💄 style: Update Hunyuan models & deepseek-r1-0528 #7993

sxjeru · 2025-05-28T05:59:10Z

💻 变更类型 | Change Type

🔀 变更说明 | Description of Change

不得不吐槽，腾讯混元也太草台班子了，官方文档各种问题，如模型型号不全，模型价格不全等。

添加 deepseek-r1-0528

📝 补充信息 | Additional Information

vercel · 2025-05-28T05:59:15Z

@sxjeru is attempting to deploy a commit to the LobeHub OSS Team on Vercel.

A member of the Team first needs to authorize it.

lobehubbot · 2025-05-28T05:59:21Z

👍 @sxjeru

Thank you for raising your pull request and contributing to our Community
Please make sure you have followed our contributing guidelines. We will review it as soon as possible.
If you encounter any problems, please feel free to connect with us.
非常感谢您提出拉取请求并为我们的社区做出贡献，请确保您已经遵循了我们的贡献指南，我们会尽快审查它。
如果您遇到任何问题，请随时与我们联系。

codecov · 2025-05-28T06:04:27Z

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 88.40%. Comparing base (585e386) to head (43555ca).
Report is 26 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #7993      +/-   ##
==========================================
- Coverage   88.45%   88.40%   -0.06%     
==========================================
  Files         822      822              
  Lines       60394    60396       +2     
  Branches     4008     5513    +1505     
==========================================
- Hits        53424    53395      -29     
- Misses       6970     7001      +31

Flag	Coverage Δ
app	`88.40% <100.00%> (-0.06%)`	⬇️
server	`95.67% <ø> (ø)`

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

entelligence-ai-reviews · 2025-05-28T12:44:13Z

Walkthrough

This PR updates AI model configuration files to expand, refine, and maintain the available model selections. It adds new Hunyuan models with enhanced capabilities, removes deprecated Deepseek models from Novita, and increases context window sizes for several SiliconCloud models. Additionally, it clarifies model lifecycle statuses and removes an outdated Qwen2.5 model, improving overall model management and maintainability.

Changes

File(s)	Summary
src/config/aiModels/hunyuan.ts	Added new Hunyuan model entries (e.g., T1 20250403, TurboS 20250416, Large Vision, T1 Vision, TurboS Role Plus); updated existing models' context windows, max outputs, descriptions, and release dates; revised comments for deprecated models.
src/config/aiModels/novita.ts	Removed 'Deepseek R1' and 'Deepseek V3' chat model configurations from novitaChatModels array.
src/config/aiModels/siliconcloud.ts	Increased contextWindowTokens for multiple models; updated DeepSeek R1 context window; added deprecation/removal comments; removed 'Qwen2.5 72B Instruct (Vendor-A)' model; performed minor comment and whitespace cleanups.

Sequence Diagram

This diagram shows the interactions between components:

sequenceDiagram
    title Hunyuan AI Models Configuration Update Flow

    actor User
    participant Client as "Client Application"
    participant ModelConfig as "AI Model Configuration"
    participant HunyuanModels as "hunyuanChatModels Array"
    participant AIService as "AI Service"

    User->>Client: Request available AI models
    activate Client
    
    Client->>ModelConfig: Load model configurations
    activate ModelConfig
    
    ModelConfig->>HunyuanModels: Get Hunyuan models
    activate HunyuanModels
    
    Note over HunyuanModels: Updated model configurations:
    
    alt New Models Added
        HunyuanModels-->>ModelConfig: Add Hunyuan T1 20250403 model
        HunyuanModels-->>ModelConfig: Add Hunyuan Large Vision model
        HunyuanModels-->>ModelConfig: Add Hunyuan TurboS 20250416 model
        HunyuanModels-->>ModelConfig: Add Hunyuan TurboS Role Plus model
    end
    
    alt Models Updated
        HunyuanModels-->>ModelConfig: Update Hunyuan TurboS latest
        Note right of HunyuanModels: - Increased context window: 32K → 44K tokens
        Note right of HunyuanModels: - Increased max output: 8K → 16K tokens
        
        HunyuanModels-->>ModelConfig: Update Hunyuan T1 Vision
        Note right of HunyuanModels: - Moved from commented to active
        Note right of HunyuanModels: - Increased max output: 8K → 24K tokens
    end
    
    alt Models Commented Out/Removed
        HunyuanModels-->>ModelConfig: Comment out Translation models
        Note right of HunyuanModels: Translation models temporarily disabled
    end
    
