ -434,6 +434,17 @@ const de: PartialLocaleType = {
          SubTitle: "Beispiel:",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "Schnittstellenschlüssel",
+          SubTitle: "Verwenden Sie einen benutzerdefinierten 302.AI API-Schlüssel",
+          Placeholder: "302.AI API-Schlüssel",
+        },
+        Endpoint: {
+          Title: "Endpunktadresse",
+          SubTitle: "Beispiel:",
+        },
+      },
      CustomModel: {
        Title: "Benutzerdefinierter Modellname",
        SubTitle:
--- a/app/locales/en.ts
+++ b/app/locales/en.ts
@ -543,6 +543,17 @@ const en: LocaleType = {
          SubTitle: "Select a safety filtering level",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "302.AI API Key",
+          SubTitle: "Use a custom 302.AI API Key",
+          Placeholder: "302.AI API Key",
+        },
+        Endpoint: {
+          Title: "Endpoint Address",
+          SubTitle: "Example: ",
+        },
+      },
    },

    Model: "Model",
--- a/app/locales/es.ts
+++ b/app/locales/es.ts
@ -436,6 +436,17 @@ const es: PartialLocaleType = {
          SubTitle: "Ejemplo:",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "Clave de interfaz",
+          SubTitle: "Usa una clave API de 302.AI personalizada",
+          Placeholder: "Clave API de 302.AI",
+        },
+        Endpoint: {
+          Title: "Dirección del endpoint",
+          SubTitle: "Ejemplo:",
+        },
+      },
      CustomModel: {
        Title: "Nombre del modelo personalizado",
        SubTitle:
--- a/app/locales/fr.ts
+++ b/app/locales/fr.ts
@ -435,6 +435,17 @@ const fr: PartialLocaleType = {
          SubTitle: "Exemple :",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "Clé d'interface",
+          SubTitle: "Utiliser une clé API 302.AI personnalisée",
+          Placeholder: "Clé API 302.AI",
+        },
+        Endpoint: {
+          Title: "Adresse de l'endpoint",
+          SubTitle: "Exemple :",
+        },
+      },
      CustomModel: {
        Title: "Nom du modèle personnalisé",
        SubTitle:
--- a/app/locales/id.ts
+++ b/app/locales/id.ts
@ -424,6 +424,17 @@ const id: PartialLocaleType = {
          SubTitle: "Contoh:",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "Kunci Antarmuka",
+          SubTitle: "Gunakan 302.AI API Key kustom",
+          Placeholder: "302.AI API Key",
+        },
+        Endpoint: {
+          Title: "Alamat Antarmuka",
+          SubTitle: "Contoh:",
+        },
+      },
      CustomModel: {
        Title: "Nama Model Kustom",
        SubTitle: "Tambahkan opsi model kustom, pisahkan dengan koma",
--- a/app/locales/it.ts
+++ b/app/locales/it.ts
@ -436,6 +436,17 @@ const it: PartialLocaleType = {
          SubTitle: "Esempio:",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "Chiave dell'interfaccia",
+          SubTitle: "Utilizza una chiave API 302.AI personalizzata",
+          Placeholder: "Chiave API 302.AI",
+        },
+        Endpoint: {
+          Title: "Indirizzo dell'interfaccia",
+          SubTitle: "Esempio:",
+        },
+      },
      CustomModel: {
        Title: "Nome del modello personalizzato",
        SubTitle:
--- a/app/locales/jp.ts
+++ b/app/locales/jp.ts
@ -420,6 +420,17 @@ const jp: PartialLocaleType = {
          SubTitle: "例：",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "APIキー",
+          SubTitle: "カスタム302.AI APIキーを使用",
+          Placeholder: "302.AI APIキー",
+        },
+        Endpoint: {
+          Title: "エンドポイント",
+          SubTitle: "例：",
+        },
+      },
      CustomModel: {
        Title: "カスタムモデル名",
        SubTitle: "カスタムモデルの選択肢を追加、英語のカンマで区切る",
--- a/app/locales/ko.ts
+++ b/app/locales/ko.ts
@ -421,6 +421,17 @@ const ko: PartialLocaleType = {
        Title: "커스텀 모델 이름",
        SubTitle: "커스텀 모델 옵션 추가, 영어 쉼표로 구분",
      },
+      AI302: {
+        ApiKey: {
+          Title: "엔드포인트 키",
+          SubTitle: "커스텀 302.AI API 키 사용",
+          Placeholder: "302.AI API 키",
+        },
+        Endpoint: {
+          Title: "엔드포인트 주소",
+          SubTitle: "예: ",
+        },
+      },
    },

    Model: "모델 (model)",
--- a/app/locales/no.ts
+++ b/app/locales/no.ts
@ -433,6 +433,17 @@ const no: PartialLocaleType = {
        Title: "Egendefinert modellnavn",
        SubTitle: "Legg til egendefinerte modellalternativer, skill med komma",
      },
+      AI302: {
+        ApiKey: {
+          Title: "API-nøkkel",
+          SubTitle: "Bruk egendefinert 302.AI API-nøkkel",
+          Placeholder: "302.AI API-nøkkel",
+        },
+        Endpoint: {
+          Title: "API-adresse",
+          SubTitle: "Eksempel:",
+        },
+      },
    },

