LangChain(@LangChainAI)
Cursor, Copilot, Pi, and OpenCode tracing: Now in LangSmith. Full session observability, no extra i...
8.5内容质量
TL;DR · AI 摘要
LangSmith新增对Cursor、Copilot等代码代理的全会话追踪功能,支持无需额外配置的稳定键标识与运行树分析。
核心要点
- LangSmith支持Cursor/Copilot/Pi/OpenCode四款代码代理的统一追踪
- 通过稳定键可跨代理查询追踪数据,无需额外仪器化
- 内置会话级token消耗统计与成本分析功能
结构提纲
按章节快速跳转。
思维导图
用一张图看清主题之间的关系。
查看大纲文本(无障碍 / 无 JS 友好)
- LangSmith代码代理追踪
- 核心功能
- 全会话可观测性
- 稳定键标识
- 运行树分析
- 附加能力
- token统计
- 成本分析
金句 / Highlights
值得收藏与分享的关键句。
无需额外仪器化即可实现全会话可观测性,简化调试流程
稳定键机制使不同代理的追踪数据可统一查询和分组
运行树视图包含模型调用、工具和子代理的完整执行路径
内置token消耗统计功能可直接生成会话成本分析报告
#LangSmith#代码代理#可观测性#调试工具
打开原文LangChain on X: "Cursor, Copilot, Pi, and OpenCode tracing: Now in LangSmith. Full session observability, no extra instrumentation. ✅Identify, group, and query any coding-agent trace with the same stable keys, regardless of which agent produced it ✅See the full run tree: turns, model calls," / X
@LangChain
Cursor, Copilot, Pi, and OpenCode tracing: Now in LangSmith. Full session observability, no extra instrumentation. ✅Identify, group, and query any coding-agent trace with the same stable keys, regardless of which agent produced it ✅See the full run tree: turns, model calls, tools, and subagents ✅Token usage and cost per session, out of the box Blog by
@
harisaiharish
langchain.com/blog/your-codi…
How to Debug Coding Agents with LangSmith Traces
From langchain.com
5:01 PM · Jul 14, 2026
14.4K
Views
6
1
2
12
4
41
3
33
Read 6 replies