Merge c3648a376f into c30ddfbb07

Merge pull request #6425 from yunlingz/o_model_md_response
Fix: Encourage markdown inclusion in model responses for o1/o3
2025-10-13 05:23:42 +08:00 · 2025-06-12 18:14:06 +08:00 · 2025-06-12 11:19:24 +08:00 · 2025-06-12 11:13:31 +08:00 · 2025-06-12 01:53:30 +00:00 · 2025-06-11 16:14:09 +08:00
53 changed files with 2250 additions and 362 deletions
--- a/.env.template
+++ b/.env.template
@@ -81,3 +81,7 @@ SILICONFLOW_API_KEY=

 ### siliconflow Api url (optional)
 SILICONFLOW_URL=
+
+HUAWEI_URL=
+
+HUAWEI_API_KEY=
--- a/README.md
+++ b/README.md
@@ -1,13 +1,13 @@
 <div align="center">

-<a href='https://nextchat.dev/chat'>
+<a href='https://nextchat.club'>
  <img src="https://github.com/user-attachments/assets/83bdcc07-ae5e-4954-a53a-ac151ba6ccf3" width="1000" alt="icon"/>
 </a>




-<h1 align="center">NextChat (ChatGPT Next Web)</h1>
+<h1 align="center">NextChat</h1>

 English / [简体中文](./README_CN.md)

@@ -22,10 +22,10 @@ English / [简体中文](./README_CN.md)
 [![MacOS][MacOS-image]][download-url]
 [![Linux][Linux-image]][download-url]

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


-[saas-url]: https://nextchat.dev/chat?utm_source=readme
+[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.dev/
 [download-url]: https://github.com/Yidadaa/ChatGPT-Next-Web/releases
@@ -40,13 +40,14 @@ English / [简体中文](./README_CN.md)

 </div>

-## 🥳 Cheer for DeepSeek, China's AI star!
- > Purpose-Built UI for DeepSeek Reasoner Model
+## 🥳 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)
+
 
-<img src="https://github.com/user-attachments/assets/f3952210-3af1-4dc0-9b81-40eaa4847d9a"/>
-
-
-
 ## 🫣 NextChat Support MCP  ! 
 > Before build, please set env ENABLE_MCP=true

--- a/README_CN.md
+++ b/README_CN.md
@@ -8,7 +8,7 @@

 一键免费部署你的私人 ChatGPT 网页应用，支持 Claude, GPT4 & Gemini Pro 模型。

-[NextChatAI](https://nextchat.dev/chat?utm_source=readme) / [企业版](#%E4%BC%81%E4%B8%9A%E7%89%88) / [演示 Demo](https://chat-gpt-next-web.vercel.app/) / [反馈 Issues](https://github.com/Yidadaa/ChatGPT-Next-Web/issues) / [加入 Discord](https://discord.gg/zrhvHCr79N)
+[NextChatAI](https://nextchat.club?utm_source=readme) / [企业版](#%E4%BC%81%E4%B8%9A%E7%89%88) / [演示 Demo](https://chat-gpt-next-web.vercel.app/) / [反馈 Issues](https://github.com/Yidadaa/ChatGPT-Next-Web/issues) / [加入 Discord](https://discord.gg/zrhvHCr79N)

 [<img src="https://vercel.com/button" alt="Deploy on Zeabur" 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)

--- a/README_JA.md
+++ b/README_JA.md
@@ -5,7 +5,7 @@

 ワンクリックで無料であなた専用の ChatGPT ウェブアプリをデプロイ。GPT3、GPT4 & Gemini Pro モデルをサポート。

-[NextChatAI](https://nextchat.dev/chat?utm_source=readme) / [企業版](#企業版) / [デモ](https://chat-gpt-next-web.vercel.app/) / [フィードバック](https://github.com/Yidadaa/ChatGPT-Next-Web/issues) / [Discordに参加](https://discord.gg/zrhvHCr79N)
+[NextChatAI](https://nextchat.club?utm_source=readme) / [企業版](#企業版) / [デモ](https://chat-gpt-next-web.vercel.app/) / [フィードバック](https://github.com/Yidadaa/ChatGPT-Next-Web/issues) / [Discordに参加](https://discord.gg/zrhvHCr79N)

 [<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)

--- 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 huaweiHandler } from "../../huawei";

 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.Huawei:
+      return huaweiHandler(req, { params });
    default:
      return proxyHandler(req, { params });
  }
--- a/app/api/huawei.ts
+++ b/app/api/huawei.ts
@@ -0,0 +1,176 @@
+import { getServerSideConfig } from "@/app/config/server";
+import {
+  HUAWEI_BASE_URL,
+  ApiPath,
+  ModelProvider,
+  Huawei,
+} from "@/app/constant";
+import { prettyObject } from "@/app/utils/format";
+import { NextRequest, NextResponse } from "next/server";
+import { auth } from "@/app/api/auth";
+
+const serverConfig = getServerSideConfig();
+
+export async function handle(
+  req: NextRequest,
+  { params }: { params: { path: string[] } },
+) {
+  console.log("[Huawei Route] params ", params);
+
+  if (req.method === "OPTIONS") {
+    return NextResponse.json({ body: "OK" }, { status: 200 });
+  }
+
+  const authResult = auth(req, ModelProvider.Huawei);
+  if (authResult.error) {
+    return NextResponse.json(authResult, {
+      status: 401,
+    });
+  }
+
+  try {
+    const response = await request(req);
+    return response;
+  } catch (e) {
+    console.error("[Huawei] ", e);
+    return NextResponse.json(prettyObject(e));
+  }
+}
+async function request(req: NextRequest) {
+  const controller = new AbortController();
+
+  let path = `${req.nextUrl.pathname}`.replaceAll(ApiPath.Huawei, "");
+  const bodyText = await req.text();
+  const body = JSON.parse(bodyText);
+  let modelName = body.model as string;
+
+  // 先用原始 modelName 获取 charUrl
+  let baseUrl: string;
+  let endpoint = "";
+  if (modelName === "DeepSeek-V3") {
+    endpoint = "271c9332-4aa6-4ff5-95b3-0cf8bd94c394";
+  }
+  if (modelName === "DeepSeek-R1") {
+    endpoint = "8a062fd4-7367-4ab4-a936-5eeb8fb821c4";
+  }
+
+
+  let charUrl = HUAWEI_BASE_URL.concat("/")
+    .concat(endpoint)
+    .concat("/v1/chat/completions")
+    .replace(/(?<!:)\/+/g, "/"); // 只替换不在 :// 后面的多个斜杠
+  console.log(`current charUrl name:${charUrl}`);
+  baseUrl = charUrl;
+
+  // 处理请求体：1. 移除 system role 消息 2. 修改 model 名称格式
+  const modifiedBody = {
+    messages: body.messages
+      .map((msg: any) => ({
+        role: msg.role,
+        content: msg.content,
+      }))
+      .filter((msg: any) => msg.role !== "system"),
+    model: modelName.replace(/^(DeepSeek-(?:R1|V3)).*$/, "$1"), // 只保留 DeepSeek-R1 或 DeepSeek-V3
+    stream: body.stream,
+    temperature: body.temperature,
+    presence_penalty: body.presence_penalty,
+    frequency_penalty: body.frequency_penalty,
+    top_p: body.top_p,
+  };
+  const modifiedBodyText = JSON.stringify(modifiedBody);
+  console.log("Modified request body:", modifiedBodyText);
+
+  // if(!baseUrl){
+  //     baseUrl = HUAWEI_BASE_URL
+  // }
+  // baseUrl = Huawei.ChatPath(modelName) || serverConfig.huaweiUrl || HUAWEI_BASE_URL;
+  console.log(
+    `current model name:${modelName},current api path:${baseUrl}.........`,
+  );
+  if (!baseUrl.startsWith("http")) {
+    baseUrl = `https://${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,
+  );
+
+  // 如果 baseUrl 来自 Huawei.ChatPath，则不需要再拼接 path
+  let fetchUrl = baseUrl.includes(HUAWEI_BASE_URL)
+    ? baseUrl
+    : `${baseUrl}${path}`;
+
+  const headers: Record<string, string> = {
+    "Content-Type": "application/json",
+    Authorization: req.headers.get("Authorization") ?? "",
+    "X-Forwarded-For": req.headers.get("X-Forwarded-For") ?? "",
+    "X-Real-IP": req.headers.get("X-Real-IP") ?? "",
+    "User-Agent": req.headers.get("User-Agent") ?? "",
+  };
+  console.debug(`headers.Authorization:${headers.Authorization}`);
+  console.debug("serverConfig.huaweiApiKey: *****");
+  // 如果没有 Authorization header，使用系统配置的 API key
+
+  headers.Authorization = `Bearer ${serverConfig.huaweiApiKey}`;
+
+  // #1815 try to refuse some request to some models
+  // if (serverConfig.customModels) {
+  //     try {
+  //         const jsonBody = JSON.parse(bodyText);  // 直接使用已解析的 body
+  //
+  //         if (
+  //             isModelNotavailableInServer(
+  //                 serverConfig.customModels,
+  //                 jsonBody?.model as string,
+  //                 ServiceProvider.Huawei as string,
+  //             )
+  //         ) {
+  //             return NextResponse.json(
+  //                 {
+  //                     error: true,
+  //                     message: `you are not allowed to use ${jsonBody?.model} model`,
+  //                 },
+  //                 {
+  //                     status: 403,
+  //                 },
+  //             );
+  //         }
+  //     } catch (e) {
+  //         console.error(`[Huawei] filter`, e);
+  //     }
+  // }
+  try {
+    const res = await fetch(fetchUrl, {
+      headers,
+      method: req.method,
+      body: modifiedBodyText,
+      redirect: "manual",
+      // @ts-ignore
+      duplex: "half",
+      signal: controller.signal,
+    });
+    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);
+  }
+}
+export { Huawei };
--- a/app/api/openai.ts
+++ b/app/api/openai.ts
@@ -14,8 +14,12 @@ 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("o1") || m.id.startsWith("o3")) ||
-        m.id.startsWith("gpt-4o-mini"),
+        !(
+          m.id.startsWith("gpt-4") ||
+          m.id.startsWith("chatgpt-4o") ||
+          m.id.startsWith("o1") ||
+          m.id.startsWith("o3")
+        ) || m.id.startsWith("gpt-4o-mini"),
    );
  }

--- 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 { HuaweiApi } from "./platforms/huawei";

 export const ROLES = ["system", "user", "assistant"] as const;
 export type MessageRole = (typeof ROLES)[number];
@@ -40,6 +41,11 @@ export interface MultimodalContent {
  };
 }

+export interface MultimodalContentForAlibaba {
+  text?: string;
+  image?: string;
+}
+
 export interface RequestMessage {
  role: MessageRole;
  content: string | MultimodalContent[];
@@ -168,6 +174,9 @@ export class ClientApi {
      case ModelProvider.SiliconFlow:
        this.llm = new SiliconflowApi();
        break;
+      case ModelProvider.Huawei:
+        this.llm = new HuaweiApi();
+        break;
      default:
        this.llm = new ChatGPTApi();
    }
@@ -260,6 +269,7 @@ export function getHeaders(ignoreHeaders: boolean = false) {
    const isChatGLM = modelConfig.providerName === ServiceProvider.ChatGLM;
    const isSiliconFlow =
      modelConfig.providerName === ServiceProvider.SiliconFlow;
+    const isHuawei = modelConfig.providerName == ServiceProvider.Huawei;
    const isEnabledAccessControl = accessStore.enabledAccessControl();
    const apiKey = isGoogle
      ? accessStore.googleApiKey
@@ -285,6 +295,8 @@ export function getHeaders(ignoreHeaders: boolean = false) {
      ? accessStore.iflytekApiKey && accessStore.iflytekApiSecret
        ? accessStore.iflytekApiKey + ":" + accessStore.iflytekApiSecret
        : ""
+      : isHuawei
+      ? accessStore.huaweiApiKey
      : accessStore.openaiApiKey;
    return {
      isGoogle,
@@ -299,6 +311,7 @@ export function getHeaders(ignoreHeaders: boolean = false) {
      isXAI,
      isChatGLM,
      isSiliconFlow,
+      isHuawei,
      apiKey,
      isEnabledAccessControl,
    };
@@ -327,6 +340,7 @@ export function getHeaders(ignoreHeaders: boolean = false) {
    isXAI,
    isChatGLM,
    isSiliconFlow,
+    isHuawei: boolean,
    apiKey,
    isEnabledAccessControl,
  } = getConfig();
@@ -377,6 +391,8 @@ export function getClientApi(provider: ServiceProvider): ClientApi {
      return new ClientApi(ModelProvider.ChatGLM);
    case ServiceProvider.SiliconFlow:
      return new ClientApi(ModelProvider.SiliconFlow);
+    case ServiceProvider.Huawei:
+      return new ClientApi(ModelProvider.Huawei);
    default:
      return new ClientApi(ModelProvider.GPT);
  }
--- a/app/client/platforms/alibaba.ts
+++ b/app/client/platforms/alibaba.ts
@@ -1,12 +1,16 @@
 "use client";
+import { ApiPath, Alibaba, ALIBABA_BASE_URL } from "@/app/constant";
 import {
-  ApiPath,
-  Alibaba,
-  ALIBABA_BASE_URL,
-  REQUEST_TIMEOUT_MS,
-} from "@/app/constant";
-import { useAccessStore, useAppConfig, useChatStore } from "@/app/store";
-
+  useAccessStore,
+  useAppConfig,
+  useChatStore,
+  ChatMessageTool,
+  usePluginStore,
+} from "@/app/store";
+import {
+  preProcessImageContentForAlibabaDashScope,
+  streamWithThink,
+} from "@/app/utils/chat";
 import {
  ChatOptions,
  getHeaders,
@@ -14,15 +18,15 @@ import {
  LLMModel,
  SpeechOptions,
  MultimodalContent,
+  MultimodalContentForAlibaba,
 } from "../api";
-import Locale from "../../locales";
-import {
-  EventStreamContentType,
-  fetchEventSource,
-} from "@fortaine/fetch-event-source";
-import { prettyObject } from "@/app/utils/format";
 import { getClientConfig } from "@/app/config/client";
-import { getMessageTextContent } from "@/app/utils";
+import {
+  getMessageTextContent,
+  getMessageTextContentWithoutThinking,
+  getTimeoutMSByModel,
+  isVisionModel,
+} from "@/app/utils";
 import { fetch } from "@/app/utils/stream";

 export interface OpenAIListModelResponse {
@@ -90,11 +94,6 @@ export class QwenApi implements LLMApi {
  }

  async chat(options: ChatOptions) {
-    const messages = options.messages.map((v) => ({
-      role: v.role,
-      content: getMessageTextContent(v),
-    }));
-
    const modelConfig = {
      ...useAppConfig.getState().modelConfig,
      ...useChatStore.getState().currentSession().mask.modelConfig,
@@ -103,6 +102,21 @@ export class QwenApi implements LLMApi {
      },
    };

+    const visionModel = isVisionModel(options.config.model);
+
+    const messages: ChatOptions["messages"] = [];
+    for (const v of options.messages) {
+      const content = (
+        visionModel
+          ? await preProcessImageContentForAlibabaDashScope(v.content)
+          : v.role === "assistant"
+          ? getMessageTextContentWithoutThinking(v)
+          : getMessageTextContent(v)
+      ) as any;
+
+      messages.push({ role: v.role, content });
+    }
+
    const shouldStream = !!options.config.stream;
    const requestPayload: RequestPayload = {
      model: modelConfig.model,
@@ -122,134 +136,120 @@ export class QwenApi implements LLMApi {
    options.onController?.(controller);

    try {
-      const chatPath = this.path(Alibaba.ChatPath);
+      const headers = {
+        ...getHeaders(),
+        "X-DashScope-SSE": shouldStream ? "enable" : "disable",
+      };
+
+      const chatPath = this.path(Alibaba.ChatPath(modelConfig.model));
      const chatPayload = {
        method: "POST",
        body: JSON.stringify(requestPayload),
        signal: controller.signal,
-        headers: {
-          ...getHeaders(),
-          "X-DashScope-SSE": shouldStream ? "enable" : "disable",
-        },
+        headers: headers,
      };

