cherry-studio/packages/aiCore
Phantom e5ccf68476
feat: use biome to format files (#10170)
* build: add @biomejs/biome as a dependency

* chore: add biome extension to vscode recommendations

* chore: migrate from prettier to biome for code formatting

Update VSCode settings to use Biome as the default formatter for multiple languages
Add Biome to code actions on save and reorder search exclude patterns

* build: add biome.json configuration file for code formatting

* build: migrate from prettier to biome for formatting

Update package.json scripts and biome.json configuration to use biome instead of prettier for code formatting. Adjust biome formatter includes/excludes patterns for better file matching.

* refactor(eslint): remove unused prettier config and imports

* chore: update biome.json configuration

- Enable linter and set custom rules
- Change jsxQuoteStyle to single quotes
- Add json parser configuration
- Set formatWithErrors to true

* chore: migrate biome config from json to jsonc format

The new jsonc format allows for comments in the configuration file, making it more maintainable and easier to document configuration choices.

* style(biome): update ignore patterns and jsx quote style

Update file ignore patterns from `/*` to `/**` for consistency
Change jsxQuoteStyle from single to double quotes for alignment with project standards

* refactor: simplify error type annotations from Error | any to any

The change standardizes error handling by using 'any' type instead of union types with Error | any, making the code more consistent and reducing unnecessary type complexity.

* chore: exclude tailwind.css from biome formatting

* style: standardize quote usage and fix JSX formatting

- Replace single quotes with double quotes in CSS imports and selectors
- Fix JSX element closing bracket alignment and formatting
- Standardize JSON formatting in package.json files

* Revert "style: standardize quote usage and fix JSX formatting"

This reverts commit 0947f8505d.

* fix: remove json import assertion for biome compatibility

The import assertion syntax is not supported by biome, so it was replaced with a standard import statement.

* style: change quote styles in biome.jsonc to use single quotes for JSX and double quotes for JS

* style: change quote style from double to single in biome config

* style: change JSX quote style from single to double

* chore: update biome.jsonc to use single quotes for CSS formatting

* chore: update biome config and format commands

- Exclude tailwind.css from linter includes
- Add biome lint to format commands

* style: format JSX closing brackets for better readability

* style: set bracketSameLine to true in biome config

The change aligns with common JSX formatting preferences where brackets on the same line improve readability for many developers

* Revert "style: format JSX closing brackets for better readability"

This reverts commit d442c934ee.

* style: format code and clean up whitespace

- Remove unnecessary whitespace in CSS and TS files
- Format package.json files to consistent style
- Reorder tsconfig.json properties alphabetically
- Improve code formatting in React components

* style(biome): update biome.jsonc config with clearer comment

Add explanation for keeping bracketSameLine as true to minimize changes in current PR while noting false would be better for future

* chore: remove prettier dependency and format package.json files

- Remove prettier from dependencies as it's no longer needed
- Reformat package.json files for better readability

* chore: replace prettier with biome for code formatting

Remove all prettier-related configuration, dependencies, and references
Update formatting scripts and documentation to use biome instead
Adjust electron-builder config to exclude biome.jsonc

* build: replace prettier with biome for formatting

Use biome as the default formatter instead of prettier for better performance and modern tooling support

* ci(i18n): replace prettier with biome for i18n formatting

Update the auto-i18n workflow to use Biome instead of Prettier for formatting translated files. This change simplifies the dependencies by removing multiple Prettier plugins and using a single tool for formatting.

* fix(i18n): Auto update translations for PR #10170

* style: format package.json files by consolidating array formatting

Consolidate multi-line array formatting into single-line format for better readability and consistency across package.json files

* Revert "fix(i18n): Auto update translations for PR #10170"

This reverts commit a7edd32efd.

* ci(workflows): specify biome config path in auto-i18n workflow

* chore: update biome.jsonc to use lexicographic sort order for json keys

* ci(workflows): update biome format command to use --config-path flag

* chore: exclude package.json from biome formatting

* ci: update biome.jsonc linter configuration

Update linter includes to target specific files and modify useSortedClasses rule

* chore: reorder search exclude patterns in vscode settings

* style(OGCard): reorder tailwind classes for consistent styling

* fix(biome): update tailwind classes sorting to safe and warn level

* docs(dev): update ide setup instructions in dev docs

Replace Prettier with Biome as the recommended formatter and clarify editor options

* build(extension-table-plus): replace prettier with biome for formatting

- Add biome.json configuration file
- Update package.json to use biome instead of prettier
- Remove prettier from dependencies
- Update lint script to use biome format