    HunyuanModels-->>ModelConfig: Return updated model list
    deactivate HunyuanModels
    
    ModelConfig-->>Client: Return available models
    deactivate ModelConfig
    
    Client-->>User: Display available AI models
    
    User->>Client: Select model for chat
    
    Client->>AIService: Initialize chat with selected model
    activate AIService
    
    AIService-->>Client: Chat session ready
    deactivate AIService
    
    Client-->>User: Chat interface with selected model
    deactivate Client

▶️ ⚡ AI Code Reviews for VS Code, Cursor, Windsurf
Install the extension

Note for Windsurf

Please change the default marketplace provider to the following in the windsurf settings:

Marketplace Extension Gallery Service URL: https://marketplace.visualstudio.com/_apis/public/gallery

Marketplace Gallery Item URL: https://marketplace.visualstudio.com/items

Entelligence.ai can learn from your feedback. Simply add 👍 / 👎 emojis to teach it your preferences. More shortcuts below

Emoji Descriptions:

⚠️ Potential Issue - May require further investigation.
🔒 Security Vulnerability - Fix to ensure system safety.
💻 Code Improvement - Suggestions to enhance code quality.
🔨 Refactor Suggestion - Recommendations for restructuring code.
ℹ️ Others - General comments and information.

Interact with the Bot:

Send a message or request using the format:
@entelligenceai + *your message*

Example: @entelligenceai Can you suggest improvements for this code?

Help the Bot learn by providing feedback on its responses.
@entelligenceai + *feedback*

Example: @entelligenceai Do not comment on `save_auth` function !

Also you can trigger various commands with the bot by doing
@entelligenceai command

The current supported commands are

config - shows the current config
retrigger_review - retriggers the review

More commands to be added soon.

src/config/aiModels/hunyuan.ts

greptile-apps

PR Summary

This PR updates various AI model configurations across multiple providers, focusing on DeepSeek and Hunyuan models.

Added new DeepSeek R1 0528 model with 8192 token maxOutput limit and updated release dates in src/config/aiModels/deepseek.ts
Added new Hunyuan T1 20250403 model with 92K context window and enhanced capabilities in src/config/aiModels/hunyuan.ts
Increased context window sizes to 131K tokens for GLM-Z1, DeepSeek and Qwen models in src/config/aiModels/siliconcloud.ts
Updated pricing for Mistral 7B Instruct from 0.059 to 0.029 in src/config/aiModels/novita.ts
Removed older models like Qwen2.5 72B and added end-of-life dates (2025-06-05) for several models

_{5 file(s) reviewed, no comment(s)}
_{Edit PR Review Bot Settings | Greptile}

hedeqiang · 2025-05-29T15:35:54Z

我看这个比较全，一次性补齐得了

大佬，火山引擎也可以添加下了，我撤回我提交的了

lobehubbot · 2025-05-29T15:36:04Z

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

I think this is quite complete, I can make it up at once

Boss, Volcano Engine can also be added, I withdraw my submitted

sxjeru · 2025-05-29T15:47:28Z

@hedeqiang 已更新。火山方舟因为用的是部署名，所以不需要添加新模型。

lobehubbot · 2025-05-29T15:47:40Z

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

@hedeqiang Updated. Since Volcanic Ark uses deployment names, there is no need to add new models.

vercel · 2025-05-31T13:45:11Z

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
lobe-chat-preview	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	May 31, 2025 2:10pm

lobehubbot · 2025-05-31T14:45:46Z

❤️ Great PR @sxjeru ❤️

The growth of project is inseparable from user feedback and contribution, thanks for your contribution! If you are interesting with the lobehub developer community, please join our discord and then dm @arvinxx or @canisminor1990. They will invite you to our private developer channel. We are talking about the lobe-chat development or sharing ai newsletter around the world.
项目的成长离不开用户反馈和贡献，感谢您的贡献! 如果您对 LobeHub 开发者社区感兴趣，请加入我们的 discord，然后私信 @arvinxx 或 @canisminor1990。他们会邀请您加入我们的私密开发者频道。我们将会讨论关于 Lobe Chat 的开发，分享和讨论全球范围内的 AI 消息。

