AI 智能体
agent-tool-calls-testing
更新于 2026-11-02
Agent Tool Calls · 测试规则
Testing rules for Agent Tool Calls: behaviour-named cases, explicit fixtures and order-independent suites.
- 技术栈
- Agent Tool Calls
- 主题
- 测试
- 条目
- 9 条
- 版本
- v0.2.0
✓ 应当这么做
- ✓ Test the smallest unit that carries the behaviour, then one end-to-end happy path
- ✓ Name tests after the behaviour, not after the function under test
- ✓ Keep fixtures explicit and local to the test that needs them
✕ 常见反模式
- ✕ Asserting on private internals that will change with any refactor
- ✕ Fixed sleeps instead of condition waits
- ✕ Tests that depend on execution order or a shared mutable world
◎ 交付前验证
- ◎ Injection cases added to the adversarial test corpus
- ◎ Tool allow-lists reviewed; new tools default to deny
- ◎ Secrets scanned in output before responding
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