♻️ refactor: improve model fetch behavior #6055

hezhijie0327 · 2025-02-12T12:10:33Z

💻 变更类型 | Change Type

🔀 变更说明 | Description of Change

当 API 无法准确获取模型能力是时，回退至内建数据
补齐 Ollama 及 LMStudio 模型获取能力
修正 Gemini Thinking 模型，functionCall tag 问题
异步加载 LOBE_DEFAULT_MODEL_LIST ~~[TODO]~~

📝 补充信息 | Additional Information

Before	After

close #5887

vercel · 2025-02-12T12:10:39Z

@hezhijie0327 is attempting to deploy a commit to the LobeChat Community Team on Vercel.

A member of the Team first needs to authorize it.

lobehubbot · 2025-02-12T12:10:48Z

👍 @hezhijie0327

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 · 2025-02-12T12:13:19Z

Codecov Report

Attention: Patch coverage is 25.94538% with 705 lines in your changes missing coverage. Please review.

Project coverage is 91.77%. Comparing base (5a012e4) to head (fc6458c).
Report is 11 commits behind head on main.

Files with missing lines	Patch %	Lines
src/libs/agent-runtime/siliconcloud/index.ts	4.00%	48 Missing ⚠️
src/libs/agent-runtime/giteeai/index.ts	4.34%	44 Missing ⚠️
src/libs/agent-runtime/qwen/index.ts	4.44%	43 Missing ⚠️
src/libs/agent-runtime/groq/index.ts	4.65%	41 Missing ⚠️
src/libs/agent-runtime/stepfun/index.ts	4.76%	40 Missing ⚠️
src/libs/agent-runtime/tencentcloud/index.ts	15.90%	37 Missing ⚠️
src/libs/agent-runtime/ai360/index.ts	5.40%	35 Missing ⚠️
src/libs/agent-runtime/higress/index.ts	26.66%	33 Missing ⚠️
src/libs/agent-runtime/hunyuan/index.ts	5.88%	32 Missing ⚠️
src/libs/agent-runtime/fireworksai/index.ts	6.66%	28 Missing ⚠️
... and 15 more

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #6055      +/-   ##
==========================================
- Coverage   92.47%   91.77%   -0.70%     
==========================================
  Files         661      660       -1     
  Lines       60005    60495     +490     
  Branches     4212     2840    -1372     
==========================================
+ Hits        55488    55520      +32     
- Misses       4517     4975     +458

Flag	Coverage Δ
app	`91.77% <25.94%> (-0.70%)`	⬇️
server	`97.90% <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.

arvinxx

有一个唯一的问题。Model List 那个导入最好是在 model() 拉取方法中异步获取。

const { LOBE_DEFAULT_MODEL_LIST } = await import('@/config/aiModels');

原因是后续随着 provider 数量增加，这部分的数据体积也会很大，这部分要做成按需导入的形式会比较好，未来能降低产物的体积

…hod - Part 1

…d - Part 2

hezhijie0327 · 2025-02-13T13:32:26Z

有一个唯一的问题。Model List 那个导入最好是在 model() 拉取方法中异步获取。

改好了

lobehubbot · 2025-02-13T13:32:42Z

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

There is one only problem. Model List The import is best obtained asynchronously in the model() pull method.

Improved

arvinxx

LGTM.

留个思考，目前每个 provider 都几乎等于重写了 models 方法，后续有没有可能把 models 的拉取方法弄一版内置到 openaiFactory 里，然后在外部用配置式的方式完成细节调整？

vercel · 2025-02-14T02:31:11Z

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	Feb 14, 2025 2:41am

lobehubbot · 2025-02-14T02:44:11Z

❤️ Great PR @hezhijie0327 ❤️

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 1.53.12](v1.53.11...v1.53.12) <sup>Released on **2025-02-14**</sup> #### ♻ Code Refactoring - **misc**: Improve model fetch behavior. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Code refactoring * **misc**: Improve model fetch behavior, closes [#6055](#6055) ([4c2aaf6](4c2aaf6)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

lobehubbot · 2025-02-14T02:52:33Z

🎉 This PR is included in version 1.53.12 🎉

The release is available on:

Your semantic-release bot 📦🚀

* ♻️ refactor: refactor model fetch behavior * 🐛 fix: fix gemini thinking model set functionCall tag * 🐛 fix: fix Spark fc tag missing * ✨ feat: add model fetch support for Tencent Cloud * ♻️ refactor: refactor import `LOBE_DEFAULT_MODEL_LIST` with async method - Part 1 * ♻️ refactor: refactor import LOBE_DEFAULT_MODEL_LIST with async method - Part 2 * 🔨 chore: add vision, reasoning, fc default value * ♻️ refactor: improve knownModel matching * 🐛 fix: fix ci error

