@ubean/ai 0.6.2 → 0.6.4

package/README.md

@@ -0,0 +1,251 @@
+# @ubean/ai
+
+**English | [中文](./README.zh-CN.md)**
+
+AI large-model integration for the ubean framework — a thin orchestration layer over the Vercel AI SDK.
+
+```ts
+import { defineAgent, defineAgentTool, v } from '@ubean/ai';
+
+const weather = defineAgentTool({
+  name: 'get_weather',
+  description: 'Get the weather for a city',
+  input: v.object({ city: v.string() }),
+  execute: async ({ city }) => ({ city, temperature: 21 })
+});
+
+const agent = defineAgent({ model: 'deepseek-chat', tools: { weather } });
+```
+
+## Table of Contents
+
+- [@ubean/ai](#ubeanai)
+  - [Package Positioning](#package-positioning)
+  - [Install](#install)
+  - [Quick Start](#quick-start)
+  - [Agent Kernel](#agent-kernel)
+  - [Vue Runtime](#vue-runtime)
+  - [Gateway Presets](#gateway-presets)
+  - [Vite Plugin](#vite-plugin)
+  - [Type Safety](#type-safety)
+  - [Architecture Notes](#architecture-notes)
+
+## Package Positioning
+
+| Layer                   | Responsibility                                                                      |
+| ----------------------- | ----------------------------------------------------------------------------------- |
+| `@ubean/ai` (kernel)    | Provider registry, agent definition, tool definition, streaming chunk protocol      |
+| `@ubean/ai/runtime/vue` | Vue composables that consume the SSE stream an agent exposes                        |
+| `@ubean/ai/gateway`     | Provider presets only — base URLs and ids for common hosted providers               |
+| `@ubean/ai/vite`        | Module wiring: registers providers, auto-imports the composables, adds optimizeDeps |
+
+**Included:**
+
+- `defineProvider` / `configureAI` / `resolveModel` — resolve a `model` string to a concrete provider + model id.
+- `defineAgent` — declares system prompt, model, tools, step budget and sampling knobs; returns a `UbeanAgent` with `run()`, `stream()` and `asHandler()`.
+- `defineAgentTool` — a type-safe identity helper that keeps the Valibot schema's inferred input type on `execute(args, ctx)`.
+- `v` — a namespace re-export of **valibot**, used to author tool input schemas.
+- `useChat` / `useAgent` / `useAIProvider` — the Vue runtime.
+- Provider presets for DeepSeek, OpenRouter, OmniRoute, OpenAI, Anthropic, Google and Groq.
+
+**NOT included** (deliberately):
+
+- No gateway service. `@ubean/ai/gateway` ships provider _presets_, not routing, fallback or cost optimization — put an external gateway (for example OmniRoute) in front if you need those.
+- No UI layer. Markdown rendering, code highlighting and message bubbles are out of scope; pick your own renderer in the `useChat` consumer.
+- No agent loop implementation. The tool-calling loop, retries and streaming come from the Vercel AI SDK (`ai`); ubean only declares and orchestrates.
+- No HTTP route files. The `asHandler()` result is a plain Hono handler — mount it in `src/routes/` yourself, the way `@ubean/routes` documents API routes.
+
+**Runtime dependency whitelist (main entry):** `@valibot/to-json-schema`, `valibot`. The AI SDK itself (`ai`, `@ai-sdk/openai-compatible`) is loaded lazily.
+
+**Optional peers:** `ai`, `@ai-sdk/openai-compatible`, `hono`, `vite`, `vue`. Every peer is optional — the package builds and imports without them. If the AI SDK is missing when an agent actually runs, the call rejects with an install hint:
+
+```
+[@ubean/ai] The AI SDK packages are not installed. Install them with:
+pnpm add ai @ai-sdk/openai-compatible (or npm/yarn/bun equivalent).
+```
+
+## Install
+
+```bash
+# the ubean-side orchestration layer
+pnpm add @ubean/ai
+
+# the AI SDK runtime — required at agent execution time
+pnpm add ai @ai-sdk/openai-compatible
+
+# peers you only need if you use that part of the surface
+pnpm add vue        # @ubean/ai/runtime/vue
+pnpm add hono       # UbeanAgent.asHandler()
+```
+
+## Quick Start
+
+**1. Enable the module**
+
+```ts
+// ubean.config.ts
+import { defineConfig } from 'ubean';
+
+export default defineConfig({
+  ai: true // or ai: { defaultProvider: 'deepseek', defaultModel: 'deepseek-chat' }
+});
+```
+
+**2. Define a tool**
+
+Tool input is a Valibot schema, so `execute` receives a fully inferred argument object.
