@lobehub/chat 1.94.15 → 1.94.16

package/CHANGELOG.md

@@ -2,6 +2,31 @@
 
 # Changelog
 
+### [Version 1.94.16](https://github.com/lobehub/lobe-chat/compare/v1.94.15...v1.94.16)
+
+<sup>Released on **2025-06-19**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Correctly pass `reasoning.summary`.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Correctly pass `reasoning.summary`, closes [#8221](https://github.com/lobehub/lobe-chat/issues/8221) ([da79815](https://github.com/lobehub/lobe-chat/commit/da79815))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
 ### [Version 1.94.15](https://github.com/lobehub/lobe-chat/compare/v1.94.14...v1.94.15)
 
 <sup>Released on **2025-06-19**</sup>

package/README.md

@@ -367,14 +367,14 @@ Our marketplace is not just a showcase platform but also a collaborative space.
 
 <!-- AGENT LIST -->
 
-| Recent Submits                                                                                                                                                                          | Description                                                                                                                                                                                |
-| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| [Academic Paper Reading Mentor](https://lobechat.com/discover/assistant/paper-understanding)<br/><sup>By **[AdijeShen](https://github.com/AdijeShen)** on **2025-05-09**</sup>          | Expert in explaining complex academic papers in simple and understandable language<br/>`academic-knowledge` `paper-analysis`                                                               |
-| [Nutritional Advisor](https://lobechat.com/discover/assistant/nutritionist)<br/><sup>By **[egornomic](https://github.com/egornomic)** on **2025-04-15**</sup>                           | Specializes in providing detailed nutritional information for food items.<br/>`nutrition` `food` `health` `information`                                                                    |
-| [Rewritten in Translation Style](https://lobechat.com/discover/assistant/rewrite-in-a-translation-tone)<br/><sup>By **[q2019715](https://github.com/q2019715)** on **2025-03-13**</sup> | Rewrites a paragraph in a translation style<br/>`translation-style` `creative-writing` `language-style` `text-rewriting` `culture`                                                         |
-| [Academic Paper Review Expert](https://lobechat.com/discover/assistant/academic-paper-overview)<br/><sup>By **[arvinxx](https://github.com/arvinxx)** on **2025-03-11**</sup>           | An academic research assistant skilled in high-quality literature retrieval and analysis<br/>`academic-research` `literature-search` `data-analysis` `information-extraction` `consulting` |
-
-> 📊 Total agents: [<kbd>**499**</kbd> ](https://lobechat.com/discover/assistants)
+| Recent Submits                                                                                                                                                                 | Description                                                                                                                                                                                                              |
+| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| [Turtle Soup Host](https://lobechat.com/discover/assistant/lateral-thinking-puzzle)<br/><sup>By **[CSY2022](https://github.com/CSY2022)** on **2025-06-19**</sup>              | A turtle soup host needs to provide the scenario, the complete story (truth of the event), and the key point (the condition for guessing correctly).<br/>`turtle-soup` `reasoning` `interaction` `puzzle` `role-playing` |
+| [Gourmet Reviewer🍟](https://lobechat.com/discover/assistant/food-reviewer)<br/><sup>By **[renhai-lab](https://github.com/renhai-lab)** on **2025-06-17**</sup>                | Food critique expert<br/>`gourmet` `review` `writing`                                                                                                                                                                    |
+| [Academic Writing Assistant](https://lobechat.com/discover/assistant/academic-writing-assistant)<br/><sup>By **[swarfte](https://github.com/swarfte)** on **2025-06-17**</sup> | Expert in academic research paper writing and formal documentation<br/>`academic-writing` `research` `formal-style`                                                                                                      |
+| [Minecraft Senior Developer](https://lobechat.com/discover/assistant/java-development)<br/><sup>By **[iamyuuk](https://github.com/iamyuuk)** on **2025-06-17**</sup>           | Expert in advanced Java development and Minecraft mod and server plugin development<br/>`development` `programming` `minecraft` `java`                                                                                   |
+
+> 📊 Total agents: [<kbd>**505**</kbd> ](https://lobechat.com/discover/assistants)
 
  <!-- AGENT LIST -->
 

package/changelog/v1.json

@@ -1,4 +1,13 @@
 [
+  {
+    "children": {
+      "fixes": [
+        "Correctly pass reasoning.summary."
+      ]
+    },
+    "date": "2025-06-19",
+    "version": "1.94.16"
+  },
   {
     "children": {
       "improvements": [

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/chat",
-  "version": "1.94.15",
+  "version": "1.94.16",
   "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/[variants]/layout.tsx

