@lobehub/chat 1.68.5 → 1.68.7

package/CHANGELOG.md

@@ -2,6 +2,56 @@
 
 # Changelog
 
+### [Version 1.68.7](https://github.com/lobehub/lobe-chat/compare/v1.68.6...v1.68.7)
+
+<sup>Released on **2025-03-05**</sup>
+
+#### ♻ Code Refactoring
+
+- **misc**: Refactor agent runtime to better code format.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Code refactoring
+
+- **misc**: Refactor agent runtime to better code format, closes [#6284](https://github.com/lobehub/lobe-chat/issues/6284) ([fc1ed4a](https://github.com/lobehub/lobe-chat/commit/fc1ed4a))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.68.6](https://github.com/lobehub/lobe-chat/compare/v1.68.5...v1.68.6)
+
+<sup>Released on **2025-03-05**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix custom ai provider sdk type.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Fix custom ai provider sdk type, closes [#6712](https://github.com/lobehub/lobe-chat/issues/6712) ([7f8c379](https://github.com/lobehub/lobe-chat/commit/7f8c379))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
 ### [Version 1.68.5](https://github.com/lobehub/lobe-chat/compare/v1.68.4...v1.68.5)
 
 <sup>Released on **2025-03-04**</sup>

package/README.md

@@ -194,12 +194,12 @@ We have implemented support for the following model service providers:
 - **[HuggingFace](https://lobechat.com/discover/provider/huggingface)**: The HuggingFace Inference API provides a fast and free way for you to explore thousands of models for various tasks. Whether you are prototyping for a new application or experimenting with the capabilities of machine learning, this API gives you instant access to high-performance models across multiple domains.
 - **[OpenRouter](https://lobechat.com/discover/provider/openrouter)**: OpenRouter is a service platform providing access to various cutting-edge large model interfaces, supporting OpenAI, Anthropic, LLaMA, and more, suitable for diverse development and application needs. Users can flexibly choose the optimal model and pricing based on their requirements, enhancing the AI experience.
 - **[Cloudflare Workers AI](https://lobechat.com/discover/provider/cloudflare)**: Run serverless GPU-powered machine learning models on Cloudflare's global network.
+- **[GitHub](https://lobechat.com/discover/provider/github)**: With GitHub Models, developers can become AI engineers and leverage the industry's leading AI models.
 
 <details><summary><kbd>See more providers (+27)</kbd></summary>
 
-- **[GitHub](https://lobechat.com/discover/provider/github)**: With GitHub Models, developers can become AI engineers and leverage the industry's leading AI models.
-- **[PPIO](https://lobechat.com/discover/provider/ppio)**: PPIO supports stable and cost-efficient open-source LLM APIs, such as DeepSeek, Llama, Qwen etc.
 - **[Novita](https://lobechat.com/discover/provider/novita)**: Novita AI is a platform providing a variety of large language models and AI image generation API services, flexible, reliable, and cost-effective. It supports the latest open-source models like Llama3 and Mistral, offering a comprehensive, user-friendly, and auto-scaling API solution for generative AI application development, suitable for the rapid growth of AI startups.
+- **[PPIO](https://lobechat.com/discover/provider/ppio)**: PPIO supports stable and cost-efficient open-source LLM APIs, such as DeepSeek, Llama, Qwen etc.
 - **[Together AI](https://lobechat.com/discover/provider/togetherai)**: Together AI is dedicated to achieving leading performance through innovative AI models, offering extensive customization capabilities, including rapid scaling support and intuitive deployment processes to meet various enterprise needs.
 - **[Fireworks AI](https://lobechat.com/discover/provider/fireworksai)**: Fireworks AI is a leading provider of advanced language model services, focusing on functional calling and multimodal processing. Its latest model, Firefunction V2, is based on Llama-3, optimized for function calling, conversation, and instruction following. The visual language model FireLLaVA-13B supports mixed input of images and text. Other notable models include the Llama series and Mixtral series, providing efficient multilingual instruction following and generation support.
 - **[Groq](https://lobechat.com/discover/provider/groq)**: Groq's LPU inference engine has excelled in the latest independent large language model (LLM) benchmarks, redefining the standards for AI solutions with its remarkable speed and efficiency. Groq represents instant inference speed, demonstrating strong performance in cloud-based deployments.

