ETF Agent’s Six-Layer Request-Processing Map
A technical overview describes ETF Agent’s request flow through six conceptual layers: task input and triggering; identity, session and context; Agent decisions and execution; tools and domain capabilities; result publication and delivery; and the user interface. The report says these layers form a reading map rather than six processes or a fixed pipeline, and that modules can participate across layers without transferring responsibility for permissions, facts or outcomes. Direct responses and background research share underlying capabilities but may take different paths. The portfolio-analysis example is instructional and is not an investment conclusion or live performance result. Implementation status and validation remain subject to each module’s specifications and acceptance records.
The framework provides a concrete way to distinguish model-generated proposals from authorized tool execution, content accepted for publication, and results users can actually read, supporting design analysis and troubleshooting of AI-agent workflows.
六层的价值，不是把模型套进一条固定流水线，而是分清每次交接：谁提出工作、谁判断下一步、谁真正执行，以及哪份结果已经交到用户手中。 本文沿一次请求解释当前实现。六层是阅读地图，不是六个进程；跨层参与也不会改变各模块对权限、事实和效果的责任。
一、一次用户提问，为什么需要六个环节
下面用一个教学场景贯穿主链：用户在聊天框输入“分析我的基金组合，看看行业集中度和汇率风险”。它用于解释调用关系，不是一份投资结论或真实运行成绩。
从界面上看，只发生了一件事：发送消息，然后收到回答。从系统内部看，至少要解决六个不同问题：工作由什么输入或事件触发；该触发归属哪个用户与 Run、允许使用什么上下文；模型准备如何处理；是否需要调用工具；哪些内容真正获准发布；用户界面如何显示或恢复它。