Skip to content

Commit d0ee3df

Browse files
sxjeruAloxaf
sxjeru
and
Aloxaf
authored
✨ feat: New API support switch Responses API mode (#9776)
* ✨ feat: 添加对新API和路由类型的支持，更新相关配置以启用Responses API * fix: 更新测试文件中的console.error和console.debug实现，确保输出格式一致；在CreateNewProvider组件中调整provider图标映射逻辑 * ✨ feat: 更新novita和qwen模型，调整定价策略，添加新模型及其功能 * 🐛 fix: OIDC error when connecting to self-host instance (#9916) fix: oidc/consent redirect header * ✨ feat: 添加 MiniMax M2 和 Qwen3 VL 235B Instruct 模型，更新模型属性 🔧 fix: 修复免费标识逻辑，确保正确判断模型是否免费 * ✨ feat: 添加 MiniMax-M2 模型，更新 SiliconCloud 和 Vercel AI Gateway 模型信息，调整 Kimi K2 的上下文窗口大小 * fix test * 📝 docs: update ComfyUI documentation cover image URL (#9997) * 🔖 chore(release): v1.142.9 [skip ci] ### [Version&nbsp;1.142.9](v1.142.8...v1.142.9) <sup>Released on **2025-11-02**</sup> #### 🐛 Bug Fixes - **misc**: OIDC error when connecting to self-host instance. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * **misc**: OIDC error when connecting to self-host instance, closes [#9916](#9916) ([2e2b9c4](2e2b9c4)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div> * 📝 docs(bot): Auto sync agents & plugin to readme * 优化 Responses API 处理逻辑，优化错误处理和流数据转换 --------- Co-authored-by: Aloxaf <bailong104@gmail.com>
1 parent 3ad336f commit d0ee3df

File tree

20 files changed

+440
-312
lines changed

20 files changed

+440
-312
lines changed

‎docs/usage/providers/comfyui.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@ tags:
1111

1212
# Using ComfyUI in LobeChat
1313

14-
<Image alt={'Using ComfyUI in LobeChat'} cover src={'https://github.com/lobehub/lobe-chat/assets/17870709/c9e5eafc-ca22-496b-a88d-cc0ae53bf720'} />
14+
<Image alt={'Using ComfyUI in LobeChat'} cover src={'https://hub-apac-1.lobeobjects.space/docs/e9b811f248a1db2bd1be1af888cf9b9d.png'} />
1515

1616
This documentation will guide you on how to use [ComfyUI](https://github.com/comfyanonymous/ComfyUI) in LobeChat for high-quality AI image generation and editing.
1717

‎docs/usage/providers/comfyui.zh-CN.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@ tags:
1111

1212
# 在 LobeChat 中使用 ComfyUI
1313

14-
<Image alt={'在 LobeChat 中使用 ComfyUI'} cover src={'https://github.com/lobehub/lobe-chat/assets/17870709/c9e5eafc-ca22-496b-a88d-cc0ae53bf720'} />
14+
<Image alt={'在 LobeChat 中使用 ComfyUI'} cover src={'https://hub-apac-1.lobeobjects.space/docs/e9b811f248a1db2bd1be1af888cf9b9d.png'} />
1515

1616
本文档将指导你如何在 LobeChat 中使用 [ComfyUI](https://github.com/comfyanonymous/ComfyUI) 进行高质量的 AI 图像生成和编辑。
1717

‎packages/model-bank/src/aiModels/novita.ts‎

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -174,10 +174,11 @@ const novitaChatModels: AIChatModelCard[] = [
174174
contextWindowTokens: 131_072,
175175
displayName: 'OpenAI GPT OSS 120B',
176176
id: 'openai/gpt-oss-120b',
177+
maxOutput: 32_768,
177178
pricing: {
178179
units: [
179-
{ name: 'textInput', rate: 0.1, strategy: 'fixed', unit: 'millionTokens' },
180-
{ name: 'textOutput', rate: 0.5, strategy: 'fixed', unit: 'millionTokens' },
180+
{ name: 'textInput', rate: 0.05, strategy: 'fixed', unit: 'millionTokens' },
181+
{ name: 'textOutput', rate: 0.25, strategy: 'fixed', unit: 'millionTokens' },
181182
],
182183
},
183184
type: 'chat',

‎packages/model-bank/src/aiModels/nvidia.ts‎

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,20 @@
11
import { AIChatModelCard } from '../types/aiModel';
22

33
const nvidiaChatModels: AIChatModelCard[] = [
4+
{
5+
abilities: {
6+
functionCall: true,
7+
reasoning: true,
8+
},
9+
contextWindowTokens: 128_000,
10+
description:
11+
'MiniMax-M2 是一款紧凑、快速且经济高效的混合专家（MoE）模型，拥有 2300 亿总参数和 100 亿激活参数，专为编码和智能体任务的顶级性能而打造，同时保持强大的通用智能。该模型在多文件编辑、编码-运行-修复闭环、测试校验修复以及复杂的长链接工具链方面表现优异，是开发者工作流的理想选择。',
12+
displayName: 'MiniMax-M2',
13+
enabled: true,
14+
id: 'minimaxai/minimax-m2',
15+
maxOutput: 16_384,
16+
type: 'chat',
17+
},
418
{
519
abilities: {
620
functionCall: true,

