@lobehub/chat 1.113.2 → 1.113.3

package/CHANGELOG.md

@@ -2,6 +2,32 @@
 
 # Changelog
 
+### [Version 1.113.3](https://github.com/lobehub/lobe-chat/compare/v1.113.2...v1.113.3)
+
+<sup>Released on **2025-08-19**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Support Grok thinking models in AiHubMix, The 'stream_options' parameter is only allowed when 'stream' is enabled.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Support Grok thinking models in AiHubMix, closes [#8713](https://github.com/lobehub/lobe-chat/issues/8713) ([ffa9b1b](https://github.com/lobehub/lobe-chat/commit/ffa9b1b))
+- **misc**: The 'stream_options' parameter is only allowed when 'stream' is enabled, closes [#8778](https://github.com/lobehub/lobe-chat/issues/8778) ([fcc32d5](https://github.com/lobehub/lobe-chat/commit/fcc32d5))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
 ### [Version 1.113.2](https://github.com/lobehub/lobe-chat/compare/v1.113.1...v1.113.2)
 
 <sup>Released on **2025-08-18**</sup>

package/changelog/v1.json

@@ -1,4 +1,13 @@
 [
+  {
+    "children": {
+      "fixes": [
+        "Support Grok thinking models in AiHubMix, The 'stream_options' parameter is only allowed when 'stream' is enabled."
+      ]
+    },
+    "date": "2025-08-19",
+    "version": "1.113.3"
+  },
   {
     "children": {},
     "date": "2025-08-18",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/chat",
-  "version": "1.113.2",
+  "version": "1.113.3",
   "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/packages/const/src/models.ts

@@ -35,8 +35,6 @@ export const responsesAPIModels = new Set([
   'codex-mini-latest',
   'computer-use-preview',
   'computer-use-preview-2025-03-11',
-  'gpt-5',
-  'gpt-5-mini',
 ]);
 
 /**

package/packages/model-runtime/src/RouterRuntime/baseRuntimeMap.ts

@@ -4,6 +4,7 @@ import { LobeCloudflareAI } from '../cloudflare';
 import { LobeFalAI } from '../fal';
 import { LobeGoogleAI } from '../google';
 import { LobeOpenAI } from '../openai';
+import { LobeXAI } from '../xai';
 
 export const baseRuntimeMap = {
   anthropic: LobeAnthropicAI,
@@ -12,4 +13,5 @@ export const baseRuntimeMap = {
   fal: LobeFalAI,
   google: LobeGoogleAI,
   openai: LobeOpenAI,
+  xai: LobeXAI,
 };

package/packages/model-runtime/src/aihubmix/index.ts

@@ -65,6 +65,13 @@ export const LobeAiHubMixAI = createRouterRuntime({
       ),
       options: { baseURL: urlJoin(baseURL, '/gemini') },
     },
+    {
+      apiType: 'xai',
+      models: LOBE_DEFAULT_MODEL_LIST.map((m) => m.id).filter(
+        (id) => detectModelProvider(id) === 'xai',
+      ),
+      options: { baseURL: urlJoin(baseURL, '/v1') },
+    },
     {
       apiType: 'openai',
       options: {

package/packages/model-runtime/src/openai/index.ts

@@ -11,6 +11,16 @@ export interface OpenAIModelCard {
 
 const prunePrefixes = ['o1', 'o3', 'o4', 'codex', 'computer-use', 'gpt-5'];
 const oaiSearchContextSize = process.env.OPENAI_SEARCH_CONTEXT_SIZE; // low, medium, high
+const enableServiceTierFlex = process.env.OPENAI_SERVICE_TIER_FLEX === '1';
+const flexSupportedModels = ['gpt-5', 'o3', 'o4-mini']; // Flex 处理仅适用于这些模型
+
+const supportsFlexTier = (model: string) => {
+  // 排除 o3-mini，其不支持 Flex 处理
+  if (model.startsWith('o3-mini')) {
+    return false;
+  }
+  return flexSupportedModels.some(supportedModel => model.startsWith(supportedModel));
+};
 