package/README.zh-CN.md

@@ -194,12 +194,12 @@ LobeChat 支持文件上传与知识库功能，你可以上传文件、图片
 - **[HuggingFace](https://lobechat.com/discover/provider/huggingface)**: HuggingFace Inference API 提供了一种快速且免费的方式，让您可以探索成千上万种模型，适用于各种任务。无论您是在为新应用程序进行原型设计，还是在尝试机器学习的功能，这个 API 都能让您即时访问多个领域的高性能模型。
 - **[OpenRouter](https://lobechat.com/discover/provider/openrouter)**: OpenRouter 是一个提供多种前沿大模型接口的服务平台，支持 OpenAI、Anthropic、LLaMA 及更多，适合多样化的开发和应用需求。用户可根据自身需求灵活选择最优的模型和价格，助力 AI 体验的提升。
 - **[Cloudflare Workers AI](https://lobechat.com/discover/provider/cloudflare)**: 在 Cloudflare 的全球网络上运行由无服务器 GPU 驱动的机器学习模型。
+- **[GitHub](https://lobechat.com/discover/provider/github)**: 通过 GitHub 模型，开发人员可以成为 AI 工程师，并使用行业领先的 AI 模型进行构建。
 
 <details><summary><kbd>See more providers (+27)</kbd></summary>
 
-- **[GitHub](https://lobechat.com/discover/provider/github)**: 通过 GitHub 模型，开发人员可以成为 AI 工程师，并使用行业领先的 AI 模型进行构建。
-- **[PPIO](https://lobechat.com/discover/provider/ppio)**: PPIO 派欧云提供稳定、高性价比的开源模型 API 服务，支持 DeepSeek 全系列、Llama、Qwen 等行业领先大模型。
 - **[Novita](https://lobechat.com/discover/provider/novita)**: Novita AI 是一个提供多种大语言模型与 AI 图像生成的 API 服务的平台，灵活、可靠且具有成本效益。它支持 Llama3、Mistral 等最新的开源模型，并为生成式 AI 应用开发提供了全面、用户友好且自动扩展的 API 解决方案，适合 AI 初创公司的快速发展。
+- **[PPIO](https://lobechat.com/discover/provider/ppio)**: PPIO 派欧云提供稳定、高性价比的开源模型 API 服务，支持 DeepSeek 全系列、Llama、Qwen 等行业领先大模型。
 - **[Together AI](https://lobechat.com/discover/provider/togetherai)**: Together AI 致力于通过创新的 AI 模型实现领先的性能，提供广泛的自定义能力，包括快速扩展支持和直观的部署流程，满足企业的各种需求。
 - **[Fireworks AI](https://lobechat.com/discover/provider/fireworksai)**: Fireworks AI 是一家领先的高级语言模型服务商，专注于功能调用和多模态处理。其最新模型 Firefunction V2 基于 Llama-3，优化用于函数调用、对话及指令跟随。视觉语言模型 FireLLaVA-13B 支持图像和文本混合输入。其他 notable 模型包括 Llama 系列和 Mixtral 系列，提供高效的多语言指令跟随与生成支持。
 - **[Groq](https://lobechat.com/discover/provider/groq)**: Groq 的 LPU 推理引擎在最新的独立大语言模型（LLM）基准测试中表现卓越，以其惊人的速度和效率重新定义了 AI 解决方案的标准。Groq 是一种即时推理速度的代表，在基于云的部署中展现了良好的性能。

package/changelog/v1.json

@@ -1,4 +1,22 @@
 [
+  {
+    "children": {
+      "improvements": [
+        "Refactor agent runtime to better code format."
+      ]
+    },
+    "date": "2025-03-05",
+    "version": "1.68.7"
+  },
+  {
+    "children": {
+      "fixes": [
+        "Fix custom ai provider sdk type."
+      ]
+    },
+    "date": "2025-03-05",
+    "version": "1.68.6"
+  },
   {
     "children": {
       "improvements": [

package/locales/ar/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "تحديث التكوين الأساسي للمزود",
     "updateSuccess": "تم التحديث بنجاح"
   },
+  "updateCustomAiProvider": {
+    "title": "تحديث إعدادات مزود الذكاء الاصطناعي المخصص"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "أدخل مفاتيح Vertex AI الخاصة بك",

package/locales/bg-BG/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "Актуализиране на основната конфигурация на доставчика",
     "updateSuccess": "Актуализацията е успешна"
   },
+  "updateCustomAiProvider": {
+    "title": "Актуализиране на конфигурацията на доставчика на персонализирани AI услуги"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "Въведете вашите ключове за Vertex AI",