‎packages/model-bank/src/aiModels/ollamacloud.ts‎

Lines changed: 23 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,18 @@
11
import { AIChatModelCard } from '../types/aiModel';
22

33
const ollamaCloudModels: AIChatModelCard[] = [
4+
{
5+
abilities: {
6+
functionCall: true,
7+
reasoning: true,
8+
},
9+
contextWindowTokens: 200_000,
10+
description: 'MiniMax M2 是专为编码和代理工作流程构建的高效大型语言模型。',
11+
displayName: 'MiniMax M2',
12+
enabled: true,
13+
id: 'minimax-m2',
14+
type: 'chat',
15+
},
416
{
517
abilities: {
618
functionCall: true,
@@ -36,7 +48,6 @@ const ollamaCloudModels: AIChatModelCard[] = [
3648
description:
3749
'DeepSeek V3.1：下一代推理模型，提升了复杂推理与链路思考能力，适合需要深入分析的任务。',
3850
displayName: 'DeepSeek V3.1',
39-
enabled: true,
4051
id: 'deepseek-v3.1:671b',
4152
type: 'chat',
4253
},
@@ -88,13 +99,23 @@ const ollamaCloudModels: AIChatModelCard[] = [
8899
id: 'qwen3-coder:480b',
89100
type: 'chat',
90101
},
102+
{
103+
abilities: {
104+
functionCall: true,
105+
vision: true,
106+
},
107+
contextWindowTokens: 262_144,
108+
displayName: 'Qwen3 VL 235B Instruct',
109+
id: 'qwen3-vl:235b-instruct',
110+
type: 'chat',
111+
},
91112
{
92113
abilities: {
93114
functionCall: true,
94115
reasoning: true,
95116
vision: true,
96117
},
97-
contextWindowTokens: 128_000,
118+
contextWindowTokens: 262_144,
98119
displayName: 'Qwen3 VL 235B',
99120
id: 'qwen3-vl:235b',
100121
type: 'chat',

‎packages/model-bank/src/aiModels/qwen.ts‎

Lines changed: 88 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -175,6 +175,51 @@ const qwenChatModels: AIChatModelCard[] = [
175175
},
176176
{
177177
abilities: {
178+
functionCall: true,
179+
reasoning: true,
180+
},
181+
contextWindowTokens: 202_752,
182+
description: 'GLM系列模型是智谱AI专为智能体设计的混合推理模型，提供思考与非思考两种模式。',
183+
displayName: 'GLM-4.6',
184+
id: 'glm-4.6',
185+
maxOutput: 16_384,
186+
pricing: {
187+
currency: 'CNY',
188+
units: [
189+
{
190+
lookup: {
191+
prices: {
192+
'[0, 0.032]': 3,
193+
'[0.032, infinity]': 4,
194+
},
195+
pricingParams: ['textInputRange'],
196+
},
197+
name: 'textInput',
198+
strategy: 'lookup',
199+
unit: 'millionTokens',
200+
},
201+
{
202+
lookup: {
203+
prices: {
204+
'[0, 0.032]': 14,
205+
'[0.032, infinity]': 16,
206+
},
207+
pricingParams: ['textInputRange'],
208+
},
209+
name: 'textOutput',
210+
strategy: 'lookup',
211+
unit: 'millionTokens',
212+
},
213+
],
214+
},
215+
settings: {
216+
extendParams: ['enableReasoning', 'reasoningBudgetToken'],
217+
},
218+
type: 'chat',
219+
},
220+
{
221+
abilities: {
222+
functionCall: true,
178223
reasoning: true,
179224
},
180225
contextWindowTokens: 131_072,
@@ -218,6 +263,7 @@ const qwenChatModels: AIChatModelCard[] = [
218263
},
219264
{
220265
abilities: {
266+
functionCall: true,
221267
reasoning: true,
222268
},
223269
contextWindowTokens: 131_072,
@@ -1451,6 +1497,48 @@ const qwenChatModels: AIChatModelCard[] = [
14511497
},
14521498
type: 'chat',
14531499
},
1500+
{
1501+
abilities: {
1502+
vision: true,
1503+
reasoning: true,
1504+
},
1505+
contextWindowTokens: 131_072,
1506+
description: 'Qwen3 VL 32B 思考模式（开源版），针对高难度强推理与长视频理解场景，提供顶尖的视觉+文本推理能力。',
1507+
displayName: 'Qwen3 VL 32B Thinking',
1508+
id: 'qwen3-vl-32b-thinking',
1509+
maxOutput: 32_768,
1510+
organization: 'Qwen',
1511+
pricing: {
1512+
currency: 'CNY',
1513+
units: [
1514+
{ name: 'textInput', rate: 2, strategy: 'fixed', unit: 'millionTokens' },
1515+
{ name: 'textOutput', rate: 20, strategy: 'fixed', unit: 'millionTokens' },
1516+
],
1517+
},
1518+
settings: {
1519+
extendParams: ['enableReasoning', 'reasoningBudgetToken'],
1520+
},
1521+
type: 'chat',
1522+
},
1523+
{
1524+
abilities: {
1525+
vision: true,
1526+
},
1527+
contextWindowTokens: 131_072,
1528+
description: 'Qwen3 VL 32B 非思考模式（Instruct），适用于非思考指令场景，保持强大的视觉理解能力。',
1529+
displayName: 'Qwen3 VL 32B Instruct',
1530+
id: 'qwen3-vl-32b-instruct',
1531+
maxOutput: 32_768,
1532+
organization: 'Qwen',
1533+
pricing: {
1534+
currency: 'CNY',
1535+
units: [
1536+
{ name: 'textInput', rate: 2, strategy: 'fixed', unit: 'millionTokens' },
1537+
{ name: 'textOutput', rate: 8, strategy: 'fixed', unit: 'millionTokens' },
1538+
],
1539+
},
1540+
type: 'chat',
1541+
},
14541542
{
14551543
config: {
14561544
deploymentName: 'qwen-math-turbo-latest',