    Model: "Modell",
--- a/app/locales/pt.ts
+++ b/app/locales/pt.ts
@ -359,6 +359,17 @@ const pt: PartialLocaleType = {
          SubTitle: "Verifique sua versão API do console Anthropic",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "Chave API 302.AI",
+          SubTitle: "Use uma chave API 302.AI personalizada",
+          Placeholder: "302.AI API Key",
+        },
+        Endpoint: {
+          Title: "Endpoint Address",
+          SubTitle: "Exemplo: ",
+        },
+      },
      CustomModel: {
        Title: "Modelos Personalizados",
        SubTitle: "Opções de modelo personalizado, separados por vírgula",
--- a/app/locales/ru.ts
+++ b/app/locales/ru.ts
@ -426,6 +426,17 @@ const ru: PartialLocaleType = {
          SubTitle: "Пример:",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "Ключ интерфейса",
+          SubTitle: "Использовать пользовательский 302.AI API-ключ",
+          Placeholder: "302.AI API-ключ",
+        },
+        Endpoint: {
+          Title: "Адрес интерфейса",
+          SubTitle: "Пример:",
+        },
+      },
      CustomModel: {
        Title: "Название пользовательской модели",
        SubTitle:
--- a/app/locales/sk.ts
+++ b/app/locales/sk.ts
@ -381,6 +381,17 @@ const sk: PartialLocaleType = {
          SubTitle: "Vyberte špecifickú verziu časti",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "API kľúč",
+          SubTitle: "Použiť vlastný API kľúč 302.AI",
+          Placeholder: "302.AI API kľúč",
+        },
+        Endpoint: {
+          Title: "Adresa koncového bodu",
+          SubTitle: "Príklad:",
+        },
+      },
    },

    Model: "Model",
--- a/app/locales/tr.ts
+++ b/app/locales/tr.ts
@ -426,6 +426,17 @@ const tr: PartialLocaleType = {
          SubTitle: "Örnek:",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "API Anahtarı",
+          SubTitle: "Özelleştirilmiş 302.AI API Anahtarı kullanın",
+          Placeholder: "302.AI API Anahtarı",
+        },
+        Endpoint: {
+          Title: "API Adresi",
+          SubTitle: "Örnek:",
+        },
+      },
      CustomModel: {
        Title: "Özelleştirilmiş Model Adı",
        SubTitle:
--- a/app/locales/tw.ts
+++ b/app/locales/tw.ts
@ -382,6 +382,17 @@ const tw = {
          SubTitle: "選擇一個特定的 API 版本",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "API 金鑰",
+          SubTitle: "使用自訂 302.AI API 金鑰",
+          Placeholder: "302.AI API 金鑰",
+        },
+        Endpoint: {
+          Title: "端點位址",
+          SubTitle: "範例：",
+        },
+      },
      CustomModel: {
        Title: "自訂模型名稱",
        SubTitle: "增加自訂模型可選擇項目，使用英文逗號隔開",
--- a/app/locales/vi.ts
+++ b/app/locales/vi.ts
@ -422,6 +422,17 @@ const vi: PartialLocaleType = {
          SubTitle: "Ví dụ:",
        },
      },
+      AI302: {
+        ApiKey: {
+          Title: "Khóa API 302.AI",
+          SubTitle: "Sử dụng khóa API 302.AI tùy chỉnh",
+          Placeholder: "302.AI API Key",
+        },
+        Endpoint: {
+          Title: "Địa chỉ giao diện",
+          SubTitle: "Ví dụ:",
+        },
+      },
      CustomModel: {
        Title: "Tên mô hình tùy chỉnh",
        SubTitle:
--- a/app/store/access.ts
+++ b/app/store/access.ts
@ -17,6 +17,7 @@ import {
  XAI_BASE_URL,
  CHATGLM_BASE_URL,
  SILICONFLOW_BASE_URL,
+  AI302_BASE_URL,
 } from "../constant";
 import { getHeaders } from "../client/api";
 import { getClientConfig } from "../config/client";
@ -59,6 +60,8 @@ const DEFAULT_SILICONFLOW_URL = isApp
  ? SILICONFLOW_BASE_URL
  : ApiPath.SiliconFlow;

+const DEFAULT_AI302_URL = isApp ? AI302_BASE_URL : ApiPath["302.AI"];
+
 const DEFAULT_ACCESS_STATE = {
  accessCode: "",
  useCustomConfig: false,
@ -132,6 +135,10 @@ const DEFAULT_ACCESS_STATE = {
  siliconflowUrl: DEFAULT_SILICONFLOW_URL,
  siliconflowApiKey: "",

+  // 302.AI
+  ai302Url: DEFAULT_AI302_URL,
+  ai302ApiKey: "",
+
  // server config
  needCode: true,
  hideUserApiKey: false,
--- a/app/store/update.ts
+++ b/app/store/update.ts
@ -10,6 +10,11 @@ import { clientUpdate } from "../utils";
 import ChatGptIcon from "../icons/chatgpt.png";
 import Locale from "../locales";
 import { ClientApi } from "../client/api";
+import {
+  isPermissionGranted,
+  requestPermission,
+  sendNotification,
+} from "@tauri-apps/plugin-notification";

