💄 style: Add Volcengine & OpenAI-like Provider (e.g. oneapi) model fetch support #7916

sxjeru · 2025-05-21T12:11:53Z

💻 变更类型 | Change Type

🔀 变更说明 | Description of Change

存在重构，需要审查代码

重构模型tag解析部分，按关键词（如 doubao）交由不同提供商的解析模板解析模型 tags.

📝 补充信息 | Additional Information

vercel · 2025-05-21T12:11:58Z

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

A member of the Team first needs to authorize it.

lobehubbot · 2025-05-21T12:12:06Z

👍 @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。

greptile-apps

PR Summary

Added Volcengine model integration to LobeChat, implementing OpenAI-compatible model fetching and capability detection.

Added VolcengineModelCard interface and model fetching implementation in src/libs/model-runtime/volcengine/index.ts
Implemented capability detection for function calling, vision, and reasoning based on model ID keywords
Added support for thinking mode in chat completion payload for vision-pro models
Integrated with LOBE_DEFAULT_MODEL_LIST to preserve known model metadata
Added debug mode toggle for chat completion via environment variable DEBUG_VOLCENGINE_CHAT_COMPLETION

_{💡 (4/5) You can add custom instructions or style guidelines for the bot here!}

_{1 file(s) reviewed, 3 comment(s)}
_{Edit PR Review Bot Settings | Greptile}

src/libs/model-runtime/volcengine/index.ts

codecov · 2025-05-22T23:00:58Z

Codecov Report

Attention: Patch coverage is 84.00000% with 36 lines in your changes missing coverage. Please review.

Project coverage is 88.51%. Comparing base (9f07e4c) to head (b18726b).
Report is 20 commits behind head on main.

Files with missing lines	Patch %	Lines
src/libs/model-runtime/google/index.ts	0.00%	23 Missing ⚠️
src/libs/model-runtime/volcengine/index.ts	20.00%	4 Missing ⚠️
src/libs/model-runtime/zhipu/index.ts	0.00%	4 Missing ⚠️
src/libs/model-runtime/nvidia/index.ts	0.00%	1 Missing ⚠️
src/libs/model-runtime/openrouter/index.ts	97.29%	1 Missing ⚠️
src/libs/model-runtime/qwen/index.ts	0.00%	1 Missing ⚠️
src/libs/model-runtime/siliconcloud/index.ts	0.00%	1 Missing ⚠️
src/libs/model-runtime/zeroone/index.ts	0.00%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #7916      +/-   ##
==========================================
- Coverage   95.67%   88.51%   -7.16%     
==========================================
  Files          14      826     +812     
  Lines        2519    60650   +58131     
  Branches      244     4030    +3786     
==========================================
+ Hits         2410    53684   +51274     
- Misses        109     6966    +6857

Flag	Coverage Δ
app	`88.51% <84.00%> (?)`
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.

sxjeru · 2025-05-23T03:41:23Z

初步测试可用。

src/libs/model-runtime/utils/modelParse.ts

arvinxx · 2025-06-01T08:25:46Z

ci 挂了，看下lint

lobehubbot · 2025-06-01T08:25:55Z

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

ci is dead, check out lint

## [Version 1.90.0](lobehub/lobe-chat@v1.89.0...v1.90.0) <sup>Released on **2025-06-01**</sup> #### ✨ Features - **misc**: Support protect page. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's improved * **misc**: Support protect page, closes [lobehub#8024](lobehub#8024) ([d61a9f5](lobehub@d61a9f5)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

…event lag caused by massive rendering tasks when switching topics (lobehub#8034)

* fix DeepSeek R1 Search issue * fix tests

…oved compatibility across platforms on macOS (lobehub#7639)

…ntain deployment name (lobehub#7719) * ♻️ refactor: use default deployment name when parseModelString doesn't contain deployment name * ✅ test: add test case for parseModelString without deployment name * 添加测试用例 * 📝 docs: clarify default deployment name behavior in model list documentation * 📝 docs: update deployment name description for clarity in model list documentation * 📝 docs: update deployment name description for clarity in model list documentation

### [Version 1.90.1](lobehub/lobe-chat@v1.90.0...v1.90.1) <sup>Released on **2025-06-01**</sup> #### 🐛 Bug Fixes - **misc**: 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**: Use default deployment name when parseModelString doesn't contain deployment name. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * **misc**: Disable LaTeX and Mermaid rendering in SystemRoleContent to prevent lag caused by massive rendering tasks when switching topics, closes [lobehub#8034](lobehub#8034) ([5b42ee2](lobehub@5b42ee2)) * **misc**: Fix DeepSeek new R1 Search error, closes [lobehub#8035](lobehub#8035) ([cf58628](lobehub@cf58628)) #### Styles * **misc**: Use default deployment name when parseModelString doesn't contain deployment name, closes [lobehub#7719](lobehub#7719) ([aef19f4](lobehub@aef19f4)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

