面试题库
共 328 题,当前筛选 1 题。
课程全部30 天从前端工程师到 Agent 工程师5 天提示词工程零基础Claude 高效使用:从对话到 Claude CodeCodex 与 OpenAI Agents SDK 高效使用7 天 MCP:把工具接进任何 Agent7 天 Agent Skills:把经验做成可复用能力5 天上下文工程14 天 RAG:从检索到可信回答14 天用 Agent 搭一条 AI 短剧生产线
标签
全部#sandbox1#cost14#evaluation14#reliability12#agent-skills11#architecture11#observability10#error-handling9#security9#api-design6#coding-agent6#debugging5
还有 235 个标签收起标签
#idempotency5#streaming5#structured-output5#chunking4#deployment4#distributed-systems4#rag4#system-prompt4#tool-calling4#client3#embeddings3#failure-modes3#ingestion3#mcp3#message-bus3#operations3#progressive-disclosure3#ranking3#timeline3#agent-loop2#agentic-rag2#agents-sdk2#caching2#citations2#code-review2#communication2#concurrency2#consistency2#context2#context-engineering2#context-rot2#cost-control2#data-modeling2#grounding2#hybrid-search2#langgraph2#latency2#model-migration2#model-routing2#multi-agent2#ordering2#pipeline-design2#prompt-basics2#prompt-engineering2#protocol2#rate-limiting2#react2#redis-streams2#responses-api2#retrieval2#retrieval-quality2#routing2#runtime2#sse2#state-management2#statelessness2#subagents2#system-design2#tool-design2#tooling2#tracing2#trade-offs2#transport2#vector-database2#versioning2#workflow2#abstention1#access-control1#agent-design1#agent-quality1#altitude1#approvals1#async1#async-task1#atomicity1#attention-budget1#auth1#av-sync1#behavioral1#bm251#candidate-selection1#capacity-planning1#chain-of-thought1#checkpointing1#ci1#citation-verification1#claude-code1#cli-design1#cloud1#compaction1#compression1#content-hash1#context-compression1#context-window1#contextual-retrieval1#cost-optimization1#cross-model1#dag1#data-quality1#database1#decision-making1#decomposition1#degradation1#deliberate-practice1#design1#diagnostics1#dimensions1#distribution1#docker1#documentation1#engineering-judgement1#engineering-tradeoffs1#eval1#event-driven1#fallback1#fan-out1#ffmpeg1#forking1#four-elements1#framework-design1#framework-selection1#golden-set1#hallucination1#handoffs1#headless1#hnsw1#hybrid1#hyde1#image-generation1#incremental-recompute1#incremental-sync1#index-maintenance1#index-routing1#indexing1#information-retrieval1#instruction-hierarchy1#intent-routing1#interrupt-merge1#interview-prep1#invalidation1#isolation1#ivfflat1#just-in-time1#knowledge-organization1#lease1#llm-as-judge1#llm-output-quality1#long-context1#loop-guard1#media-pipeline1#metadata1#metrics1#mobile1#model-selection1#multi-tenancy1#multimodal1#nodejs1#orchestration1#pagination1#parent-child1#pdf-parsing1#performance1#permissions1#persistence1#pgvector1#pipeline-reliability1#portfolio1#prioritization1#production-readiness1#prompt-assembly1#prompt-caching1#prompt-injection1#prompt-limits1#prompt-techniques1#prompt-template1#prompt-versioning1#provider-abstraction1#quality-check1#quantization1#query-transformation1#quiet-hours1#rank-fusion1#reasoning1#recall1#redis1#reflection1#refusal1#reporting1#reproducibility1#rerank1#retrieval-failure1#retrieval-metrics1#retry1#retry-semantics1#retry-strategy1#review1#rollback1#rrf1#sandboxing1#scalability1#scheduling1#schema-design1#scoping1#scripts1#secrets-management1#self-assessment1#self-presentation1#self-reflection1#service-architecture1#session-management1#sessions1#sharding1#skill-authoring1#skill-description1#skills1#spec1#state-machine1#stateless1#stopping-criteria1#subtitles1#task-graph1#team-governance1#testing1#tool-budget1#tool-execution1#tool-naming1#tools1#tts1#tuning1#ux1#validation1#vector-index1#verification1#workflow-engine1#xml-tags1
Codex 与 OpenAI Agents SDK 高效使用
D1 Codex CLI 入门:安装、AGENTS.md、审批模式与沙箱、常用命令
Codex 把「什么时候问用户」和「能碰到什么」拆成 approval_policy 和 sandbox_mode 两组独立开关。为什么要拆?各自解决什么问题?Codex splits 'when to ask the user' and 'what can be touched' into two independent settings, approval_policy and sandbox_mode. Why separate them, and what does each solve?
国内高频海外高频进阶#coding-agent#security#sandbox分析过程 · 先想清楚再作答
- 题眼是「为什么拆」。只背出每组的取值等于没答,面试官要听的是两者正交带来的好处。
- 先给定义:审批策略是流程控制,决定动作执行前要不要人点头;沙箱是权限控制,决定即使模型想做、操作系统允不允许。
- 再说为什么正交:你可能想要「不打扰我,但绝不许出工作区」(on-request 加 workspace-write),也可能想要「每步都问,但只让它读」(untrusted 加 read-only);合成一个滑杆就表达不了这两种组合。
- 落到实现:沙箱靠操作系统机制(macOS Seatbelt、Linux bubblewrap),不是靠模型自觉,所以它是硬约束;审批则是唯一由人把关的环节。
- 可预期的追问:为什么网络默认关?因为联网是把内部代码送出去或把外部代码拉进来的通道,风险等级和改本地文件不同,需要单独授权。
How to reason about it · think before answering
- The discriminating part is 'why separate'; reciting the values without explaining orthogonality earns little.
- Define both: approval policy is process control, whether a human must nod before an action; sandbox is permission control, whether the OS allows the action at all.
- Then justify orthogonality with combinations a single slider cannot express: 'do not interrupt me but never leave the workspace' versus 'ask every time but read-only'.
- Ground it in implementation: the sandbox uses OS mechanisms (Seatbelt on macOS, bubblewrap on Linux) rather than model goodwill, so it is a hard limit, while approval is the one human checkpoint.
- Expect the follow-up: why is network off by default? Because network is the channel for code leaving or entering the machine, a different risk class from local edits.
答题要点
- approval_policy 管流程:untrusted / on-request / on-failure / never 决定动作前是否要人确认
- sandbox_mode 管权限:read-only / workspace-write / danger-full-access 决定操作系统放行什么
- 两者正交才能表达「不打扰但不越界」和「步步问但只读」这类组合
- 沙箱是操作系统级硬约束,审批是唯一的人工把关点;网络默认关闭需单独放开
Key points
- approval_policy governs process: untrusted / on-request / on-failure / never decide whether a human confirms first
- sandbox_mode governs permission: read-only / workspace-write / danger-full-access decide what the OS allows
- Orthogonality lets you express 'no interruptions but stay in the workspace' and 'ask each step but read-only'
- The sandbox is an OS-level hard limit, approval is the human checkpoint, and network is off by default