 const ONE_MINUTE = 60 * 1000;
 const isApp = !!getClientConfig()?.isApp;
@ -90,31 +95,29 @@ export const useUpdateStore = createPersistStore(
          remoteVersion: remoteId,
        }));
        if (window.__TAURI__?.notification && isApp) {
+          try {
            // Check if notification permission is granted
-          await window.__TAURI__?.notification
-            .isPermissionGranted()
-            .then((granted) => {
+            const granted = await isPermissionGranted();
            if (!granted) {
-                return;
-              } else {
              // Request permission to show notifications
-                window.__TAURI__?.notification
-                  .requestPermission()
-                  .then((permission) => {
-                    if (permission === "granted") {
+              const permission = await requestPermission();
+              if (permission !== "granted") return;
+            }
+
            if (version === remoteId) {
              // Show a notification using Tauri
-                        window.__TAURI__?.notification.sendNotification({
+              await sendNotification({
                title: "NextChat",
                body: `${Locale.Settings.Update.IsLatest}`,
                icon: `${ChatGptIcon.src}`,
                sound: "Default",
              });
            } else {
-                        const updateMessage =
-                          Locale.Settings.Update.FoundUpdate(`${remoteId}`);
+              const updateMessage = Locale.Settings.Update.FoundUpdate(
+                `${remoteId}`,
+              );
              // Show a notification for the new version using Tauri
-                        window.__TAURI__?.notification.sendNotification({
+              await sendNotification({
                title: "NextChat",
                body: updateMessage,
                icon: `${ChatGptIcon.src}`,
@ -122,10 +125,9 @@ export const useUpdateStore = createPersistStore(
              });
              clientUpdate();
            }
+          } catch (error) {
+            console.error("[Notification Error]", error);
          }
-                  });
-              }
-            });
        }
        console.log("[Got Upstream] ", remoteId);
      } catch (error) {
--- a/app/utils.ts
+++ b/app/utils.ts
@ -12,6 +12,9 @@ import { fetch as tauriStreamFetch } from "./utils/stream";
 import { VISION_MODEL_REGEXES, EXCLUDE_VISION_MODEL_REGEXES } from "./constant";
 import { useAccessStore } from "./store";
 import { ModelSize } from "./typing";
+import { writeText } from "@tauri-apps/plugin-clipboard-manager";
+import { save } from "@tauri-apps/plugin-dialog";
+import { writeTextFile } from "@tauri-apps/plugin-fs";

 export function trimTopic(topic: string) {
  // Fix an issue where double quotes still show in the Indonesian language
@ -20,15 +23,15 @@ export function trimTopic(topic: string) {
  return (
    topic
      // fix for gemini
-      .replace(/^["“”*]+|["“”*]+$/g, "")
-      .replace(/[，。！？”“"、,.!?*]*$/, "")
+      .replace(/^["""*]+|["""*]+$/g, "")
+      .replace(/[，。！？""""、,.!?*]*$/, "")
  );
 }

 export async function copyToClipboard(text: string) {
  try {
    if (window.__TAURI__) {
-      window.__TAURI__.writeText(text);
+      await writeText(text);
    } else {
      await navigator.clipboard.writeText(text);
    }
@ -52,7 +55,7 @@ export async function copyToClipboard(text: string) {

 export async function downloadAs(text: string, filename: string) {
  if (window.__TAURI__) {
-    const result = await window.__TAURI__.dialog.save({
+    const result = await save({
      defaultPath: `${filename}`,
      filters: [
        {
@ -68,7 +71,7 @@ export async function downloadAs(text: string, filename: string) {

    if (result !== null) {
      try {
-        await window.__TAURI__.fs.writeTextFile(result, text);
+        await writeTextFile(result, text);
        showToast(Locale.Download.Success);
      } catch (error) {
        showToast(Locale.Download.Failed);
@ -448,24 +451,29 @@ export function getOperationId(operation: {

 export function clientUpdate() {
  // this a wild for updating client app
-  return window.__TAURI__?.updater
+  const tauriApp = window.__TAURI__;
+  if (!tauriApp || !tauriApp.updater) return Promise.resolve();
+
+  return tauriApp.updater
    .checkUpdate()
-    .then((updateResult) => {
+    .then((updateResult: any) => {
      if (updateResult.shouldUpdate) {
-        window.__TAURI__?.updater
+        return tauriApp.updater
          .installUpdate()
-          .then((result) => {
+          .then((result: any) => {
            showToast(Locale.Settings.Update.Success);
          })
-          .catch((e) => {
+          .catch((e: any) => {
            console.error("[Install Update Error]", e);
            showToast(Locale.Settings.Update.Failed);
          });
      }
+      return updateResult;
    })
-    .catch((e) => {
+    .catch((e: any) => {
      console.error("[Check Update Error]", e);
      showToast(Locale.Settings.Update.Failed);
+      return e;
    });
 }

--- a/app/utils/stream.ts
+++ b/app/utils/stream.ts
@ -3,6 +3,9 @@
 // 1. invoke('stream_fetch', {url, method, headers, body}), get response with headers.
 // 2. listen event: `stream-response` multi times to get body

+import { invoke } from "@tauri-apps/api/core";
+import { listen } from "@tauri-apps/api/event";
+
 type ResponseEvent = {
  id: number;
  payload: {
@ -27,8 +30,8 @@ export function fetch(url: string, options?: RequestInit): Promise<Response> {
      headers: _headers = {},
      body = [],
    } = options || {};
-    let unlisten: Function | undefined;
-    let setRequestId: Function | undefined;
+    let unlisten: (() => void) | undefined;
+    let setRequestId: ((value: number) => void) | undefined;
    const requestIdPromise = new Promise((resolve) => (setRequestId = resolve));
    const ts = new TransformStream();
    const writer = ts.writable.getWriter();
@ -46,9 +49,9 @@ export function fetch(url: string, options?: RequestInit): Promise<Response> {
    if (signal) {
      signal.addEventListener("abort", () => close());
    }
-    // @ts-ignore 2. listen response multi times, and write to Response.body
-    window.__TAURI__.event
-      .listen("stream-response", (e: ResponseEvent) =>
+
+    // Listen for stream response events
+    listen("stream-response", (e: ResponseEvent) =>
      requestIdPromise.then((request_id) => {
        const { request_id: rid, chunk, status } = e?.payload || {};
        if (request_id != rid) {
@ -63,8 +66,7 @@ export function fetch(url: string, options?: RequestInit): Promise<Response> {
          close();
        }
      }),
-      )
-      .then((u: Function) => (unlisten = u));
+    ).then((u: () => void) => (unlisten = u));