package/locales/de-DE/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "Aktualisieren Sie die grundlegenden Anbieterinformationen",
     "updateSuccess": "Aktualisierung erfolgreich"
   },
+  "updateCustomAiProvider": {
+    "title": "Konfiguration des benutzerdefinierten KI-Anbieters aktualisieren"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "Geben Sie Ihre Vertex AI-Schlüssel ein",

package/locales/en-US/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "Update provider basic configuration",
     "updateSuccess": "Update successful"
   },
+  "updateCustomAiProvider": {
+    "title": "Update Custom AI Provider Configuration"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "Enter your Vertex AI Keys",

package/locales/es-ES/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "Actualizar configuración básica del proveedor",
     "updateSuccess": "Actualización exitosa"
   },
+  "updateCustomAiProvider": {
+    "title": "Actualizar la configuración del proveedor de IA personalizado"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "Introduce tus claves de Vertex AI",

package/locales/fa-IR/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "به‌روزرسانی پیکربندی پایه ارائه‌دهنده",
     "updateSuccess": "به‌روزرسانی با موفقیت انجام شد"
   },
+  "updateCustomAiProvider": {
+    "title": "به‌روزرسانی تنظیمات ارائه‌دهنده AI سفارشی"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "کلیدهای Vertex AI خود را وارد کنید",

package/locales/fr-FR/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "Mettre à jour la configuration de base du fournisseur",
     "updateSuccess": "Mise à jour réussie"
   },
+  "updateCustomAiProvider": {
+    "title": "Mettre à jour la configuration du fournisseur de services AI personnalisé"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "Entrez vos clés Vertex AI",

package/locales/it-IT/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "Aggiorna la configurazione di base del fornitore",
     "updateSuccess": "Aggiornamento avvenuto con successo"
   },
+  "updateCustomAiProvider": {
+    "title": "Aggiorna la configurazione del fornitore di AI personalizzato"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "Inserisci le tue chiavi Vertex AI",

package/locales/ja-JP/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "サービスプロバイダーの基本設定を更新",
     "updateSuccess": "更新に成功しました"
   },
+  "updateCustomAiProvider": {
+    "title": "カスタム AI プロバイダー設定の更新"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "あなたの Vertex AI キーを入力してください",

package/locales/ko-KR/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "서비스 제공자 기본 설정 업데이트",
     "updateSuccess": "업데이트 성공"
   },
+  "updateCustomAiProvider": {
+    "title": "사용자 정의 AI 서비스 제공자 구성 업데이트"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "당신의 Vertex AI 키를 입력하세요",

package/locales/nl-NL/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "Werk basisconfiguratie van provider bij",
     "updateSuccess": "Bijwerking geslaagd"
   },
+  "updateCustomAiProvider": {
+    "title": "Bijwerken van de configuratie van de aangepaste AI-provider"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "Vul je Vertex AI-sleutels in",

package/locales/pl-PL/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "Aktualizuj podstawowe ustawienia dostawcy",
     "updateSuccess": "Aktualizacja zakończona sukcesem"
   },
+  "updateCustomAiProvider": {
+    "title": "Aktualizuj konfigurację dostawcy AI"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "Wprowadź swoje klucze Vertex AI",

package/locales/pt-BR/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "Atualizar configurações básicas do provedor",
     "updateSuccess": "Atualização bem-sucedida"
   },
+  "updateCustomAiProvider": {
+    "title": "Atualizar configuração do provedor de IA personalizado"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "Insira suas Chaves do Vertex AI",

package/locales/ru-RU/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "Обновить базовую конфигурацию провайдера",
     "updateSuccess": "Обновление успешно"
   },
+  "updateCustomAiProvider": {
+    "title": "Обновить настройки поставщика пользовательского ИИ"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "Введите ваши ключи Vertex AI",

package/locales/tr-TR/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "Hizmet sağlayıcının temel yapılandırmasını güncelle",
     "updateSuccess": "Güncelleme başarılı"
   },
+  "updateCustomAiProvider": {
+    "title": "Özel AI Sağlayıcı Yapılandırmasını Güncelle"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "Vertex AI Anahtarlarınızı buraya girin",

package/locales/vi-VN/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "Cập nhật cấu hình cơ bản của nhà cung cấp",
     "updateSuccess": "Cập nhật thành công"
   },
+  "updateCustomAiProvider": {
+    "title": "Cập nhật cấu hình nhà cung cấp AI tùy chỉnh"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "Nhập khóa Vertex AI của bạn",

