shareAI-lab / shareAI-lab/learn-claude-code
缺少程序运行日志???HTML 可视化追踪报告让Agent运行全过程清晰可见、透明可观测!
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 77.2k
- Forks
- 12.4k
- Avg merge
- 2d 5h
- Merged PRs (30d)
- 6
Description
learn-claude-code教程给了我很大帮助,但是实践过程中,弄清楚Agent的每一步输入、输出究竟是什么确实非常困难。
经过不断探索,做到使用可视化日志手段追踪Agent详细执行过程,希望帮助到有同样困难的小伙伴。
希望开发者考虑把可视化日志追踪功能合入
如果你绝对我的工作对你有点帮助,请star,hhh
https://github.com/in-people/learn-claude-code-with-logging-everything
本教程基于 shareAI-lab/learn-claude-code 演变而来。
https://github.com/YYHDBL/MyCodeAgent 项目Trace 追踪给了我很大启发。
核心特色:Agent 运行可视化日志追踪
本教程通过完整的日志追踪系统,帮助读者深入理解 Agent 的每个执行步骤:
📤 发送消息:发送给大模型的消息列表内容。
📥 接收响应:大模型的响应内容和结构。
🔧 工具调用:调用了哪些工具?工具执行结果如何?
📚 技能使用:使用了哪些技能?何时加载的?
🤖 子 Agent 协作:subAgent 如何运行?返回了什么结果?
🗜️ 上下文压缩:何时进行消息压缩?压缩了哪些数据?
📨 团队协作:不同子 Agent 之间传递了哪些数据?
所有这些信息都通过HTML 追踪报告清晰呈现,让 Agent 的"黑盒"变得透明可观测!!!
快速预览HTML追踪报告: all_logs/01_agent_loop/Agent loop log.pdf
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Begin with the linked learn-claude-code-with-logging-everything project and its all_logs/01_agent_loop/Agent loop log.pdf preview; compare its logged agent lifecycle with this repository. The issue names no target files or tests, so confirm the integration scope and acceptance criteria with maintainers; done should mean the requested HTML trace covers the listed agent inputs, outputs, tool and skill use, subagents, compression, and team data.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, observability
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100