    const headers: Record<string, string> = {
      Accept: "application/json, text/plain, */*",
@ -74,8 +76,7 @@ export function fetch(url: string, options?: RequestInit): Promise<Response> {
    for (const item of new Headers(_headers || {})) {
      headers[item[0]] = item[1];
    }
-    return window.__TAURI__
-      .invoke("stream_fetch", {
+    return invoke<StreamResponse>("stream_fetch", {
      method: method.toUpperCase(),
      url,
      headers,
--- a/package.json
+++ b/package.json
@ -26,6 +26,14 @@
    "@modelcontextprotocol/sdk": "^1.0.4",
    "@next/third-parties": "^14.1.0",
    "@svgr/webpack": "^6.5.1",
+    "@tauri-apps/plugin-clipboard-manager": "~2",
+    "@tauri-apps/plugin-dialog": "~2",
+    "@tauri-apps/plugin-fs": "~2",
+    "@tauri-apps/plugin-http": "~2",
+    "@tauri-apps/plugin-notification": "~2",
+    "@tauri-apps/plugin-shell": "~2",
+    "@tauri-apps/plugin-updater": "~2",
+    "@tauri-apps/plugin-window-state": "^2.2.1",
    "@vercel/analytics": "^0.1.11",
    "@vercel/speed-insights": "^1.0.2",
    "axios": "^1.7.5",
@ -39,7 +47,7 @@
    "markdown-to-txt": "^2.0.1",
    "mermaid": "^10.6.1",
    "nanoid": "^5.0.3",
-    "next": "^14.1.1",
+    "next": "14.2.24",
    "node-fetch": "^3.3.1",
    "openapi-client-axios": "^7.5.5",
    "react": "^18.2.0",
@ -59,8 +67,8 @@
    "zustand": "^4.3.8"
  },
  "devDependencies": {
-    "@tauri-apps/api": "^2.1.1",
-    "@tauri-apps/cli": "1.5.11",
+    "@tauri-apps/api": "^2.3.0",
+    "@tauri-apps/cli": "^2.3.1",
    "@testing-library/dom": "^10.4.0",
    "@testing-library/jest-dom": "^6.6.3",
    "@testing-library/react": "^16.1.0",
@ -75,7 +83,7 @@
    "concurrently": "^8.2.2",
    "cross-env": "^7.0.3",
    "eslint": "^8.49.0",
-    "eslint-config-next": "13.4.19",
+    "eslint-config-next": "14.2.24",
    "eslint-config-prettier": "^8.8.0",
    "eslint-plugin-prettier": "^5.1.3",
    "eslint-plugin-unused-imports": "^3.2.0",
--- a/src-tauri/Cargo.lock
+++ b/src-tauri/Cargo.lock
--- a/src-tauri/Cargo.toml
+++ b/src-tauri/Cargo.toml
@ -12,38 +12,31 @@ rust-version = "1.60"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

 [build-dependencies]
-tauri-build = { version = "1.5.1", features = [] }
+tauri-build = { version = "2", features = [] }

 [dependencies]
 serde_json = "1.0"
 serde = { version = "1.0", features = ["derive"] }
-tauri = { version = "1.5.4", features = [ "http-all",
-    "notification-all",
-    "fs-all",
-    "clipboard-all",
-    "dialog-all",
-    "shell-open",
-    "updater",
-    "window-close",
-    "window-hide",
-    "window-maximize",
-    "window-minimize",
-    "window-set-icon",
-    "window-set-ignore-cursor-events",
-    "window-set-resizable",
-    "window-show",
-    "window-start-dragging",
-    "window-unmaximize",
-    "window-unminimize",
+tauri = { version = "2", features = [
 ] }
-tauri-plugin-window-state = { git = "https://github.com/tauri-apps/plugins-workspace", branch = "v1" }
+tauri-plugin-window-state = { version = "2" }
 percent-encoding = "2.3.1"
 reqwest = "0.11.18"
 futures-util = "0.3.30"
 bytes = "1.7.2"
+log = "0.4.21"
+tauri-plugin-dialog = "2"
+tauri-plugin-shell = "2"
+tauri-plugin-notification = "2"
+tauri-plugin-fs = "2"
+tauri-plugin-http = "2"
+tauri-plugin-clipboard-manager = "2"