* chore: replace biome.json with biome.jsonc for extended configuration

Update biome configuration file to use JSONC format for comments and more detailed settings

* chore: remove unused biome.jsonc configuration file

---------

Co-authored-by: GitHub Action <action@github.com>
2025-09-15 19:21:15 +08:00
..
src feat: use biome to format files (#10170) 2025-09-15 19:21:15 +08:00
AI_SDK_ARCHITECTURE.md Feat/aisdk package (#7404) 2025-09-04 14:03:04 +08:00
package.json feat: use biome to format files (#10170) 2025-09-15 19:21:15 +08:00
README.md Feat/aisdk package (#7404) 2025-09-04 14:03:04 +08:00
setupVitest.ts Feat/aisdk package (#7404) 2025-09-04 14:03:04 +08:00
tsconfig.json feat: use biome to format files (#10170) 2025-09-15 19:21:15 +08:00
tsdown.config.ts Feat/aisdk package (#7404) 2025-09-04 14:03:04 +08:00
vitest.config.ts Feat/aisdk package (#7404) 2025-09-04 14:03:04 +08:00

@cherrystudio/ai-core

Cherry Studio AI Core 是一个基于 Vercel AI SDK 的统一 AI Provider 接口包,为 AI 应用提供强大的抽象层和插件化架构。

核心亮点

🏗️ 优雅的架构设计

  • 简化分层models(模型层)→ runtime(运行时层),清晰的职责分离
  • 函数式优先:避免过度抽象,提供简洁直观的 API
  • 类型安全:完整的 TypeScript 支持,直接复用 AI SDK 类型系统
  • 最小包装:直接使用 AI SDK 的接口,避免重复定义和性能损耗

🔌 强大的插件系统

  • 生命周期钩子:支持请求全生命周期的扩展点
  • 流转换支持:基于 AI SDK 的 experimental_transform 实现流处理
  • 插件分类First、Sequential、Parallel 三种钩子类型,满足不同场景
  • 内置插件webSearch、logging、toolUse 等开箱即用的功能

🌐 统一多 Provider 接口

  • 扩展注册:支持自定义 Provider 注册,无限扩展能力
  • 配置统一:统一的配置接口,简化多 Provider 管理

🚀 多种使用方式

  • 函数式调用:适合简单场景的直接函数调用
  • 执行器实例:适合复杂场景的可复用执行器
  • 静态工厂:便捷的静态创建方法
  • 原生兼容:完全兼容 AI SDK 原生 Provider Registry

🔮 面向未来

  • Agent 就绪:为 OpenAI Agents SDK 集成预留架构空间
  • 模块化设计:独立包结构,支持跨项目复用
  • 渐进式迁移:可以逐步从现有 AI SDK 代码迁移

特性

  • 🚀 统一的 AI Provider 接口
  • 🔄 动态导入支持
  • 🛠️ TypeScript 支持
  • 📦 强大的插件系统
  • 🌍 内置webSearch(Openai,Google,Anthropic,xAI)
  • 🎯 多种使用模式(函数式/实例式/静态工厂)
  • 🔌 可扩展的 Provider 注册系统
  • 🧩 完整的中间件支持
  • 📊 插件统计和调试功能

支持的 Providers

基于 AI SDK 官方支持的 providers

核心 Providers内置支持:

  • OpenAI
  • Anthropic
  • Google Generative AI
  • OpenAI-Compatible
  • xAI (Grok)
  • Azure OpenAI
  • DeepSeek

扩展 Providers通过注册API支持:

  • Google Vertex AI
  • ...
  • 自定义 Provider

安装

npm install @cherrystudio/ai-core ai

React Native

如果你在 React Native 项目中使用此包,需要在 metro.config.js 中添加以下配置:

// metro.config.js
const { getDefaultConfig } = require('expo/metro-config')

const config = getDefaultConfig(__dirname)

// 添加对 @cherrystudio/ai-core 的支持
config.resolver.resolverMainFields = ['react-native', 'browser', 'main']
config.resolver.platforms = ['ios', 'android', 'native', 'web']

module.exports = config

还需要安装你要使用的 AI SDK provider:

npm install @ai-sdk/openai @ai-sdk/anthropic @ai-sdk/google

使用示例

基础用法

import { AiCore } from '@cherrystudio/ai-core'

// 创建 OpenAI executor
const executor = AiCore.create('openai', {
  apiKey: 'your-api-key'
})