package/locales/zh-CN/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "更新服务商基础配置",
     "updateSuccess": "更新成功"
   },
+  "updateCustomAiProvider": {
+    "title": "更新自定义 AI 服务商配置"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "填入你的 Vertex Ai Keys",

package/locales/zh-TW/modelProvider.json

@@ -322,6 +322,9 @@
     "tooltip": "更新服務商基礎配置",
     "updateSuccess": "更新成功"
   },
+  "updateCustomAiProvider": {
+    "title": "更新自訂 AI 服務商配置"
+  },
   "vertexai": {
     "apiKey": {
       "desc": "填入你的 Vertex AI 金鑰",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/chat",
-  "version": "1.68.5",
+  "version": "1.68.7",
   "description": "Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.",
   "keywords": [
     "framework",

package/src/app/(backend)/webapi/chat/[provider]/route.test.ts

@@ -71,7 +71,7 @@ describe('POST handler', () => {
 
       // migrate to new AgentRuntime init api
       const spy = vi
-        .spyOn(AgentRuntime, 'initializeWithProviderOptions')
+        .spyOn(AgentRuntime, 'initializeWithProvider')
         .mockResolvedValue(new AgentRuntime(mockRuntime));
 
       // 调用 POST 函数
@@ -117,7 +117,7 @@ describe('POST handler', () => {
 
       const mockRuntime: LobeRuntimeAI = { baseURL: 'abc', chat: vi.fn() };
 
-      vi.spyOn(AgentRuntime, 'initializeWithProviderOptions').mockResolvedValue(
+      vi.spyOn(AgentRuntime, 'initializeWithProvider').mockResolvedValue(
         new AgentRuntime(mockRuntime),
       );
 

package/src/app/[variants]/(main)/settings/provider/features/CreateNewProvider/index.tsx

@@ -107,7 +107,7 @@ const CreateNewProvider = memo<CreateNewProviderProps>(({ onClose, open }) => {
       ),
       label: t('createNewAiProvider.sdkType.title'),
       minWidth: 400,
-      name: 'sdkType',
+      name: ['settings', 'sdkType'],
       rules: [{ message: t('createNewAiProvider.sdkType.required'), required: true }],
     },
     {

package/src/app/[variants]/(main)/settings/provider/features/ProviderConfig/UpdateProviderInfo/SettingModal.tsx

@@ -1,6 +1,7 @@
+import { ProviderIcon } from '@lobehub/icons';
 import { FormModal, Icon } from '@lobehub/ui';
 import type { FormItemProps } from '@lobehub/ui/es/Form/components/FormItem';
-import { App, Button, Input } from 'antd';
+import { App, Button, Input, Select } from 'antd';
 import { BrainIcon } from 'lucide-react';
 import { useRouter } from 'next/navigation';
 import { memo, useState } from 'react';
@@ -78,6 +79,33 @@ const CreateNewProvider = memo<CreateNewProviderProps>(({ onClose, open, initial
     },
   ];
 
+  const configItems: FormItemProps[] = [
+    {
+      children: (
+        <Select
+          optionRender={({ label, value }) => (
+            <Flexbox align={'center'} gap={8} horizontal>
+              <ProviderIcon provider={value as string} size={18} />
+              {label}
+            </Flexbox>
+          )}
+          options={[
+            { label: 'OpenAI', value: 'openai' },
+            { label: 'Anthropic', value: 'anthropic' },
+            { label: 'Ollama', value: 'ollama' },
+            // { label: 'Azure AI', value: 'azureai' },
+          ]}
+          placeholder={t('createNewAiProvider.sdkType.placeholder')}
+          variant={'filled'}
+        />
+      ),
+      label: t('createNewAiProvider.sdkType.title'),
+      minWidth: 400,
+      name: ['settings', 'sdkType'],
+      rules: [{ message: t('createNewAiProvider.sdkType.required'), required: true }],
+    },
+  ];
+
   return (
     <FormModal
       footer={
@@ -118,6 +146,10 @@ const CreateNewProvider = memo<CreateNewProviderProps>(({ onClose, open, initial
           children: basicItems,
           title: t('createNewAiProvider.basicTitle'),
         },
+        {
+          children: configItems,
+          title: t('createNewAiProvider.configTitle'),
+        },
       ]}
       onCancel={onClose}
       onFinish={onFinish}
@@ -127,7 +159,7 @@ const CreateNewProvider = memo<CreateNewProviderProps>(({ onClose, open, initial
       title={
         <Flexbox gap={8} horizontal>
           <Icon icon={BrainIcon} />
-          {t('createNewAiProvider.title')}
+          {t('updateCustomAiProvider.title')}
         </Flexbox>
       }
     />

package/src/app/[variants]/(main)/settings/provider/features/ProviderConfig/index.tsx