      // make a fetch request
      const requestTimeoutId = setTimeout(
        () => controller.abort(),
-        REQUEST_TIMEOUT_MS,
+        getTimeoutMSByModel(options.config.model),
      );

      if (shouldStream) {
-        let responseText = "";
-        let remainText = "";
-        let finished = false;
-        let responseRes: Response;
+        const [tools, funcs] = usePluginStore
+          .getState()
+          .getAsTools(
+            useChatStore.getState().currentSession().mask?.plugin || [],
+          );
+        return streamWithThink(
+          chatPath,
+          requestPayload,
+          headers,
+          tools as any,
+          funcs,
+          controller,
+          // parseSSE
+          (text: string, runTools: ChatMessageTool[]) => {
+            // console.log("parseSSE", text, runTools);
+            const json = JSON.parse(text);
+            const choices = json.output.choices as Array<{
+              message: {
+                content: string | null | MultimodalContentForAlibaba[];
+                tool_calls: ChatMessageTool[];
+                reasoning_content: string | null;
+              };
+            }>;

-        // animate response to make it looks smooth
-        function animateResponseText() {
-          if (finished || controller.signal.aborted) {
-            responseText += remainText;
-            console.log("[Response Animation] finished");
-            if (responseText?.length === 0) {
-              options.onError?.(new Error("empty response from server"));
-            }
-            return;
-          }
+            if (!choices?.length) return { isThinking: false, content: "" };

-          if (remainText.length > 0) {
-            const fetchCount = Math.max(1, Math.round(remainText.length / 60));
-            const fetchText = remainText.slice(0, fetchCount);
-            responseText += fetchText;
-            remainText = remainText.slice(fetchCount);
-            options.onUpdate?.(responseText, fetchText);
-          }
-
-          requestAnimationFrame(animateResponseText);
-        }
-
-        // start animaion
-        animateResponseText();
-
-        const finish = () => {
-          if (!finished) {
-            finished = true;
-            options.onFinish(responseText + remainText, responseRes);
-          }
-        };
-
-        controller.signal.onabort = finish;
-
-        fetchEventSource(chatPath, {
-          fetch: fetch as any,
-          ...chatPayload,
-          async onopen(res) {
-            clearTimeout(requestTimeoutId);
-            const contentType = res.headers.get("content-type");
-            console.log(
-              "[Alibaba] request response content type: ",
-              contentType,
-            );
-            responseRes = res;
-
-            if (contentType?.startsWith("text/plain")) {
-              responseText = await res.clone().text();
-              return finish();
+            const tool_calls = choices[0]?.message?.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]?.message?.reasoning_content;
+            const content = choices[0]?.message?.content;
+
+            // Skip if both content and reasoning_content are empty or null
            if (
-              !res.ok ||
-              !res.headers
-                .get("content-type")
-                ?.startsWith(EventStreamContentType) ||
-              res.status !== 200
+              (!reasoning || reasoning.length === 0) &&
+              (!content || content.length === 0)
            ) {
-              const responseTexts = [responseText];
-              let extraInfo = await res.clone().text();
-              try {
-                const resJson = await res.clone().json();
-                extraInfo = prettyObject(resJson);
-              } catch {}
-
-              if (res.status === 401) {
-                responseTexts.push(Locale.Error.Unauthorized);
-              }
-
-              if (extraInfo) {
-                responseTexts.push(extraInfo);
-              }
-
-              responseText = responseTexts.join("\n\n");
-
-              return finish();
+              return {
+                isThinking: false,
+                content: "",
+              };
            }
-          },
-          onmessage(msg) {
-            if (msg.data === "[DONE]" || finished) {
-              return finish();
-            }
-            const text = msg.data;
-            try {
-              const json = JSON.parse(text);
-              const choices = json.output.choices as Array<{
-                message: { content: string };
-              }>;
-              const delta = choices[0]?.message?.content;
-              if (delta) {
-                remainText += delta;
-              }
-            } catch (e) {
-              console.error("[Request] parse error", text, msg);
+
+            if (reasoning && reasoning.length > 0) {
+              return {
+                isThinking: true,
+                content: reasoning,
+              };
+            } else if (content && content.length > 0) {
+              return {
+                isThinking: false,
+                content: Array.isArray(content)
+                  ? content.map((item) => item.text).join(",")
+                  : content,
+              };
            }
+
+            return {
+              isThinking: false,
+              content: "",
+            };
          },
-          onclose() {
-            finish();
+          // processToolMessage, include tool_calls message and tool call results
+          (
+            requestPayload: RequestPayload,
+            toolCallMessage: any,
+            toolCallResult: any[],
+          ) => {
+            requestPayload?.input?.messages?.splice(
+              requestPayload?.input?.messages?.length,
+              0,
+              toolCallMessage,
+              ...toolCallResult,
+            );
          },
-          onerror(e) {
-            options.onError?.(e);
-            throw e;
-          },
-          openWhenHidden: true,
-        });
+          options,
+        );
      } else {
        const res = await fetch(chatPath, chatPayload);
        clearTimeout(requestTimeoutId);
--- a/app/client/platforms/baidu.ts
+++ b/app/client/platforms/baidu.ts
@@ -1,10 +1,5 @@
 "use client";
-import {
-  ApiPath,
-  Baidu,
-  BAIDU_BASE_URL,
-  REQUEST_TIMEOUT_MS,
-} from "@/app/constant";
+import { ApiPath, Baidu, BAIDU_BASE_URL } from "@/app/constant";
 import { useAccessStore, useAppConfig, useChatStore } from "@/app/store";
 import { getAccessToken } from "@/app/utils/baidu";

@@ -23,7 +18,7 @@ import {
 } from "@fortaine/fetch-event-source";
 import { prettyObject } from "@/app/utils/format";
 import { getClientConfig } from "@/app/config/client";
-import { getMessageTextContent } from "@/app/utils";
+import { getMessageTextContent, getTimeoutMSByModel } from "@/app/utils";
 import { fetch } from "@/app/utils/stream";

 export interface OpenAIListModelResponse {
@@ -155,7 +150,7 @@ export class ErnieApi implements LLMApi {
      // make a fetch request
      const requestTimeoutId = setTimeout(
        () => controller.abort(),
-        REQUEST_TIMEOUT_MS,
+        getTimeoutMSByModel(options.config.model),
      );

      if (shouldStream) {
--- a/app/client/platforms/bytedance.ts
+++ b/app/client/platforms/bytedance.ts
@@ -1,11 +1,12 @@
 "use client";
+import { ApiPath, ByteDance, BYTEDANCE_BASE_URL } from "@/app/constant";
 import {
-  ApiPath,
-  ByteDance,
-  BYTEDANCE_BASE_URL,
-  REQUEST_TIMEOUT_MS,
-} from "@/app/constant";
-import { useAccessStore, useAppConfig, useChatStore } from "@/app/store";
+  useAccessStore,
+  useAppConfig,
+  useChatStore,
+  ChatMessageTool,
+  usePluginStore,
+} from "@/app/store";

 import {
  ChatOptions,
@@ -15,14 +16,14 @@ import {
  MultimodalContent,
  SpeechOptions,
 } from "../api";
-import Locale from "../../locales";
-import {
-  EventStreamContentType,
-  fetchEventSource,
-} from "@fortaine/fetch-event-source";
-import { prettyObject } from "@/app/utils/format";
+
+import { streamWithThink } from "@/app/utils/chat";
 import { getClientConfig } from "@/app/config/client";
 import { preProcessImageContent } from "@/app/utils/chat";
+import {
+  getMessageTextContentWithoutThinking,
+  getTimeoutMSByModel,
+} from "@/app/utils";
 import { fetch } from "@/app/utils/stream";

 export interface OpenAIListModelResponse {
@@ -34,7 +35,7 @@ export interface OpenAIListModelResponse {
  }>;
 }

-interface RequestPayload {
+interface RequestPayloadForByteDance {
  messages: {
    role: "system" | "user" | "assistant";
    content: string | MultimodalContent[];
@@ -86,7 +87,10 @@ export class DoubaoApi implements LLMApi {
  async chat(options: ChatOptions) {
    const messages: ChatOptions["messages"] = [];
    for (const v of options.messages) {
-      const content = await preProcessImageContent(v.content);
+      const content =
+        v.role === "assistant"
+          ? getMessageTextContentWithoutThinking(v)
+          : await preProcessImageContent(v.content);
      messages.push({ role: v.role, content });
    }

@@ -99,7 +103,7 @@ export class DoubaoApi implements LLMApi {
    };

    const shouldStream = !!options.config.stream;
-    const requestPayload: RequestPayload = {
+    const requestPayload: RequestPayloadForByteDance = {
      messages,
      stream: shouldStream,
      model: modelConfig.model,
@@ -124,119 +128,101 @@ export class DoubaoApi implements LLMApi {
      // make a fetch request
      const requestTimeoutId = setTimeout(
        () => controller.abort(),
-        REQUEST_TIMEOUT_MS,
+        getTimeoutMSByModel(options.config.model),
      );

      if (shouldStream) {
-        let responseText = "";
-        let remainText = "";
-        let finished = false;
-        let responseRes: Response;
+        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;
+              };
+            }>;

-        // animate response to make it looks smooth
-        function animateResponseText() {
-          if (finished || controller.signal.aborted) {
-            responseText += remainText;
-            console.log("[Response Animation] finished");
-            if (responseText?.length === 0) {
-              options.onError?.(new Error("empty response from server"));
-            }
-            return;
-          }
-
-          if (remainText.length > 0) {
-            const fetchCount = Math.max(1, Math.round(remainText.length / 60));
-            const fetchText = remainText.slice(0, fetchCount);
-            responseText += fetchText;
-            remainText = remainText.slice(fetchCount);
-            options.onUpdate?.(responseText, fetchText);
-          }
-
-          requestAnimationFrame(animateResponseText);
-        }
-
-        // start animaion
-        animateResponseText();
-
-        const finish = () => {
-          if (!finished) {
-            finished = true;
-            options.onFinish(responseText + remainText, responseRes);
-          }
-        };
-
-        controller.signal.onabort = finish;
-
-        fetchEventSource(chatPath, {
-          fetch: fetch as any,
-          ...chatPayload,
-          async onopen(res) {
-            clearTimeout(requestTimeoutId);
-            const contentType = res.headers.get("content-type");
-            console.log(
-              "[ByteDance] request response content type: ",
-              contentType,
-            );
-            responseRes = res;
-            if (contentType?.startsWith("text/plain")) {
-              responseText = await res.clone().text();
-              return finish();
+            if (!choices?.length) return { isThinking: false, content: "" };
+
+            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 (
-              !res.ok ||
-              !res.headers
-                .get("content-type")
-                ?.startsWith(EventStreamContentType) ||
-              res.status !== 200
+              (!reasoning || reasoning.length === 0) &&
+              (!content || content.length === 0)
            ) {
-              const responseTexts = [responseText];
-              let extraInfo = await res.clone().text();
-              try {
-                const resJson = await res.clone().json();
-                extraInfo = prettyObject(resJson);
-              } catch {}
-
-              if (res.status === 401) {
-                responseTexts.push(Locale.Error.Unauthorized);
-              }
-
-              if (extraInfo) {
-                responseTexts.push(extraInfo);
-              }
-
-              responseText = responseTexts.join("\n\n");
-
-              return finish();
+              return {
+                isThinking: false,
+                content: "",
+              };
            }
-          },
-          onmessage(msg) {
-            if (msg.data === "[DONE]" || finished) {
-              return finish();
-            }
-            const text = msg.data;
-            try {
-              const json = JSON.parse(text);
-              const choices = json.choices as Array<{
-                delta: { content: string };
-              }>;
-              const delta = choices[0]?.delta?.content;
-              if (delta) {
-                remainText += delta;
-              }
-            } catch (e) {
-              console.error("[Request] parse error", text, msg);
+
+            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: "",
+            };
          },
-          onclose() {
-            finish();
+          // processToolMessage, include tool_calls message and tool call results
+          (
+            requestPayload: RequestPayloadForByteDance,
+            toolCallMessage: any,
+            toolCallResult: any[],
+          ) => {
+            requestPayload?.messages?.splice(
+              requestPayload?.messages?.length,
+              0,
+              toolCallMessage,
+              ...toolCallResult,
+            );
          },
-          onerror(e) {
-            options.onError?.(e);
-            throw e;
-          },
-          openWhenHidden: true,
-        });
+          options,
+        );
      } else {
        const res = await fetch(chatPath, chatPayload);
        clearTimeout(requestTimeoutId);
--- a/app/client/platforms/deepseek.ts
+++ b/app/client/platforms/deepseek.ts
@@ -1,12 +1,6 @@
 "use client";
 // azure and openai, using same models. so using same LLMApi.
-import {
-  ApiPath,
-  DEEPSEEK_BASE_URL,
-  DeepSeek,
-  REQUEST_TIMEOUT_MS,
-  REQUEST_TIMEOUT_MS_FOR_THINKING,
-} from "@/app/constant";
+import { ApiPath, DEEPSEEK_BASE_URL, DeepSeek } from "@/app/constant";
 import {
  useAccessStore,
  useAppConfig,
@@ -26,6 +20,7 @@ import { getClientConfig } from "@/app/config/client";
 import {
  getMessageTextContent,
  getMessageTextContentWithoutThinking,
+  getTimeoutMSByModel,
 } from "@/app/utils";
 import { RequestPayload } from "./openai";
 import { fetch } from "@/app/utils/stream";
@@ -80,6 +75,25 @@ export class DeepSeekApi implements LLMApi {
      }
    }

+    // 检测并修复消息顺序，确保除system外的第一个消息是user
+    const filteredMessages: ChatOptions["messages"] = [];
+    let hasFoundFirstUser = false;
+
+    for (const msg of messages) {
+      if (msg.role === "system") {
+        // Keep all system messages
+        filteredMessages.push(msg);
+      } else if (msg.role === "user") {
+        // User message directly added
+        filteredMessages.push(msg);
+        hasFoundFirstUser = true;
+      } else if (hasFoundFirstUser) {
+        // After finding the first user message, all subsequent non-system messages are retained.
+        filteredMessages.push(msg);
+      }
+      // If hasFoundFirstUser is false and it is not a system message, it will be skipped.
+    }
+
    const modelConfig = {
      ...useAppConfig.getState().modelConfig,
      ...useChatStore.getState().currentSession().mask.modelConfig,
@@ -90,7 +104,7 @@ export class DeepSeekApi implements LLMApi {
    };

    const requestPayload: RequestPayload = {
-      messages,
+      messages: filteredMessages,
      stream: options.config.stream,
      model: modelConfig.model,
      temperature: modelConfig.temperature,
@@ -116,16 +130,10 @@ export class DeepSeekApi implements LLMApi {
        headers: getHeaders(),
      };

-      // console.log(chatPayload);
-
-      const isR1 =
-        options.config.model.endsWith("-reasoner") ||
-        options.config.model.endsWith("-r1");
-
      // make a fetch request
      const requestTimeoutId = setTimeout(
        () => controller.abort(),
-        isR1 ? REQUEST_TIMEOUT_MS_FOR_THINKING : REQUEST_TIMEOUT_MS,
+        getTimeoutMSByModel(options.config.model),
      );

      if (shouldStream) {
@@ -176,8 +184,8 @@ export class DeepSeekApi implements LLMApi {

            // Skip if both content and reasoning_content are empty or null
            if (
-              (!reasoning || reasoning.trim().length === 0) &&
-              (!content || content.trim().length === 0)
+              (!reasoning || reasoning.length === 0) &&
+              (!content || content.length === 0)
            ) {
              return {
                isThinking: false,
@@ -185,12 +193,12 @@ export class DeepSeekApi implements LLMApi {
              };
            }

