mono项目开发模板，内置cli管理构建

dash 695000b710 feat: add xllm package with streaming provider adapters Introduce @dm/xllm with a unified request/response model, streaming AsyncIterable events, and adapter-based support for OpenAI-compatible and DeepSeek backends. Add an example integration that demonstrates provider/model switching via Vite env variables and direct stream output consumption. Made-with: Cursor		3 months ago
..
src	feat: add xllm package with streaming provider adapters	3 months ago
README.md	feat: add xllm package with streaming provider adapters	3 months ago
package.json	feat: add xllm package with streaming provider adapters	3 months ago
vitest.config.ts	feat: add xllm package with streaming provider adapters	3 months ago

README.md

@dm/xllm

统一的大模型请求库，支持：

流式输出（for await...of）
OpenAI-Compatible 与 DeepSeek 供应商适配
文本、多模态输入（图片 URL）、工具调用结构统一

快速开始

import { createXllm } from "@dm/xllm";

const xllm = createXllm({
  provider: "deepseek",
  model: "deepseek-chat",
  apiKey: process.env.DEEPSEEK_API_KEY,
});

for await (const event of xllm.stream({
  messages: [{ role: "user", content: [{ type: "text", text: "你好" }] }],
})) {
  if (event.type === "text.delta") process.stdout.write(event.text);
}