@aigne/core 1.13.0 → 1.15.0

package/CHANGELOG.md

@@ -22,6 +22,33 @@
 * rename @aigne/core-next to @aigne/core ([3a81009](https://github.com/AIGNE-io/aigne-framework/commit/3a8100962c81813217b687ae28e8de604419c622))
 * use text resource from MCP correctly ([8b9eba8](https://github.com/AIGNE-io/aigne-framework/commit/8b9eba83352ec096a2a5d4f410d4c4bde7420bce))
 
+## [1.15.0](https://github.com/AIGNE-io/aigne-framework/compare/core-v1.14.0...core-v1.15.0) (2025-05-15)
+
+
+### Features
+
+* optimize the stability of the model and ci ([#119](https://github.com/AIGNE-io/aigne-framework/issues/119)) ([de93887](https://github.com/AIGNE-io/aigne-framework/commit/de938879452a8be82a198dda0eda1eb9fcbb0474))
+
+
+### Bug Fixes
+
+* **core:** response.headers.toJSON is not a function ([#121](https://github.com/AIGNE-io/aigne-framework/issues/121)) ([4609ba6](https://github.com/AIGNE-io/aigne-framework/commit/4609ba645e6b8fe8d76ecd475cd2d7817483a4bd))
+
+## [1.14.0](https://github.com/AIGNE-io/aigne-framework/compare/core-v1.13.0...core-v1.14.0) (2025-05-12)
+
+
+### Features
+
+* **docs:** use typedoc build and publish docs to gh-pages ([#100](https://github.com/AIGNE-io/aigne-framework/issues/100)) ([b9074c0](https://github.com/AIGNE-io/aigne-framework/commit/b9074c0148ea343ada92b5919a52b47537a1ad48))
+* **memory:** allow agents to act as retrievers and recorders in memory ([#65](https://github.com/AIGNE-io/aigne-framework/issues/65)) ([2bafcbb](https://github.com/AIGNE-io/aigne-framework/commit/2bafcbb66a94fcf55dad8c21ede483eaf075c11d))
+* optimize the stability of ci and example ([#113](https://github.com/AIGNE-io/aigne-framework/issues/113)) ([d16ed6c](https://github.com/AIGNE-io/aigne-framework/commit/d16ed6cb60faea19fb4f1c12e1f83d69563b153f))
+
+
+### Bug Fixes
+
+* **core:** default catch tool's error and continue processing ([#115](https://github.com/AIGNE-io/aigne-framework/issues/115)) ([983b0de](https://github.com/AIGNE-io/aigne-framework/commit/983b0de491afb3f0904e145cb491d432b62f9312))
+* **core:** handle response for UserAgent automatically in pub/sub mode ([#116](https://github.com/AIGNE-io/aigne-framework/issues/116)) ([b659714](https://github.com/AIGNE-io/aigne-framework/commit/b659714f2398ea042f21cb22eccc1014f181cd46))
+
 ## [1.13.0](https://github.com/AIGNE-io/aigne-framework/compare/core-v1.12.0...core-v1.13.0) (2025-04-30)
 
 

package/README.md

@@ -6,7 +6,7 @@
 [![NPM Version](https://img.shields.io/npm/v/@aigne/core)](https://www.npmjs.com/package/@aigne/core)
 [![Elastic-2.0 licensed](https://img.shields.io/npm/l/@aigne/core)](https://github.com/AIGNE-io/aigne-framework/blob/main/LICENSE)
 
-**English** | [中文](README.zh.md)
+**English** | [中文](./README.zh.md)
 
 Core library of [AIGNE Framework](https://github.com/AIGNE-io/aigne-framework) for building AI-powered applications.
 
@@ -16,7 +16,7 @@ Core library of [AIGNE Framework](https://github.com/AIGNE-io/aigne-framework) f
 
 ## Features
 
-- **Multiple AI Model Support**: Built-in support for OpenAI, Gemini, Claude, and other mainstream AI models, easily extensible to support additional models
+- **Multiple AI Model Support**: Built-in support for OpenAI, Gemini, Claude, Nova, and other mainstream AI models, easily extensible to support additional models
 - **Agent System**: Powerful agent abstractions supporting AI agents, function agents, MCP agents, and more
 - **AIGNE Environment**: Flexible handling communication between agents and workflow execution
 - **Workflow Patterns**: Support for sequential, concurrent, routing, handoff, and other workflow patterns
@@ -25,14 +25,21 @@ Core library of [AIGNE Framework](https://github.com/AIGNE-io/aigne-framework) f
 
 ## Installation
 
+### Using npm
+
 ```bash
-# Using npm
 npm install @aigne/core
+```
+
+### Using yarn
 
-# Using yarn
+```bash
 yarn add @aigne/core
+```
+
+### Using pnpm
 
-# Using pnpm
+```bash
 pnpm add @aigne/core
 ```
 
@@ -54,7 +61,7 @@ const agent = AIAgent.from({
   instructions: "You are a helpful assistant.",
 });
 
-// Create AIGNE
+// AIGNE: Main execution engine of AIGNE Framework.
 const aigne = new AIGNE({ model });
 