+
+```ts
+// src/server/ai/tools.ts
+import { defineAgentTool, v } from '@ubean/ai';
+
+export const searchDocs = defineAgentTool({
+  name: 'search_docs',
+  description: 'Search the documentation index for a query',
+  input: v.object({
+    query: v.string(),
+    limit: v.optional(v.pipe(v.number(), v.integer()), 5)
+  }),
+  execute: async ({ query, limit }, ctx) => {
+    ctx.signal?.throwIfAborted();
+    return { query, limit, hits: [] };
+  }
+});
+```
+
+**3. Define an agent**
+
+```ts
+// src/server/ai/agent.ts
+import { defineAgent } from '@ubean/ai';
+import { searchDocs } from './tools';
+
+export const supportAgent = defineAgent<{ answer: string }>({
+  model: 'deepseek-chat',
+  system: 'You are a documentation assistant. Cite the docs you used.',
+  tools: { searchDocs },
+  maxSteps: 5
+});
+```
+
+**4. Expose it over HTTP**
+
+```ts
+// src/routes/api/chat.ts
+import { supportAgent } from '~/server/ai/agent';
+
+export const POST = supportAgent.asHandler();
+```
+
+`asHandler()` reads the request body as an `AgentInput` and responds with a Server-Sent Events stream of `AgentStreamChunk` frames.
+
+## Agent Kernel
+
+`defineAgent(config)` accepts a model string, a system prompt, a tool set, and optional sampling knobs (`temperature`, `maxTokens`, `headers`, `provider`, `context`). It returns a `UbeanAgent`:
+
+| Member          | Description                                                                              |
+| --------------- | ---------------------------------------------------------------------------------------- |
+| `config`        | The resolved agent configuration.                                                        |
+| `run(input)`    | Await the full result: `{ text, output?, toolResults, usage? }`.                         |
+| `stream(input)` | `AsyncIterable<AgentStreamChunk>` — text deltas, tool calls, tool results, errors, done. |
+| `asHandler()`   | A Hono `Handler` that streams the agent over SSE.                                        |
+
+Providers are resolved by `model` string. Register one with `defineProvider`, or set a default through `configureAI`:
+
+```ts
+import { configureAI, defineProvider, resolveModel } from '@ubean/ai';
+
+defineProvider({
+  id: 'my-proxy',
+  kind: 'openai-compatible',
+  baseURL: 'https://gateway.internal/v1',
+  apiKey: process.env.MY_PROXY_KEY,
+  modelAliases: { chat: 'deepseek-chat' }
+});
+
+configureAI({ defaultProvider: 'my-proxy', defaultModel: 'chat' });
+
+const { provider, modelId } = resolveModel('chat');
+```
+
+`defineProvider` is idempotent per `id` and ignores ids containing `/` (those are treated as explicit `provider/model` strings). When no provider matches, `resolveModel` throws:
+
+```
+[@ubean/ai] No provider resolved for "<model>". Define a provider via defineProvider() or configure a default with configureAI().
+```
+
+If nothing is configured, an environment fallback provider (`id: 'env'`, `kind: 'openai-compatible'`) is used, taking its key from `DEEPSEEK_API_KEY || UBEAN_AI_API_KEY || OPENAI_API_KEY` and its base URL from `UBEAN_AI_API_BASE` (default `https://api.deepseek.com/v1`).
+
+## Vue Runtime
+
+`@ubean/ai/runtime/vue` is a self-built, SSR-safe SSE consumer. It does not depend on `@ai-sdk/vue`.
+
+```ts
+import { useChat } from '@ubean/ai/runtime/vue';
+
+const { messages, input, setInput, sendMessage, status, error, isStreaming, abort, reload } = useChat({
+  url: '/api/chat'
+});
+```
+
+| Composable         | Returns                                                                                       |
+| ------------------ | --------------------------------------------------------------------------------------------- |
+| `useChat(options)` | `{ messages, status, error, input, data, setInput, sendMessage, abort, reload, isStreaming }` |
+| `useAgent(agent)`  | `{ isStreaming, error, result, chunks, run, stream }` — drives an in-process `UbeanAgent`     |
+| `useAIProvider()`  | `{ defaultProvider?, defaultModel? }` — the runtime provider configuration                    |
+
+`useChat` defaults its `url` to the relative `./chat`, POSTs `{ ...body, messages }`, and parses `AgentStreamChunk` frames into `ChatMessage[]`. Set the runtime provider defaults with `setAIProviderConfig({ defaultProvider, defaultModel })`.