 export const LobeOpenAI = createOpenAICompatibleRuntime({
   baseURL: 'https://api.openai.com/v1',
@@ -32,6 +42,7 @@ export const LobeOpenAI = createOpenAICompatibleRuntime({
           frequency_penalty: undefined,
           model,
           presence_penalty: undefined,
+          ...(enableServiceTierFlex && supportsFlexTier(model) && { service_tier: 'flex' }),
           stream: payload.stream ?? true,
           temperature: undefined,
           top_p: undefined,
@@ -43,7 +54,7 @@ export const LobeOpenAI = createOpenAICompatibleRuntime({
         } as any;
       }
 
-      return { ...rest, model, stream: payload.stream ?? true };
+      return { ...rest, model, ...(enableServiceTierFlex && supportsFlexTier(model) && { service_tier: 'flex' }), stream: payload.stream ?? true };
     },
   },
   debug: {
@@ -81,6 +92,7 @@ export const LobeOpenAI = createOpenAICompatibleRuntime({
           reasoning: payload.reasoning
             ? { ...payload.reasoning, summary: 'auto' }
             : { summary: 'auto' },
+          ...(enableServiceTierFlex && supportsFlexTier(model) && { service_tier: 'flex' }),
           stream: payload.stream ?? true,
           tools: openaiTools as any,
           // computer-use series must set truncation as auto
@@ -91,7 +103,7 @@ export const LobeOpenAI = createOpenAICompatibleRuntime({
         }) as any;
       }
 
-      return { ...rest, model, stream: payload.stream ?? true, tools: openaiTools } as any;
+      return { ...rest, model, ...(enableServiceTierFlex && supportsFlexTier(model) && { service_tier: 'flex' }), stream: payload.stream ?? true, tools: openaiTools } as any;
     },
   },
 });

package/packages/model-runtime/src/utils/openaiHelpers.ts

@@ -101,8 +101,11 @@ export const convertOpenAIResponseInputs = async (
 };
 
 export const pruneReasoningPayload = (payload: ChatStreamPayload) => {
+  const shouldStream = !disableStreamModels.has(payload.model);
+  const { stream_options, ...cleanedPayload } = payload as any;
+  
   return {
-    ...payload,
+    ...cleanedPayload,
     frequency_penalty: 0,
     messages: payload.messages.map((message: OpenAIChatMessage) => ({
       ...message,
@@ -114,7 +117,9 @@ export const pruneReasoningPayload = (payload: ChatStreamPayload) => {
           : message.role,
     })),
     presence_penalty: 0,
-    stream: !disableStreamModels.has(payload.model),
+    stream: shouldStream,
+    // Only include stream_options when stream is enabled
+    ...(shouldStream && stream_options && { stream_options }),
     temperature: 1,
     top_p: 1,
   };

package/src/config/aiModels/groq.ts

@@ -33,7 +33,7 @@ const groqChatModels: AIChatModelCard[] = [
       'OpenAI GPT-OSS 120B 是一款拥有 1200 亿参数的顶尖语言模型，内置浏览器搜索和代码执行功能，并具备推理能力。',
     displayName: 'GPT OSS 120B',
     id: 'openai/gpt-oss-120b',
-    maxOutput: 32_768,
+    maxOutput: 65_536,
     pricing: {
       units: [
         { name: 'textInput', rate: 0.15, strategy: 'fixed', unit: 'millionTokens' },
@@ -53,7 +53,7 @@ const groqChatModels: AIChatModelCard[] = [
       'OpenAI GPT-OSS 20B 是一款拥有 200 亿参数的顶尖语言模型，内置浏览器搜索和代码执行功能，并具备推理能力。',
     displayName: 'GPT OSS 20B',
     id: 'openai/gpt-oss-20b',
-    maxOutput: 32_768,
+    maxOutput: 65_536,
     pricing: {
       units: [
         { name: 'textInput', rate: 0.1, strategy: 'fixed', unit: 'millionTokens' },

