✨ feat: add v0 (Vercel) provider support

[hezhijie0327]

💻 变更类型 | Change Type

• ✨ feat
• 🐛 fix
• ♻️ refactor
• 💄 style
• 👷 build
• ⚡️ perf
• 📝 docs
• 🔨 chore

🔀 变更说明 | Description of Change

1. 增加 v0 (Vercel) 提供商
2. 适配提供商及模型图标 💄 style: support v0 (Vercel) provider & model icons lobe-icons#124
3. 适配 ModelFetch

---

Screenshot

---

Note:
按照 v0 模型介绍页面，底层模型对照如下：

v0 Models	Base Models
v0-1.0-md	Sonnet 3.7
v0-1.5-md	Sonnet 4
v0-1.5-lg	Sonnet 4

---

Model Fetch:

{
  "object": "list",
  "data": [
    {
      "id": "v0-1.0-md",
      "object": "model",
      "created": 1747843882,
      "owned_by": "vercel"
    },
    {
      "id": "v0-1.5-md",
      "object": "model",
      "created": 1748873425,
      "owned_by": "vercel"
    },
    {
      "id": "v0-1.5-lg",
      "object": "model",
      "created": 1748873425,
      "owned_by": "vercel"
    }
  ]
}

📝 补充信息 | Additional Information

discussion: #6157 (comment)

ref: https://vercel.com/blog/v0-composite-model-family
ref: https://vercel.com/docs/v0/api#models
ref: https://vercel.com/docs/v0/api#api-reference
ref: https://v0.dev/pricing

Summary by Sourcery

Add end-to-end support for the Vercel v0 API as an LLM provider by updating configuration schemas, Docker environments, UI components, model catalogs, type definitions, and runtime integration

New Features:

• Add Vercel (v0) as a new LLM provider with model catalog, provider card, and runtime implementation

Enhancements:

• Include VercelProviderCard in the provider selection UI
• Extend LLM configuration and type definitions to support Vercel

Build:

• Expose VERCEL_API_KEY and VERCEL_MODEL_LIST environment variables in Dockerfiles

Summary by Sourcery

Add end-to-end support for the Vercel v0 API as a new LLM provider

New Features:

• Create v0 model definitions and include them in the default AI model catalog
• Add V0 provider card to the UI and include it in the provider selection list
• Implement LobeV0AI runtime integration using the OpenAI-compatible factory

Enhancements:

• Extend configuration schemas, types, and the ModelProvider enum to support V0 API keys
• Update runtime map and key vault interfaces to recognize the V0 provider

Build:

• Expose V0_API_KEY and V0_MODEL_LIST environment variables in Dockerfiles

[vercel]

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

A member of the Team first needs to authorize it.

[sourcery-ai]

Reviewer's Guide

This PR adds end-to-end support for the Vercel v0 provider by updating configuration schemas, environment variables, UI components, model catalogs, type definitions, and runtime integration to register and operate V0 alongside existing providers.

Entity relationship diagram for Vercel v0 provider configuration and models

erDiagram
  LLMConfig {
    boolean ENABLED_V0
    string V0_API_KEY
  }
  DockerEnv {
    string V0_API_KEY
    string V0_MODEL_LIST
  }
  UserKeyVaults {
    OpenAICompatibleKeyVault v0
  }
  V0Provider {
    string id
    string name
    string description
    string url
    string modelsUrl
  }
  v0ChatModels {
    string id
    string displayName
    string description
    int contextWindowTokens
    int maxOutput
    object abilities
    object pricing
    string type
  }

  V0Provider ||--o{ v0ChatModels : provides
  LLMConfig ||--|| DockerEnv : mirrors
  UserKeyVaults ||--|| V0Provider : uses