+
+## Gateway Presets
+
+`@ubean/ai/gateway` exports provider definitions you can register directly:
+
+```ts
+import { defineProvider } from '@ubean/ai';
+import { deepseek, openrouter, allGatewayProviders } from '@ubean/ai/gateway';
+
+for (const provider of allGatewayProviders) defineProvider(provider);
+```
+
+| Export       | Provider id  | Base URL                       |
+| ------------ | ------------ | ------------------------------ |
+| `deepseek`   | `deepseek`   | `https://api.deepseek.com/v1`  |
+| `openrouter` | `openrouter` | `https://openrouter.ai/api/v1` |
+| `omniRoute`  | `omniroute`  | `http://localhost:8080/v1`     |
+| `openai`     | `openai`     | `https://api.openai.com/v1`    |
+| `anthropic`  | `anthropic`  | —                              |
+| `google`     | `google`     | —                              |
+| `groq`       | `groq`       | —                              |
+
+> This subpath provides presets only. It does not implement gateway-level routing, fallback or cost optimization — that belongs to an external gateway such as OmniRoute.
+
+## Vite Plugin
+
+The `ai` field in `ubean.config.ts` wires the module for you. When you need explicit control, use the plugin directly:
+
+```ts
+import { ubeanAiPlugin, defineAiConfig } from '@ubean/ai/vite';
+
+export default defineConfig({
+  plugins: [ubeanAiPlugin(defineAiConfig({ defaultProvider: 'deepseek' }))]
+});
+```
+
+The plugin registers the provider presets via `defineProvider`, registers a component resolver for `useChat` / `useAgent` / `useAIProvider` from `@ubean/ai/runtime/vue`, generates `virtual:ubean-ai/runtime`, and adds the runtime packages to `optimizeDeps.include`. It does **not** start a dev gateway proxy.
+
+## Type Safety
+
+- `AgentTool<TInput>` carries the Valibot schema, so `execute(args, ctx)` is inferred from `input` — no casts, no manual generics.
+- `defineAgentTool` is an identity function whose only job is to preserve that inference.
+- `defineAgent<T>(config)` types `AgentRunResult<T>.output` and `AgentRunResult<T>.text`.
+- `AgentStreamChunk` is a discriminated union on `type` (`'text-delta' | 'tool-call' | 'tool-result' | 'error' | 'done'`), so exhaustive switches work in the `stream()` consumer.
+- `UbeanAgent.asHandler()` returns a Hono `Handler`, which keeps route typing intact when mounted from `src/routes/`.
+
+## Architecture Notes
+
+- **Thin over the AI SDK.** ubean owns declaration and orchestration; the agent loop, tool-calling protocol and streaming primitives come from `ai`.
+- **Lazy AI SDK import.** Missing peers never break the module graph — they fail at execution with an actionable message.
+- **`v` is valibot.** The namespace re-export exists so tool schemas and the agent config can come from one import.
+- **Streaming protocol is the contract.** `AgentStreamChunk` is what both `stream()` and the Vue runtime speak, which is why `useChat` can consume any agent's SSE endpoint.
+- **Rendering is out of scope.** The runtime returns structured messages and chunks; bring your own markdown/code renderer.
+- **No gateway implementation.** Presets are data; routing policy stays outside the framework.

