
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Yuga Sun 的博客</title>
      <link>https://yugasun.com/post</link>
      <description>全栈工程师 yugasun 的个人博客</description>
      <language>zh-CN</language>
      <managingEditor>yuga.sun.bj@gmail.com (yugasun)</managingEditor>
      <webMaster>yuga.sun.bj@gmail.com (yugasun)</webMaster>
      <lastBuildDate>Thu, 02 Apr 2026 10:00:00 GMT</lastBuildDate>
      <atom:link href="https://yugasun.com/tags/架构设计/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://yugasun.com/post/agent-harness-architecture</guid>
    <title>Agent Harness：AI Agent 可靠性的真正瓶颈在哪里？</title>
    <link>https://yugasun.com/post/agent-harness-architecture</link>
    <description>构建 AI Agent 最难的部分不是选模型，而是包裹模型运行的那套基础设施：工具调用、上下文管理、错误恢复、状态持久化、权限控制。这篇文章拆解 Agent Harness 的五大支柱，解释每个设计决策背后的原因与取舍。</description>
    <pubDate>Thu, 02 Apr 2026 10:00:00 GMT</pubDate>
    <author>yuga.sun.bj@gmail.com (yugasun)</author>
    <category>AI Agent</category><category>Agent Harness</category><category>LLM</category><category>架构设计</category>
  </item>

  <item>
    <guid>https://yugasun.com/post/claw-code-architecture</guid>
    <title>Claw Code 架构解析：Rust 如何重塑 AI Agent 的可靠性边界</title>
    <link>https://yugasun.com/post/claw-code-architecture</link>
    <description>大多数 AI Agent 框架用 TypeScript 或 Python 构建，Claw Code 选择了 Rust 并基于 Trait 泛型设计了一套完全解耦的运行时架构。这篇文章深入拆解它的核心设计决策：依赖倒置、分层工具系统、分级权限模型、Hook 机制和 MCP 集成。</description>
    <pubDate>Thu, 02 Apr 2026 10:00:00 GMT</pubDate>
    <author>yuga.sun.bj@gmail.com (yugasun)</author>
    <category>AI Agent</category><category>Rust</category><category>架构设计</category><category>Claw Code</category><category>MCP</category>
  </item>

    </channel>
  </rss>