@@ -324,19 +324,21 @@ const ProviderConfig = memo<ProviderConfigProps>(
               {name}
             </Flexbox>
           ) : (
-            <ProviderCombine provider={id} size={24} />
+            <>
+              <ProviderCombine provider={id} size={24} />
+              <Tooltip title={t('providerModels.config.helpDoc')}>
+                <Link
+                  href={urlJoin(BASE_PROVIDER_DOC_URL, id)}
+                  onClick={(e) => e.stopPropagation()}
+                  target={'_blank'}
+                >
+                  <Center className={styles.help} height={20} width={20}>
+                    ?
+                  </Center>
+                </Link>
+              </Tooltip>
+            </>
           )}
-          <Tooltip title={t('providerModels.config.helpDoc')}>
-            <Link
-              href={urlJoin(BASE_PROVIDER_DOC_URL, id)}
-              onClick={(e) => e.stopPropagation()}
-              target={'_blank'}
-            >
-              <Center className={styles.help} height={20} width={20}>
-                ?
-              </Center>
-            </Link>
-          </Tooltip>
         </Flexbox>
       ),
     };

package/src/features/Conversation/Extras/Usage/UsageDetail/ModelCard.tsx

@@ -96,6 +96,12 @@ const ModelCard = memo<ModelCardProps>(({ pricing, id, provider, displayName })
           <div />
           <Flexbox align={'center'} className={styles.pricing} gap={8} horizontal>
             {t('messages.modelCard.creditPricing')}:
+            <Tooltip title={t('messages.modelCard.pricing.inputTokens', { amount: inputPrice })}>
+              <Flexbox gap={2} horizontal>
+                <Icon icon={ArrowUpFromDot} />
+                {inputPrice}
+              </Flexbox>
+            </Tooltip>
             {pricing?.cachedInput && (
               <Tooltip
                 title={t('messages.modelCard.pricing.inputCachedTokens', {
@@ -108,12 +114,6 @@ const ModelCard = memo<ModelCardProps>(({ pricing, id, provider, displayName })
                 </Flexbox>
               </Tooltip>
             )}
-            <Tooltip title={t('messages.modelCard.pricing.inputTokens', { amount: inputPrice })}>
-              <Flexbox gap={2} horizontal>
-                <Icon icon={ArrowUpFromDot} />
-                {inputPrice}
-              </Flexbox>
-            </Tooltip>
             <Tooltip title={t('messages.modelCard.pricing.outputTokens', { amount: outputPrice })}>
               <Flexbox gap={2} horizontal>
                 <Icon icon={ArrowDownToDot} />

package/src/features/Conversation/Extras/Usage/UsageDetail/index.tsx

@@ -67,12 +67,6 @@ const TokenDetail = memo<TokenDetailProps>(({ usage, model, provider }) => {
   ].filter(Boolean) as TokenProgressItem[];
 
   const totalDetail = [
-    !!detailTokens.cachedInput && {
-      color: theme.orange,
-      id: 'cachedInput',
-      title: t('messages.tokenDetails.inputCached'),
-      value: isShowCredit ? detailTokens.cachedInput.credit : detailTokens.cachedInput.token,
-    },
     !!detailTokens.uncachedInput && {
       color: theme.colorFill,
 
@@ -80,6 +74,12 @@ const TokenDetail = memo<TokenDetailProps>(({ usage, model, provider }) => {
       title: t('messages.tokenDetails.inputUncached'),
       value: isShowCredit ? detailTokens.uncachedInput.credit : detailTokens.uncachedInput.token,
     },
+    !!detailTokens.cachedInput && {
+      color: theme.orange,
+      id: 'cachedInput',
+      title: t('messages.tokenDetails.inputCached'),
+      value: isShowCredit ? detailTokens.cachedInput.credit : detailTokens.cachedInput.token,
+    },
     !!detailTokens.totalOutput && {
       color: theme.colorSuccess,
       id: 'output',