面试题库

Claude 高效使用：从对话到 Claude Code

D5 自动化与规模化：headless -p 进 CI、并行会话与 worktree、Writer / Reviewer 双会话、对抗式审查、常见失败模式；Agent SDK 20 行最小 agent

• Agent SDK 和直接调 Messages API 各适合什么场景？它们和 claude -p 是什么关系？When do you use the Claude Agent SDK versus the Messages API directly, and how do both relate to claude -p?

  国内高频海外高频基础#agent-sdk#messages-api

  分析过程 · 先想清楚再作答

  1. 这题考的是分层认知：三个入口底下是同一个模型，差别在于「谁提供循环和工具」。答成「SDK 更高级」没有信息量。
  2. Messages API（@anthropic-ai/sdk / anthropic）：一次请求一次响应，工具由你定义、循环由你写、上下文由你管。适合问答、抽取、分类、结构化输出、带引用的文档问答，以及你想完全掌控循环的自定义 Agent。
  3. Agent SDK（@anthropic-ai/claude-agent-sdk / claude-agent-sdk）：把 Claude Code 打包成库——内置 Read / Edit / Bash / Glob / Grep 等工具、完整的 agent 循环、上下文管理、权限系统、hooks、subagent、会话。你给一句任务和一组选项（allowedTools、permissionMode、maxTurns、systemPrompt），它在文件系统里干活。适合「在自己的程序里嵌一个会改代码的 agent」。
  4. claude -p：同一套 Claude Code 能力的命令行形态，适合 shell 脚本与 CI；Agent SDK 就是它的库形态，官方文档把两者放在同一页讲。判据一句话：要模型调用用 API，要文件系统里的 agent 用 Agent SDK，只想在脚本里调一下用 -p。
  5. 生产视角：Agent SDK 的部署仍是你自己的（它只提供循环，不提供托管），密钥走 ANTHROPIC_API_KEY，不能复用 claude.ai 的订阅登录给第三方产品。可预期的追问：Agent SDK 和 Messages API 里的 tool runner 是不是一回事？不是——tool runner 只帮你跑「你自己定义的工具」的循环，没有内置文件工具。

  How to reason about it · think before answering

  1. This tests layered understanding: all three entry points share one model; the difference is who supplies the loop and the tools. 'The SDK is higher level' says nothing.
  2. Messages API (@anthropic-ai/sdk / anthropic): one request, one response; you define tools, write the loop, manage context. Fits Q&A, extraction, classification, structured output, cited document Q&A, and custom agents where you want full control of the loop.
  3. Agent SDK (@anthropic-ai/claude-agent-sdk / claude-agent-sdk): Claude Code packaged as a library — built-in Read/Edit/Bash/Glob/Grep, the full agent loop, context management, permissions, hooks, subagents, sessions. You pass a task and options (allowedTools, permissionMode, maxTurns, systemPrompt) and it works in the filesystem. Fits embedding a code-editing agent in your own program.
  4. claude -p: the CLI form of the same Claude Code capabilities, for shell scripts and CI; the Agent SDK is its library form and the docs present them together. One-line rule: model call → API; filesystem agent → Agent SDK; quick scripted call → -p.
  5. Production nuance: with the Agent SDK you still own deployment (it supplies the harness, not hosting); auth is ANTHROPIC_API_KEY, and claude.ai subscription login can't be offered to third-party products. Follow-up: is the Agent SDK the same as the Messages API tool runner? No — the tool runner loops over tools you define and has no built-in file tools.

  答题要点

  • Messages API：一问一答，工具与循环自己写；适合问答、抽取、结构化输出、自定义 Agent
  • Agent SDK：Claude Code 的库形态，内置文件与 Bash 工具、循环、权限、hooks；适合嵌入会改代码的 agent
  • claude -p 是同一能力的命令行形态，适合脚本与 CI
  • 部署仍归自己，认证用 ANTHROPIC_API_KEY；tool runner 不是 Agent SDK

  Key points

  • Messages API: request/response, you write tools and the loop; for Q&A, extraction, structured output, custom agents
  • Agent SDK: Claude Code as a library with built-in file/Bash tools, loop, permissions, hooks; for embedding a code-editing agent
  • claude -p is the CLI form of the same capabilities, for scripts and CI
  • You still own deployment; auth via ANTHROPIC_API_KEY; the tool runner is not the Agent SDK