 [features]
 # this feature is used for production builds or when `devPath` points to the filesystem and the built-in dev server is disabled.
 # If you use cargo directly instead of tauri's cli you can use this feature flag to switch between tauri's `dev` and `build` modes.
 # DO NOT REMOVE!!
 custom-protocol = ["tauri/custom-protocol"]
+
+[target.'cfg(not(any(target_os = "android", target_os = "ios")))'.dependencies]
+tauri-plugin-updater = "2"
--- a/src-tauri/capabilities/desktop.json
+++ b/src-tauri/capabilities/desktop.json
@ -0,0 +1,14 @@
+{
+  "identifier": "desktop-capability",
+  "platforms": [
+    "macOS",
+    "windows",
+    "linux"
+  ],
+  "windows": [
+    "main"
+  ],
+  "permissions": [
+    "updater:default"
+  ]
+}
--- a/src-tauri/capabilities/migrated.json
+++ b/src-tauri/capabilities/migrated.json
@ -0,0 +1,57 @@
+{
+  "identifier": "migrated",
+  "description": "permissions that were migrated from v1",
+  "local": true,
+  "windows": [
+    "main"
+  ],
+  "permissions": [
+    "core:default",
+    "fs:allow-read-file",
+    "fs:allow-write-file",
+    "fs:allow-read-dir",
+    "fs:allow-copy-file",
+    "fs:allow-mkdir",
+    "fs:allow-remove",
+    "fs:allow-remove",
+    "fs:allow-rename",
+    "fs:allow-exists",
+    "core:window:allow-set-resizable",
+    "core:window:allow-maximize",
+    "core:window:allow-unmaximize",
+    "core:window:allow-minimize",
+    "core:window:allow-unminimize",
+    "core:window:allow-show",
+    "core:window:allow-hide",
+    "core:window:allow-close",
+    "core:window:allow-set-icon",
+    "core:window:allow-set-ignore-cursor-events",
+    "core:window:allow-start-dragging",
+    "shell:allow-open",
+    "dialog:allow-open",
+    "dialog:allow-save",
+    "dialog:allow-message",
+    "dialog:allow-ask",
+    "dialog:allow-confirm",
+    {
+      "identifier": "http:default",
+      "allow": [
+        {
+          "url": "https://*/"
+        },
+        {
+          "url": "http://*/"
+        }
+      ]
+    },
+    "notification:default",
+    "clipboard-manager:allow-read-text",
+    "clipboard-manager:allow-write-text",
+    "dialog:default",
+    "shell:default",
+    "notification:default",
+    "fs:default",
+    "http:default",
+    "clipboard-manager:default"
+  ]
+}
--- a/src-tauri/gen/schemas/acl-manifests.json
+++ b/src-tauri/gen/schemas/acl-manifests.json
--- a/src-tauri/gen/schemas/capabilities.json
+++ b/src-tauri/gen/schemas/capabilities.json
@ -0,0 +1 @@
+{"desktop-capability":{"identifier":"desktop-capability","description":"","local":true,"windows":["main"],"permissions":["updater:default"],"platforms":["macOS","windows","linux"]},"migrated":{"identifier":"migrated","description":"permissions that were migrated from v1","local":true,"windows":["main"],"permissions":["core:default","fs:allow-read-file","fs:allow-write-file","fs:allow-read-dir","fs:allow-copy-file","fs:allow-mkdir","fs:allow-remove","fs:allow-remove","fs:allow-rename","fs:allow-exists","core:window:allow-set-resizable","core:window:allow-maximize","core:window:allow-unmaximize","core:window:allow-minimize","core:window:allow-unminimize","core:window:allow-show","core:window:allow-hide","core:window:allow-close","core:window:allow-set-icon","core:window:allow-set-ignore-cursor-events","core:window:allow-start-dragging","shell:allow-open","dialog:allow-open","dialog:allow-save","dialog:allow-message","dialog:allow-ask","dialog:allow-confirm",{"identifier":"http:default","allow":[{"url":"https://*/"},{"url":"http://*/"}]},"notification:default","clipboard-manager:allow-read-text","clipboard-manager:allow-write-text","dialog:default","shell:default","notification:default","fs:default","http:default","clipboard-manager:default"]}}
--- a/src-tauri/gen/schemas/desktop-schema.json
+++ b/src-tauri/gen/schemas/desktop-schema.json
--- a/src-tauri/gen/schemas/macOS-schema.json
+++ b/src-tauri/gen/schemas/macOS-schema.json
--- a/src-tauri/src/main.rs
+++ b/src-tauri/src/main.rs
@ -5,6 +5,13 @@ mod stream;

 fn main() {
    tauri::Builder::default()
+        .plugin(tauri_plugin_updater::Builder::new().build())
+        .plugin(tauri_plugin_clipboard_manager::init())
+        .plugin(tauri_plugin_http::init())
+        .plugin(tauri_plugin_fs::init())
+        .plugin(tauri_plugin_notification::init())
+        .plugin(tauri_plugin_shell::init())
+        .plugin(tauri_plugin_dialog::init())
        .invoke_handler(tauri::generate_handler![stream::stream_fetch])
        .plugin(tauri_plugin_window_state::Builder::default().build())
        .run(tauri::generate_context!())
--- a/src-tauri/src/stream.rs
+++ b/src-tauri/src/stream.rs
@ -1,13 +1,15 @@
 //
 //

-use std::time::Duration;
+use futures_util::StreamExt;
+use std::collections::HashMap;
 use std::error::Error;
 use std::sync::atomic::{AtomicU32, Ordering};
-use std::collections::HashMap;
-use futures_util::{StreamExt};
-use reqwest::Client;
-use reqwest::header::{HeaderName, HeaderMap};
+use std::time::Duration;
+use tauri::Emitter;
+use tauri_plugin_http::reqwest;
+use tauri_plugin_http::reqwest::header::{HeaderMap, HeaderName};
+use tauri_plugin_http::reqwest::Client;

 static REQUEST_COUNTER: AtomicU32 = AtomicU32::new(0);

@ -16,7 +18,7 @@ pub struct StreamResponse {
    request_id: u32,
    status: u16,
    status_text: String,
-  headers: HashMap<String, String>
+    headers: HashMap<String, String>,
 }

 #[derive(Clone, serde::Serialize)]
@ -28,18 +30,17 @@ pub struct EndPayload {
 #[derive(Clone, serde::Serialize)]
 pub struct ChunkPayload {
    request_id: u32,
-  chunk: bytes::Bytes,
+    chunk: Vec<u8>,
 }

 #[tauri::command]
 pub async fn stream_fetch(
-  window: tauri::Window,
+    window: tauri::WebviewWindow,
    method: String,
    url: String,
    headers: HashMap<String, String>,
    body: Vec<u8>,
 ) -> Result<StreamResponse, String> {
-
    let event_name = "stream-response";
    let request_id = REQUEST_COUNTER.fetch_add(1, Ordering::SeqCst);

@ -53,7 +54,9 @@ pub async fn stream_fetch(
    // println!("headers: {:?}", headers);
    // println!("headers: {:?}", _headers);

-  let method = method.parse::<reqwest::Method>().map_err(|err| format!("failed to parse method: {}", err))?;
+    let method = method
+        .parse::<reqwest::Method>()
+        .map_err(|err| format!("failed to parse method: {}", err))?;
    let client = Client::builder()
        .default_headers(_headers)
        .redirect(reqwest::redirect::Policy::limited(3))
@ -63,10 +66,14 @@ pub async fn stream_fetch(

    let mut request = client.request(
        method.clone(),
-    url.parse::<reqwest::Url>().map_err(|err| format!("failed to parse url: {}", err))?
+        url.parse::<reqwest::Url>()
+            .map_err(|err| format!("failed to parse url: {}", err))?,
    );