package/README.zh-CN.md

@@ -0,0 +1,251 @@
+# @ubean/ai
+
+**[English](./README.md) | 中文**
+
+ubean 框架的 AI 大模型集成 —— 一层薄编排，底层是 Vercel AI SDK。
+
+```ts
+import { defineAgent, defineAgentTool, v } from '@ubean/ai';
+
+const weather = defineAgentTool({
+  name: 'get_weather',
+  description: 'Get the weather for a city',
+  input: v.object({ city: v.string() }),
+  execute: async ({ city }) => ({ city, temperature: 21 })
+});
+
+const agent = defineAgent({ model: 'deepseek-chat', tools: { weather } });
+```
+
+## 目录
+
+- [@ubean/ai](#ubeanai)
+  - [包定位](#包定位)
+  - [安装](#安装)
+  - [快速开始](#快速开始)
+  - [Agent 内核](#agent-内核)
+  - [Vue 运行时](#vue-运行时)
+  - [Gateway 预设](#gateway-预设)
+  - [Vite 插件](#vite-插件)
+  - [类型安全](#类型安全)
+  - [架构说明](#架构说明)
+
+## 包定位
+
+| 分层                    | 职责                                                            |
+| ----------------------- | --------------------------------------------------------------- |
+| `@ubean/ai`（内核）     | provider 注册表、agent 定义、工具定义、流式 chunk 协议          |
+| `@ubean/ai/runtime/vue` | 消费 agent 暴露的 SSE 流的 Vue composable                       |
+| `@ubean/ai/gateway`     | 仅提供 provider 预设 —— 常见托管服务的 base URL 与 id           |
+| `@ubean/ai/vite`        | 模块接线：注册 provider、自动导入 composable、补 `optimizeDeps` |
+
+**包含：**
+
+- `defineProvider` / `configureAI` / `resolveModel` —— 把 `model` 字符串解析为具体的 provider + model id。
+- `defineAgent` —— 声明 system prompt、model、工具集、步数预算与采样参数；返回带 `run()`、`stream()`、`asHandler()` 的 `UbeanAgent`。
+- `defineAgentTool` —— 类型安全的恒等辅助函数，让 Valibot schema 推导出的输入类型保留到 `execute(args, ctx)` 上。
+- `v` —— **valibot** 的命名空间重导出，用于编写工具输入 schema。
+- `useChat` / `useAgent` / `useAIProvider` —— Vue 运行时。
+- DeepSeek、OpenRouter、OmniRoute、OpenAI、Anthropic、Google、Groq 的 provider 预设。
+
+**不包含**（刻意为之）：
+
+- 不提供网关服务。`@ubean/ai/gateway` 给的是 provider _预设_，不是路由、回退或成本优化 —— 需要这些能力请在前面接外部网关（例如 OmniRoute）。
+- 不含 UI 层。Markdown 渲染、代码高亮、消息气泡都不在本包范围内；在 `useChat` 的消费侧自选渲染器。
+- 不实现 agent 循环。工具调用循环、重试与流式原语来自 Vercel AI SDK（`ai`）；ubean 只负责声明与编排。
+- 不生成 HTTP 路由文件。`asHandler()` 的结果就是一个普通 Hono handler —— 由你挂到 `src/routes/`，与 `@ubean/routes` 记录的 API 路由写法一致。
+
+**运行时依赖白名单（主入口）：** `@valibot/to-json-schema`、`valibot`。AI SDK 本体（`ai`、`@ai-sdk/openai-compatible`）为懒加载。
+
+**可选 peer：** `ai`、`@ai-sdk/openai-compatible`、`hono`、`vite`、`vue`。所有 peer 均为可选 —— 缺少它们时包依然能构建和导入。若 agent 真正执行时 AI SDK 缺失，调用会带安装提示直接 reject：
+
+```
+[@ubean/ai] The AI SDK packages are not installed. Install them with:
+pnpm add ai @ai-sdk/openai-compatible (or npm/yarn/bun equivalent).
+```
+
+## 安装
+
+```bash
+# ubean 侧的编排层
+pnpm add @ubean/ai
+
+# AI SDK 运行时 —— agent 执行时必需
+pnpm add ai @ai-sdk/openai-compatible
+
+# 只在用到对应能力时才需要的 peer
+pnpm add vue        # @ubean/ai/runtime/vue
+pnpm add hono       # UbeanAgent.asHandler()
+```
+
+## 快速开始
+
+**1. 启用模块**
+
+```ts
+// ubean.config.ts
+import { defineConfig } from 'ubean';
+
+export default defineConfig({
+  ai: true // 或 ai: { defaultProvider: 'deepseek', defaultModel: 'deepseek-chat' }
+});
+```
+
+**2. 定义工具**
+
+工具输入是 Valibot schema，因此 `execute` 收到的参数对象类型是完整推导出来的。
+
+```ts
+// src/server/ai/tools.ts
+import { defineAgentTool, v } from '@ubean/ai';
+
+export const searchDocs = defineAgentTool({
+  name: 'search_docs',
+  description: 'Search the documentation index for a query',
+  input: v.object({
+    query: v.string(),