-            if (reasoning && reasoning.trim().length > 0) {
+            if (reasoning && reasoning.length > 0) {
              return {
                isThinking: true,
                content: reasoning,
              };
-            } else if (content && content.trim().length > 0) {
+            } else if (content && content.length > 0) {
              return {
                isThinking: false,
                content: content,
--- a/app/client/platforms/glm.ts
+++ b/app/client/platforms/glm.ts
@@ -1,10 +1,5 @@
 "use client";
-import {
-  ApiPath,
-  CHATGLM_BASE_URL,
-  ChatGLM,
-  REQUEST_TIMEOUT_MS,
-} from "@/app/constant";
+import { ApiPath, CHATGLM_BASE_URL, ChatGLM } from "@/app/constant";
 import {
  useAccessStore,
  useAppConfig,
@@ -21,7 +16,11 @@ import {
  SpeechOptions,
 } from "../api";
 import { getClientConfig } from "@/app/config/client";
-import { getMessageTextContent, isVisionModel } from "@/app/utils";
+import {
+  getMessageTextContent,
+  isVisionModel,
+  getTimeoutMSByModel,
+} from "@/app/utils";
 import { RequestPayload } from "./openai";
 import { fetch } from "@/app/utils/stream";
 import { preProcessImageContent } from "@/app/utils/chat";
@@ -191,7 +190,7 @@ export class ChatGLMApi implements LLMApi {

      const requestTimeoutId = setTimeout(
        () => controller.abort(),
-        REQUEST_TIMEOUT_MS,
+        getTimeoutMSByModel(options.config.model),
      );

      if (modelType === "image" || modelType === "video") {
--- a/app/client/platforms/google.ts
+++ b/app/client/platforms/google.ts
@@ -1,9 +1,4 @@
-import {
-  ApiPath,
-  Google,
-  REQUEST_TIMEOUT_MS,
-  REQUEST_TIMEOUT_MS_FOR_THINKING,
-} from "@/app/constant";
+import { ApiPath, Google } from "@/app/constant";
 import {
  ChatOptions,
  getHeaders,
@@ -27,6 +22,7 @@ import {
  getMessageTextContent,
  getMessageImages,
  isVisionModel,
+  getTimeoutMSByModel,
 } from "@/app/utils";
 import { preProcessImageContent } from "@/app/utils/chat";
 import { nanoid } from "nanoid";
@@ -206,7 +202,7 @@ export class GeminiProApi implements LLMApi {
      // make a fetch request
      const requestTimeoutId = setTimeout(
        () => controller.abort(),
-        isThinking ? REQUEST_TIMEOUT_MS_FOR_THINKING : REQUEST_TIMEOUT_MS,
+        getTimeoutMSByModel(options.config.model),
      );

      if (shouldStream) {
--- a/app/client/platforms/huawei.ts
+++ b/app/client/platforms/huawei.ts
@@ -0,0 +1,200 @@
+"use client";
+
+import { ApiPath, HUAWEI_BASE_URL, Huawei } from "@/app/constant";
+import {
+  useAccessStore,
+  useAppConfig,
+  useChatStore,
+  usePluginStore,
+  ChatMessageTool,
+} from "@/app/store";
+import {
+  ChatOptions,
+  getHeaders,
+  LLMApi,
+  LLMModel,
+  MultimodalContent,
+  SpeechOptions,
+} from "../api";
+import { getClientConfig } from "@/app/config/client";
+import { getTimeoutMSByModel } from "@/app/utils";
+import { streamWithThink } from "@/app/utils/chat";
+import { fetch } from "@/app/utils/stream";
+
+interface RequestPayloadForHuawei {
+  messages: {
+    role: "system" | "user" | "assistant";
+    content: string | MultimodalContent[];
+  }[];
+  stream?: boolean;
+  model: string;
+  temperature: number;
+  presence_penalty: number;
+  frequency_penalty: number;
+  top_p: number;
+  max_tokens?: number;
+}
+
+export class HuaweiApi implements LLMApi {
+  path(path: string): string {
+    const accessStore = useAccessStore.getState();
+
+    let baseUrl = "";
+
+    if (accessStore.useCustomConfig) {
+      baseUrl = accessStore.huaweiUrl;
+    }
+
+    if (baseUrl.length === 0) {
+      const isApp = !!getClientConfig()?.isApp;
+      baseUrl = isApp ? HUAWEI_BASE_URL : ApiPath.Huawei;
+    }
+
+    if (baseUrl.endsWith("/")) {
+      baseUrl = baseUrl.slice(0, baseUrl.length - 1);
+    }
+    if (!baseUrl.startsWith("http") && !baseUrl.startsWith(ApiPath.Huawei)) {
+      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 messages = options.messages.map((v) => ({
+      role: v.role,
+      content: v.content,
+    }));
+
+    const modelConfig = {
+      ...useAppConfig.getState().modelConfig,
+      ...useChatStore.getState().currentSession().mask.modelConfig,
+      ...{
+        model: options.config.model,
+      },
+    };
+
+    const requestPayload: RequestPayloadForHuawei = {
+      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,
+    };
+
+    const shouldStream = !!options.config.stream;
+    const controller = new AbortController();
+    options.onController?.(controller);
+
+    try {
+      const chatPath = this.path(Huawei.ChatPath);
+      const chatPayload = {
+        method: "POST",
+        body: JSON.stringify(requestPayload),
+        signal: controller.signal,
+        headers: getHeaders(),
+      };
+
+      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[]) => {
+            const json = JSON.parse(text);
+            const choices = json.choices as Array<{
+              delta: {
+                content: string;
+                tool_calls: ChatMessageTool[];
+              };
+            }>;
+            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;
+              }
+            }
+            return {
+              isThinking: false,
+              content: choices[0]?.delta?.content || "",
+            };
+          },
+          // processToolMessage
+          (
+            payload: RequestPayloadForHuawei,
+            toolCallMessage: any,
+            toolCallResult: any[],
+          ) => {
+            payload?.messages?.splice(
+              payload?.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[]> {
+    return [];
+  }
+}
--- a/app/client/platforms/openai.ts
+++ b/app/client/platforms/openai.ts
@@ -8,7 +8,6 @@ import {
  Azure,
  REQUEST_TIMEOUT_MS,
  ServiceProvider,
-  REQUEST_TIMEOUT_MS_FOR_THINKING,
 } from "@/app/constant";
 import {
  ChatMessageTool,
@@ -22,7 +21,7 @@ import {
  preProcessImageContent,
  uploadImage,
  base64Image2Blob,
-  stream,
+  streamWithThink,
 } from "@/app/utils/chat";
 import { cloudflareAIGatewayUrl } from "@/app/utils/cloudflare";
 import { ModelSize, DalleQuality, DalleStyle } from "@/app/typing";
@@ -42,6 +41,7 @@ import {
  getMessageTextContent,
  isVisionModel,
  isDalle3 as _isDalle3,
+  getTimeoutMSByModel,
 } from "@/app/utils";
 import { fetch } from "@/app/utils/stream";

@@ -56,7 +56,7 @@ export interface OpenAIListModelResponse {

 export interface RequestPayload {
  messages: {
-    role: "system" | "user" | "assistant";
+    role: "developer" | "system" | "user" | "assistant";
    content: string | MultimodalContent[];
  }[];
  stream?: boolean;
@@ -198,7 +198,8 @@ export class ChatGPTApi implements LLMApi {
    const isDalle3 = _isDalle3(options.config.model);
    const isO1OrO3 =
      options.config.model.startsWith("o1") ||
-      options.config.model.startsWith("o3");
+      options.config.model.startsWith("o3") ||
+      options.config.model.startsWith("o4-mini");
    if (isDalle3) {
      const prompt = getMessageTextContent(
        options.messages.slice(-1)?.pop() as any,
@@ -237,13 +238,21 @@ export class ChatGPTApi implements LLMApi {
        // Please do not ask me why not send max_tokens, no reason, this param is just shit, I dont want to explain anymore.
      };

-      // O1 使用 max_completion_tokens 控制token数 (https://platform.openai.com/docs/guides/reasoning#controlling-costs)
      if (isO1OrO3) {
+        // by default the o1/o3 models will not attempt to produce output that includes markdown formatting
+        // manually add "Formatting re-enabled" developer message to encourage markdown inclusion in model responses
+        // (https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/reasoning?tabs=python-secure#markdown-output)
+        requestPayload["messages"].unshift({
+          role: "developer",
+          content: "Formatting re-enabled",
+        });
+
+        // o1/o3 uses max_completion_tokens to control the number of tokens (https://platform.openai.com/docs/guides/reasoning#controlling-costs)
        requestPayload["max_completion_tokens"] = modelConfig.max_tokens;
      }

      // add max_tokens to vision model
-      if (visionModel) {
+      if (visionModel && !isO1OrO3) {
        requestPayload["max_tokens"] = Math.max(modelConfig.max_tokens, 4000);
      }
    }
@@ -294,7 +303,7 @@ export class ChatGPTApi implements LLMApi {
            useChatStore.getState().currentSession().mask?.plugin || [],
          );
        // console.log("getAsTools", tools, funcs);
-        stream(
+        streamWithThink(
          chatPath,
          requestPayload,
          getHeaders(),
@@ -309,8 +318,12 @@ export class ChatGPTApi implements LLMApi {
              delta: {
                content: string;
                tool_calls: ChatMessageTool[];
+                reasoning_content: string | null;
              };
            }>;
+
+            if (!choices?.length) return { isThinking: false, content: "" };
+
            const tool_calls = choices[0]?.delta?.tool_calls;
            if (tool_calls?.length > 0) {
              const id = tool_calls[0]?.id;
@@ -330,7 +343,37 @@ export class ChatGPTApi implements LLMApi {
                runTools[index]["function"]["arguments"] += args;
              }
            }
-            return choices[0]?.delta?.content;
+
+            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
          (
@@ -362,9 +405,7 @@ export class ChatGPTApi implements LLMApi {
        // make a fetch request
        const requestTimeoutId = setTimeout(
          () => controller.abort(),
-          isDalle3 || isO1OrO3
-            ? REQUEST_TIMEOUT_MS_FOR_THINKING
-            : REQUEST_TIMEOUT_MS, // dalle3 using b64_json is slow.
+          getTimeoutMSByModel(options.config.model),
        );

        const res = await fetch(chatPath, chatPayload);
--- a/app/client/platforms/siliconflow.ts
+++ b/app/client/platforms/siliconflow.ts
@@ -4,7 +4,7 @@ import {
  ApiPath,
  SILICONFLOW_BASE_URL,
  SiliconFlow,
-  REQUEST_TIMEOUT_MS_FOR_THINKING,
+  DEFAULT_MODELS,
 } from "@/app/constant";
 import {
  useAccessStore,
@@ -13,7 +13,7 @@ import {
  ChatMessageTool,
  usePluginStore,
 } from "@/app/store";
-import { streamWithThink } from "@/app/utils/chat";
+import { preProcessImageContent, streamWithThink } from "@/app/utils/chat";
 import {
  ChatOptions,
  getHeaders,
@@ -25,12 +25,23 @@ 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 SiliconFlowListModelResponse {
+  object: string;
+  data: Array<{
+    id: string;
+    object: string;
+    root: string;
+  }>;
+}

 export class SiliconflowApi implements LLMApi {
-  private disableListModels = true;
+  private disableListModels = false;

  path(path: string): string {
    const accessStore = useAccessStore.getState();
@@ -71,13 +82,16 @@ export class SiliconflowApi implements LLMApi {
  }

  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 = getMessageTextContent(v);
+        const content = visionModel
+          ? await preProcessImageContent(v.content)
+          : getMessageTextContent(v);
        messages.push({ role: v.role, content });
      }
    }
@@ -123,7 +137,7 @@ export class SiliconflowApi implements LLMApi {
      // Use extended timeout for thinking models as they typically require more processing time
      const requestTimeoutId = setTimeout(
        () => controller.abort(),
-        REQUEST_TIMEOUT_MS_FOR_THINKING,
+        getTimeoutMSByModel(options.config.model),
      );

      if (shouldStream) {
@@ -238,6 +252,36 @@ export class SiliconflowApi implements LLMApi {
  }

  async models(): Promise<LLMModel[]> {
-    return [];
+    if (this.disableListModels) {
+      return DEFAULT_MODELS.slice();
+    }
+
+    const res = await fetch(this.path(SiliconFlow.ListModelPath), {
+      method: "GET",
+      headers: {
+        ...getHeaders(),
+      },
+    });
+
+    const resJson = (await res.json()) as SiliconFlowListModelResponse;
+    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: "siliconflow",
+        providerName: "SiliconFlow",
+        providerType: "siliconflow",
+        sorted: 14,
+      },
+    }));
  }
 }
--- a/app/client/platforms/tencent.ts
+++ b/app/client/platforms/tencent.ts
@@ -1,5 +1,5 @@
 "use client";
-import { ApiPath, TENCENT_BASE_URL, REQUEST_TIMEOUT_MS } from "@/app/constant";
+import { ApiPath, TENCENT_BASE_URL } from "@/app/constant";
 import { useAccessStore, useAppConfig, useChatStore } from "@/app/store";

 import {
@@ -17,7 +17,11 @@ import {
 } from "@fortaine/fetch-event-source";
 import { prettyObject } from "@/app/utils/format";
 import { getClientConfig } from "@/app/config/client";
-import { getMessageTextContent, isVisionModel } from "@/app/utils";
+import {
+  getMessageTextContent,
+  isVisionModel,
+  getTimeoutMSByModel,
+} from "@/app/utils";
 import mapKeys from "lodash-es/mapKeys";
 import mapValues from "lodash-es/mapValues";
 import isArray from "lodash-es/isArray";
@@ -135,7 +139,7 @@ export class HunyuanApi implements LLMApi {
      // make a fetch request
      const requestTimeoutId = setTimeout(
        () => controller.abort(),
-        REQUEST_TIMEOUT_MS,
+        getTimeoutMSByModel(options.config.model),
      );

      if (shouldStream) {
--- a/app/client/platforms/xai.ts
+++ b/app/client/platforms/xai.ts
@@ -1,6 +1,6 @@
 "use client";
 // azure and openai, using same models. so using same LLMApi.
-import { ApiPath, XAI_BASE_URL, XAI, REQUEST_TIMEOUT_MS } from "@/app/constant";
+import { ApiPath, XAI_BASE_URL, XAI } from "@/app/constant";
 import {
  useAccessStore,
  useAppConfig,
@@ -17,6 +17,7 @@ import {
  SpeechOptions,
 } from "../api";
 import { getClientConfig } from "@/app/config/client";
+import { getTimeoutMSByModel } from "@/app/utils";
 import { preProcessImageContent } from "@/app/utils/chat";
 import { RequestPayload } from "./openai";
 import { fetch } from "@/app/utils/stream";
@@ -103,7 +104,7 @@ export class XAIApi implements LLMApi {
      // make a fetch request
      const requestTimeoutId = setTimeout(
        () => controller.abort(),
-        REQUEST_TIMEOUT_MS,
+        getTimeoutMSByModel(options.config.model),
      );

      if (shouldStream) {
--- a/app/components/emoji.tsx
+++ b/app/components/emoji.tsx
@@ -66,11 +66,11 @@ export function Avatar(props: { model?: ModelType; avatar?: string }) {
      LlmIcon = BotIconGemma;
    } else if (modelName.startsWith("claude")) {
      LlmIcon = BotIconClaude;
-    } else if (modelName.startsWith("llama")) {
+    } else if (modelName.includes("llama")) {
      LlmIcon = BotIconMeta;
-    } else if (modelName.startsWith("mixtral")) {
+    } else if (modelName.startsWith("mixtral") || modelName.startsWith("codestral")) {
      LlmIcon = BotIconMistral;
-    } else if (modelName.startsWith("deepseek")) {
+    } else if (modelName.includes("deepseek")) {
      LlmIcon = BotIconDeepseek;
    } else if (modelName.startsWith("moonshot")) {
      LlmIcon = BotIconMoonshot;
@@ -85,7 +85,7 @@ export function Avatar(props: { model?: ModelType; avatar?: string }) {
    } else if (modelName.startsWith("doubao") || modelName.startsWith("ep-")) {
      LlmIcon = BotIconDoubao;
    } else if (
-      modelName.startsWith("glm") ||
+      modelName.includes("glm") ||
      modelName.startsWith("cogview-") ||
      modelName.startsWith("cogvideox-")
    ) {
--- a/app/components/exporter.tsx
+++ b/app/components/exporter.tsx
@@ -23,7 +23,6 @@ import CopyIcon from "../icons/copy.svg";
 import LoadingIcon from "../icons/three-dots.svg";
 import ChatGptIcon from "../icons/chatgpt.png";
 import ShareIcon from "../icons/share.svg";
-import BotIcon from "../icons/bot.png";

 import DownloadIcon from "../icons/download.svg";
 import { useEffect, useMemo, useRef, useState } from "react";
@@ -33,13 +32,13 @@ import dynamic from "next/dynamic";
 import NextImage from "next/image";

 import { toBlob, toPng } from "html-to-image";
-import { DEFAULT_MASK_AVATAR } from "../store/mask";

 import { prettyObject } from "../utils/format";
 import { EXPORT_MESSAGE_CLASS_NAME } from "../constant";
 import { getClientConfig } from "../config/client";
 import { type ClientApi, getClientApi } from "../client/api";
 import { getMessageTextContent } from "../utils";
+import { MaskAvatar } from "./mask";
 import clsx from "clsx";

 const Markdown = dynamic(async () => (await import("./markdown")).Markdown, {
@@ -407,22 +406,6 @@ export function PreviewActions(props: {
  );
 }