// 流式生成
const result = await executor.streamText('gpt-4', {
  messages: [{ role: 'user', content: 'Hello!' }]
})

// 非流式生成
const response = await executor.generateText('gpt-4', {
  messages: [{ role: 'user', content: 'Hello!' }]
})

便捷函数

import { createOpenAIExecutor } from '@cherrystudio/ai-core'

// 快速创建 OpenAI executor
const executor = createOpenAIExecutor({
  apiKey: 'your-api-key'
})

// 使用 executor
const result = await executor.streamText('gpt-4', {
  messages: [{ role: 'user', content: 'Hello!' }]
})

多 Provider 支持

import { AiCore } from '@cherrystudio/ai-core'

// 支持多种 AI providers
const openaiExecutor = AiCore.create('openai', { apiKey: 'openai-key' })
const anthropicExecutor = AiCore.create('anthropic', { apiKey: 'anthropic-key' })
const googleExecutor = AiCore.create('google', { apiKey: 'google-key' })
const xaiExecutor = AiCore.create('xai', { apiKey: 'xai-key' })

扩展 Provider 注册

对于非内置的 providers可以通过注册 API 扩展支持:

import { registerProvider, AiCore } from '@cherrystudio/ai-core'

// 方式一:导入并注册第三方 provider
import { createGroq } from '@ai-sdk/groq'

registerProvider({
  id: 'groq',
  name: 'Groq',
  creator: createGroq,
  supportsImageGeneration: false
})

// 现在可以使用 Groq
const groqExecutor = AiCore.create('groq', { apiKey: 'groq-key' })

// 方式二:动态导入方式注册
registerProvider({
  id: 'mistral',
  name: 'Mistral AI',
  import: () => import('@ai-sdk/mistral'),
  creatorFunctionName: 'createMistral'
})

const mistralExecutor = AiCore.create('mistral', { apiKey: 'mistral-key' })

🔌 插件系统

AI Core 提供了强大的插件系统,支持请求全生命周期的扩展。

内置插件

webSearchPlugin - 网络搜索插件

为不同 AI Provider 提供统一的网络搜索能力:

import { webSearchPlugin } from '@cherrystudio/ai-core/built-in/plugins'

const executor = AiCore.create('openai', { apiKey: 'your-key' }, [
  webSearchPlugin({
    openai: {
      /* OpenAI 搜索配置 */
    },
    anthropic: { maxUses: 5 },
    google: {
      /* Google 搜索配置 */
    },
    xai: {
      mode: 'on',
      returnCitations: true,
      maxSearchResults: 5,
      sources: [{ type: 'web' }, { type: 'x' }, { type: 'news' }]
    }
  })
])

loggingPlugin - 日志插件

提供详细的请求日志记录:

import { createLoggingPlugin } from '@cherrystudio/ai-core/built-in/plugins'

const executor = AiCore.create('openai', { apiKey: 'your-key' }, [
  createLoggingPlugin({
    logLevel: 'info',
    includeParams: true,
    includeResult: false
  })
])

promptToolUsePlugin - 提示工具使用插件

为不支持原生 Function Call 的模型提供 prompt 方式的工具调用:

import { createPromptToolUsePlugin } from '@cherrystudio/ai-core/built-in/plugins'

// 对于不支持 function call 的模型
const executor = AiCore.create(
  'providerId',
  {
    apiKey: 'your-key',
    baseURL: 'https://your-model-endpoint'
  },
  [
    createPromptToolUsePlugin({
      enabled: true,
      // 可选:自定义系统提示符构建
      buildSystemPrompt: (userPrompt, tools) => {
        return `${userPrompt}\n\nAvailable tools: ${Object.keys(tools).join(', ')}`
      }
    })
  ]
)

自定义插件

创建自定义插件非常简单:

import { definePlugin } from '@cherrystudio/ai-core'

const customPlugin = definePlugin({
  name: 'custom-plugin',
  enforce: 'pre', // 'pre' | 'post' | undefined

  // 在请求开始时记录日志
  onRequestStart: async (context) => {
    console.log(`Starting request for model: ${context.modelId}`)
  },

  // 转换请求参数
  transformParams: async (params, context) => {
    // 添加自定义系统消息
    if (params.messages) {
      params.messages.unshift({
        role: 'system',
        content: 'You are a helpful assistant.'
      })
    }
    return params
  },

  // 处理响应结果
  transformResult: async (result, context) => {
    // 添加元数据
    if (result.text) {
      result.metadata = {
        processedAt: new Date().toISOString(),
        modelId: context.modelId
      }
    }
    return result
  }
})

