面试题库

Codex 与 OpenAI Agents SDK 高效使用

D4 OpenAI Agents SDK：agents、handoffs、guardrails、sessions、tracing

• guardrail 应该放在输入侧还是输出侧？各自的成本、能拦住什么、拦不住什么？Should guardrails sit on the input side or the output side? What does each cost, what does it catch, and what slips through?

  国内高频海外高频深入#agents-sdk#guardrails#safety

  分析过程 · 先想清楚再作答

  1. 题眼在「拦不住什么」。只说两边都要放而不说各自的漏网情况，就是没在生产里被漏网案例打过脸。
  2. 先给分工：输入侧管「该不该做」——话题越界、明显注入、超出服务范围，越早拦越省；输出侧管「能不能说」——泄露敏感信息、格式不合规、违反业务规则，只有模型说完才能查。
  3. 再说成本：输入护栏与主 Agent 并行跑，警报一响就取消主 Agent 的昂贵运行，所以用便宜小模型做输入护栏是省钱手段；输出护栏必须等主 Agent 跑完，省不了钱，只能防事故。
  4. 漏网情况：输入侧拦不住「问题正常但回答跑偏」；输出侧拦不住「模型已经调了有副作用的工具」——所以有副作用的工具需要第三层，围着每次函数调用跑的工具级护栏。
  5. 补一条 SDK 约束：输入护栏只在链条第一个 Agent 上跑，输出护栏只在产出最终回答的 Agent 上跑，挂错位置等于没挂。
  6. 可预期的追问：护栏最常见的失败模式是什么？太严而不是太松——正则黑名单误拦正常用户；上线前要有正常请求的回归集，误拦率是必看指标。

  How to reason about it · think before answering

  1. The crux is 'what slips through'; saying 'use both' without naming each side's blind spot signals no production incidents survived.
  2. Division of labor: input guardrails decide whether to act at all (off-topic, obvious injection, out of scope) and are cheapest early; output guardrails decide whether the answer may be said (leaks, format, policy) and can only run after generation.
  3. Cost: input guardrails run in parallel with the main agent and cancel its expensive run on a tripwire, so a cheap classifier there saves money; output guardrails wait for the full run and only prevent incidents.
  4. Blind spots: input cannot catch a normal question with a drifting answer; output cannot undo a side-effecting tool already called, hence a third layer of tool-level guardrails around each function call.
  5. Add the SDK constraint: input guardrails run only on the first agent, output guardrails only on the agent producing the final answer; misplaced guardrails never execute.
  6. Expect the follow-up: the common failure mode? Too strict, not too loose; regex blocklists over-block real users, so keep a regression set of legitimate requests and watch the false-block rate.

  答题要点

  • 输入侧管该不该做，越早拦越省；输出侧管能不能说，只能事后查
  • 输入护栏与主 Agent 并行、触发即取消，便宜模型在此省钱；输出护栏省不了钱只防事故
  • 输入侧漏「回答跑偏」，输出侧漏「已调有副作用的工具」，需工具级护栏补第三层
  • 输入护栏只在第一个 Agent 生效；常见失败是太严，需正常请求回归集

  Key points

  • Input side decides whether to act and is cheapest early; output side decides what may be said and only runs afterwards
  • Input guardrails run in parallel and cancel the main run, so cheap models save money there; output guardrails only prevent incidents
  • Input misses drifting answers, output misses side effects already taken; tool-level guardrails add the third layer
  • Input guardrails run only on the first agent; the common failure is over-blocking, so keep a regression set

D5 Claude 与 Codex 选型与协作：同一任务双工具实测对比、一个写一个审的混用工作流

• 怎么评价一个 coding agent 这次任务的输出质量，而不只是看它跑没跑通？How do you judge the quality of a coding agent's output on a task, beyond whether it ran?

  国内高频海外高频深入#coding-agent#evaluation#quality

  分析过程 · 先想清楚再作答

  1. 这题考的是你有没有把「测试绿了」当终点。答「看测试」是及格线，区分度在测试之外。
  2. 拆成四层：正确性（测试是否覆盖了需求里的边界，比如 title 超长、done 传字符串）、契约（错误响应形状是否与需求一字不差，还是它自作主张改了）、范围（有没有改不该改的文件、有没有偷偷加依赖或改默认值）、可维护性（校验规则是否抽成常量、测试是否隔离、命名是否与仓库一致）。
  3. 再说怎么量：正确性看它写的测试之外你再补的反例能不能过；契约与范围看 diff 与需求逐条对照；可维护性交给第二家模型或人做结构化审查。
  4. 补一条随机性：单次结果不能下结论，同一需求跑三次看方差，方差大本身就是一个质量信号。
  5. 可预期的追问：它自己说「已完成并通过测试」能信吗？只信你能复现的部分——在你的机器上重跑测试、看 diff，agent 的汇报是线索不是证据。

  How to reason about it · think before answering

  1. This tests whether you treat green tests as the finish line; 'check the tests' is the pass mark, differentiation lies beyond it.
  2. Four layers: correctness (do the tests cover the requirement's edges such as overly long titles or a string for done), contract (does the error shape match the spec exactly or did it improvise), scope (did it touch forbidden files, add dependencies or change defaults silently), maintainability (constants extracted, tests isolated, naming consistent with the repo).
  3. How to measure: correctness by adding your own counterexamples beyond its tests; contract and scope by diffing against the requirement line by line; maintainability via a structured review by a second model or a person.
  4. Add variance: one run proves nothing; run the same requirement three times and treat high variance as a quality signal in itself.
  5. Expect the follow-up: can you trust its 'done, tests pass'? Only what you can reproduce; rerun tests and read the diff yourself, the agent's report is a lead, not evidence.

  答题要点

  • 四层：正确性、契约、范围、可维护性，测试绿只是正确性的一部分
  • 正确性用自己补的反例验证，契约与范围对照需求逐条看 diff，可维护性做结构化审查
  • 同一需求跑多次看方差，方差大本身是质量信号
  • agent 的汇报是线索不是证据，只信自己能复现的部分

  Key points

  • Four layers: correctness, contract, scope, maintainability; green tests cover only part of correctness
  • Verify correctness with your own counterexamples, contract and scope by diffing against the spec, maintainability via structured review
  • Run the same requirement several times; high variance is itself a quality signal
  • The agent's report is a lead, not evidence; trust only what you reproduce