diff --git a/electron-builder.yml b/electron-builder.yml
index ce48c92848..a092c7137f 100644
--- a/electron-builder.yml
+++ b/electron-builder.yml
@@ -65,9 +65,15 @@ afterSign: scripts/notarize.js
 releaseInfo:
   releaseNotes: |
     本次更新：
+      增加流式输出开关
+      Windows 安装程序支持修改安装位置了
+      服务商和小程序图标更新
+      增加 ocoolAI 服务商
+      小程序增加 HuggingChat
+      Gemini 模型回复安全级别关闭
+      修复 macOS 切换窗口透明不生效问题
+      修复消息回复完成界面会自动滚动到最底部的问题
+    近期更新：
       全新应用图标
       模型图标更新
-    近期更新：
-      支持话题导出为图片
-      支持粘贴图片和文件到聊天输入框
-      支持将对话移动到其他智能体了
+      支持 Linux ARM 架构
diff --git a/src/renderer/src/assets/images/apps/huggingchat.svg b/src/renderer/src/assets/images/apps/huggingchat.svg
new file mode 100644
index 0000000000..49765f6468
--- /dev/null
+++ b/src/renderer/src/assets/images/apps/huggingchat.svg
@@ -0,0 +1,14 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="32" height="32" fill="none">
+	<path
+		fill="#FFD21E"
+		d="M4 15.55C4 9.72 8.72 5 14.55 5h4.11a9.34 9.34 0 1 1 0 18.68H7.58l-2.89 2.8a.41.41 0 0 1-.69-.3V15.55Z"
+	/>
+	<path
+		fill="#32343D"
+		d="M19.63 12.48c.37.14.52.9.9.7.71-.38.98-1.27.6-1.98a1.46 1.46 0 0 0-1.98-.61 1.47 1.47 0 0 0-.6 1.99c.17.34.74-.21 1.08-.1ZM12.72 12.48c-.37.14-.52.9-.9.7a1.47 1.47 0 0 1-.6-1.98 1.46 1.46 0 0 1 1.98-.61c.71.38.98 1.27.6 1.99-.18.34-.74-.21-1.08-.1ZM16.24 19.55c2.89 0 3.82-2.58 3.82-3.9 0-1.33-1.71.7-3.82.7-2.1 0-3.8-2.03-3.8-.7 0 1.32.92 3.9 3.8 3.9Z"
+	/>
+	<path
+		fill="#FF323D"
+		d="M18.56 18.8c-.57.44-1.33.75-2.32.75-.92 0-1.65-.27-2.2-.68.3-.63.87-1.11 1.55-1.32.12-.03.24.17.36.38.12.2.24.4.37.4s.26-.2.39-.4.26-.4.38-.36a2.56 2.56 0 0 1 1.47 1.23Z"
+	/>
+</svg>
diff --git a/src/renderer/src/config/minapps.ts b/src/renderer/src/config/minapps.ts
index 784bb309c9..98770c0588 100644
--- a/src/renderer/src/config/minapps.ts
+++ b/src/renderer/src/config/minapps.ts
@@ -5,6 +5,7 @@ import BaicuanAppLogo from '@renderer/assets/images/apps/baixiaoying.webp'
 import DevvAppLogo from '@renderer/assets/images/apps/devv.png'
 import DoubaoAppLogo from '@renderer/assets/images/apps/doubao.png'
 import GeminiAppLogo from '@renderer/assets/images/apps/gemini.png'
+import HuggingChatLogo from '@renderer/assets/images/apps/huggingchat.svg'
 import KimiAppLogo from '@renderer/assets/images/apps/kimi.jpg'
 import MetasoAppLogo from '@renderer/assets/images/apps/metaso.webp'
 import PerplexityAppLogo from '@renderer/assets/images/apps/perplexity.webp'
@@ -191,6 +192,13 @@ const _apps: MinAppType[] = [
     logo: ZhihuAppLogo,
     url: 'https://zhida.zhihu.com/',
     bodered: true
+  },
+  {
+    id: 'hugging-chat',
+    name: 'HuggingChat',
+    logo: HuggingChatLogo,
+    url: 'https://huggingface.co/chat/',
+    bodered: true
   }
 ]
 
diff --git a/src/renderer/src/providers/AnthropicProvider.ts b/src/renderer/src/providers/AnthropicProvider.ts
index e1432a0eed..feef21d1a0 100644
--- a/src/renderer/src/providers/AnthropicProvider.ts
+++ b/src/renderer/src/providers/AnthropicProvider.ts
@@ -72,15 +72,16 @@ export default class AnthropicProvider extends BaseProvider {
       userMessages.shift()
     }
 
+    const body: MessageCreateParamsNonStreaming = {
+      model: model.id,
+      messages: userMessages,
+      max_tokens: maxTokens || DEFAULT_MAX_TOKENS,
+      temperature: assistant?.settings?.temperature,
+      system: assistant.prompt
+    }
+
     if (!streamOutput) {
-      const message = await this.sdk.messages.create({
-        model: model.id,
-        messages: userMessages,
-        max_tokens: maxTokens || DEFAULT_MAX_TOKENS,
-        temperature: assistant?.settings?.temperature,
-        system: assistant.prompt,
-        stream: false
-      })
+      const message = await this.sdk.messages.create({ ...body, stream: false })
       return onChunk({
         text: message.content[0].type === 'text' ? message.content[0].text : '',
         usage: message.usage
@@ -89,14 +90,7 @@ export default class AnthropicProvider extends BaseProvider {
 
     return new Promise<void>((resolve, reject) => {
       const stream = this.sdk.messages
-        .stream({
-          model: model.id,
-          messages: userMessages,
-          max_tokens: maxTokens || DEFAULT_MAX_TOKENS,
-          temperature: assistant?.settings?.temperature,
-          system: assistant.prompt,
-          stream: true
-        })
+        .stream({ ...body, stream: true })
         .on('text', (text) => {
           if (window.keyv.get(EVENT_NAMES.CHAT_COMPLETION_PAUSED)) {
             stream.controller.abort()
diff --git a/src/renderer/src/providers/OpenAIProvider.ts b/src/renderer/src/providers/OpenAIProvider.ts
index 733845bb8d..cfa3be8e7d 100644
--- a/src/renderer/src/providers/OpenAIProvider.ts
+++ b/src/renderer/src/providers/OpenAIProvider.ts
@@ -130,10 +130,10 @@ export default class OpenAIProvider extends BaseProvider {
     const stream = await this.sdk.chat.completions.create({
       model: model.id,
       messages: [systemMessage, ...userMessages].filter(Boolean) as ChatCompletionMessageParam[],
-      stream: isSupportStreamOutput,
       temperature: assistant?.settings?.temperature,
       max_tokens: maxTokens,
-      keep_alive: this.keepAliveTime
+      keep_alive: this.keepAliveTime,
+      stream: isSupportStreamOutput
     })
 
     if (!isSupportStreamOutput) {