-function ExportAvatar(props: { avatar: string }) {
-  if (props.avatar === DEFAULT_MASK_AVATAR) {
-    return (
-      <img
-        src={BotIcon.src}
-        width={30}
-        height={30}
-        alt="bot"
-        className="user-avatar"
-      />
-    );
-  }
-
-  return <Avatar avatar={props.avatar} />;
-}
-
 export function ImagePreviewer(props: {
  messages: ChatMessage[];
  topic: string;
@@ -546,9 +529,12 @@ export function ImagePreviewer(props: {
              github.com/ChatGPTNextWeb/ChatGPT-Next-Web
            </div>
            <div className={styles["icons"]}>
-              <ExportAvatar avatar={config.avatar} />
+              <MaskAvatar avatar={config.avatar} />
              <span className={styles["icon-space"]}>&</span>
-              <ExportAvatar avatar={mask.avatar} />
+              <MaskAvatar
+                avatar={mask.avatar}
+                model={session.mask.modelConfig.model}
+              />
            </div>
          </div>
          <div>
@@ -576,9 +562,14 @@ export function ImagePreviewer(props: {
              key={i}
            >
              <div className={styles["avatar"]}>
-                <ExportAvatar
-                  avatar={m.role === "user" ? config.avatar : mask.avatar}
-                />
+                {m.role === "user" ? (
+                  <Avatar avatar={config.avatar}></Avatar>
+                ) : (
+                  <MaskAvatar
+                    avatar={session.mask.avatar}
+                    model={m.model || session.mask.modelConfig.model}
+                  />
+                )}
              </div>

              <div className={styles["body"]}>
--- a/app/components/settings.tsx
+++ b/app/components/settings.tsx
@@ -75,6 +75,7 @@ import {
  ChatGLM,
  DeepSeek,
  SiliconFlow,
+  Huawei,
 } from "../constant";
 import { Prompt, SearchService, usePromptStore } from "../store/prompt";
 import { ErrorBoundary } from "./error";
@@ -1457,6 +1458,46 @@ export function Settings() {
      </ListItem>
    </>
  );
+  const huaweiConfigComponent = accessStore.provider ===
+    ServiceProvider.Huawei && (
+    <>
+      <ListItem
+        title={Locale.Settings.Access.Huawei.Endpoint.Title}
+        subTitle={
+          Locale.Settings.Access.Huawei.Endpoint.SubTitle +
+          Huawei.ExampleEndpoint
+        }
+      >
+        <input
+          aria-label={Locale.Settings.Access.Huawei.Endpoint.Title}
+          type="text"
+          value={accessStore.huaweiUrl}
+          placeholder={Huawei.ExampleEndpoint}
+          onChange={(e) =>
+            accessStore.update(
+              (access) => (access.huaweiUrl = e.currentTarget.value),
+            )
+          }
+        ></input>
+      </ListItem>
+      <ListItem
+        title={Locale.Settings.Access.Huawei.ApiKey.Title}
+        subTitle={Locale.Settings.Access.Huawei.ApiKey.SubTitle}
+      >
+        <PasswordInput
+          aria-label={Locale.Settings.Access.Huawei.ApiKey.Title}
+          value={accessStore.huaweiApiKey}
+          type="text"
+          placeholder={Locale.Settings.Access.Huawei.ApiKey.Placeholder}
+          onChange={(e) => {
+            accessStore.update(
+              (access) => (access.huaweiApiKey = e.currentTarget.value),
+            );
+          }}
+        />
+      </ListItem>
+    </>
+  );

  return (
    <ErrorBoundary>
@@ -1822,6 +1863,7 @@ export function Settings() {
                  {XAIConfigComponent}
                  {chatglmConfigComponent}
                  {siliconflowConfigComponent}
+                  {huaweiConfigComponent}
                </>
              )}
            </>
--- a/app/config/server.ts
+++ b/app/config/server.ts
@@ -88,6 +88,10 @@ declare global {
      SILICONFLOW_URL?: string;
      SILICONFLOW_API_KEY?: string;

+      //huaweionly
+      HUAWEI_URL?: string;
+      HUAWEI_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 isHuawei = !!process.env.HUAWEI_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);
@@ -233,6 +238,10 @@ export const getServerSideConfig = () => {
    xaiUrl: process.env.XAI_URL,
    xaiApiKey: getApiKey(process.env.XAI_API_KEY),

+    isHuawei,
+    huaweiUrl: process.env.HUAWEI_URL,
+    huaweiApiKey: getApiKey(process.env.HUAWEI_API_KEY),
+
    isChatGLM,
    chatglmUrl: process.env.CHATGLM_URL,
    chatglmApiKey: getApiKey(process.env.CHATGLM_API_KEY),
--- a/app/constant.ts
+++ b/app/constant.ts
@@ -36,6 +36,9 @@ export const CHATGLM_BASE_URL = "https://open.bigmodel.cn";

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

+export const HUAWEI_BASE_URL =
+  "https://maas-cn-southwest-2.modelarts-maas.com/v1/infers";
+
 export const CACHE_URL_PREFIX = "/api/cache";
 export const UPLOAD_URL = `${CACHE_URL_PREFIX}/upload`;

@@ -72,6 +75,7 @@ export enum ApiPath {
  ChatGLM = "/api/chatglm",
  DeepSeek = "/api/deepseek",
  SiliconFlow = "/api/siliconflow",
+  Huawei = "/api/huawei",
 }

 export enum SlotID {
@@ -130,6 +134,7 @@ export enum ServiceProvider {
  ChatGLM = "ChatGLM",
  DeepSeek = "DeepSeek",
  SiliconFlow = "SiliconFlow",
+  Huawei = "Huawei",
 }

 // Google API safety settings, see https://ai.google.dev/gemini-api/docs/safety-settings
@@ -156,6 +161,7 @@ export enum ModelProvider {
  ChatGLM = "ChatGLM",
  DeepSeek = "DeepSeek",
  SiliconFlow = "SiliconFlow",
+  Huawei = "Huawei",
 }

 export const Stability = {
@@ -214,6 +220,11 @@ export const Baidu = {
  },
 };

+export const Huawei = {
+  ExampleEndpoint: HUAWEI_BASE_URL,
+  ChatPath: "/v1/chat/completions",
+};
+
 export const ByteDance = {
  ExampleEndpoint: "https://ark.cn-beijing.volces.com/api/",
  ChatPath: "api/v3/chat/completions",
@@ -221,7 +232,12 @@ export const ByteDance = {

 export const Alibaba = {
  ExampleEndpoint: ALIBABA_BASE_URL,
-  ChatPath: "v1/services/aigc/text-generation/generation",
+  ChatPath: (modelName: string) => {
+    if (modelName.includes("vl") || modelName.includes("omni")) {
+      return "v1/services/aigc/multimodal-generation/generation";
+    }
+    return `v1/services/aigc/text-generation/generation`;
+  },
 };

 export const Tencent = {
@@ -258,6 +274,7 @@ export const ChatGLM = {
 export const SiliconFlow = {
  ExampleEndpoint: SILICONFLOW_BASE_URL,
  ChatPath: "v1/chat/completions",
+  ListModelPath: "v1/models?&sub_type=chat",
 };

 export const DEFAULT_INPUT_TEMPLATE = `{{input}}`; // input / time / model / lang
@@ -411,6 +428,14 @@ export const KnowledgeCutOffDate: Record<string, string> = {
  "gpt-4-turbo": "2023-12",
  "gpt-4-turbo-2024-04-09": "2023-12",
  "gpt-4-turbo-preview": "2023-12",
+  "gpt-4.1": "2024-06",
+  "gpt-4.1-2025-04-14": "2024-06",
+  "gpt-4.1-mini": "2024-06",
+  "gpt-4.1-mini-2025-04-14": "2024-06",
+  "gpt-4.1-nano": "2024-06",
+  "gpt-4.1-nano-2025-04-14": "2024-06",
+  "gpt-4.5-preview": "2023-10",
+  "gpt-4.5-preview-2025-02-27": "2023-10",
  "gpt-4o": "2023-10",
  "gpt-4o-2024-05-13": "2023-10",
  "gpt-4o-2024-08-06": "2023-10",
@@ -452,6 +477,7 @@ export const DEFAULT_TTS_VOICES = [
 export const VISION_MODEL_REGEXES = [
  /vision/,
  /gpt-4o/,
+  /gpt-4\.1/,
  /claude-3/,
  /gemini-1\.5/,
  /gemini-exp/,
@@ -462,6 +488,9 @@ export const VISION_MODEL_REGEXES = [
  /gpt-4-turbo(?!.*preview)/, // Matches "gpt-4-turbo" but not "gpt-4-turbo-preview"
  /^dall-e-3$/, // Matches exactly "dall-e-3"
  /glm-4v/,
+  /vl/i,
+  /o3/,
+  /o4-mini/,
 ];

 export const EXCLUDE_VISION_MODEL_REGEXES = [/claude-3-5-haiku-20241022/];
@@ -478,6 +507,14 @@ const openaiModels = [
  "gpt-4-32k-0613",
  "gpt-4-turbo",
  "gpt-4-turbo-preview",
+  "gpt-4.1",
+  "gpt-4.1-2025-04-14",
+  "gpt-4.1-mini",
+  "gpt-4.1-mini-2025-04-14",
+  "gpt-4.1-nano",
+  "gpt-4.1-nano-2025-04-14",
+  "gpt-4.5-preview",
+  "gpt-4.5-preview-2025-02-27",
  "gpt-4o",
  "gpt-4o-2024-05-13",
  "gpt-4o-2024-08-06",
@@ -492,6 +529,8 @@ const openaiModels = [
  "o1-mini",
  "o1-preview",
  "o3-mini",
+  "o3",
+  "o4-mini",
 ];

 const googleModels = [
@@ -518,6 +557,7 @@ const googleModels = [
  "gemini-2.0-flash-thinking-exp-01-21",
  "gemini-2.0-pro-exp",
  "gemini-2.0-pro-exp-02-05",
+  "gemini-2.5-pro-preview-06-05",
 ];

 const anthropicModels = [
@@ -533,6 +573,8 @@ const anthropicModels = [
  "claude-3-5-sonnet-20240620",
  "claude-3-5-sonnet-20241022",
  "claude-3-5-sonnet-latest",
+  "claude-3-7-sonnet-20250219",
+  "claude-3-7-sonnet-latest",
 ];

 const baiduModels = [
@@ -556,6 +598,11 @@ const bytedanceModels = [
  "Doubao-pro-4k",
  "Doubao-pro-32k",
  "Doubao-pro-128k",
+  "deepseek-r1-250120",
+  "deepseek-v3-241226",
+  "deepseek-v3-250324",
+  "deepseek-r1-distill-qwen-7b-250120",
+  "deepseek-r1-distill-qwen-32b-250120",
 ];

 const alibabaModes = [
@@ -566,6 +613,9 @@ const alibabaModes = [
  "qwen-max-0403",
  "qwen-max-0107",
  "qwen-max-longcontext",
+  "qwen-omni-turbo",
+  "qwen-vl-plus",
+  "qwen-vl-max",
 ];

 const tencentModels = [
@@ -599,6 +649,18 @@ const xAIModes = [
  "grok-2-vision-1212",
  "grok-2-vision",
  "grok-2-vision-latest",
+  "grok-3-mini-fast-beta",
+  "grok-3-mini-fast",
+  "grok-3-mini-fast-latest",
+  "grok-3-mini-beta",
+  "grok-3-mini",
+  "grok-3-mini-latest",
+  "grok-3-fast-beta",
+  "grok-3-fast",
+  "grok-3-fast-latest",
+  "grok-3-beta",
+  "grok-3",
+  "grok-3-latest",
 ];

 const chatglmModels = [
@@ -638,6 +700,11 @@ const siliconflowModels = [
  "Pro/deepseek-ai/DeepSeek-V3",
 ];

+const huaweiModels = [
+  "DeepSeek-R1",
+  "DeepSeek-V3",
+];
+
 let seq = 1000; // 内置的模型序号生成器从1000开始
 export const DEFAULT_MODELS = [
  ...openaiModels.map((name) => ({
@@ -794,6 +861,17 @@ export const DEFAULT_MODELS = [
      sorted: 14,
    },
  })),
+  ...huaweiModels.map((name) => ({
+    name,
+    available: true,
+    sorted: seq++,
+    provider: {
+      id: "huawei",
+      providerName: "Huawei",
+      providerType: "Huawei",
+      sorted: 15,
+    },
+  })),
 ] as const;

 export const CHAT_PAGE_SIZE = 15;
@@ -814,5 +892,5 @@ export const internalAllowedWebDavEndpoints = [

 export const DEFAULT_GA_ID = "G-89WN60ZK2E";

-export const SAAS_CHAT_URL = "https://nextchat.dev/chat";
-export const SAAS_CHAT_UTM_URL = "https://nextchat.dev/chat?utm=github";
+export const SAAS_CHAT_URL = "https://nextchat.club";
+export const SAAS_CHAT_UTM_URL = "https://nextchat.club?utm=github";
--- a/app/locales/ar.ts
+++ b/app/locales/ar.ts
@@ -420,6 +420,22 @@ const ar: PartialLocaleType = {
        Title: "اسم النموذج المخصص",
        SubTitle: "أضف خيارات نموذج مخصص، مفصولة بفواصل إنجليزية",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "مفتاح API",
+          SubTitle: "استخدم مفتاح API الخاص بـ HUAWEI",
+          Placeholder: "مفتاح HUAWEI",
+        },
+        SecretKey: {
+          Title: "المفتاح السري",
+          SubTitle: "استخدم مفتاح HUAWEI السري الخاص بك",
+          Placeholder: "المفتاح السري HUAWEI",
+        },
+        Endpoint: {
+          Title: "عنوان الواجهة",
+          SubTitle: "لا يدعم التكوين المخصص .env",
+        },
+      },
    },

    Model: "النموذج",
--- a/app/locales/bn.ts
+++ b/app/locales/bn.ts
@@ -428,6 +428,22 @@ const bn: PartialLocaleType = {
        SubTitle:
          "স্বনির্ধারিত মডেল বিকল্পগুলি যুক্ত করুন, ইংরেজি কমা দ্বারা আলাদা করুন",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "এপিআই কী",
+          SubTitle: "আপনার HUAWEI এপিআই কী ব্যবহার করুন",
+          Placeholder: "HUAWEI কী",
+        },
+        SecretKey: {
+          Title: "গোপন কী",
+          SubTitle: "আপনার HUAWEI গোপন কী ব্যবহার করুন",
+          Placeholder: "HUAWEI গোপন কী",
+        },
+        Endpoint: {
+          Title: "এন্ডপয়েন্ট ঠিকানা",
+          SubTitle: "কাস্টম কনফিগারেশনের জন্য .env-এ যান",
+        },
+      },
    },

    Model: "মডেল (model)",
--- a/app/locales/cn.ts
+++ b/app/locales/cn.ts
@@ -538,6 +538,22 @@ 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",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "API Key",
+          SubTitle: "使用自定义华为API Key",
+          Placeholder: "HUAWEI Key",
+        },
+        SecretKey: {
+          Title: "Secret Key",
+          SubTitle: "使用自定义HUAWEI Secret Key",
+          Placeholder: "HUAWEI Secret Key",
+        },
+        Endpoint: {
+          Title: "接口地址",
+          SubTitle: "不支持自定义前往.env配置",
+        },
+      },
    },

    Model: "模型 (model)",
--- a/app/locales/cs.ts
+++ b/app/locales/cs.ts
@@ -427,6 +427,22 @@ const cs: PartialLocaleType = {
        Title: "Vlastní názvy modelů",
        SubTitle: "Přidejte možnosti vlastních modelů, oddělené čárkami",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "API Klíč",
+          SubTitle: "Použijte svůj HUAWEI API klíč",
+          Placeholder: "HUAWEI Klíč",
+        },
+        SecretKey: {
+          Title: "Tajný Klíč",
+          SubTitle: "Použijte svůj HUAWEI Tajný klíč",
+          Placeholder: "HUAWEI Tajný Klíč",
+        },
+        Endpoint: {
+          Title: "Adresa rozhraní",
+          SubTitle: "Nepodporuje vlastní konfiguraci .env",
+        },
+      },
    },