Loading

File-Level Changes

Change	Details	Files
Extend LLM configuration and environment setup for V0	Add ENABLED_V0 and V0_API_KEY to runtimeEnv and schema Expose V0_API_KEY and V0_MODEL_LIST in Dockerfiles Include v0 key vault in user settings types	src/config/llm.ts Dockerfile src/types/user/settings/keyVaults.ts
Integrate V0 provider into model provider lists and UI	Register V0Provider in default provider and model lists Import and export V0ProviderCard in provider index Include V0ProviderCard in the settings UI provider list	src/config/modelProviders/index.ts src/app/[variants]/(main)/settings/llm/ProviderList/providers.tsx
Add V0 AI model catalog	Create v0.ts defining v0ChatModels entries Include v0 export in aiModels index	src/config/aiModels/v0.ts src/config/aiModels/index.ts
Implement V0 runtime integration	Add ModelProvider.V0 enum entry Map v0 to LobeV0AI in runtimeMap Define LobeV0AI via openaiCompatibleFactory	src/libs/model-runtime/types/type.ts src/libs/model-runtime/runtimeMap.ts src/libs/model-runtime/v0/index.ts

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[lobehubbot]

👍 @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]

Codecov Report

Attention: Patch coverage is 96.03960% with 4 lines in your changes missing coverage. Please review.

Project coverage is 87.88%. Comparing base (88c4362) to head (1e85772).
Report is 9 commits behind head on main.

Files with missing lines	Patch %	Lines
src/libs/model-runtime/v0/index.ts	69.23%	4 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #8235      +/-   ##
==========================================
- Coverage   95.67%   87.88%   -7.80%     
==========================================
  Files          14      839     +825     
  Lines        2522    62456   +59934     
  Branches      445     3936    +3491     
==========================================
+ Hits         2413    54888   +52475     
- Misses        109     7568    +7459     

Flag	Coverage Δ
app	87.88% <96.03%> (?)
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.

[greptile-apps]

Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.

[gru-agent]

TestGru Assignment

Summary

Link	CommitId	Status	Reason
Detail	4320d97	🚫 Skipped	No files need to be tested {"Dockerfile":"File path does not match include patterns.","Dockerfile.database":"File path does not match include patterns.","Dockerfile.pglite":"File path does not match include patterns.","src/app/[variants]/(main)/settings/llm/ProviderList/providers.tsx":"File path does not match include patterns.","src/config/aiModels/index.ts":"File path does not match include patterns.","src/config/aiModels/v0.ts":"File path does not match include patterns.","src/config/llm.ts":"File path does not match include patterns.","src/config/modelProviders/index.ts":"File path does not match include patterns.","src/config/modelProviders/v0.ts":"File path does not match include patterns.","src/libs/model-runtime/runtimeMap.ts":"File path does not match include patterns.","src/libs/model-runtime/types/type.ts":"File path does not match include patterns.","src/libs/model-runtime/v0/index.ts":"File path does not match include patterns.","src/types/user/settings/keyVaults.ts":"File…

History Assignment

Tip

You can @gru-agent and leave your feedback. TestGru will make adjustments based on your input

[sourcery-ai]

Hey @hezhijie0327 - I've reviewed your changes - here's some feedback:

• V0ProviderCard.chatModels is currently empty – import and assign your v0ChatModels so the UI can display available models.
• Either hook V0_MODEL_LIST into your configuration/runtime for dynamic model selection or remove it if it's not used.

Prompt for AI Agents

Please address the comments from this code review:
## Overall Comments
- V0ProviderCard.chatModels is currently empty – import and assign your v0ChatModels so the UI can display available models.
- Either hook V0_MODEL_LIST into your configuration/runtime for dynamic model selection or remove it if it's not used.

## Individual Comments

### Comment 1
<location> `src/config/aiModels/v0.ts:14` </location>
<code_context>
+    description:
+      'v0-1.5-lg 模型适用于高级思考或推理任务',
+    displayName: 'v0-1.5-lg',
+    enabled: true,
+    id: 'v0-1.5-lg',
+    maxOutput: 32_000,
</code_context>

<issue_to_address>
Missing 'enabled' property in the third model.

Consider adding the 'enabled' property to the third model for consistency and to prevent issues in code that expects this property.
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[sourcery-ai]

suggestion: Missing 'enabled' property in the third model.

Consider adding the 'enabled' property to the third model for consistency and to prevent issues in code that expects this property.

[vercel]

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	Jun 20, 2025 4:20pm

[lobehubbot]

❤️ 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。

[lobehubbot]

🎉 This PR is included in version 1.96.0 🎉

The release is available on:

• npm package (@latest dist-tag)
• GitHub release

Your semantic-release bot 📦🚀