Agent Has No Secret

Table of Contents

I’m PsiACE. My recent work focuses on Agent and RAG: less metaphysics, more getting the feedback loop working, making systems that can explain themselves clearly, run stably, and be replayed and switched.
我是 PsiACE。我最近的工作聚焦于 Agent 和 RAG：少谈玄学，多让反馈循环跑起来，打造能清晰解释自身、稳定运行、可重放和切换的系统。

Agent is not a new religion. It’s still engineering practice with events, queues, and CRUD, plus a layer of model collaboration.
Agent 并不是一种新宗教。它依然是包含事件、队列和 CRUD 的工程实践，只是多了一层模型协作。
Share one EventBus, connect agent.* and huey.* events; print every event immediately; finally use a Cascade tree to review causality and timing.
共享一个 EventBus，连接 agent.* 和 huey.* 事件；立即打印每个事件；最后用 Cascade 树回顾因果关系和时序。
Single-file demo, run immediately: first see events, then see causality, finally see results.
单文件演示，立即运行：先看到事件，再看到因果关系，最后看到结果。

Cascade Viewer

I don’t want to discuss “how to draw a complex Agent architecture diagram” anymore. I care more about “how to make systems explain themselves clearly, fail gracefully, and review transparently”.
我不想再讨论 “如何绘制复杂的 Agent 架构图”。我更关心 “如何让系统清晰自解释、优雅失败并透明可审”。
This article comes with a single-file demo: shared bus, strict ReACT, causality and timing combined, immediate observability. Ready to use.
本文附带一个单文件演示：共享总线、严格 ReACT、因果与时间结合、即时可观测。开箱即用。
Shared EventBus: Agent, ToolExecutor, Storage all publish to the same bus.
共享 EventBus：Agent、ToolExecutor、Storage 都发布到同一个总线。
Strict ReACT: Thought → Action → Action Input → Observation → Final Answer.
严格的 ReACT：Thought → Action → Action Input → Observation → Final Answer。
Causality + Timing: Each user input advances tick; each Observation advances tick; Action → huey.* → Observation is linked through parent-child relationships.
因果关系 + 时序：每次用户输入都会推进 tick；每次 Observation 也会推进 tick；Action → huey.* → Observation 通过父子关系关联。
Immediate Observability: Print every event in real-time; finally use tree-shaped Cascade Viewer for time-based review.
即时可观测：实时打印每个事件；最后用树形 Cascade Viewer 按时间回顾。

huey.queue.* / huey.data.*

No difference: Events, queues, CRUD...