@@ -78,6 +78,13 @@ export const generateViewport = async (props: DynamicLayoutProps): ResolvingView
 };
 
 export const generateStaticParams = () => {
+  // if in dev mode or in vercel preview mode, use ISR to speed up
+  const isVercelPreview = process.env.VERCEL === '1' && process.env.VERCEL_ENV !== 'production';
+
+  if (process.env.NODE_ENV !== 'production' || isVercelPreview) {
+    return [];
+  }
+
   const themes: ThemeAppearance[] = ['dark', 'light'];
   const mobileOptions = isDesktop ? [false] : [true, false];
   // only static for serveral page, other go to dynamtic

package/src/config/aiModels/google.ts

@@ -113,6 +113,7 @@ const googleChatModels: AIChatModelCard[] = [
     id: 'gemini-2.5-flash',
     maxOutput: 65_536,
     pricing: {
+      cachedInput: 0.075,
       input: 0.3,
       output: 2.5,
     },
@@ -134,7 +135,6 @@ const googleChatModels: AIChatModelCard[] = [
     contextWindowTokens: 1_048_576 + 65_536,
     description: 'Gemini 2.5 Flash Preview 是 Google 性价比最高的模型，提供全面的功能。',
     displayName: 'Gemini 2.5 Flash Preview 05-20',
-    enabled: true,
     id: 'gemini-2.5-flash-preview-05-20',
     maxOutput: 65_536,
     pricing: {
@@ -202,18 +202,18 @@ const googleChatModels: AIChatModelCard[] = [
       search: true,
       vision: true,
     },
-    contextWindowTokens: 1_000_000 + 64_000,
+    contextWindowTokens: 65_536 + 65_536,
     description:
       'Gemini 2.5 Flash-Lite Preview 是 Google 最小、性价比最高的模型，专为大规模使用而设计。',
     displayName: 'Gemini 2.5 Flash-Lite Preview 06-17',
-    enabled: true,
     id: 'gemini-2.5-flash-lite-preview-06-17',
-    maxOutput: 64_000,
+    maxOutput: 65_536,
     pricing: {
+      cachedInput: 0.025,
       input: 0.1,
       output: 0.4,
     },
-    releasedAt: '2025-06-17',
+    releasedAt: '2025-06-11',
     settings: {
       extendParams: ['enableReasoning', 'reasoningBudgetToken'],
       searchImpl: 'params',

package/src/config/aiModels/groq.ts

@@ -56,6 +56,7 @@ const groqChatModels: AIChatModelCard[] = [
     displayName: 'Qwen QwQ 32B',
     enabled: true,
     id: 'qwen-qwq-32b',
+    maxOutput: 131_072,
     pricing: {
       input: 0.29,
       output: 0.39,
@@ -69,7 +70,7 @@ const groqChatModels: AIChatModelCard[] = [
     contextWindowTokens: 131_072,
     displayName: 'Qwen3 32B',
     id: 'qwen/qwen3-32b',
-    maxOutput: 16_384,
+    maxOutput: 40_960,
     pricing: {
       input: 0.29,
       output: 0.59,
@@ -84,6 +85,7 @@ const groqChatModels: AIChatModelCard[] = [
     contextWindowTokens: 131_072,
     displayName: 'DeepSeek R1 Distill Llama 70B',
     id: 'deepseek-r1-distill-llama-70b',
+    maxOutput: 131_072,
     pricing: {
       input: 0.75, // 0.75 - 5.00
       output: 0.99, // 0.99 - 5.00
@@ -98,6 +100,7 @@ const groqChatModels: AIChatModelCard[] = [
     description: 'Gemma 2 9B 是一款优化用于特定任务和工具整合的模型。',
     displayName: 'Gemma 2 9B',
     id: 'gemma2-9b-it',
+    maxOutput: 8192,
     pricing: {
       input: 0.2,
       output: 0.2,
@@ -113,7 +116,7 @@ const groqChatModels: AIChatModelCard[] = [
       'Llama 3.1 8B 是一款高效能模型，提供了快速的文本生成能力，非常适合需要大规模效率和成本效益的应用场景。',
     displayName: 'Llama 3.1 8B Instant',
     id: 'llama-3.1-8b-instant',
-    maxOutput: 8192,
+    maxOutput: 131_072,
     pricing: {
       input: 0.05,
       output: 0.08,
@@ -136,32 +139,11 @@ const groqChatModels: AIChatModelCard[] = [
     },
     type: 'chat',
   },
-  {
-    contextWindowTokens: 8192,
-    description: 'Meta Llama 3 70B 提供无与伦比的复杂性处理能力，为高要求项目量身定制。',
-    displayName: 'Llama 3 70B',
-    id: 'llama3-70b-8192',
-    pricing: {
-      input: 0.59,
-      output: 0.79,
-    },
-    type: 'chat',
-  },
-  {
-    contextWindowTokens: 8192,
-    description: 'Meta Llama 3 8B 带来优质的推理效能，适合多场景应用需求。',
-    displayName: 'Llama 3 8B',
-    id: 'llama3-8b-8192',
-    pricing: {
-      input: 0.05,
-      output: 0.08,
-    },
-    type: 'chat',
-  },
   {
     contextWindowTokens: 32_768,
     displayName: 'Mistral Saba 24B',
     id: 'mistral-saba-24b',
+    maxOutput: 32_768,
     pricing: {
       input: 0.79,
       output: 0.79,
@@ -172,39 +154,25 @@ const groqChatModels: AIChatModelCard[] = [
     contextWindowTokens: 131_072,
     displayName: 'Llama Guard 4 12B',
     id: 'meta-llama/llama-guard-4-12b',
-    maxOutput: 128,
+    maxOutput: 1024,
     pricing: {
       input: 0.2,
       output: 0.2,
     },
     type: 'chat',
   },
-  {
-    contextWindowTokens: 8192,
-    displayName: 'Llama Guard 3 8B',
-    id: 'llama-guard-3-8b',
-    pricing: {
-      input: 0.2,
-      output: 0.2,
-    },
-    type: 'chat',
-  },
-  {
-    contextWindowTokens: 4096,
-    displayName: 'ALLaM 2 7B',
-    id: 'allam-2-7b',
-    type: 'chat',
-  },
   {
     contextWindowTokens: 512,
     displayName: 'Llama Prompt Guard 2 22M',
     id: 'meta-llama/llama-prompt-guard-2-22m',
+    maxOutput: 512,
     type: 'chat',
   },
   {
     contextWindowTokens: 512,
     displayName: 'Llama Prompt Guard 2 86M',
     id: 'meta-llama/llama-prompt-guard-2-86m',
+    maxOutput: 512,
     type: 'chat',
   },
 ];