* 💄 style: support web_search for MiniMax * ♻️ refactor: refactor zhipu `web_search` tools * 🐛 fix: fix live search citations * ♻️ refactor: refactor Minimax citations * 🐛 fix: fix ci error * 🐛 fix: fix ci error * 💄 style: support OpenAI Search model citations --------- Co-authored-by: Arvin Xu <arvinx@foxmail.com>

### [Version 1.90.2](lobehub/lobe-chat@v1.90.1...v1.90.2) <sup>Released on **2025-06-01**</sup> #### 💄 Styles - **misc**: Support `web_search` tool for MiniMax & Zhipu. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Styles * **misc**: Support `web_search` tool for MiniMax & Zhipu, closes [lobehub#7980](lobehub#7980) ([28cdafb](lobehub@28cdafb)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

* Adds Qwen deployment name support Enables deploymentName flag for Qwen in global config Includes Qwen in chat service’s deployment-name providers * update * Update qwen.ts * Update qwen.ts * Update qwen.ts * Update xai.ts * Update qwen.ts --------- Co-authored-by: Arvin Xu <arvinx@foxmail.com>

### [Version 1.90.3](lobehub/lobe-chat@v1.90.2...v1.90.3) <sup>Released on **2025-06-01**</sup> #### 💄 Styles - **misc**: Enable deploymentName for Aliyun Bailian. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Styles * **misc**: Enable deploymentName for Aliyun Bailian, closes [lobehub#7576](lobehub#7576) ([169e598](lobehub@169e598)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

* 📝 docs: add some more cursor rules * 📝 docs: fix greptile reported issue

…ub#8044)

* 📝 docs: update Qwen model providers in documentation * 📝 docs: update example for model list customization in documentation

* refactor model runtime createOpenAICompatibleRuntime * upgrade version and fix tests * fix tests * fix tests

### [Version 1.90.4](lobehub/lobe-chat@v1.90.3...v1.90.4) <sup>Released on **2025-06-02**</sup> #### ♻ Code Refactoring - **misc**: Rename the createOpenAICompatibleRuntime. #### 🐛 Bug Fixes - **misc**: Update the clerk middleware to support route protection. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Code refactoring * **misc**: Rename the createOpenAICompatibleRuntime, closes [lobehub#8049](lobehub#8049) ([ee660d6](lobehub@ee660d6)) #### What's fixed * **misc**: Update the clerk middleware to support route protection, closes [lobehub#8044](lobehub#8044) ([309f973](lobehub@309f973)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

…behub#8055) * migration: 添加移除 reasoning_effort 参数和删除 doubao 的迁移脚本 * Refactor code structure for improved readability and maintainability

* style: update modelscope * style: update modelscope

* ✨ feat: support tavily as search provider * ✨ feat: support tavily as crawl provider * 🐛 fix: fix category mapping * ✨ feat: support firecrwal as crawl provider * ✨ feat: support firecrawl as search provider * 🔨 chore: support firecrawl baseUrl for self-host * 🐛 fix: fix build error * ✨ feat: support jina as search provider * 🐛 fix: fix build error * ✨ feat: support BoChaAI & Exa as search & crawl provider * 🐛 fix: fix build error * 🔨 chore: rename to bocha * 🐛 fix: fix typo in bocha impl * ♻️ refactor: add `category` & `time_range` support for Exa --------- Co-authored-by: Arvin Xu <arvinx@foxmail.com>

## [Version 1.91.0](lobehub/lobe-chat@v1.90.4...v1.91.0) <sup>Released on **2025-06-03**</sup> #### ✨ Features - **misc**: Add more provider support for search & crawl. #### 💄 Styles - **misc**: Update modelscope models. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's improved * **misc**: Add more provider support for search & crawl, closes [lobehub#8033](lobehub#8033) ([23fade3](lobehub@23fade3)) #### Styles * **misc**: Update modelscope models, closes [lobehub#8057](lobehub#8057) ([3e02c25](lobehub@3e02c25)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

Update index.ts

a116194

dosubot bot added the size:M This PR changes 30-99 lines, ignoring generated files. label May 21, 2025

sxjeru changed the title ~~💄 style: AddVolcengine model fetch support~~ 💄 style: Add Volcengine model fetch support May 21, 2025

greptile-apps bot reviewed May 21, 2025

View reviewed changes

src/libs/model-runtime/volcengine/index.ts Show resolved Hide resolved

src/libs/model-runtime/volcengine/index.ts Show resolved Hide resolved

src/libs/model-runtime/volcengine/index.ts Outdated Show resolved Hide resolved

Merge branch 'main' into patch-5

83229d7

sxjeru changed the title ~~💄 style: Add Volcengine model fetch support~~ 💄 style: Add Volcengine & OpenAI-like Provider (e.g. oneapi) model fetch support May 23, 2025