    Model: "Model (model)",
--- a/app/locales/da.ts
+++ b/app/locales/da.ts
@@ -0,0 +1,848 @@
+import { getClientConfig } from "../config/client";
+import { SubmitKey } from "../store/config";
+import { SAAS_CHAT_UTM_URL } from "@/app/constant";
+import { PartialLocaleType } from "./index";
+
+const isApp = !!getClientConfig()?.isApp;
+const da: PartialLocaleType = {
+  WIP: "Der kommer snart mere...",
+  Error: {
+    Unauthorized: isApp
+      ? `Hov, der skete en fejl. Sådan kan du komme videre:
+       \\ 1️⃣ Er du ny her? [Tryk for at starte nu 🚀](${SAAS_CHAT_UTM_URL})
+       \\ 2️⃣ Vil du bruge dine egne OpenAI-nøgler? [Tryk her](/#/settings) for at ændre indstillinger ⚙️`
+      : `Hov, der skete en fejl. Lad os løse det:
+       \\ 1️⃣ Er du ny her? [Tryk for at starte nu 🚀](${SAAS_CHAT_UTM_URL})
+       \\ 2️⃣ Bruger du en privat opsætning? [Tryk her](/#/auth) for at taste din nøgle 🔑
+       \\ 3️⃣ Vil du bruge dine egne OpenAI-nøgler? [Tryk her](/#/settings) for at ændre indstillinger ⚙️
+       `,
+  },
+  Auth: {
+    Return: "Tilbage",
+    Title: "Adgangskode",
+    Tips: "Skriv venligst koden herunder",
+    SubTips: "Eller brug din egen OpenAI- eller Google-nøgle",
+    Input: "Adgangskode",
+    Confirm: "OK",
+    Later: "Senere",
+    SaasTips: "Hvis det er for svært, kan du starte nu",
+  },
+  ChatItem: {
+    ChatItemCount: (count: number) => `${count} beskeder`,
+  },
+  Chat: {
+    SubTitle: (count: number) => `${count} beskeder`,
+    EditMessage: {
+      Title: "Rediger beskeder",
+      Topic: {
+        Title: "Emne",
+        SubTitle: "Skift emne for denne chat",
+      },
+    },
+    Actions: {
+      ChatList: "Gå til chatliste",
+      CompressedHistory: "Komprimeret historie",
+      Export: "Eksporter alle beskeder som Markdown",
+      Copy: "Kopiér",
+      Stop: "Stop",
+      Retry: "Prøv igen",
+      Pin: "Fastgør",
+      PinToastContent: "1 besked er nu fastgjort",
+      PinToastAction: "Se",
+      Delete: "Slet",
+      Edit: "Rediger",
+      FullScreen: "Fuld skærm",
+      RefreshTitle: "Opdatér titel",
+      RefreshToast: "Anmodning om ny titel sendt",
+      Speech: "Afspil",
+      StopSpeech: "Stop",
+    },
+    Commands: {
+      new: "Ny chat",
+      newm: "Ny chat med persona",
+      next: "Næste chat",
+      prev: "Forrige chat",
+      clear: "Ryd alt før",
+      fork: "Kopiér chat",
+      del: "Slet chat",
+    },
+    InputActions: {
+      Stop: "Stop",
+      ToBottom: "Ned til nyeste",
+      Theme: {
+        auto: "Automatisk",
+        light: "Lyst tema",
+        dark: "Mørkt tema",
+      },
+      Prompt: "Prompts",
+      Masks: "Personaer",
+      Clear: "Ryd kontekst",
+      Settings: "Indstillinger",
+      UploadImage: "Upload billeder",
+    },
+    Rename: "Omdøb chat",
+    Typing: "Skriver…",
+    Input: (submitKey: string) => {
+      let inputHints = `${submitKey} for at sende`;
+      if (submitKey === String(SubmitKey.Enter)) {
+        inputHints += ", Shift + Enter for ny linje";
+      }
+      return (
+        inputHints + ", / for at søge i prompts, : for at bruge kommandoer"
+      );
+    },
+    Send: "Send",
+    StartSpeak: "Start oplæsning",
+    StopSpeak: "Stop oplæsning",
+    Config: {
+      Reset: "Nulstil til standard",
+      SaveAs: "Gem som persona",
+    },
+    IsContext: "Ekstra prompt til baggrund",
+    ShortcutKey: {
+      Title: "Hurtigtaster",
+      newChat: "Åbn ny chat",
+      focusInput: "Fokus på tekstfeltet",
+      copyLastMessage: "Kopiér sidste svar",
+      copyLastCode: "Kopiér sidste kodeblok",
+      showShortcutKey: "Vis hurtigtaster",
+      clearContext: "Ryd kontekst",
+    },
+  },
+  Export: {
+    Title: "Eksportér beskeder",
+    Copy: "Kopiér alt",
+    Download: "Download",
+    MessageFromYou: "Fra dig",
+    MessageFromChatGPT: "Fra ChatGPT",
+    Share: "Del til ShareGPT",
+    Format: {
+      Title: "Filformat",
+      SubTitle: "Vælg enten Markdown eller PNG-billede",
+    },
+    IncludeContext: {
+      Title: "Tag baggrund med",
+      SubTitle: "Skal ekstra baggrund (persona) med i eksporten?",
+    },
+    Steps: {
+      Select: "Vælg",
+      Preview: "Forhåndsvis",
+    },
+    Image: {
+      Toast: "Laver billede...",
+      Modal: "Tryk længe eller højreklik for at gemme",
+    },
+    Artifacts: {
+      Title: "Del side",
+      Error: "Fejl ved deling",
+    },
+  },
+  Select: {
+    Search: "Søg",
+    All: "Vælg alle",
+    Latest: "Vælg nyeste",
+    Clear: "Ryd alt",
+  },
+  Memory: {
+    Title: "Huskesætning",
+    EmptyContent: "Ingenting lige nu.",
+    Send: "Send huskesætning",
+    Copy: "Kopiér huskesætning",
+    Reset: "Nulstil chat",
+    ResetConfirm:
+      "Dette sletter nuværende samtale og hukommelse. Er du sikker?",
+  },
+  Home: {
+    NewChat: "Ny Chat",
+    DeleteChat: "Vil du slette den valgte chat?",
+    DeleteToast: "Chat slettet",
+    Revert: "Fortryd",
+  },
+  Settings: {
+    Title: "Indstillinger",
+    SubTitle: "Alle indstillinger",
+    ShowPassword: "Vis kodeord",
+    Danger: {
+      Reset: {
+        Title: "Nulstil alle indstillinger",
+        SubTitle: "Gendan alt til standard",
+        Action: "Nulstil",
+        Confirm: "Vil du virkelig nulstille alt?",
+      },
+      Clear: {
+        Title: "Slet alle data",
+        SubTitle: "Sletter alt om beskeder og indstillinger",
+        Action: "Slet",
+        Confirm: "Er du sikker på, at du vil slette alt?",
+      },
+    },
+    Lang: {
+      Name: "Language",
+      All: "Alle sprog",
+    },
+    Avatar: "Avatar",
+    FontSize: {
+      Title: "Skriftstørrelse",
+      SubTitle: "Vælg, hvor stor teksten skal være",
+    },
+    FontFamily: {
+      Title: "Skrifttype",
+      SubTitle: "Hvis tom, bruger den standard skrifttype",
+      Placeholder: "Skrifttype-navn",
+    },
+    InjectSystemPrompts: {
+      Title: "Tilføj system-prompt",
+      SubTitle: "Læg altid en ekstra prompt først i anmodninger",
+    },
+    InputTemplate: {
+      Title: "Tekstskabelon",
+      SubTitle: "Den seneste besked placeres i denne skabelon",
+    },
+    Update: {
+      Version: (x: string) => `Version: ${x}`,
+      IsLatest: "Du har nyeste version",
+      CheckUpdate: "Tjek efter opdatering",
+      IsChecking: "Tjekker...",
+      FoundUpdate: (x: string) => `Ny version fundet: ${x}`,
+      GoToUpdate: "Opdatér",
+      Success: "Opdatering lykkedes.",
+      Failed: "Opdatering mislykkedes.",
+    },
+    SendKey: "Tast for send",
+    Theme: "Tema",
+    TightBorder: "Stram kant",
+    SendPreviewBubble: {
+      Title: "Forhåndsvisnings-boble",
+      SubTitle: "Vis tekst, før den sendes",
+    },
+    AutoGenerateTitle: {
+      Title: "Lav titel automatisk",
+      SubTitle: "Foreslå en titel ud fra chatten",
+    },
+    Sync: {
+      CloudState: "Seneste opdatering",
+      NotSyncYet: "Endnu ikke synkroniseret",
+      Success: "Synkronisering lykkedes",
+      Fail: "Synkronisering mislykkedes",
+      Config: {
+        Modal: {
+          Title: "Indstil synk",
+          Check: "Tjek forbindelse",
+        },
+        SyncType: {
+          Title: "Synk-type",
+          SubTitle: "Vælg en synk-tjeneste",
+        },
+        Proxy: {
+          Title: "Aktivér proxy",
+          SubTitle: "Brug proxy for at undgå netværksproblemer",
+        },
+        ProxyUrl: {
+          Title: "Proxy-adresse",
+          SubTitle: "Bruges kun til projektets egen proxy",
+        },
+        WebDav: {
+          Endpoint: "WebDAV-adresse",
+          UserName: "Brugernavn",
+          Password: "Kodeord",
+        },
+        UpStash: {
+          Endpoint: "UpStash Redis REST URL",
+          UserName: "Backup-navn",
+          Password: "UpStash Redis REST Token",
+        },
+      },
+      LocalState: "Lokale data",
+      Overview: (overview: any) =>
+        `${overview.chat} chats, ${overview.message} beskeder, ${overview.prompt} prompts, ${overview.mask} personaer`,
+      ImportFailed: "Import mislykkedes",
+    },
+    Mask: {
+      Splash: {
+        Title: "Persona-forside",
+        SubTitle: "Vis denne side, når du opretter ny chat",
+      },
+      Builtin: {
+        Title: "Skjul indbyggede personaer",
+        SubTitle: "Vis ikke de indbyggede personaer i listen",
+      },
+    },
+    Prompt: {
+      Disable: {
+        Title: "Slå auto-forslag fra",
+        SubTitle: "Tast / for at få forslag",
+      },
+      List: "Prompt-liste",
+      ListCount: (builtin: number, custom: number) =>
+        `${builtin} indbygget, ${custom} brugerdefineret`,
+      Edit: "Rediger",
+      Modal: {
+        Title: "Prompt-liste",
+        Add: "Tilføj",
+        Search: "Søg prompts",
+      },
+      EditModal: {
+        Title: "Rediger prompt",
+      },
+    },
+    HistoryCount: {
+      Title: "Antal beskeder, der følger med",
+      SubTitle: "Hvor mange af de tidligere beskeder, der sendes hver gang",
+    },
+    CompressThreshold: {
+      Title: "Komprimeringsgrænse",
+      SubTitle:
+        "Hvis chatten bliver for lang, vil den komprimeres efter dette antal tegn",
+    },
+    Usage: {
+      Title: "Brug og saldo",
+      SubTitle(used: any, total: any) {
+        return `Du har brugt $${used} i denne måned, og din grænse er $${total}.`;
+      },
+      IsChecking: "Tjekker...",
+      Check: "Tjek igen",
+      NoAccess: "Indtast API-nøgle for at se forbrug",
+    },
+    Access: {
+      AccessCode: {
+        Title: "Adgangskode",
+        SubTitle: "Adgangskontrol er slået til",
+        Placeholder: "Skriv kode her",
+      },
+      CustomEndpoint: {
+        Title: "Brugerdefineret adresse",
+        SubTitle: "Brug Azure eller OpenAI fra egen server",
+      },
+      Provider: {
+        Title: "Model-udbyder",
+        SubTitle: "Vælg Azure eller OpenAI",
+      },
+      OpenAI: {
+        ApiKey: {
+          Title: "OpenAI API-nøgle",
+          SubTitle: "Brug din egen nøgle",
+          Placeholder: "sk-xxx",
+        },
+        Endpoint: {
+          Title: "OpenAI Endpoint",
+          SubTitle: "Skal starte med http(s):// eller /api/openai som standard",
+        },
+      },
+      Azure: {
+        ApiKey: {
+          Title: "Azure Api Key",
+          SubTitle: "Hent din nøgle fra Azure-portalen",
+          Placeholder: "Azure Api Key",
+        },
+        Endpoint: {
+          Title: "Azure Endpoint",
+          SubTitle: "F.eks.: ",
+        },
+        ApiVerion: {
+          Title: "Azure Api Version",
+          SubTitle: "Hentet fra Azure-portalen",
+        },
+      },
+      Anthropic: {
+        ApiKey: {
+          Title: "Anthropic API-nøgle",
+          SubTitle: "Brug din egen Anthropic-nøgle",
+          Placeholder: "Anthropic API Key",
+        },
+        Endpoint: {
+          Title: "Endpoint-adresse",
+          SubTitle: "F.eks.: ",
+        },
+        ApiVerion: {
+          Title: "API-version (Claude)",
+          SubTitle: "Vælg den ønskede version",
+        },
+      },
+      Baidu: {
+        ApiKey: {
+          Title: "Baidu-nøgle",
+          SubTitle: "Din egen Baidu-nøgle",
+          Placeholder: "Baidu API Key",
+        },
+        SecretKey: {
+          Title: "Baidu hemmelig nøgle",
+          SubTitle: "Din egen hemmelige nøgle fra Baidu",
+          Placeholder: "Baidu Secret Key",
+        },
+        Endpoint: {
+          Title: "Adresse",
+          SubTitle: "Kan ikke ændres, se .env",
+        },
+      },
+      Tencent: {
+        ApiKey: {
+          Title: "Tencent-nøgle",
+          SubTitle: "Din egen nøgle fra Tencent",
+          Placeholder: "Tencent API Key",
+        },
+        SecretKey: {
+          Title: "Tencent hemmelig nøgle",
+          SubTitle: "Din egen hemmelige nøgle fra Tencent",
+          Placeholder: "Tencent Secret Key",
+        },
+        Endpoint: {
+          Title: "Adresse",
+          SubTitle: "Kan ikke ændres, se .env",
+        },
+      },
+      ByteDance: {
+        ApiKey: {
+          Title: "ByteDance-nøgle",
+          SubTitle: "Din egen nøgle til ByteDance",
+          Placeholder: "ByteDance API Key",
+        },
+        Endpoint: {
+          Title: "Adresse",
+          SubTitle: "F.eks.: ",
+        },
+      },
+      Alibaba: {
+        ApiKey: {
+          Title: "Alibaba-nøgle",
+          SubTitle: "Din egen Alibaba Cloud-nøgle",
+          Placeholder: "Alibaba Cloud API Key",
+        },
+        Endpoint: {
+          Title: "Adresse",
+          SubTitle: "F.eks.: ",
+        },
+      },
+      Moonshot: {
+        ApiKey: {
+          Title: "Moonshot-nøgle",
+          SubTitle: "Din egen Moonshot-nøgle",
+          Placeholder: "Moonshot API Key",
+        },
+        Endpoint: {
+          Title: "Adresse",
+          SubTitle: "F.eks.: ",
+        },
+      },
+      DeepSeek: {
+        ApiKey: {
+          Title: "DeepSeek-nøgle",
+          SubTitle: "Din egen DeepSeek-nøgle",
+          Placeholder: "DeepSeek API Key",
+        },
+        Endpoint: {
+          Title: "Adresse",
+          SubTitle: "F.eks.: ",
+        },
+      },
+      XAI: {
+        ApiKey: {
+          Title: "XAI-nøgle",
+          SubTitle: "Din egen XAI-nøgle",
+          Placeholder: "XAI API Key",
+        },
+        Endpoint: {
+          Title: "Adresse",
+          SubTitle: "F.eks.: ",
+        },
+      },
+      ChatGLM: {
+        ApiKey: {
+          Title: "ChatGLM-nøgle",
+          SubTitle: "Din egen ChatGLM-nøgle",
+          Placeholder: "ChatGLM API Key",
+        },
+        Endpoint: {
+          Title: "Adresse",
+          SubTitle: "F.eks.: ",
+        },
+      },
+      SiliconFlow: {
+        ApiKey: {
+          Title: "SiliconFlow-nøgle",
+          SubTitle: "Din egen SiliconFlow-nøgle",
+          Placeholder: "SiliconFlow API Key",
+        },
+        Endpoint: {
+          Title: "Adresse",
+          SubTitle: "F.eks.: ",
+        },
+      },
+      Stability: {
+        ApiKey: {
+          Title: "Stability-nøgle",
+          SubTitle: "Din egen Stability-nøgle",
+          Placeholder: "Stability API Key",
+        },
+        Endpoint: {
+          Title: "Adresse",
+          SubTitle: "F.eks.: ",
+        },
+      },
+      Iflytek: {
+        ApiKey: {
+          Title: "Iflytek API Key",
+          SubTitle: "Nøgle fra Iflytek",
+          Placeholder: "Iflytek API Key",
+        },
+        ApiSecret: {
+          Title: "Iflytek hemmelig nøgle",
+          SubTitle: "Hentet fra Iflytek",
+          Placeholder: "Iflytek API Secret",
+        },
+        Endpoint: {
+          Title: "Adresse",
+          SubTitle: "F.eks.: ",
+        },
+      },
+      CustomModel: {
+        Title: "Egne modelnavne",
+        SubTitle: "Skriv komma-adskilte navne",
+      },
+      Huawei: {
+        ApiKey: {
+          Title: "API-nøgle",
+          SubTitle: "Brug din egen HUAWEI API-nøgle",
+          Placeholder: "HUAWEI-nøgle",
+        },
+        SecretKey: {
+          Title: "Hemmelig nøgle",
+          SubTitle: "Brug din egen HUAWEI hemmelige nøgle",
+          Placeholder: "HUAWEI hemmelig nøgle",
+        },
+        Endpoint: {
+          Title: "Grænsefladeadresse",
+          SubTitle: "Understøtter ikke tilpasset .env-konfiguration",
+        },
+      },
+      Google: {
+        ApiKey: {
+          Title: "Google-nøgle",
+          SubTitle: "Få din nøgle hos Google AI",
+          Placeholder: "Google AI API Key",
+        },
+        Endpoint: {
+          Title: "Adresse",
+          SubTitle: "F.eks.: ",
+        },
+        ApiVersion: {
+          Title: "API-version (til gemini-pro)",
+          SubTitle: "Vælg en bestemt version",
+        },
+        GoogleSafetySettings: {
+          Title: "Google sikkerhedsindstillinger",
+          SubTitle: "Vælg et niveau for indholdskontrol",
+        },
+      },
+    },
+    Model: "Model",
+    CompressModel: {
+      Title: "Opsummeringsmodel",
+      SubTitle: "Bruges til at korte historik ned og lave titel",
+    },
+    Temperature: {
+      Title: "Temperatur",
+      SubTitle: "Jo højere tal, jo mere kreativt svar",
+    },
+    TopP: {
+      Title: "Top P",
+      SubTitle: "Skal ikke ændres sammen med temperatur",
+    },
+    MaxTokens: {
+      Title: "Maks. længde",
+      SubTitle: "Hvor mange tokens (ord/stykker tekst) der kan bruges",
+    },
+    PresencePenalty: {
+      Title: "Nye emner",
+      SubTitle: "Jo højere tal, jo mere nyt indhold",
+    },
+    FrequencyPenalty: {
+      Title: "Gentagelsesstraf",
+      SubTitle: "Jo højere tal, jo mindre gentagelse",
+    },
+    TTS: {
+      Enable: {
+        Title: "Tænd for oplæsning (TTS)",
+        SubTitle: "Slå tekst-til-tale til",
+      },
+      Autoplay: {
+        Title: "Automatisk oplæsning",
+        SubTitle: "Laver lyd automatisk, hvis TTS er slået til",
+      },
+      Model: "Model",
+      Voice: {
+        Title: "Stemme",
+        SubTitle: "Hvilken stemme der bruges til lyd",
+      },
+      Speed: {
+        Title: "Hastighed",
+        SubTitle: "Hvor hurtigt der oplæses",
+      },
+      Engine: "TTS-motor",
+    },
+    Realtime: {
+      Enable: {
+        Title: "Live-chat",
+        SubTitle: "Slå live-svar til",
+      },
+      Provider: {
+        Title: "Modeludbyder",
+        SubTitle: "Vælg forskellig udbyder",
+      },
+      Model: {
+        Title: "Model",
+        SubTitle: "Vælg en model",
+      },
+      ApiKey: {
+        Title: "API-nøgle",
+        SubTitle: "Din nøgle",
+        Placeholder: "API-nøgle",
+      },
+      Azure: {
+        Endpoint: {
+          Title: "Adresse",
+          SubTitle: "Endpoint til Azure",
+        },
+        Deployment: {
+          Title: "Udrulningsnavn",
+          SubTitle: "Navn for dit Azure-setup",
+        },
+      },
+      Temperature: {
+        Title: "Temperatur",
+        SubTitle: "Højere tal = mere varierede svar",
+      },
+    },
+  },
+  Store: {
+    DefaultTopic: "Ny samtale",
+    BotHello: "Hej! Hvordan kan jeg hjælpe dig i dag?",
+    Error: "Noget gik galt. Prøv igen senere.",
+    Prompt: {
+      History: (content: string) =>
+        "Her er et kort resume af, hvad vi har snakket om: " + content,
+      Topic:
+        "Find en kort overskrift med 4-5 ord om emnet. Ingen tegnsætning eller anførselstegn.",
+      Summarize:
+        "Skriv et kort resumé (under 200 ord) af vores samtale til senere brug.",
+    },
+  },
+  Copy: {
+    Success: "Kopieret",
+    Failed: "Kunne ikke kopiere. Giv adgang til udklipsholder.",
+  },
+  Download: {
+    Success: "Filen er downloadet.",
+    Failed: "Download fejlede.",
+  },
+  Context: {
+    Toast: (x: any) => `Inkluderer ${x} ekstra prompts`,
+    Edit: "Chatindstillinger",
+    Add: "Tilføj prompt",
+    Clear: "Kontekst ryddet",
+    Revert: "Fortryd",
+  },
+  Discovery: {
+    Name: "Søgning og plugins",
+  },
+  Mcp: {
+    Name: "MCP",
+  },
+  FineTuned: {
+    Sysmessage: "Du er en hjælper, der skal...",
+  },
+  SearchChat: {
+    Name: "Søg",
+    Page: {
+      Title: "Søg i tidligere chats",
+      Search: "Skriv her for at søge",
+      NoResult: "Ingen resultater",
+      NoData: "Ingen data",
+      Loading: "Henter...",
+      SubTitle: (count: number) => `Fandt ${count} resultater`,
+    },
+    Item: {
+      View: "Vis",
+    },
+  },
+  Plugin: {
+    Name: "Plugin",
+    Page: {
+      Title: "Plugins",
+      SubTitle: (count: number) => `${count} plugins`,
+      Search: "Søg plugin",
+      Create: "Opret nyt",
+      Find: "Du kan finde flere plugins på GitHub: ",
+    },
+    Item: {
+      Info: (count: number) => `${count} metode`,
+      View: "Vis",
+      Edit: "Rediger",
+      Delete: "Slet",
+      DeleteConfirm: "Vil du slette?",
+    },
+    Auth: {
+      None: "Ingen",
+      Basic: "Basic",
+      Bearer: "Bearer",
+      Custom: "Tilpasset",
+      CustomHeader: "Parameternavn",
+      Token: "Token",
+      Proxy: "Brug Proxy",
+      ProxyDescription: "Løs CORS-problemer med Proxy",
+      Location: "Sted",
+      LocationHeader: "Header",
+      LocationQuery: "Query",
+      LocationBody: "Body",
+    },
+    EditModal: {
+      Title: (readonly: boolean) =>
+        `Rediger Plugin ${readonly ? "(skrivebeskyttet)" : ""}`,
+      Download: "Download",
+      Auth: "Godkendelsestype",
+      Content: "OpenAPI Schema",
+      Load: "Hent fra URL",
+      Method: "Metode",
+      Error: "Fejl i OpenAPI Schema",
+    },
+  },
+  Mask: {
+    Name: "Persona",
+    Page: {
+      Title: "Prompts som personaer",
+      SubTitle: (count: number) => `${count} skabeloner`,
+      Search: "Søg skabeloner",
+      Create: "Opret ny",
+    },
+    Item: {
+      Info: (count: number) => `${count} prompts`,
+      Chat: "Chat",
+      View: "Vis",
+      Edit: "Rediger",
+      Delete: "Slet",
+      DeleteConfirm: "Vil du slette?",
+    },
+    EditModal: {
+      Title: (readonly: boolean) =>
+        `Rediger skabelon ${readonly ? "(skrivebeskyttet)" : ""}`,
+      Download: "Download",
+      Clone: "Klon",
+    },
+    Config: {
+      Avatar: "Chat-avatar",
+      Name: "Chat-navn",
+      Sync: {
+        Title: "Brug globale indstillinger",
+        SubTitle: "Gældende for denne chat",
+        Confirm: "Erstat nuværende indstillinger med globale?",
+      },
+      HideContext: {
+        Title: "Skjul ekstra prompts",
+        SubTitle: "Vis dem ikke på chat-skærmen",
+      },
+      Artifacts: {
+        Title: "Brug Artefakter",
+        SubTitle: "Gør det muligt at vise HTML-sider",
+      },
+      CodeFold: {
+        Title: "Fold kode sammen",
+        SubTitle: "Luk/åbn lange kodestykker automatisk",
+      },
+      Share: {
+        Title: "Del denne persona",
+        SubTitle: "Få et link til denne skabelon",
+        Action: "Kopiér link",
+      },
+    },
+  },
+  NewChat: {
+    Return: "Tilbage",
+    Skip: "Start straks",
+    Title: "Vælg en persona",
+    SubTitle: "Chat med den persona, du vælger",
+    More: "Se flere",
+    NotShow: "Vis ikke igen",
+    ConfirmNoShow:
+      "Er du sikker på, at du ikke vil se det igen? Du kan altid slå det til under indstillinger.",
+  },
+  UI: {
+    Confirm: "OK",
+    Cancel: "Fortryd",
+    Close: "Luk",
+    Create: "Opret",
+    Edit: "Rediger",
+    Export: "Eksporter",
+    Import: "Importér",
+    Sync: "Synk",
+    Config: "Konfigurer",
+  },
+  Exporter: {
+    Description: {
+      Title: "Kun beskeder efter sidste rydning vises",
+    },
+    Model: "Model",
+    Messages: "Beskeder",
+    Topic: "Emne",
+    Time: "Tid",
+  },
+  URLCommand: {
+    Code: "Så ud til, at der var en kode i linket. Vil du bruge den?",
+    Settings: "Så ud til, at der var indstillinger i linket. Vil du bruge dem?",
+  },
+  SdPanel: {
+    Prompt: "Prompt",
+    NegativePrompt: "Negativ prompt",
+    PleaseInput: (name: string) => `Indtast: ${name}`,
+    AspectRatio: "Billedformat",
+    ImageStyle: "Stil",
+    OutFormat: "Uddataformat",
+    AIModel: "AI-model",
+    ModelVersion: "Version",
+    Submit: "Send",
+    ParamIsRequired: (name: string) => `${name} er krævet`,
+    Styles: {
+      D3Model: "3d-model",
+      AnalogFilm: "analog-film",
+      Anime: "anime",
+      Cinematic: "cinematisk",
+      ComicBook: "tegneserie",
+      DigitalArt: "digital-art",
+      Enhance: "enhance",
+      FantasyArt: "fantasy-art",
+      Isometric: "isometric",
+      LineArt: "line-art",
+      LowPoly: "low-poly",
+      ModelingCompound: "modeling-compound",
+      NeonPunk: "neon-punk",
+      Origami: "origami",
+      Photographic: "fotografisk",
+      PixelArt: "pixel-art",
+      TileTexture: "tile-texture",
+    },
+  },
+  Sd: {
+    SubTitle: (count: number) => `${count} billeder`,
+    Actions: {
+      Params: "Se indstillinger",
+      Copy: "Kopiér prompt",
+      Delete: "Slet",
+      Retry: "Prøv igen",
+      ReturnHome: "Til forsiden",
+      History: "Historik",
+    },
+    EmptyRecord: "Ingen billeder endnu",
+    Status: {
+      Name: "Status",
+      Success: "Ok",
+      Error: "Fejl",
+      Wait: "Venter",
+      Running: "I gang",
+    },
+    Danger: {
+      Delete: "Vil du slette?",
+    },
+    GenerateParams: "Genereringsvalg",
+    Detail: "Detaljer",
+  },
+};
+
+export default da;
--- a/app/locales/de.ts
+++ b/app/locales/de.ts
@@ -439,6 +439,22 @@ const de: PartialLocaleType = {
        SubTitle:
          "Fügen Sie benutzerdefinierte Modelloptionen hinzu, getrennt durch Kommas",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "API-Schlüssel",
+          SubTitle: "Verwenden Sie Ihren eigenen HUAWEI API-Schlüssel",
+          Placeholder: "HUAWEI-Schlüssel",
+        },
+        SecretKey: {
+          Title: "Geheimer Schlüssel",
+          SubTitle: "Verwenden Sie Ihren eigenen HUAWEI geheimen Schlüssel",
+          Placeholder: "HUAWEI geheimer Schlüssel",
+        },
+        Endpoint: {
+          Title: "Schnittstellenadresse",
+          SubTitle: "Unterstützt keine benutzerdefinierte .env-Konfiguration",
+        },
+      },
    },