+    limit: v.optional(v.pipe(v.number(), v.integer()), 5)
+  }),
+  execute: async ({ query, limit }, ctx) => {
+    ctx.signal?.throwIfAborted();
+    return { query, limit, hits: [] };
+  }
+});
+```
+
+**3. 定义 agent**
+
+```ts
+// src/server/ai/agent.ts
+import { defineAgent } from '@ubean/ai';
+import { searchDocs } from './tools';
+
+export const supportAgent = defineAgent<{ answer: string }>({
+  model: 'deepseek-chat',
+  system: 'You are a documentation assistant. Cite the docs you used.',
+  tools: { searchDocs },
+  maxSteps: 5
+});
+```
+
+**4. 通过 HTTP 暴露**
+
+```ts
+// src/routes/api/chat.ts
+import { supportAgent } from '~/server/ai/agent';
+
+export const POST = supportAgent.asHandler();
+```
+
+`asHandler()` 把请求体读作 `AgentInput`，并以 Server-Sent Events 流的形式返回 `AgentStreamChunk` 帧。
+
+## Agent 内核
+
+`defineAgent(config)` 接受 model 字符串、system prompt、工具集，以及可选的采样参数（`temperature`、`maxTokens`、`headers`、`provider`、`context`）。返回的 `UbeanAgent`：
+
+| 成员            | 说明                                                                            |
+| --------------- | ------------------------------------------------------------------------------- |
+| `config`        | 解析后的 agent 配置。                                                           |
+| `run(input)`    | 等待完整结果：`{ text, output?, toolResults, usage? }`。                        |
+| `stream(input)` | `AsyncIterable<AgentStreamChunk>` —— 文本增量、工具调用、工具结果、错误、结束。 |
+| `asHandler()`   | 通过 SSE 流式输出该 agent 的 Hono `Handler`。                                   |
+
+provider 由 `model` 字符串解析。用 `defineProvider` 注册，或用 `configureAI` 设置默认值：
+
+```ts
+import { configureAI, defineProvider, resolveModel } from '@ubean/ai';
+
+defineProvider({
+  id: 'my-proxy',
+  kind: 'openai-compatible',
+  baseURL: 'https://gateway.internal/v1',
+  apiKey: process.env.MY_PROXY_KEY,
+  modelAliases: { chat: 'deepseek-chat' }
+});
+
+configureAI({ defaultProvider: 'my-proxy', defaultModel: 'chat' });
+
+const { provider, modelId } = resolveModel('chat');
+```
+
+`defineProvider` 按 `id` 幂等，并会忽略含 `/` 的 id（这类字符串被当作显式的 `provider/model`）。没有匹配到 provider 时，`resolveModel` 抛出：
+
+```
+[@ubean/ai] No provider resolved for "<model>". Define a provider via defineProvider() or configure a default with configureAI().
+```
+
+若完全未配置，则使用环境变量回退 provider（`id: 'env'`、`kind: 'openai-compatible'`）：密钥取自 `DEEPSEEK_API_KEY || UBEAN_AI_API_KEY || OPENAI_API_KEY`，base URL 取自 `UBEAN_AI_API_BASE`（默认 `https://api.deepseek.com/v1`）。
+
+## Vue 运行时
+
+`@ubean/ai/runtime/vue` 是自研的、SSR 安全的 SSE 消费者，不依赖 `@ai-sdk/vue`。
+
+```ts
+import { useChat } from '@ubean/ai/runtime/vue';
+
+const { messages, input, setInput, sendMessage, status, error, isStreaming, abort, reload } = useChat({
+  url: '/api/chat'
+});
+```
+
+| Composable         | 返回值                                                                                        |
+| ------------------ | --------------------------------------------------------------------------------------------- |
+| `useChat(options)` | `{ messages, status, error, input, data, setInput, sendMessage, abort, reload, isStreaming }` |
+| `useAgent(agent)`  | `{ isStreaming, error, result, chunks, run, stream }` —— 驱动进程内的 `UbeanAgent`            |
+| `useAIProvider()`  | `{ defaultProvider?, defaultModel? }` —— 运行时 provider 配置                                 |
+