重构 modelParse

4fc39ca

dosubot bot added size:L This PR changes 100-499 lines, ignoring generated files. and removed size:M This PR changes 30-99 lines, ignoring generated files. labels May 23, 2025

sxjeru added 3 commits May 23, 2025 10:54

Merge remote-tracking branch 'upstream/main' into pr/sxjeru/7916

f36ef90

继续重构

294439f

fix

f1c4dfc

sxjeru added 2 commits May 23, 2025 11:59

fix test & zeroone

d3ef8ed

support openrouter

927a136

arvinxx reviewed May 25, 2025

View reviewed changes

src/libs/model-runtime/utils/modelParse.ts Show resolved Hide resolved

src/libs/model-runtime/utils/modelParse.ts Outdated Show resolved Hide resolved

src/libs/model-runtime/utils/modelParse.ts Show resolved Hide resolved

sxjeru added 2 commits May 27, 2025 21:07

support Gemini

9e107c0

support Qwen

5911066

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 27, 2025

add tests

8bd0d62

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 May 27, 2025

sxjeru and others added 2 commits May 28, 2025 20:55

optm

2df959f

Merge branch 'main' into patch-5

103730f

semantic-release-bot and others added 26 commits June 4, 2025 10:07

📝 docs(bot): Auto sync agents & plugin to readme

6366e1f

🐛 fix: disable LaTeX and Mermaid rendering in SystemRoleContent to pr…

9c28c64

…event lag caused by massive rendering tasks when switching topics (lobehub#8034)

🐛 fix: fix DeepSeek new R1 Search error (lobehub#8035)

4a6fcff

* fix DeepSeek R1 Search issue * fix tests

🔨 chore(setup.sh): Replace SED_COMMAND with SED_INPLACE_ARGS for impr…

289aa6b

…oved compatibility across platforms on macOS (lobehub#7639)

📝 docs(bot): Auto sync agents & plugin to readme

606db37

📝 docs(bot): Auto sync agents & plugin to readme

08fb934

📝 docs(bot): Auto sync agents & plugin to readme

96dd56b

📝 docs: add more cursor rules (lobehub#8047)

c859f65

* 📝 docs: add some more cursor rules * 📝 docs: fix greptile reported issue

🐛 fix: Update the clerk middleware to support route protection (lobeh…

8920f8e

…ub#8044)

📝 docs: update Qwen model provider in documentation (lobehub#8041)

c053e8f

* 📝 docs: update Qwen model providers in documentation * 📝 docs: update example for model list customization in documentation

♻️ refactor: rename the createOpenAICompatibleRuntime (lobehub#8049)

c26d945

* refactor model runtime createOpenAICompatibleRuntime * upgrade version and fix tests * fix tests * fix tests

📝 docs(bot): Auto sync agents & plugin to readme

63f703f

🐛 fix (migration): Remove abandoned reasoning_effort & doubao (lo…

4f5d941

…behub#8055) * migration: 添加移除 reasoning_effort 参数和删除 doubao 的迁移脚本 * Refactor code structure for improved readability and maintainability

💄 style: update modelscope models (lobehub#8057)

dca0fd5

* style: update modelscope * style: update modelscope

📝 docs(bot): Auto sync agents & plugin to readme

5f74826

reset

ea25c6d

sxjeru mentioned this pull request Jun 4, 2025

💄 style: Add Volcengine & OpenAI-like Provider (e.g. oneapi) model fetch support sxjeru/lobe-chat#80

Closed

8 tasks

sxjeru closed this Jun 4, 2025

sxjeru mentioned this pull request Jun 4, 2025

💄 style: Add Volcengine & OpenAI-like Provider (e.g. oneapi) model fetch support #8064

Merged

8 tasks

sxjeru deleted the patch-5 branch June 4, 2025 06:57

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

💄 style: Add Volcengine & OpenAI-like Provider (e.g. oneapi) model fetch support #7916

💄 style: Add Volcengine & OpenAI-like Provider (e.g. oneapi) model fetch support #7916

Uh oh!

sxjeru commented May 21, 2025 •

edited

Loading

Uh oh!

vercel bot commented May 21, 2025

Uh oh!

lobehubbot commented May 21, 2025

Uh oh!

greptile-apps bot left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

codecov bot commented May 22, 2025 •

edited

Loading

Uh oh!

sxjeru commented May 23, 2025

Uh oh!

Uh oh!

Uh oh!

Uh oh!

arvinxx commented Jun 1, 2025

Uh oh!

lobehubbot commented Jun 1, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

10 participants

Uh oh!

💄 style: Add Volcengine & OpenAI-like Provider (e.g. oneapi) model fetch support #7916

💄 style: Add Volcengine & OpenAI-like Provider (e.g. oneapi) model fetch support #7916

Uh oh!

Conversation

sxjeru commented May 21, 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

存在重构，需要审查代码

📝 补充信息 | Additional Information

Uh oh!

vercel bot commented May 21, 2025

Uh oh!

lobehubbot commented May 21, 2025

Uh oh!

greptile-apps bot left a comment

Choose a reason for hiding this comment

PR Summary

Uh oh!

Uh oh!

Uh oh!

Uh oh!

codecov bot commented May 22, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

sxjeru commented May 23, 2025

Uh oh!

Uh oh!

Uh oh!

Uh oh!

arvinxx commented Jun 1, 2025

Uh oh!

lobehubbot commented Jun 1, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

10 participants

sxjeru commented May 21, 2025 •

edited

Loading

codecov bot commented May 22, 2025 •

edited

Loading