    Model: "Modell",
--- a/app/locales/en.ts
+++ b/app/locales/en.ts
@@ -522,6 +522,22 @@ const en: LocaleType = {
        Title: "Custom Models",
        SubTitle: "Custom model options, seperated by comma",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "API Key",
+          SubTitle: "Use your own HUAWEI API key",
+          Placeholder: "HUAWEI Key",
+        },
+        SecretKey: {
+          Title: "Secret Key",
+          SubTitle: "Use your own HUAWEI Secret key",
+          Placeholder: "HUAWEI Secret Key",
+        },
+        Endpoint: {
+          Title: "Endpoint Address",
+          SubTitle: "Does not support custom .env configuration",
+        },
+      },
      Google: {
        ApiKey: {
          Title: "API Key",
--- a/app/locales/es.ts
+++ b/app/locales/es.ts
@@ -441,6 +441,22 @@ const es: PartialLocaleType = {
        SubTitle:
          "Agrega opciones de modelos personalizados, separados por comas",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "Clave API",
+          SubTitle: "Utiliza tu propia clave API de HUAWEI",
+          Placeholder: "Clave HUAWEI",
+        },
+        SecretKey: {
+          Title: "Clave Secreta",
+          SubTitle: "Utiliza tu propia clave secreta de HUAWEI",
+          Placeholder: "Clave secreta HUAWEI",
+        },
+        Endpoint: {
+          Title: "Dirección del Endpoint",
+          SubTitle: "No admite configuración personalizada .env",
+        },
+      },
    },

    Model: "Modelo (model)",
--- a/app/locales/fr.ts
+++ b/app/locales/fr.ts
@@ -440,6 +440,23 @@ const fr: PartialLocaleType = {
        SubTitle:
          "Ajouter des options de modèles personnalisés, séparées par des virgules",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "Clé API",
+          SubTitle: "Utilisez votre propre clé API HUAWEI",
+          Placeholder: "Clé HUAWEI",
+        },
+        SecretKey: {
+          Title: "Clé secrète",
+          SubTitle: "Utilisez votre propre clé secrète HUAWEI",
+          Placeholder: "Clé secrète HUAWEI",
+        },
+        Endpoint: {
+          Title: "Adresse de l'endpoint",
+          SubTitle:
+            "Ne prend pas en charge la configuration personnalisée .env",
+        },
+      },
    },

    Model: "Modèle",
--- a/app/locales/id.ts
+++ b/app/locales/id.ts
@@ -428,6 +428,22 @@ const id: PartialLocaleType = {
        Title: "Nama Model Kustom",
        SubTitle: "Tambahkan opsi model kustom, pisahkan dengan koma",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "Kunci API",
+          SubTitle: "Gunakan kunci API HUAWEI Anda sendiri",
+          Placeholder: "Kunci HUAWEI",
+        },
+        SecretKey: {
+          Title: "Kunci Rahasia",
+          SubTitle: "Gunakan kunci rahasia HUAWEI Anda sendiri",
+          Placeholder: "Kunci Rahasia HUAWEI",
+        },
+        Endpoint: {
+          Title: "Alamat Endpoint",
+          SubTitle: "Tidak mendukung konfigurasi .env kustom",
+        },
+      },
    },