### [Version 1.88.21](v1.88.20...v1.88.21) <sup>Released on **2025-05-31**</sup> #### 💄 Styles - **misc**: Enhanced reasoning_effort Slider Component, Update Hunyuan models & deepseek-r1-0528. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Styles * **misc**: Enhanced reasoning_effort Slider Component, closes [#7998](#7998) ([750b26a](750b26a)) * **misc**: Update Hunyuan models & deepseek-r1-0528, closes [#7993](#7993) ([2eb198c](2eb198c)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

lobehubbot · 2025-05-31T15:22:46Z

🎉 This PR is included in version 1.88.21 🎉

The release is available on:

Your semantic-release bot 📦🚀

## [Version 1.88.0](v1.87.2...v1.88.0) <sup>Released on **2025-06-02**</sup> #### ✨ Features - **misc**: Support ModelScope Provider, support protect page. #### 🐛 Bug Fixes - **misc**: Agent automatic completion meta not working error, disable LaTeX and Mermaid rendering in SystemRoleContent to prevent lag caused by massive rendering tasks when switching topics, fix DeepSeek new R1 Search error. #### 💄 Styles - **misc**: `+` in the welcome message can be clicked to create an assistant, Enable deploymentName for Aliyun Bailian, Enhanced reasoning_effort Slider Component, support `web_search` tool for MiniMax & Zhipu, support 01.ai proxy url, Update Hunyuan models & deepseek-r1-0528, use default deployment name when parseModelString doesn't contain deployment name. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's improved * **misc**: Support ModelScope Provider, closes [lobehub#8026](https://github.com/jaworldwideorg/OneJA-Bot/issues/8026) ([7b91dfd](7b91dfd)) * **misc**: Support protect page, closes [lobehub#8024](https://github.com/jaworldwideorg/OneJA-Bot/issues/8024) ([d61a9f5](d61a9f5)) #### What's fixed * **misc**: Agent automatic completion meta not working error, closes [lobehub#8003](https://github.com/jaworldwideorg/OneJA-Bot/issues/8003) ([c5307bf](c5307bf)) * **misc**: Disable LaTeX and Mermaid rendering in SystemRoleContent to prevent lag caused by massive rendering tasks when switching topics, closes [lobehub#8034](https://github.com/jaworldwideorg/OneJA-Bot/issues/8034) ([5b42ee2](5b42ee2)) * **misc**: Fix DeepSeek new R1 Search error, closes [lobehub#8035](https://github.com/jaworldwideorg/OneJA-Bot/issues/8035) ([cf58628](cf58628)) #### Styles * **misc**: `+` in the welcome message can be clicked to create an assistant, closes [lobehub#7984](https://github.com/jaworldwideorg/OneJA-Bot/issues/7984) ([9f07e4c](9f07e4c)) * **misc**: Enable deploymentName for Aliyun Bailian, closes [lobehub#7576](https://github.com/jaworldwideorg/OneJA-Bot/issues/7576) ([169e598](169e598)) * **misc**: Enhanced reasoning_effort Slider Component, closes [lobehub#7998](https://github.com/jaworldwideorg/OneJA-Bot/issues/7998) ([750b26a](750b26a)) * **misc**: Support `web_search` tool for MiniMax & Zhipu, closes [lobehub#7980](https://github.com/jaworldwideorg/OneJA-Bot/issues/7980) ([28cdafb](28cdafb)) * **misc**: Support 01.ai proxy url, closes [lobehub#8025](https://github.com/jaworldwideorg/OneJA-Bot/issues/8025) ([e0442b8](e0442b8)) * **misc**: Update Hunyuan models & deepseek-r1-0528, closes [lobehub#7993](https://github.com/jaworldwideorg/OneJA-Bot/issues/7993) ([2eb198c](2eb198c)) * **misc**: Use default deployment name when parseModelString doesn't contain deployment name, closes [lobehub#7719](https://github.com/jaworldwideorg/OneJA-Bot/issues/7719) ([aef19f4](aef19f4)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

