Learn Claude Code
从 0 到 1 构建 nano Claude Code-like agent，每次只加一个机制
核心模式
所有 AI 编程 Agent 共享同一个循环：调用模型、执行工具、回传结果。生产级系统会在其上叠加策略、权限和生命周期层。
@Override
public void run(String... args) {
var scanner = new Scanner(System.in);
var messages = new ArrayList<>();
while (true) {
var response = chatClient
.prompt()
.user(msg)
.call()
.chatResponse();
if (!response.hasToolCalls()) break;
messages.addAll(handleToolCalls(response));
}
}
消息增长
观察 Agent 循环执行时消息数组的增长
学习路径
12 个渐进式课程，从简单循环到隔离化自治执行
The Agent Loop
The minimal agent kernel is a while loop + one tool
Tools
The loop stays the same; new tools register into the dispatch map
TodoWrite
An agent without a plan drifts; list the steps first, then execute
Subagents
Subagents use independent messages[], keeping the main conversation clean
Skills
Inject knowledge via tool_result when needed, not upfront in the system prompt
Compact
Context will fill up; three-layer compression strategy enables infinite sessions
Tasks
A file-based task graph with ordering, parallelism, and dependencies -- the coordination backbone for multi-agent work
Background Tasks
Run slow operations in the background; the agent keeps thinking ahead
Agent Teams
When one agent can't finish, delegate to persistent teammates via async mailboxes
Team Protocols
One request-response pattern drives all team negotiation
Autonomous Agents
Teammates scan the board and claim tasks themselves; no need for the lead to assign each one
Worktree + Task Isolation
Each works in its own directory; tasks manage goals, worktrees manage directories, bound by ID
架构层次
五个正交关注点组合成完整的 Agent