    Model: "Model",
--- a/app/locales/index.ts
+++ b/app/locales/index.ts
@@ -2,6 +2,7 @@ import cn from "./cn";
 import en from "./en";
 import pt from "./pt";
 import tw from "./tw";
+import da from "./da";
 import id from "./id";
 import fr from "./fr";
 import es from "./es";
@@ -30,6 +31,7 @@ const ALL_LANGS = {
  en,
  tw,
  pt,
+  da,
  jp,
  ko,
  id,
@@ -56,6 +58,7 @@ export const ALL_LANG_OPTIONS: Record<Lang, string> = {
  en: "English",
  pt: "Português",
  tw: "繁體中文",
+  da: "Dansk",
  jp: "日本語",
  ko: "한국어",
  id: "Indonesia",
@@ -141,6 +144,7 @@ export const STT_LANG_MAP: Record<Lang, string> = {
  en: "en-US",
  pt: "pt-BR",
  tw: "zh-TW",
+  da: "da-DK",
  jp: "ja-JP",
  ko: "ko-KR",
  id: "id-ID",
--- a/app/locales/it.ts
+++ b/app/locales/it.ts
@@ -441,6 +441,22 @@ const it: PartialLocaleType = {
        SubTitle:
          "Aggiungi opzioni di modelli personalizzati, separati da virgole",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "Chiave API",
+          SubTitle: "Usa la tua chiave API HUAWEI",
+          Placeholder: "Chiave HUAWEI",
+        },
+        SecretKey: {
+          Title: "Chiave Segreta",
+          SubTitle: "Usa la tua chiave segreta HUAWEI",
+          Placeholder: "Chiave segreta HUAWEI",
+        },
+        Endpoint: {
+          Title: "Indirizzo dell'Endpoint",
+          SubTitle: "Non supporta configurazioni personalizzate .env",
+        },
+      },
    },

    Model: "Modello (model)",
--- a/app/locales/jp.ts
+++ b/app/locales/jp.ts
@@ -424,6 +424,22 @@ const jp: PartialLocaleType = {
        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",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "APIキー",
+          SubTitle: "自分のHUAWEI APIキーを使用してください",
+          Placeholder: "HUAWEIキー",
+        },
+        SecretKey: {
+          Title: "秘密キー",
+          SubTitle: "自分のHUAWEI秘密キーを使用してください",
+          Placeholder: "HUAWEI秘密キー",
+        },
+        Endpoint: {
+          Title: "エンドポイントアドレス",
+          SubTitle: "カスタム.env構成はサポートされていません",
+        },
+      },
    },

    Model: "モデル (model)",
--- a/app/locales/ko.ts
+++ b/app/locales/ko.ts
@@ -421,6 +421,22 @@ const ko: PartialLocaleType = {
        Title: "커스텀 모델 이름",
        SubTitle: "커스텀 모델 옵션 추가, 영어 쉼표로 구분",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "API 키",
+          SubTitle: "자신의 HUAWEI API 키를 사용하세요",
+          Placeholder: "HUAWEI 키",
+        },
+        SecretKey: {
+          Title: "비밀 키",
+          SubTitle: "자신의 HUAWEI 비밀 키를 사용하세요",
+          Placeholder: "HUAWEI 비밀 키",
+        },
+        Endpoint: {
+          Title: "엔드포인트 주소",
+          SubTitle: "사용자 정의 .env 구성을 지원하지 않습니다",
+        },
+      },
    },

    Model: "모델 (model)",
--- a/app/locales/no.ts
+++ b/app/locales/no.ts
@@ -433,6 +433,22 @@ const no: PartialLocaleType = {
        Title: "Egendefinert modellnavn",
        SubTitle: "Legg til egendefinerte modellalternativer, skill med komma",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "API-nøkkel",
+          SubTitle: "Bruk din egen HUAWEI API-nøkkel",
+          Placeholder: "HUAWEI-nøkkel",
+        },
+        SecretKey: {
+          Title: "Hemmelig nøkkel",
+          SubTitle: "Bruk din egen HUAWEI hemmelige nøkkel",
+          Placeholder: "HUAWEI hemmelig nøkkel",
+        },
+        Endpoint: {
+          Title: "Grensesnittadresse",
+          SubTitle: "Støtter ikke tilpasset .env-konfigurasjon",
+        },
+      },
    },

    Model: "Modell",
--- a/app/locales/pt.ts
+++ b/app/locales/pt.ts
@@ -363,6 +363,22 @@ const pt: PartialLocaleType = {
        Title: "Modelos Personalizados",
        SubTitle: "Opções de modelo personalizado, separados por vírgula",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "Chave API",
+          SubTitle: "Use sua própria chave API HUAWEI",
+          Placeholder: "Chave HUAWEI",
+        },
+        SecretKey: {
+          Title: "Chave Secreta",
+          SubTitle: "Use sua própria chave secreta HUAWEI",
+          Placeholder: "Chave Secreta HUAWEI",
+        },
+        Endpoint: {
+          Title: "Endereço do Endpoint",
+          SubTitle: "Não suporta configuração personalizada .env",
+        },
+      },
    },

    Model: "Modelo",
--- a/app/locales/ru.ts
+++ b/app/locales/ru.ts
@@ -431,6 +431,22 @@ const ru: PartialLocaleType = {
        SubTitle:
          "Добавьте варианты пользовательских моделей, разделяя запятыми",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "API Ключ",
+          SubTitle: "Используйте свой HUAWEI API ключ",
+          Placeholder: "HUAWEI Ключ",
+        },
+        SecretKey: {
+          Title: "Секретный Ключ",
+          SubTitle: "Используйте свой HUAWEI Секретный ключ",
+          Placeholder: "HUAWEI Секретный Ключ",
+        },
+        Endpoint: {
+          Title: "Адрес интерфейса",
+          SubTitle: "Не поддерживает собственную конфигурацию .env",
+        },
+      },
    },

    Model: "Модель",
--- a/app/locales/sk.ts
+++ b/app/locales/sk.ts
@@ -363,6 +363,22 @@ const sk: PartialLocaleType = {
        Title: "Vlastné modely",
        SubTitle: "Možnosti vlastného modelu, oddelené čiarkou",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "API kľúč",
+          SubTitle: "Použite svoj vlastný HUAWEI API kľúč",
+          Placeholder: "HUAWEI kľúč",
+        },
+        SecretKey: {
+          Title: "Tajný kľúč",
+          SubTitle: "Použite svoj vlastný HUAWEI tajný kľúč",
+          Placeholder: "HUAWEI tajný kľúč",
+        },
+        Endpoint: {
+          Title: "Adresa rozhrania",
+          SubTitle: "Nepodporuje vlastnú konfiguráciu .env",
+        },
+      },
      Google: {
        ApiKey: {
          Title: "API kľúč",
--- a/app/locales/tr.ts
+++ b/app/locales/tr.ts
@@ -431,6 +431,22 @@ const tr: PartialLocaleType = {
        SubTitle:
          "Özelleştirilmiş model seçenekleri ekleyin, İngilizce virgül ile ayırın",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "API Anahtarı",
+          SubTitle: "Kendi Huawei API Anahtarınızı kullanın",
+          Placeholder: "HUAWEI Anahtarı",
+        },
+        SecretKey: {
+          Title: "Gizli Anahtar",
+          SubTitle: "Kendi HUAWEI Gizli Anahtarınızı kullanın",
+          Placeholder: "HUAWEI Gizli Anahtarı",
+        },
+        Endpoint: {
+          Title: "Arayüz Adresi",
+          SubTitle: "Özelleştirilmiş .env yapılandırmasına desteklenmez",
+        },
+      },
    },

    Model: "Model (model)",
--- a/app/locales/tw.ts
+++ b/app/locales/tw.ts
@@ -386,6 +386,22 @@ const tw = {
        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",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "API金鑰",
+          SubTitle: "使用您的HUAWEI API金鑰",
+          Placeholder: "HUAWEI金鑰",
+        },
+        SecretKey: {
+          Title: "密鑰",
+          SubTitle: "使用您的HUAWEI密鑰",
+          Placeholder: "HUAWEI密鑰",
+        },
+        Endpoint: {
+          Title: "端點地址",
+          SubTitle: "不支援自訂的.env配置",
+        },
+      },
    },

    Model: "模型 (model)",
--- a/app/locales/vi.ts
+++ b/app/locales/vi.ts
@@ -427,6 +427,22 @@ const vi: PartialLocaleType = {
        SubTitle:
          "Thêm tùy chọn mô hình tùy chỉnh, sử dụng dấu phẩy để phân cách",
      },
+      Huawei: {
+        ApiKey: {
+          Title: "Khóa API",
+          SubTitle: "Sử dụng khóa API HUAWEI của bạn",
+          Placeholder: "Khóa HUAWEI",
+        },
+        SecretKey: {
+          Title: "Khóa bí mật",
+          SubTitle: "Sử dụng khóa bí mật HUAWEI của bạn",
+          Placeholder: "Khóa bí mật HUAWEI",
+        },
+        Endpoint: {
+          Title: "Địa chỉ điểm cuối",
+          SubTitle: "Không hỗ trợ cấu hình .env tùy chỉnh",
+        },
+      },
    },

    Model: "Mô hình (model)",
--- a/app/store/access.ts
+++ b/app/store/access.ts
@@ -17,6 +17,7 @@ import {
  XAI_BASE_URL,
  CHATGLM_BASE_URL,
  SILICONFLOW_BASE_URL,
+  HUAWEI_BASE_URL,
 } from "../constant";
 import { getHeaders } from "../client/api";
 import { getClientConfig } from "../config/client";
@@ -55,6 +56,8 @@ const DEFAULT_XAI_URL = isApp ? XAI_BASE_URL : ApiPath.XAI;

 const DEFAULT_CHATGLM_URL = isApp ? CHATGLM_BASE_URL : ApiPath.ChatGLM;

+const DEFAULT_HUAWEI_URL = isApp ? HUAWEI_BASE_URL : ApiPath.Huawei;
+
 const DEFAULT_SILICONFLOW_URL = isApp
  ? SILICONFLOW_BASE_URL
  : ApiPath.SiliconFlow;
@@ -131,6 +134,9 @@ const DEFAULT_ACCESS_STATE = {
  // siliconflow
  siliconflowUrl: DEFAULT_SILICONFLOW_URL,
  siliconflowApiKey: "",
+  // huawei
+  huaweiUrl: DEFAULT_HUAWEI_URL,
+  huaweiApiKey: "",

  // server config
  needCode: true,
@@ -219,6 +225,9 @@ export const useAccessStore = createPersistStore(
      return ensure(get(), ["siliconflowApiKey"]);
    },

+    isValidHuawei() {
+      return ensure(get(), ["huaweiApiKey"]);
+    },
    isAuthorized() {
      this.fetch();

@@ -238,6 +247,7 @@ export const useAccessStore = createPersistStore(
        this.isValidXAI() ||
        this.isValidChatGLM() ||
        this.isValidSiliconFlow() ||
+        this.isValidHuawei() ||
        !this.enabledAccessControl() ||
        (this.enabledAccessControl() && ensure(get(), ["accessCode"]))
      );
--- a/app/utils.ts
+++ b/app/utils.ts
@@ -2,7 +2,11 @@ import { useEffect, useState } from "react";
 import { showToast } from "./components/ui-lib";
 import Locale from "./locales";
 import { RequestMessage } from "./client/api";
-import { ServiceProvider } from "./constant";
+import {
+  REQUEST_TIMEOUT_MS,
+  REQUEST_TIMEOUT_MS_FOR_THINKING,
+  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";
@@ -292,6 +296,20 @@ export function isDalle3(model: string) {
  return "dall-e-3" === model;
 }

+export function getTimeoutMSByModel(model: string) {
+  model = model.toLowerCase();
+  if (
+    model.startsWith("dall-e") ||
+    model.startsWith("dalle") ||
+    model.startsWith("o1") ||
+    model.startsWith("o3") ||
+    model.includes("deepseek-r") ||
+    model.includes("-thinking")
+  )
+    return REQUEST_TIMEOUT_MS_FOR_THINKING;
+  return REQUEST_TIMEOUT_MS;
+}
+
 export function getModelSizes(model: string): ModelSize[] {
  if (isDalle3(model)) {
    return ["1024x1024", "1792x1024", "1024x1792"];
--- a/app/utils/chat.ts
+++ b/app/utils/chat.ts
@@ -3,7 +3,7 @@ import {
  UPLOAD_URL,
  REQUEST_TIMEOUT_MS,
 } from "@/app/constant";
-import { RequestMessage } from "@/app/client/api";
+import { MultimodalContent, RequestMessage } from "@/app/client/api";
 import Locale from "@/app/locales";
 import {
  EventStreamContentType,
@@ -70,8 +70,9 @@ export function compressImage(file: Blob, maxSize: number): Promise<string> {
  });
 }

-export async function preProcessImageContent(
+export async function preProcessImageContentBase(
  content: RequestMessage["content"],
+  transformImageUrl: (url: string) => Promise<{ [key: string]: any }>,
 ) {
  if (typeof content === "string") {
    return content;
@@ -81,7 +82,7 @@ export async function preProcessImageContent(
    if (part?.type == "image_url" && part?.image_url?.url) {
      try {
        const url = await cacheImageToBase64Image(part?.image_url?.url);
-        result.push({ type: part.type, image_url: { url } });
+        result.push(await transformImageUrl(url));
      } catch (error) {
        console.error("Error processing image URL:", error);
      }
@@ -92,6 +93,23 @@ export async function preProcessImageContent(
  return result;
 }

+export async function preProcessImageContent(
+  content: RequestMessage["content"],
+) {
+  return preProcessImageContentBase(content, async (url) => ({
+    type: "image_url",
+    image_url: { url },
+  })) as Promise<MultimodalContent[] | string>;
+}
+
+export async function preProcessImageContentForAlibabaDashScope(
+  content: RequestMessage["content"],
+) {
+  return preProcessImageContentBase(content, async (url) => ({
+    image: url,
+  }));
+}
+
 const imageCaches: Record<string, string> = {};
 export function cacheImageToBase64Image(imageUrl: string) {
  if (imageUrl.includes(CACHE_URL_PREFIX)) {
@@ -400,6 +418,7 @@ export function streamWithThink(
  let responseRes: Response;
  let isInThinkingMode = false;
  let lastIsThinking = false;
+  let lastIsThinkingTagged = false; //between <think> and </think> tags

  // animate response to make it looks smooth
  function animateResponseText() {
@@ -579,6 +598,23 @@ export function streamWithThink(
          if (!chunk?.content || chunk.content.length === 0) {
            return;
          }
+
+          // deal with <think> and </think> tags start
+          if (!chunk.isThinking) {
+            if (chunk.content.startsWith("<think>")) {
+              chunk.isThinking = true;
+              chunk.content = chunk.content.slice(7).trim();
+              lastIsThinkingTagged = true;
+            } else if (chunk.content.endsWith("</think>")) {
+              chunk.isThinking = false;
+              chunk.content = chunk.content.slice(0, -8).trim();
+              lastIsThinkingTagged = false;
+            } else if (lastIsThinkingTagged) {
+              chunk.isThinking = true;
+            }
+          }
+          // deal with <think> and </think> tags start
+
          // Check if thinking mode changed
          const isThinkingChanged = lastIsThinking !== chunk.isThinking;
          lastIsThinking = chunk.isThinking;
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -17,6 +17,40 @@ services:
      - ENABLE_BALANCE_QUERY=$ENABLE_BALANCE_QUERY
      - DISABLE_FAST_LINK=$DISABLE_FAST_LINK
      - OPENAI_SB=$OPENAI_SB
+      - SILICONFLOW_API_KEY=$SILICONFLOW_API_KEY
+      - SILICONFLOW_URL=$SILICONFLOW_URL
+      - AZURE_URL=$AZURE_URL
+      - AZURE_API_KEY=$AZURE_API_KEY
+      - AZURE_API_VERSION=$AZURE_API_VERSION
+      - GOOGLE_URL=$GOOGLE_URL
+      - GTM_ID=$GTM_ID
+      - ANTHROPIC_URL=$ANTHROPIC_URL
+      - ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY
+      - ANTHROPIC_API_VERSION=$ANTHROPIC_API_VERSION
+      - BAIDU_URL=$BAIDU_URL
+      - BAIDU_API_KEY=$BAIDU_API_KEY
+      - BAIDU_SECRET_KEY=$BAIDU_SECRET_KEY
+      - BYTEDANCE_URL=$BYTEDANCE_URL
+      - BYTEDANCE_API_KEY=$BYTEDANCE_API_KEY
+      - ALIBABA_URL=$ALIBABA_URL
+      - ALIBABA_API_KEY=$ALIBABA_API_KEY
+      - TENCENT_URL=$TENCENT_URL
+      - TENCENT_SECRET_KEY=$TENCENT_SECRET_KEY
+      - TENCENT_SECRET_ID=$TENCENT_SECRET_ID
+      - MOONSHOT_URL=$MOONSHOT_URL
+      - MOONSHOT_API_KEY=$MOONSHOT_API_KEY
+      - IFLYTEK_URL=$IFLYTEK_URL
+      - IFLYTEK_API_KEY=$IFLYTEK_API_KEY
+      - IFLYTEK_API_SECRET=$IFLYTEK_API_SECRET
+      - DEEPSEEK_URL=$DEEPSEEK_URL
+      - DEEPSEEK_API_KEY=$DEEPSEEK_API_KEY
+      - XAI_URL=$XAI_URL
+      - XAI_API_KEY=$XAI_API_KEY
+      - CHATGLM_URL=$CHATGLM_URL
+      - CHATGLM_API_KEY=$CHATGLM_API_KEY
+      - DEFAULT_INPUT_TEMPLATE=$DEFAULT_INPUT_TEMPLATE
+      - HUAWEI_API_KEY=$HUAWEI_API_KEY
+      - HUAWEI_URL=$HUAWEI_URL