// 使用自定义插件
const executor = AiCore.create('openai', { apiKey: 'your-key' }, [customPlugin])

使用 AI SDK 原生 Provider 注册表

https://ai-sdk.dev/docs/reference/ai-sdk-core/provider-registry

除了使用内建的 provider 管理,你还可以使用 AI SDK 原生的 createProviderRegistry 来构建自己的 provider 注册表。

基本用法示例

import { createClient } from '@cherrystudio/ai-core'
import { createProviderRegistry } from 'ai'
import { createOpenAI } from '@ai-sdk/openai'
import { anthropic } from '@ai-sdk/anthropic'

// 1. 创建 AI SDK 原生注册表
export const registry = createProviderRegistry({
  // register provider with prefix and default setup:
  anthropic,

  // register provider with prefix and custom setup:
  openai: createOpenAI({
    apiKey: process.env.OPENAI_API_KEY
  })
})

// 2. 创建client,'openai'可以传空或者传providerId(内建的provider)
const client = PluginEnabledAiClient.create('openai', {
  apiKey: process.env.OPENAI_API_KEY
})

// 3. 方式1使用内建逻辑传统方式
const result1 = await client.streamText('gpt-4', {
  messages: [{ role: 'user', content: 'Hello with built-in logic!' }]
})

// 4. 方式2使用自定义注册表灵活方式
const result2 = await client.streamText({
  model: registry.languageModel('openai:gpt-4'),
  messages: [{ role: 'user', content: 'Hello with custom registry!' }]
})

// 5. 支持的重载方法
await client.generateObject({
  model: registry.languageModel('openai:gpt-4'),
  schema: z.object({ name: z.string() }),
  messages: [{ role: 'user', content: 'Generate a user' }]
})

await client.streamObject({
  model: registry.languageModel('anthropic:claude-3-opus-20240229'),
  schema: z.object({ items: z.array(z.string()) }),
  messages: [{ role: 'user', content: 'Generate a list' }]
})

与插件系统配合使用

更强大的是,你还可以将自定义注册表与 Cherry Studio 的插件系统结合使用:

import { PluginEnabledAiClient } from '@cherrystudio/ai-core'
import { createProviderRegistry } from 'ai'
import { createOpenAI } from '@ai-sdk/openai'
import { anthropic } from '@ai-sdk/anthropic'

// 1. 创建带插件的客户端
const client = PluginEnabledAiClient.create(
  'openai',
  {
    apiKey: process.env.OPENAI_API_KEY
  },
  [LoggingPlugin, RetryPlugin]
)

// 2. 创建自定义注册表
const registry = createProviderRegistry({
  openai: createOpenAI({ apiKey: process.env.OPENAI_API_KEY }),
  anthropic: anthropic({ apiKey: process.env.ANTHROPIC_API_KEY })
})

// 3. 方式1使用内建逻辑 + 完整插件系统
await client.streamText('gpt-4', {
  messages: [{ role: 'user', content: 'Hello with plugins!' }]
})

// 4. 方式2使用自定义注册表 + 有限插件支持
await client.streamText({
  model: registry.languageModel('anthropic:claude-3-opus-20240229'),
  messages: [{ role: 'user', content: 'Hello from Claude!' }]
})

// 5. 支持的方法
await client.generateObject({
  model: registry.languageModel('openai:gpt-4'),
  schema: z.object({ name: z.string() }),
  messages: [{ role: 'user', content: 'Generate a user' }]
})

await client.streamObject({
  model: registry.languageModel('openai:gpt-4'),
  schema: z.object({ items: z.array(z.string()) }),
  messages: [{ role: 'user', content: 'Generate a list' }]
})

混合使用的优势

  • 灵活性:可以根据需要选择使用内建逻辑或自定义注册表
  • 兼容性:完全兼容 AI SDK 的 createProviderRegistry API
  • 渐进式:可以逐步迁移现有代码,无需一次性重构
  • 插件支持:自定义注册表仍可享受插件系统的部分功能
  • 最佳实践:结合两种方式的优点,既有动态加载的性能优势,又有统一注册表的便利性

📚 相关资源

未来版本

  • 🔮 多 Agent 编排
  • 🔮 可视化插件配置
  • 🔮 实时监控和分析
  • 🔮 云端插件同步

📄 License

MIT License - 详见 LICENSE 文件


Cherry Studio AI Core - 让 AI 开发更简单、更强大、更灵活 🚀