package/src/config/aiModels/qwen.ts

@@ -519,21 +519,61 @@ const qwenChatModels: AIChatModelCard[] = [
       search: true,
     },
     config: {
-      deploymentName: 'qwen-plus-2025-07-14',
+      deploymentName: 'qwen-plus-2025-07-28',
     },
-    contextWindowTokens: 131_072,
+    contextWindowTokens: 1_000_000,
     description: '通义千问超大规模语言模型增强版，支持中文、英文等不同语言输入。',
     displayName: 'Qwen Plus',
     enabled: true,
     id: 'qwen-plus',
-    maxOutput: 16_384,
+    maxOutput: 32_768,
     organization: 'Qwen',
     pricing: {
       currency: 'CNY',
       units: [
-        { name: 'textInput_cacheRead', rate: 0.32, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textInput', rate: 0.8, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 8, strategy: 'fixed', unit: 'millionTokens' },
+        {
+          lookup: {
+            prices: {
+              '[0, 128_000]': 0.8 * 0.4,
+              '[128_000, 256_000]': 2.4 * 0.4,
+              '[256_000, infinity]': 4.8 * 0.4,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textInput_cacheRead',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 128_000]': 0.8,
+              '[128_000, 256_000]': 2.4,
+              '[256_000, infinity]': 4.8,
+            },
+            pricingParams: ['textInputRange'],
+          },
+          name: 'textInput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
+        {
+          lookup: {
+            prices: {
+              '[0, 128_000]_[false]': 2,
+              '[0, 128_000]_[true]': 8,
+              '[128_000, 256_000]_[false]': 20,
+
+              '[128_000, 256_000]_[true]': 24,
+              '[256_000, infinity]_[false]': 48,
+              '[256_000, infinity]_[true]': 64,
+            },
+            pricingParams: ['textInputRange', 'thinkingMode'],
+          },
+          name: 'textOutput',
+          strategy: 'lookup',
+          unit: 'millionTokens',
+        },
       ],
     },
     releasedAt: '2025-07-14',
@@ -643,7 +683,7 @@ const qwenChatModels: AIChatModelCard[] = [
       vision: true,
     },
     config: {
-      deploymentName: 'qwen-vl-plus-2025-01-25',
+      deploymentName: 'qwen-vl-plus-2025-08-15',
     },
     contextWindowTokens: 131_072,
     description:
@@ -655,9 +695,9 @@ const qwenChatModels: AIChatModelCard[] = [
     pricing: {
       currency: 'CNY',
       units: [
-        { name: 'textInput_cacheRead', rate: 0.6, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textInput', rate: 1.5, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 4.5, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textInput_cacheRead', rate: 0.8 * 0.4, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textInput', rate: 0.8, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 2, strategy: 'fixed', unit: 'millionTokens' },
       ],
     },
     type: 'chat',
@@ -667,7 +707,7 @@ const qwenChatModels: AIChatModelCard[] = [
       vision: true,
     },
     config: {
-      deploymentName: 'qwen-vl-max-2025-04-08',
+      deploymentName: 'qwen-vl-max-2025-08-13',
     },
     contextWindowTokens: 131_072,
     description:
@@ -679,9 +719,9 @@ const qwenChatModels: AIChatModelCard[] = [
     pricing: {
       currency: 'CNY',
       units: [
-        { name: 'textInput_cacheRead', rate: 1.2, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textInput', rate: 3, strategy: 'fixed', unit: 'millionTokens' },
-        { name: 'textOutput', rate: 9, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textInput_cacheRead', rate: 1.6 * 0.4, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textInput', rate: 1.6, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 4, strategy: 'fixed', unit: 'millionTokens' },
       ],
     },
     type: 'chat',
@@ -1304,6 +1344,30 @@ const qwenChatModels: AIChatModelCard[] = [
 ];
 