  chatgpt-next-web-proxy:
    profiles: [ "proxy" ]
@@ -36,3 +70,37 @@ services:
      - ENABLE_BALANCE_QUERY=$ENABLE_BALANCE_QUERY
      - DISABLE_FAST_LINK=$DISABLE_FAST_LINK
      - OPENAI_SB=$OPENAI_SB
+      - SILICONFLOW_API_KEY=$SILICONFLOW_API_KEY
+      - SILICONFLOW_URL=$SILICONFLOW_URL
+      - AZURE_URL=$AZURE_URL
+      - AZURE_API_KEY=$AZURE_API_KEY
+      - AZURE_API_VERSION=$AZURE_API_VERSION
+      - GOOGLE_URL=$GOOGLE_URL
+      - GTM_ID=$GTM_ID
+      - ANTHROPIC_URL=$ANTHROPIC_URL
+      - ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY
+      - ANTHROPIC_API_VERSION=$ANTHROPIC_API_VERSION
+      - BAIDU_URL=$BAIDU_URL
+      - BAIDU_API_KEY=$BAIDU_API_KEY
+      - BAIDU_SECRET_KEY=$BAIDU_SECRET_KEY
+      - BYTEDANCE_URL=$BYTEDANCE_URL
+      - BYTEDANCE_API_KEY=$BYTEDANCE_API_KEY
+      - ALIBABA_URL=$ALIBABA_URL
+      - ALIBABA_API_KEY=$ALIBABA_API_KEY
+      - TENCENT_URL=$TENCENT_URL
+      - TENCENT_SECRET_KEY=$TENCENT_SECRET_KEY
+      - TENCENT_SECRET_ID=$TENCENT_SECRET_ID
+      - MOONSHOT_URL=$MOONSHOT_URL
+      - MOONSHOT_API_KEY=$MOONSHOT_API_KEY
+      - IFLYTEK_URL=$IFLYTEK_URL
+      - IFLYTEK_API_KEY=$IFLYTEK_API_KEY
+      - IFLYTEK_API_SECRET=$IFLYTEK_API_SECRET
+      - DEEPSEEK_URL=$DEEPSEEK_URL
+      - DEEPSEEK_API_KEY=$DEEPSEEK_API_KEY
+      - XAI_URL=$XAI_URL
+      - XAI_API_KEY=$XAI_API_KEY
+      - CHATGLM_URL=$CHATGLM_URL
+      - CHATGLM_API_KEY=$CHATGLM_API_KEY
+      - DEFAULT_INPUT_TEMPLATE=$DEFAULT_INPUT_TEMPLATE
+      - HUAWEI_API_KEY=$HUAWEI_API_KEY
+      - HUAWEI_URL=$HUAWEI_URL
--- a/jest.config.ts
+++ b/jest.config.ts
@@ -15,6 +15,8 @@ const config: Config = {
  moduleNameMapper: {
    "^@/(.*)$": "<rootDir>/$1",
  },
+  extensionsToTreatAsEsm: [".ts", ".tsx"],
+  injectGlobals: true,
 };

 // createJestConfig is exported this way to ensure that next/jest can load the Next.js config which is async
--- a/jest.setup.ts
+++ b/jest.setup.ts
@@ -1,24 +1,22 @@
 // Learn more: https://github.com/testing-library/jest-dom
 import "@testing-library/jest-dom";
+import { jest } from "@jest/globals";

 global.fetch = jest.fn(() =>
  Promise.resolve({
    ok: true,
    status: 200,
-    json: () => Promise.resolve({}),
+    json: () => Promise.resolve([]),
    headers: new Headers(),
    redirected: false,
    statusText: "OK",
    type: "basic",
    url: "",
-    clone: function () {
-      return this;
-    },
    body: null,
    bodyUsed: false,
    arrayBuffer: () => Promise.resolve(new ArrayBuffer(0)),
    blob: () => Promise.resolve(new Blob()),
    formData: () => Promise.resolve(new FormData()),
    text: () => Promise.resolve(""),
-  }),
+  } as Response),
 );
--- a/package.json
+++ b/package.json
@@ -17,8 +17,8 @@
    "prompts": "node ./scripts/fetch-prompts.mjs",
    "prepare": "husky install",
    "proxy-dev": "sh ./scripts/init-proxy.sh && proxychains -f ./scripts/proxychains.conf yarn dev",
-    "test": "jest --watch",
-    "test:ci": "jest --ci"
+    "test": "node --no-warnings --experimental-vm-modules $(yarn bin jest) --watch",
+    "test:ci": "node --no-warnings --experimental-vm-modules $(yarn bin jest) --ci"
  },
  "dependencies": {
    "@fortaine/fetch-event-source": "^3.0.6",
--- a/test/vision-model-checker.test.ts
+++ b/test/vision-model-checker.test.ts
@@ -1,3 +1,4 @@
+import { jest } from "@jest/globals";
 import { isVisionModel } from "../app/utils";

 describe("isVisionModel", () => {
@@ -50,7 +51,7 @@ describe("isVisionModel", () => {

  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);
@@ -64,4 +65,4 @@ describe("isVisionModel", () => {
    expect(isVisionModel("unrelated-model")).toBe(false);
    expect(isVisionModel("gpt-4-vision")).toBe(true);
  });
-});
+});
Author	SHA1	Message	Date
shiyebushihua	26a7d30c79	Merge `c3648a376f` into `c30ddfbb07`	2025-06-12 18:14:06 +08:00
RiverRay	c30ddfbb07	Merge pull request #6425 from yunlingz/o_model_md_response Some checks failed Run Tests / test (push) Has been cancelled Details Fix: Encourage markdown inclusion in model responses for o1/o3	2025-06-12 11:19:24 +08:00
RiverRay	a2f0149786	Merge pull request #6460 from dreamsafari/main 加入Grok3模型列表	2025-06-12 11:13:31 +08:00
GH Action - Upstream Sync	03d36f96ed	Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web	2025-06-12 01:53:30 +00:00
RiverRay	705dffc664	Merge pull request #6514 from KevinShiCN/patch-1 Some checks failed Run Tests / test (push) Has been cancelled Details Add gemini-2.5-pro-preview-06-05 into constant.ts	2025-06-11 16:14:09 +08:00
KevinShiCN	02f7e6de98	Add gemini-2.5-pro-preview-06-05 into constant.ts	2025-06-08 23:59:49 +08:00
dreamsafari	843dc52efa	加入Grok3模型列表	2025-04-22 13:06:54 +08:00
RiverRay	3809375694	Merge pull request #6457 from ACTOR-ALCHEMIST/main Some checks failed Run Tests / test (push) Has been cancelled Details Support OpenAI o3 and o4-mini	2025-04-19 16:00:41 +08:00
RiverRay	1b0de25986	Update README.md	2025-04-19 15:59:31 +08:00
RiverRay	865c45dd29	Update README.md	2025-04-19 15:56:53 +08:00
RiverRay	1f5d8e6d9c	Merge pull request #6458 from ChatGPTNextWeb/Leizhenpeng-patch-7 Update README.md	2025-04-19 15:50:48 +08:00
RiverRay	c9ef6d58ed	Update README.md	2025-04-19 15:50:17 +08:00
Jasper Hu	2d7229d2b8	feat: 支持 OpenAI 新模型 o3 与 o4-mini，并适配新参数	2025-04-18 20:36:07 +01:00
RiverRay	11b37c15bd	Merge pull request #6450 from stephen-zeng/main Some checks failed Run Tests / test (push) Has been cancelled Details Add gpt-4.1 family & gpt-4.5-preview support	2025-04-17 08:29:19 +08:00
QwQwQ	1d0038f17d	add gpt-4.5-preview support	2025-04-16 22:10:47 +08:00
QwQwQ	619fa519c0	add gpt-4.1 family support	2025-04-16 22:02:35 +08:00
Yunling Zhu	c261ebc82c	use unshift to improve perf	2025-04-06 16:56:54 +08:00
Yunling Zhu	f7c747c65f	encourage markdown inclusion for o1/o3	2025-04-03 22:11:59 +08:00
wangjianhua	c3648a376f	字节v3新模型兼容	2025-03-26 19:28:10 +08:00
wangjianhua	62d50e916e	Merge branch 'main' of https://github.com/wangjianhuaa/NextChat into feature-dsmodels-20250228	2025-03-26 18:54:55 +08:00
wangjianhuaa	bb84a816b2	Merge branch 'ChatGPTNextWeb:main' into main	2025-03-26 18:54:25 +08:00
wangjianhua	18e2ab0dea	华为兼容	2025-03-26 18:53:33 +08:00
RiverRay	48469bd8ca	Merge pull request #6392 from ChatGPTNextWeb/Leizhenpeng-patch-6 Some checks failed Run Tests / test (push) Has been cancelled Details Update README.md	2025-03-20 17:52:02 +08:00
RiverRay	5a5e887f2b	Update README.md	2025-03-20 17:51:47 +08:00
wangjianhuaa	60fe83a412	Merge branch 'ChatGPTNextWeb:main' into main	2025-03-18 18:35:56 +08:00
RiverRay	b6f5d75656	Merge pull request #6344 from vangie/fix/jest-setup-esm Some checks failed Run Tests / test (push) Has been cancelled Details test: fix unit test failures	2025-03-14 20:04:56 +08:00
Vangie Du	0d41a17ef6	test: fix unit test failures	2025-03-07 14:49:17 +08:00
wangjianhuaa	334fff6241	Merge pull request #1 from wangjianhuaa/feature-dsmodels-20250228 feature-dsmodels-20250228	2025-03-01 14:56:00 +08:00
wangjianhuaa	bc34792494	fix some bugs for suggestion	2025-03-01 14:46:20 +08:00
wangjianhuaa	b49910ad59	fix some bugs for suggestion	2025-03-01 14:45:20 +08:00
RiverRay	f7cde17919	Merge pull request #6292 from Little-LittleProgrammer/feature/alibaba-omni-support Some checks failed Run Tests / test (push) Has been cancelled Details feat(alibaba): Added alibaba vision model and omni model support	2025-03-01 10:25:16 +08:00
RiverRay	570cbb34b6	Merge pull request #6310 from agi-dude/patch-1 Remove duplicate links	2025-03-01 10:24:38 +08:00
RiverRay	7aa9ae0a3e	Merge pull request #6311 from ChatGPTNextWeb/6305-bugthe-first-message-except-the-system-message-of-deepseek-reasoner-must-be-a-user-message-but-an-assistant-message-detected Some checks are pending Run Tests / test (push) Waiting to run Details fix: enforce that the first message (excluding system messages) is a …	2025-02-28 19:48:09 +08:00
wangjianhua	bd1a39b0de	国际化	2025-02-28 15:04:59 +08:00
Kadxy	2d4180f5be	fix: update request payload to use filtered messages in Deepseek API	2025-02-28 13:59:30 +08:00
Kadxy	9f0182b55e	fix: enforce that the first message (excluding system messages) is a user message in the Deepseek API	2025-02-28 13:54:58 +08:00
wangjianhua	cf9d088789	新增字节跳动ds模型兼容,新增华为ds模型兼容	2025-02-28 13:54:14 +08:00
Mr. AGI	ad6666eeaf	Update README.md	2025-02-28 10:47:52 +05:00
EvanWu	a2c4e468a0	fix(app/utils/chat.ts): fix type error	2025-02-26 19:58:32 +08:00
RiverRay	2167076652	Merge pull request #6293 from hyiip/main Some checks failed Run Tests / test (push) Has been cancelled Details claude 3.7 support	2025-02-26 18:41:28 +08:00
RiverRay	e123076250	Merge pull request #6295 from rexkyng/patch-1 Fix: Improve Mistral icon detection and remove redundant code.	2025-02-26 18:39:59 +08:00
Rex Ng	ebcb4db245	Fix: Improve Mistral icon detection and remove redundant code. - Added "codestral" to the list of acceptable names for the Mistral icon, ensuring proper detection. - Removed duplicate `toLowerCase()` calls.	2025-02-25 14:30:18 +08:00
EvanWu	0a25a1a8cb	refacto(app/utils/chat.ts)r: optimize function preProcessImageContentBase	2025-02-25 09:22:47 +08:00
hyiip	f3154b20a5	claude 3.7 support	2025-02-25 03:55:24 +08:00
EvanWu	b709ee3983	feat(alibaba): Added alibaba vision model and omni model support	2025-02-24 20:18:07 +08:00
RiverRay	f5f3ce94f6	Update README.md Some checks failed Run Tests / test (push) Has been cancelled Details	2025-02-21 08:56:43 +08:00
RiverRay	2b5f600308	Update README.md	2025-02-21 08:55:40 +08:00
RiverRay	b966107117	Merge pull request #6235 from DBCDK/danish-locale Some checks failed Run Tests / test (push) Has been cancelled Details Translation to danish	2025-02-17 22:58:01 +08:00
river	377480b448	Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web Some checks failed Run Tests / test (push) Has been cancelled Details	2025-02-16 10:50:07 +08:00
river	8bd0d6a1a7	chore: Update NextChatAI domain from nextchat.dev to nextchat.club	2025-02-16 10:48:54 +08:00
Rasmus Erik Voel Jensen	90827fc593	danish rewording / improved button label	2025-02-15 13:08:58 +01:00
Rasmus Erik Voel Jensen	008e339b6d	danish locale	2025-02-15 12:52:44 +01:00
RiverRay	12863f5213	Merge pull request #6204 from bestsanmao/ali_bytedance_reasoning_content Some checks failed Run Tests / test (push) Has been cancelled Details add 3 type of reasoning_content support (+deepseek-r1@OpenAI @Alibaba @ByteDance), parse <think></think> from SSE	2025-02-13 14:53:47 +08:00
suruiqiang	cf140d4228	Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web into ali_bytedance_reasoning_content	2025-02-12 17:54:50 +08:00
suruiqiang	476d946f96	fix bug (trim eats space or \n mistakenly), optimize timeout by model	2025-02-12 17:49:54 +08:00
suruiqiang	9714258322	support deepseek-r1@OpenAI's reasoning_content, parse <think></think> from stream	2025-02-11 18:57:16 +08:00
RiverRay	48cd4b11b5	Merge pull request #6190 from siliconflow/refine-emoji-siliconflow Some checks failed Run Tests / test (push) Has been cancelled Details Fix model icon on SiliconFlow	2025-02-11 18:37:47 +08:00
RiverRay	77c78b230a	Merge pull request #6193 from siliconflow/get-models-siliconflow Model listing of SiliconFlow	2025-02-11 18:37:22 +08:00
RiverRay	b44686b887	Merge pull request #6189 from bestsanmao/bug_fix fix avatar for export message preview and saved image	2025-02-11 18:36:50 +08:00
RiverRay	34bdd4b945	Merge pull request #6194 from siliconflow/vl-support-on-sf Support VLM on SiliconFlow	2025-02-11 18:35:02 +08:00
suruiqiang	b0758cccde	optimization	2025-02-11 16:08:30 +08:00
suruiqiang	98a11e56d2	support alibaba and bytedance's reasoning_content	2025-02-11 12:46:46 +08:00
Shenghang Tsai	86f86962fb	Support VLM on SiliconFlow	2025-02-10 13:39:06 +08:00
Shenghang Tsai	2137aa65bf	Model listing of SiliconFlow	2025-02-10 11:03:49 +08:00
Shenghang Tsai	18fa2cc30d	fix model icon on siliconflow	2025-02-09 18:49:26 +08:00
Shenghang Tsai	0bfc648085	fix model icon on siliconflow	2025-02-09 18:47:57 +08:00
suruiqiang	9f91c2d05c	fix avatar for export message preview and saved image	2025-02-09 16:52:46 +08:00
RiverRay	a029b4330b	Merge pull request #6188 from ChatGPTNextWeb/Leizhenpeng-patch-4 Some checks failed Run Tests / test (push) Has been cancelled Details Update LICENSE	2025-02-09 11:05:43 +08:00