-  if method == reqwest::Method::POST || method == reqwest::Method::PUT || method == reqwest::Method::PATCH {
+    if method == reqwest::Method::POST
+        || method == reqwest::Method::PUT
+        || method == reqwest::Method::PATCH
+    {
        let body = bytes::Bytes::from(body);
        // println!("body: {:?}", body);
        request = request.body(body);
@ -85,7 +92,7 @@ pub async fn stream_fetch(
            for (name, value) in res.headers() {
                headers.insert(
                    name.as_str().to_string(),
-          std::str::from_utf8(value.as_bytes()).unwrap().to_string()
+                    std::str::from_utf8(value.as_bytes()).unwrap().to_string(),
                );
            }
            let status = res.status().as_u16();
@ -97,7 +104,13 @@ pub async fn stream_fetch(
                    match chunk {
                        Ok(bytes) => {
                            // println!("chunk: {:?}", bytes);
-              if let Err(e) = window.emit(event_name, ChunkPayload{ request_id, chunk: bytes }) {
+                            if let Err(e) = window.emit(
+                                event_name,
+                                ChunkPayload {
+                                    request_id,
+                                    chunk: bytes.to_vec(),
+                                },
+                            ) {
                                println!("Failed to emit chunk payload: {:?}", e);
                            }
                        }
@ -106,7 +119,13 @@ pub async fn stream_fetch(
                        }
                    }
                }
-        if let Err(e) = window.emit(event_name, EndPayload{ request_id, status: 0 }) {
+                if let Err(e) = window.emit(
+                    event_name,
+                    EndPayload {
+                        request_id,
+                        status: 0,
+                    },
+                ) {
                    println!("Failed to emit end payload: {:?}", e);
                }
            });
@ -119,15 +138,28 @@ pub async fn stream_fetch(
            }
        }
        Err(err) => {
-      let error: String = err.source()
+            let error: String = err
+                .source()
                .map(|e| e.to_string())
                .unwrap_or_else(|| "Unknown error occurred".to_string());
            println!("Error response: {:?}", error);
            tauri::async_runtime::spawn(async move {
-        if let Err(e) = window.emit(event_name, ChunkPayload{ request_id, chunk: error.into() }) {
+                if let Err(e) = window.emit(
+                    event_name,
+                    ChunkPayload {
+                        request_id,
+                        chunk: error.into_bytes(),
+                    },
+                ) {
                    println!("Failed to emit chunk payload: {:?}", e);
                }
-        if let Err(e) = window.emit(event_name, EndPayload{ request_id, status: 0 }) {
+                if let Err(e) = window.emit(
+                    event_name,
+                    EndPayload {
+                        request_id,
+                        status: 0,
+                    },
+                ) {
                    println!("Failed to emit end payload: {:?}", e);
                }
            });
@ -142,4 +174,3 @@ pub async fn stream_fetch(
    // println!("Response: {:?}", response);
    Ok(response)
 }
-
--- a/src-tauri/tauri.conf.json
+++ b/src-tauri/tauri.conf.json
@ -3,67 +3,14 @@
  "build": {
    "beforeBuildCommand": "yarn export",
    "beforeDevCommand": "yarn export:dev",
-    "devPath": "http://localhost:3000",
-    "distDir": "../out",
-    "withGlobalTauri": true
-  },
-  "package": {
-    "productName": "NextChat",
-    "version": "2.15.8"
-  },
-  "tauri": {
-    "allowlist": {
-      "all": false,
-      "shell": {
-        "all": false,
-        "open": true
-      },
-      "dialog": {
-        "all": true,
-        "ask": true,
-        "confirm": true,
-        "message": true,
-        "open": true,
-        "save": true
-      },
-      "clipboard": {
-        "all": true,
-        "writeText": true,
-        "readText": true
-      },
-      "window": {
-        "all": false,
-        "close": true,
-        "hide": true,
-        "maximize": true,
-        "minimize": true,
-        "setIcon": true,
-        "setIgnoreCursorEvents": true,
-        "setResizable": true,
-        "show": true,
-        "startDragging": true,
-        "unmaximize": true,
-        "unminimize": true
-      },
-      "fs": {
-        "all": true
-      },
-      "notification": {
-        "all": true
-      },
-      "http": {
-        "all": true,
-        "request": true,
-        "scope": ["https://*", "http://*"]
-      }
+    "frontendDist": "../out",
+    "devUrl": "http://localhost:3000"
  },
  "bundle": {
    "active": true,
    "category": "DeveloperTool",
    "copyright": "2023, Zhang Yifei All Rights Reserved.",
-      "deb": {
-        "depends": []
-      },
+    "targets": "all",
    "externalBin": [],
    "icon": [
      "icons/32x32.png",
@ -72,7 +19,11 @@
      "icons/icon.icns",
      "icons/icon.ico"
    ],
-      "identifier": "com.yida.chatgpt.next.web",
+    "windows": {
+      "certificateThumbprint": null,
+      "digestAlgorithm": "sha256",
+      "timestampUrl": ""
+    },
    "longDescription": "NextChat is a cross-platform ChatGPT client, including Web/Win/Linux/OSX/PWA.",
    "macOS": {
      "entitlements": null,
@ -83,28 +34,30 @@
    },
    "resources": [],