package/src/config/aiModels/xai.ts

@@ -14,6 +14,7 @@ const xaiChatModels: AIChatModelCard[] = [
     enabled: true,
     id: 'grok-3',
     pricing: {
+      cachedInput: 0.75,
       input: 3,
       output: 15,
     },
@@ -34,6 +35,7 @@ const xaiChatModels: AIChatModelCard[] = [
     displayName: 'Grok 3 (Fast mode)',
     id: 'grok-3-fast',
     pricing: {
+      cachedInput: 1.25,
       input: 5,
       output: 25,
     },
@@ -56,6 +58,7 @@ const xaiChatModels: AIChatModelCard[] = [
     enabled: true,
     id: 'grok-3-mini',
     pricing: {
+      cachedInput: 0.075,
       input: 0.3,
       output: 0.5,
     },
@@ -78,6 +81,7 @@ const xaiChatModels: AIChatModelCard[] = [
     displayName: 'Grok 3 Mini (Fast mode)',
     id: 'grok-3-mini-fast',
     pricing: {
+      cachedInput: 0.15,
       input: 0.6,
       output: 4,
     },

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

@@ -1,8 +1,9 @@
+import { responsesAPIModels } from '@/const/models';
+
 import { ChatStreamPayload, ModelProvider } from '../types';
 import { processMultiProviderModelList } from '../utils/modelParse';
 import { createOpenAICompatibleRuntime } from '../utils/openaiCompatibleFactory';
 import { pruneReasoningPayload } from '../utils/openaiHelpers';
-import { responsesAPIModels } from '@/const/models';
 
 export interface OpenAIModelCard {
   id: string;

package/src/libs/model-runtime/utils/openaiCompatibleFactory/index.ts

@@ -208,10 +208,7 @@ export const createOpenAICompatibleRuntime = <T extends Record<string, any> = an
       this.id = options.id || provider;
     }
 
-    async chat(
-      { responseMode, ...payload }: ChatStreamPayload,
-      options?: ChatMethodOptions,
-    ) {
+    async chat({ responseMode, ...payload }: ChatStreamPayload, options?: ChatMethodOptions) {
       try {
         const inputStartAt = Date.now();
         const postPayload = chatCompletion?.handlePayload
@@ -478,7 +475,7 @@ export const createOpenAICompatibleRuntime = <T extends Record<string, any> = an
     ): Promise<Response> {
       const inputStartAt = Date.now();
 
-      const { messages, reasoning_effort, tools, ...res } = responses?.handlePayload
+      const { messages, reasoning_effort, tools, reasoning, ...res } = responses?.handlePayload
         ? (responses?.handlePayload(payload, this._options) as ChatStreamPayload)
         : payload;
 
@@ -491,7 +488,14 @@ export const createOpenAICompatibleRuntime = <T extends Record<string, any> = an
 
       const postPayload = {
         ...res,
-        ...(reasoning_effort ? { reasoning: { effort: reasoning_effort } } : {}),
+        ...(reasoning || reasoning_effort
+          ? {
+              reasoning: {
+                ...reasoning,
+                ...(reasoning_effort && { effort: reasoning_effort }),
+              },
+            }
+          : {}),
         input,
         store: false,
         tools: tools?.map((tool) => this.convertChatCompletionToolToResponseTool(tool)),