Update hunyuan.ts

f4dc604

Update novita.ts

87e236f

Update siliconcloud.ts

02e0c0d

entelligence-ai-reviews reviewed May 28, 2025

View reviewed changes

src/config/aiModels/hunyuan.ts Show resolved Hide resolved

sxjeru added 5 commits May 28, 2025 22:47

Update deepseek.ts

677d467

Update deepseek.ts

cc07bde

Update novita.ts

b2c85c6

Update openrouter.ts

50aa955

Update novita.ts

ac79d65

sxjeru changed the title ~~💄 style: Update Hunyuan models~~ 💄 style: Update Hunyuan models & deepseek-r1-0528 May 29, 2025

Update siliconcloud.ts

cdca38c

sxjeru marked this pull request as ready for review May 29, 2025 07:27

dosubot bot added the size:L This PR changes 100-499 lines, ignoring generated files. label May 29, 2025

greptile-apps bot reviewed May 29, 2025

View reviewed changes

Update volcengine.ts

202e026

sxjeru added 2 commits May 29, 2025 23:49

Update volcengine.ts

762ddce

Update novita.ts

d710880

dosubot bot added size:XL This PR changes 500-999 lines, ignoring generated files. and removed size:L This PR changes 100-499 lines, ignoring generated files. labels May 29, 2025

sxjeru added 3 commits May 30, 2025 00:16

Update siliconcloud.ts

01cf7a8

update snap

1971130

Update novita.ts

a51fb6a

sxjeru added 3 commits May 30, 2025 23:59

Update siliconcloud.ts

8b2f3a1

Update siliconcloud.ts

807fd9d

Update groq.ts

43555ca

vercel bot deployed to Preview – lobe-chat-preview May 31, 2025 14:10 View deployment

arvinxx merged commit 2eb198c into lobehub:main May 31, 2025
17 of 18 checks passed

sxjeru deleted the patch-3 branch May 31, 2025 14:46

lobehubbot added the released label May 31, 2025

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

💄 style: Update Hunyuan models & deepseek-r1-0528 #7993

💄 style: Update Hunyuan models & deepseek-r1-0528 #7993

sxjeru commented May 28, 2025 •

edited

Loading

Uh oh!

vercel bot commented May 28, 2025

Uh oh!

lobehubbot commented May 28, 2025

Uh oh!

codecov bot commented May 28, 2025 •

edited

Loading

Uh oh!

entelligence-ai-reviews commented May 28, 2025

Emoji Descriptions:

Interact with the Bot:

Uh oh!

Uh oh!

greptile-apps bot left a comment

Uh oh!

hedeqiang commented May 29, 2025

Uh oh!

lobehubbot commented May 29, 2025

Uh oh!

sxjeru commented May 29, 2025

Uh oh!

lobehubbot commented May 29, 2025

Uh oh!

vercel bot commented May 31, 2025 •

edited

Loading

Uh oh!

Uh oh!

lobehubbot commented May 31, 2025

Uh oh!

lobehubbot commented May 31, 2025

Uh oh!

Uh oh!

Uh oh!

💄 style: Update Hunyuan models & deepseek-r1-0528 #7993

💄 style: Update Hunyuan models & deepseek-r1-0528 #7993

Conversation

sxjeru commented May 28, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

💻 变更类型 | Change Type

🔀 变更说明 | Description of Change

📝 补充信息 | Additional Information

Uh oh!

vercel bot commented May 28, 2025

Uh oh!

lobehubbot commented May 28, 2025

Uh oh!

codecov bot commented May 28, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

entelligence-ai-reviews commented May 28, 2025

Walkthrough

Changes

Sequence Diagram

Emoji Descriptions:

Interact with the Bot:

Uh oh!

Uh oh!

greptile-apps bot left a comment

Choose a reason for hiding this comment

PR Summary

Uh oh!

hedeqiang commented May 29, 2025

Uh oh!

lobehubbot commented May 29, 2025

Uh oh!

sxjeru commented May 29, 2025

Uh oh!

lobehubbot commented May 29, 2025

Uh oh!

vercel bot commented May 31, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

lobehubbot commented May 31, 2025

Uh oh!

lobehubbot commented May 31, 2025

Uh oh!

Uh oh!

sxjeru commented May 28, 2025 •

edited

Loading

codecov bot commented May 28, 2025 •

edited

Loading

vercel bot commented May 31, 2025 •

edited

Loading