    "shortDescription": "NextChat App",
-      "targets": "all",
-      "windows": {
-        "certificateThumbprint": null,
-        "digestAlgorithm": "sha256",
-        "timestampUrl": ""
+    "linux": {
+      "deb": {
+        "depends": []
      }
    },
-    "security": {
-      "csp": null,
-      "dangerousUseHttpScheme": true
+    "createUpdaterArtifacts": "v1Compatible"
  },
+  "productName": "NextChat",
+  "mainBinaryName": "NextChat",
+  "version": "2.15.8",
+  "identifier": "com.yida.chatgpt.next.web",
+  "plugins": {
    "updater": {
-      "active": true,
-      "endpoints": [
-        "https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/releases/latest/download/latest.json"
-      ],
-      "dialog": true,
      "windows": {
        "installMode": "passive"
      },
+      "endpoints": [
+        "https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/releases/latest/download/latest.json"
+      ],
      "pubkey": "dW50cnVzdGVkIGNvbW1lbnQ6IG1pbmlzaWduIHB1YmxpYyBrZXk6IERFNDE4MENFM0Y1RTZBOTQKUldTVWFsNC96b0JCM3RqM2NmMnlFTmxIaStRaEJrTHNOU2VqRVlIV1hwVURoWUdVdEc1eDcxVEYK"
+    }
  },
+  "app": {
+    "withGlobalTauri": true,
    "windows": [
      {
        "fullscreen": false,
@ -113,8 +66,12 @@
        "title": "NextChat",
        "width": 960,
        "hiddenTitle": true,
-        "titleBarStyle": "Overlay"
+        "titleBarStyle": "Overlay",
+        "useHttpsScheme": false
+      }
+    ],
+    "security": {
+      "csp": null
    }
-    ]
  }
 }
--- a/test/stream-fetch.test.ts
+++ b/test/stream-fetch.test.ts
@ -0,0 +1,167 @@
+import { jest } from '@jest/globals';
+
+// Create mocks
+const mockInvoke = jest.fn();
+const mockListen = jest.fn();
+
+// Mock Tauri modules before import
+jest.mock('@tauri-apps/api/core', () => ({
+  invoke: (...args: any[]) => mockInvoke(...args)
+}));
+
+jest.mock('@tauri-apps/api/event', () => ({
+  listen: (...args: any[]) => mockListen(...args)
+}));
+
+// Import function after mocking
+import { fetch as streamFetch } from '../app/utils/stream';
+import { invoke } from '@tauri-apps/api/core';
+import { listen } from '@tauri-apps/api/event';
+
+// Mock global objects
+// @ts-ignore
+global.TransformStream = class TransformStream {
+  writable = {
+    getWriter: () => ({
+      ready: Promise.resolve(),
+      // @ts-ignore
+      write: jest.fn().mockResolvedValue(undefined as any),
+      // @ts-ignore
+      close: jest.fn().mockResolvedValue(undefined as any)
+    })
+  };
+  readable = {} as any;
+} as any;
+
+// Add Response to global context
+global.Response = class Response {
+  constructor(public body: any, public init: any) {
+    Object.assign(this, init);
+  }
+  status: number = 200;
+  statusText: string = 'OK';
+  headers: any = {};
+} as any;
+
+describe('stream-fetch', () => {
+  let originalFetch: any;
+  let originalWindow: any;
+
+  beforeAll(() => {
+    originalFetch = global.fetch;
+    originalWindow = global.window;
+
+    // Mock window object
+    Object.defineProperty(global, 'window', {
+      value: {
+        __TAURI__: true,
+        __TAURI_INTERNALS__: {
+          transformCallback: (callback: Function) => callback,
+          invoke: mockInvoke
+        },
+        fetch: jest.fn(),
+        Headers: class Headers {
+          constructor() {}
+          entries() { return []; }
+        },
+        TextEncoder: class TextEncoder {
+          encode(text: string) {
+            return new Uint8Array(Array.from(text).map(c => c.charCodeAt(0)));
+          }
+        },
+        navigator: {
+          userAgent: 'test-agent'
+        },
+        Response: class Response {
+          constructor(public body: any, public init: any) {}
+          status: number = 200;
+          statusText: string = 'OK';
+          headers: any = {};
+        }
+      },
+      writable: true,
+    });
+  });
+
+  afterAll(() => {
+    Object.defineProperty(global, 'window', {
+      value: originalWindow,
+      writable: true,
+    });
+    global.fetch = originalFetch;
+  });
+
+  beforeEach(() => {
+    jest.clearAllMocks();
+
+    // Set up default behavior for listen
+    mockListen.mockImplementation(() => Promise.resolve(() => {}));
+  });
+
+  test('should use native fetch when Tauri is unavailable', async () => {
+    // Temporarily remove __TAURI__
+    const tempWindow = { ...window };
+    delete (tempWindow as any).__TAURI__;
+    Object.defineProperty(global, 'window', {
+      value: tempWindow,
+      writable: true,
+    });
+
+    await streamFetch('https://example.com');
+
+    // Check that native fetch was called
+    expect(window.fetch).toHaveBeenCalledWith('https://example.com', undefined);
+
+    // Restore __TAURI__
+    Object.defineProperty(global, 'window', {
+      value: { ...tempWindow, __TAURI__: true },
+      writable: true,
+    });
+  });
+
+  test('should use Tauri API when Tauri is available', async () => {
+    // Mock successful response from Tauri
+    // @ts-ignore
+    mockInvoke.mockResolvedValue({
+      request_id: 123,
+      status: 200,
+      status_text: 'OK',
+      headers: {}
+    } as any);
+
+    // Call fetch function
+    await streamFetch('https://example.com');
+
+    // Check that Tauri invoke was called with correct parameters
+    expect(mockInvoke).toHaveBeenCalledWith(
+      'stream_fetch',
+      expect.objectContaining({
+        url: 'https://example.com'
+      }),
+      undefined
+    );
+  });
+
+  test('should add abort signal to request', async () => {
+    // Mock successful response from Tauri
+    // @ts-ignore