### [Version 1.53.12](lobehub/lobe-chat@v1.53.11...v1.53.12) <sup>Released on **2025-02-14**</sup> #### ♻ Code Refactoring - **misc**: Improve model fetch behavior. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Code refactoring * **misc**: Improve model fetch behavior, closes [lobehub#6055](lobehub#6055) ([4c2aaf6](lobehub@4c2aaf6)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

### [Version 1.95.5](v1.95.4...v1.95.5) <sup>Released on **2025-02-14**</sup> #### ♻ Code Refactoring - **misc**: Improve model fetch behavior. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Code refactoring * **misc**: Improve model fetch behavior, closes [lobehub#6055](https://github.com/bentwnghk/lobe-chat/issues/6055) ([4c2aaf6](4c2aaf6)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

Thinker-Joe · 2025-02-14T07:33:05Z

Perfect，点个大大的赞，成功修复问题了

lobehubbot · 2025-02-14T07:33:18Z

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

Perfect, please give me a big thumbs up and successfully fixed the problem

♻️ refactor: refactor model fetch behavior

0389451

hezhijie0327 marked this pull request as ready for review February 12, 2025 12:26

dosubot bot added the size:XL This PR changes 500-999 lines, ignoring generated files. label Feb 12, 2025

hezhijie0327 added 3 commits February 12, 2025 20:38

🐛 fix: fix gemini thinking model set functionCall tag

4598565

🐛 fix: fix Spark fc tag missing

0e5702c

✨ feat: add model fetch support for Tencent Cloud

de935e7

arvinxx requested changes Feb 12, 2025

View reviewed changes

hezhijie0327 added 3 commits February 13, 2025 19:25

♻️ refactor: refactor import LOBE_DEFAULT_MODEL_LIST with async met…

256d044

…hod - Part 1

Merge branch 'main' into models

a2cb19c

♻️ refactor: refactor import LOBE_DEFAULT_MODEL_LIST with async metho…

b29c689

…d - Part 2

dosubot bot added size:XXL This PR changes 1000+ lines, ignoring generated files. and removed size:XL This PR changes 500-999 lines, ignoring generated files. labels Feb 13, 2025

hezhijie0327 added 3 commits February 13, 2025 21:48

🔨 chore: add vision, reasoning, fc default value

93647e4

♻️ refactor: improve knownModel matching

d4bb784

🐛 fix: fix ci error

fc6458c

arvinxx approved these changes Feb 14, 2025

View reviewed changes

vercel bot deployed to Preview – lobe-chat-preview February 14, 2025 02:41 View deployment

arvinxx changed the title ~~♻️ refactor: refactor model fetch behavior~~ ♻️ refactor: improve model fetch behavior Feb 14, 2025

arvinxx merged commit 4c2aaf6 into lobehub:main Feb 14, 2025
10 of 12 checks passed

lobehubbot added the released label Feb 14, 2025

hezhijie0327 deleted the models branch February 14, 2025 07:07

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

♻️ refactor: improve model fetch behavior #6055

♻️ refactor: improve model fetch behavior #6055

hezhijie0327 commented Feb 12, 2025 •

edited

Loading

vercel bot commented Feb 12, 2025

lobehubbot commented Feb 12, 2025

codecov bot commented Feb 12, 2025 •

edited

Loading

arvinxx left a comment

hezhijie0327 commented Feb 13, 2025

lobehubbot commented Feb 13, 2025

arvinxx left a comment •

edited

Loading

vercel bot commented Feb 14, 2025 •

edited

Loading

lobehubbot commented Feb 14, 2025

lobehubbot commented Feb 14, 2025

Thinker-Joe commented Feb 14, 2025

lobehubbot commented Feb 14, 2025

♻️ refactor: improve model fetch behavior #6055

♻️ refactor: improve model fetch behavior #6055

Conversation

hezhijie0327 commented Feb 12, 2025 • edited Loading

💻 变更类型 | Change Type

🔀 变更说明 | Description of Change

📝 补充信息 | Additional Information

vercel bot commented Feb 12, 2025

lobehubbot commented Feb 12, 2025

codecov bot commented Feb 12, 2025 • edited Loading

Codecov Report

arvinxx left a comment

Choose a reason for hiding this comment

hezhijie0327 commented Feb 13, 2025

lobehubbot commented Feb 13, 2025

arvinxx left a comment • edited Loading

Choose a reason for hiding this comment

vercel bot commented Feb 14, 2025 • edited Loading

lobehubbot commented Feb 14, 2025

lobehubbot commented Feb 14, 2025

Thinker-Joe commented Feb 14, 2025

lobehubbot commented Feb 14, 2025

hezhijie0327 commented Feb 12, 2025 •

edited

Loading

codecov bot commented Feb 12, 2025 •

edited

Loading

arvinxx left a comment •

edited

Loading

vercel bot commented Feb 14, 2025 •

edited

Loading