 const qwenImageModels: AIImageModelCard[] = [
+  {
+    description:
+      'Qwen-Image 是一款通用图像生成模型，支持多种艺术风格，尤其擅长复杂文本渲染，特别是中英文文本渲染。模型支持多行布局、段落级文本生成以及细粒度细节刻画，可实现复杂的图文混合布局设计。',
+    displayName: 'Qwen Image',
+    enabled: true,
+    id: 'qwen-image',
+    organization: 'Qwen',
+    parameters: {
+      prompt: {
+        default: '',
+      },
+      seed: { default: null },
+      size: {
+        default: '1328*1328',
+        enum: ['1664*928', '1472*1140', '1328*1328', '1140*1472', '928*1664'],
+      },
+    },
+    pricing: {
+      currency: 'CNY',
+      units: [{ name: 'imageGeneration', rate: 0.25, strategy: 'fixed', unit: 'image' }],
+    },
+    releasedAt: '2025-08-13',
+    type: 'image',
+  },
   {
     description:
       '万相2.2极速版，当前最新模型。在创意性、稳定性、写实质感上全面升级，生成速度快，性价比高。',

package/src/config/aiModels/siliconcloud.ts

@@ -61,6 +61,27 @@ const siliconcloudChatModels: AIChatModelCard[] = [
     releasedAt: '2025-07-31',
     type: 'chat',
   },
+  {
+    abilities: {
+      functionCall: true,
+      reasoning: true,
+      vision: true,
+    },
+    contextWindowTokens: 65_536,
+    description:
+      'GLM-4.5V 是由智谱 AI（Zhipu AI）发布的最新一代视觉语言模型（VLM）该模型基于拥有 106B 总参数和 12B 激活参数的旗舰文本模型 GLM-4.5-Air 构建，采用了混合专家（MoE）架构，旨在以更低的推理成本实现卓越性能 GLM-4.5V 在技术上延续了 GLM-4.1V-Thinking 的路线，并引入了三维旋转位置编码（3D-RoPE）等创新，显著增强了对三维空间关系的感知与推理能力。通过在预训练、监督微调和强化学习阶段的优化，该模型具备了处理图像、视频、长文档等多种视觉内容的能力，在 41 个公开的多模态基准测试中达到了同级别开源模型的顶尖水平此外，模型还新增了“思考模式”开关，允许用户在快速响应和深度推理之间灵活选择，以平衡效率与效果。',
+    displayName: 'GLM-4.5V',
+    id: 'zai-org/GLM-4.5V',
+    pricing: {
+      currency: 'CNY',
+      units: [
+        { name: 'textInput', rate: 1, strategy: 'fixed', unit: 'millionTokens' },
+        { name: 'textOutput', rate: 6, strategy: 'fixed', unit: 'millionTokens' },
+      ],
+    },
+    releasedAt: '2025-08-11',
+    type: 'chat',
+  },
   {
     abilities: {
       functionCall: true,

package/src/services/discover.ts

@@ -143,6 +143,10 @@ class DiscoverService {
     errorCode,
     ...params
   }: InstallReportRequest) => {
+    // if user don't allow tracing, just not report installation
+    const allow = preferenceSelectors.userAllowTrace(useUserStore.getState());
+
+    if (!allow) return;
     await this.injectMPToken();
 
     const reportData = {
@@ -164,7 +168,8 @@ class DiscoverService {
    * 上报插件调用结果
    */
   reportPluginCall = async (reportData: CallReportRequest) => {
-    const allow = useUserStore(preferenceSelectors.userAllowTrace);
+    // if user don't allow tracing , just not report calling
+    const allow = preferenceSelectors.userAllowTrace(useUserStore.getState());
 
     if (!allow) return;