+    mockInvoke.mockResolvedValue({
+      request_id: 123,
+      status: 200,
+      status_text: 'OK',
+      headers: {}
+    } as any);
+
+    // Create AbortController
+    const controller = new AbortController();
+    const addEventListenerSpy = jest.spyOn(controller.signal, 'addEventListener');
+
+    // Call fetch with signal
+    await streamFetch('https://example.com', {
+      signal: controller.signal
+    });
+
+    // Check that signal was added
+    expect(addEventListenerSpy).toHaveBeenCalledWith('abort', expect.any(Function));
+  });
+});
--- a/yarn.lock
+++ b/yarn.lock
Author	SHA1	Message	Date
Mike Klimin	8d8ca7f64e	Merge `956ec96d51` into `0031544e14`	2025-07-11 14:57:35 +03:00
RiverRay	0031544e14	Merge pull request #6552 from hyiip/main Some checks failed Run Tests / test (push) Has been cancelled Details Migrate to claude 4	2025-07-08 23:35:22 +08:00
RiverRay	1f33ceee8f	Merge pull request #6557 from JI4JUN/feat/support-302ai-provider Feat/support 302ai provider	2025-07-08 23:34:38 +08:00
JI4JUN	666ca734ec	docs: update README	2025-07-07 18:20:04 +08:00
JI4JUN	fda2eb1fb5	docs: update README	2025-07-07 18:18:46 +08:00
JI4JUN	93f8340744	Merge branch 'main' into feat/support-302ai-provider	2025-07-07 18:17:57 +08:00
hyiip	21d39b8dd6	Migrate to claude 4	2025-07-02 22:14:32 +08:00
RiverRay	814fd2786e	Merge pull request #6542 from JI4JUN/feat/support-302ai-provider Some checks failed Run Tests / test (push) Has been cancelled Details Feat/support 302ai provider	2025-06-30 20:29:47 +08:00
river	29dbffac3e	fix: update section title for Sponsor AI API in README	2025-06-30 14:58:36 +08:00
river	92532b2c74	fix: update 302.AI banners in README files and standardize formatting	2025-06-30 14:57:37 +08:00
river	4f16ca1320	fix: update 302.AI banners in README files and remove old images	2025-06-30 14:54:47 +08:00
JI4JUN	4d43fac12a	chore: add banners of 302.AI	2025-06-26 19:02:08 +08:00
JI4JUN	d3e164f23e	feat: add 302.AI provider	2025-06-25 18:10:02 +08:00
Mihail Klimin	956ec96d51	fix(types): improve typings in stream.ts - Replace generic Function type with specific () => void for unlisten - Enhance typing for setRequestId from Function to ((value: number) => void) - Address code review feedback from Biome linter	2025-03-16 12:03:49 +03:00
Mihail Klimin	8fa7c14f18	feat(tauri): Migrate from Tauri v1 to v2 # Summary This commit completes the migration from Tauri v1 to v2, resolves configuration issues, upgrades Next.js, and adds test coverage for critical components to ensure stability during the transition. # Details ## Tauri v2 Migration - Updated Tauri dependencies to v2.3.0 series in package.json - Restructured build configuration in `/app/config/build.ts` to align with Tauri v2 requirements - Fixed imports and API usage patterns across the codebase - Added compatibility layer for window.__TAURI__ references to maintain backward compatibility ## Next.js Issues - Upgraded Next.js from 14.1.1 to 14.2.24 - Resolved caching problems with Server Actions - Updated eslint-config-next to match the new version - Cleared Next.js cache and temporary files to address build issues ## Testing & Stability - Added comprehensive tests for `stream.ts` to verify streaming functionality - Created mocks for Tauri API to support test environment - Verified that critical functionality continues to work correctly - Translated all comments to English for consistency ## Infrastructure - Fixed peer dependency warnings during installation - Ensured proper integration with Tauri v2 plugins (clipboard-manager, dialog, fs, http, notification, shell, updater, window-state) # Approach Prioritized stability by: 1. Making minimal necessary changes to configuration files 2. Preserving most `window.__TAURI__` calls as they still function in v2 3. Planning gradual migration to new APIs with test coverage for critical components 4. Documenting areas that will require future attention # Testing - Created unit tests for critical streaming functionality - Performed manual testing of key application features - Verified successful build and launch with Tauri v2 # Future Work - Future PRs will gradually replace deprecated Tauri v1 API calls with v2 equivalents - Additional test coverage will be added for other critical components	2025-03-16 02:14:47 +03:00
				`@ -0,0 +1 @@`
				{"desktop-capability":{"identifier":"desktop-capability","description":"","local":true,"windows":["main"],"permissions":["updater:default"],"platforms":["macOS","windows","linux"]},"migrated":{"identifier":"migrated","description":"permissions that were migrated from v1","local":true,"windows":["main"],"permissions":["core:default","fs:allow-read-file","fs:allow-write-file","fs:allow-read-dir","fs:allow-copy-file","fs:allow-mkdir","fs:allow-remove","fs:allow-remove","fs:allow-rename","fs:allow-exists","core:window:allow-set-resizable","core:window:allow-maximize","core:window:allow-unmaximize","core:window:allow-minimize","core:window:allow-unminimize","core:window:allow-show","core:window:allow-hide","core:window:allow-close","core:window:allow-set-icon","core:window:allow-set-ignore-cursor-events","core:window:allow-start-dragging","shell:allow-open","dialog:allow-open","dialog:allow-save","dialog:allow-message","dialog:allow-ask","dialog:allow-confirm",{"identifier":"http:default","allow":[{"url":"https:///"},{"url":"http:///"}]},"notification:default","clipboard-manager:allow-read-text","clipboard-manager:allow-write-text","dialog:default","shell:default","notification:default","fs:default","http:default","clipboard-manager:default"]}}