‎packages/model-bank/src/aiModels/siliconcloud.ts‎

Lines changed: 20 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,26 @@ import { AIChatModelCard, AIImageModelCard } from '../types/aiModel';
22

33
// https://siliconflow.cn/zh-cn/models
44
const siliconcloudChatModels: AIChatModelCard[] = [
5+
{
6+
abilities: {
7+
functionCall: true,
8+
reasoning: true,
9+
},
10+
contextWindowTokens: 128_000,
11+
description:
12+
'MiniMax-M2 为智能体重新定义了效率。它是一款紧凑、快速且经济高效的 MoE 模型，拥有 2300 亿总参数和 100 亿激活参数，专为编码和智能体任务的顶级性能而打造，同时保持强大的通用智能。仅需 100 亿激活参数，MiniMax-M2 就能提供与大规模模型相媲美的性能，使其成为高效率应用的理想选择。',
13+
displayName: 'MiniMax-M2',
14+
id: 'MiniMaxAI/MiniMax-M2',
15+
pricing: {
16+
currency: 'CNY',
17+
units: [
18+
{ name: 'textInput', rate: 2.1, strategy: 'fixed', unit: 'millionTokens' },
19+
{ name: 'textOutput', rate: 8.4, strategy: 'fixed', unit: 'millionTokens' },
20+
],
21+
},
22+
releasedAt: '2025-10-28',
23+
type: 'chat',
24+
},
525
{
626
abilities: {
727
functionCall: true,

‎packages/model-bank/src/aiModels/vercelaigateway.ts‎

Lines changed: 0 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -1565,23 +1565,6 @@ const vercelAIGatewayChatModels: AIChatModelCard[] = [
15651565
},
15661566
type: 'chat',
15671567
},
1568-
{
1569-
abilities: {
1570-
functionCall: true,
1571-
},
1572-
contextWindowTokens: 131_072,
1573-
description:
1574-
'DeepSeek-R1-Distill-Llama-70B 是 70B Llama 模型的蒸馏、更高效变体。它在文本生成任务中保持强大性能，减少计算开销以便于部署和研究。由 Groq 使用其自定义语言处理单元 (LPU) 硬件提供服务，以提供快速高效的推理。',
1575-
displayName: 'DeepSeek R1 Distill Llama 70B',
1576-
id: 'deepseek/deepseek-r1-distill-llama-70b',
1577-
pricing: {
1578-
units: [
1579-
{ name: 'textInput', rate: 0.75, strategy: 'fixed', unit: 'millionTokens' },
1580-
{ name: 'textOutput', rate: 0.99, strategy: 'fixed', unit: 'millionTokens' },
1581-
],
1582-
},
1583-
type: 'chat',
1584-
},
15851568
{
15861569
abilities: {
15871570
functionCall: true,

‎packages/model-bank/src/aiModels/volcengine.ts‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@ const doubaoChatModels: AIChatModelCard[] = [
3737
config: {
3838
deploymentName: 'kimi-k2-250905',
3939
},
40-
contextWindowTokens: 131_072,
40+
contextWindowTokens: 262_144,
4141
description:
4242
'Kimi-K2 是一款Moonshot AI推出的具备超强代码和 Agent 能力的 MoE 架构基础模型，总参数 1T，激活参数 32B。在通用知识推理、编程、数学、Agent 等主要类别的基准性能测试中，K2 模型的性能超过其他主流开源模型。',
4343
displayName: 'Kimi K2',

0 commit comments

Comments
 (0)