AI 智能体
agent-observability-code-review
更新于 2026-07-20
Agent Observability · 代码评审规则
Code-review rules for Agent Observability: risk-first reading, reproducible verification and bounded diffs.
- 技术栈
- Agent Observability
- 主题
- 代码评审
- 条目
- 9 条
- 版本
- v0.2.0
✓ 应当这么做
- ✓ Read the diff risk-first: data changes, auth changes, then everything else
- ✓ Ask for reproducible verification instead of "looks good"
- ✓ Keep review requests under a few hundred lines where possible
✕ 常见反模式
- ✕ Style debates that the formatter should settle
- ✕ Approving migrations without a rollback plan
- ✕ Rubber-stamping config changes that touch production
◎ 交付前验证
- ◎ The new code path is visible in logs end-to-end
- ◎ Dashboard panel added or updated to match the new metric
- ◎ Alert routing tested once end-to-end
同分类条目
42 篇AI 智能体
Vector Search 工程规则
Vector search rules: chunking strategy, recall evaluation and index rebuild path
AI 智能体
Feature Store 工程规则
Feature store rules: point-in-time correctness and train/serve parity
AI 智能体
Agent Skill Design 工程规则
Skill design rules: narrow triggers, explicit boundaries and verifiable outputs
AI 智能体
Agent Tool Calls 工程规则
Tool-call rules: server-side authorisation and deny-by-default allow-lists
AI 智能体
Agent Memory 工程规则
Memory rules: scoped retrieval, expiry and user-visible deletion
AI 智能体
RAG Retrieval 工程规则
RAG rules: citation-grade retrieval and evaluated recall before shipping