 // Use the AIGNE to invoke the agent
@@ -65,26 +72,6 @@ const response = await userAgent.invoke("Hello, can you help me write a short ar
 console.log(response);
 ```
 
-## Module Structure
-
-- `agents/`: Agent implementations, including AI agents, function agents, MCP agents, etc.
-- `aigne/`: AIGNE is agents execution environment
-- `loader/`: Loader-related functionality
-- `models/`: Integration with various AI models
-- `prompt/`: Prompt handling functionality
-- `utils/`: Utility functions and helper methods
-
-## Documentation
-
-For more detailed API documentation, please refer to:
-
-- [Agent API](../../docs/apis/agent-api.md)
-- [AI Agent API](../../docs/apis/ai-agent-api.md)
-- [Function Agent API](../../docs/apis/function-agent-api.md)
-- [MCP Agent API](../../docs/apis/mcp-agent-api.md)
-- [AIGNE API](../../docs/apis/aigne-api.md)
-- [Server/Client API](../../docs/apis/server-client-api.md)
-
 ## License
 
 Elastic-2.0

package/README.zh.md

@@ -6,33 +6,40 @@
 [![NPM Version](https://img.shields.io/npm/v/@aigne/core)](https://www.npmjs.com/package/@aigne/core)
 [![Elastic-2.0 licensed](https://img.shields.io/npm/l/@aigne/core)](https://github.com/AIGNE-io/aigne-framework/blob/main/LICENSE)
 
-[English](README.md) | **中文**
+[English](./README.md) | **中文**
 
-[AIGNE 框架](https://github.com/AIGNE-io/aigne-framework)的核心库，用于构建 AI 驱动的应用程序。
+[AIGNE Framework](https://github.com/AIGNE-io/aigne-framework) 的核心库，用于构建 AI 驱动的应用程序。
 
 ## 简介
 
-`@aigne/core` 是 [AIGNE 框架](https://github.com/AIGNE-io/aigne-framework)的基础核心组件，提供了构建 AI 驱动应用程序所需的基本模块和工具。该包实现了框架的核心功能，包括代理系统、执行引擎、模型集成以及工作流模式支持等。
+`@aigne/core` 是 [AIGNE Framework](https://github.com/AIGNE-io/aigne-framework) 的基础组件，提供构建 AI 驱动应用程序所需的核心模块和工具。该包实现了框架的核心功能，包括代理系统、aigne 环境、模型集成和工作流模式支持。
 
 ## 特性
 
-- **多种 AI 模型支持**：内置支持 OpenAI、Gemini、Claude 等主流 AI 模型，可轻松扩展支持其他模型
-- **代理系统**：强大的代理抽象，支持 AI 代理、函数代理、MCP 代理等多种类型
-- **执行引擎**：灵活的执行引擎，处理代理之间的通信和工作流执行
+- **多 AI 模型支持**：内置支持 OpenAI、Gemini、Claude、Nova 等主流 AI 模型，可轻松扩展支持其他模型
+- **代理系统**：强大的代理抽象，支持 AI 代理、功能代理、MCP 代理等
+- **AIGNE 环境**：灵活处理代理之间的通信和工作流执行
 - **工作流模式**：支持顺序、并发、路由、交接等多种工作流模式
-- **MCP 协议集成**：通过模型上下文协议（Model Context Protocol）实现与外部系统的无缝集成
-- **TypeScript 支持**：完善的类型定义，提供良好的开发体验
+- **MCP 协议集成**：通过模型上下文协议与外部系统无缝集成
+- **TypeScript 支持**：全面的类型定义，提供出色的开发体验
 
 ## 安装
 
+### 使用 npm
+
 ```bash
-# 使用 npm
 npm install @aigne/core
+```
+
+### 使用 yarn
 
-# 使用 yarn
+```bash
 yarn add @aigne/core
+```
+
+### 使用 pnpm
 
-# 使用 pnpm
+```bash
 pnpm add @aigne/core
 ```
 
@@ -50,41 +57,21 @@ const model = new OpenAIChatModel({
 
 // 创建 AI 代理
 const agent = AIAgent.from({
-  name: "助手",
-  instructions: "你是一个有帮助的助手。",
+  name: "Assistant",
+  instructions: "You are a helpful assistant.",
 });
 
-// 创建执行引擎
+// AIGNE: AIGNE Framework 的主要执行引擎
 const aigne = new AIGNE({ model });
 
-// 使用执行引擎调用代理
+// 使用 AIGNE 调用代理
 const userAgent = await aigne.invoke(agent);
 
 // 向代理发送消息
-const response = await userAgent.invoke("你好，能帮我写一篇短文吗？");
+const response = await userAgent.invoke("Hello, can you help me write a short article?");
 console.log(response);
 ```
 
-## 模块结构
-
-- `agents/`: 代理相关的实现，包括 AI 代理、函数代理、MCP 代理等
-- `aigne/`: AIGNE 提供 Agents 执行环境
-- `loader/`: 加载器相关功能
-- `models/`: 各种 AI 模型的集成
-- `prompt/`: 提示词处理相关功能
-- `utils/`: 工具函数和辅助方法
-
-## 文档
-
-更多详细的 API 文档，请参考：
-
-- [Agent API](../../docs/apis/agent-api.zh.md)
-- [AI Agent API](../../docs/apis/ai-agent-api.zh.md)
-- [Function Agent API](../../docs/apis/function-agent-api.zh.md)
-- [MCP Agent API](../../docs/apis/mcp-agent-api.zh.md)
-- [AIGNE API](../../docs/apis/aigne-api.zh.md)
-- [服务器/客户端 API](../../docs/apis/server-client-api.zh.md)
-
-## 协议
+## 许可证
 
 Elastic-2.0