+`useChat` 的 `url` 默认是相对路径 `./chat`，POST `{ ...body, messages }`，并把 `AgentStreamChunk` 帧解析为 `ChatMessage[]`。运行时 provider 默认值通过 `setAIProviderConfig({ defaultProvider, defaultModel })` 设置。
+
+## Gateway 预设
+
+`@ubean/ai/gateway` 导出的 provider 定义可直接注册：
+
+```ts
+import { defineProvider } from '@ubean/ai';
+import { deepseek, openrouter, allGatewayProviders } from '@ubean/ai/gateway';
+
+for (const provider of allGatewayProviders) defineProvider(provider);
+```
+
+| 导出         | provider id  | Base URL                       |
+| ------------ | ------------ | ------------------------------ |
+| `deepseek`   | `deepseek`   | `https://api.deepseek.com/v1`  |
+| `openrouter` | `openrouter` | `https://openrouter.ai/api/v1` |
+| `omniRoute`  | `omniroute`  | `http://localhost:8080/v1`     |
+| `openai`     | `openai`     | `https://api.openai.com/v1`    |
+| `anthropic`  | `anthropic`  | —                              |
+| `google`     | `google`     | —                              |
+| `groq`       | `groq`       | —                              |
+
+> 该子路径只提供预设。它不实现网关级的路由、回退或成本优化 —— 那些属于外部网关（如 OmniRoute）。
+
+## Vite 插件
+
+`ubean.config.ts` 里的 `ai` 字段会替你完成接线。需要显式控制时直接使用插件：
+
+```ts
+import { ubeanAiPlugin, defineAiConfig } from '@ubean/ai/vite';
+
+export default defineConfig({
+  plugins: [ubeanAiPlugin(defineAiConfig({ defaultProvider: 'deepseek' }))]
+});
+```
+
+插件会通过 `defineProvider` 注册 provider 预设，为来自 `@ubean/ai/runtime/vue` 的 `useChat` / `useAgent` / `useAIProvider` 注册组件解析器，生成 `virtual:ubean-ai/runtime`，并把运行时包加入 `optimizeDeps.include`。它**不会**启动 dev 网关代理。
+
+## 类型安全
+
+- `AgentTool<TInput>` 携带 Valibot schema，因此 `execute(args, ctx)` 的参数由 `input` 推导 —— 无需断言，也无需手写泛型。
+- `defineAgentTool` 是恒等函数，唯一职责就是保留这份推导。
+- `defineAgent<T>(config)` 为 `AgentRunResult<T>.output` 与 `AgentRunResult<T>.text` 提供类型。
+- `AgentStreamChunk` 是按 `type` 判别的联合类型（`'text-delta' | 'tool-call' | 'tool-result' | 'error' | 'done'`），因此 `stream()` 消费侧可以做穷尽分支。
+- `UbeanAgent.asHandler()` 返回 Hono `Handler`，从 `src/routes/` 挂载时路由类型保持完整。
+
+## 架构说明
+
+- **薄封装 AI SDK。** ubean 负责声明与编排；agent 循环、工具调用协议与流式原语来自 `ai`。
+- **AI SDK 懒加载。** 缺少 peer 不会破坏模块图 —— 只会在执行时以可操作的提示失败。
+- **`v` 就是 valibot。** 命名空间重导出让工具 schema 与 agent 配置来自同一次 import。
+- **流式协议即契约。** `AgentStreamChunk` 是 `stream()` 与 Vue 运行时共同使用的语言，`useChat` 因此能消费任意 agent 的 SSE 端点。
+- **渲染不在范围内。** 运行时返回结构化的消息与 chunk；markdown/代码渲染器由你自备。
+- **不实现网关。** 预设只是数据；路由策略留在框架之外。

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ubean/ai",
-  "version": "0.6.2",
+  "version": "0.6.4",
   "description": "AI large-model integration for the ubean framework: defineAgent + defineAgentTool + Vue runtime (thin orchestration over the Vercel AI SDK)",
   "files": [
     "dist"
@@ -28,7 +28,7 @@
     }
   },
   "dependencies": {
-    "@ubean/build": "0.6.2",
+    "@ubean/build": "0.6.4",
     "@valibot/to-json-schema": "^1.8.0",
     "valibot": "^1.5.0"
   },
@@ -36,9 +36,9 @@
     "@types/node": "^26.6.5",
     "hono": "4.13.13",
     "typescript": "npm:typescript-native-bridge@latest",
-    "vite": "npm:@voidzero-dev/vite-plus-core@1.1.0",
-    "vite-plus": "1.1.0",
-    "vue": "^3.5.43"
+    "vite": "npm:@voidzero-dev/vite-plus-core@1.3.0",
+    "vite-plus": "1.3.0",
+    "vue": "^3.5.44"
   },
   "peerDependencies": {
     "@ai-sdk/openai-compatible": "^1.0.0 || ^2.0.0 || ^3.0.0",