Event ·Multi-source

LangChain ToolRuntime 入门:context、state 与 store 的实际用法

LangChain 在执行工具时会自动注入 ToolRuntime 对象,工具参数分模型填写的普通参数和框架注入的 runtime 两类。文章用 create_agent 和 openai:gpt-4o-mini 的代码示例分别演示三个核心对象:context 通过 context_schema 传入用户 ID 和角色等运行条件,state 保存当前流程的临时数据如消息列表和重试次数,store 用于跨请求保存用户偏好等长期数据。文中还给出通过 AgentMiddleware 扩展 CustomAgentState 来统计模型调用次数的完整示例。

Current read

写 LangChain 智能体经常分不清 context、state、store 各管什么,这篇直接上代码讲清三个对象怎么用,还带限流中间件例子。

11 sources43° AI heatLast updated 2026/11/9 02:28:22

Evidence

11 sources
Primary source掘金本周最热
View source
Related source 3shao__meng
View source
Related source 4@koltregaskes
View source
Related source 5TestingCatalog
View source
Related source 6Gergely Orosz
View source
Related source 8rohanpaul_ai
View source
Related source 9Rest of World
View source
Related source 10marktechpost
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.