integration — report【免费下载链接】comet-llmDebug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.项目地址: https://gitcode.com/GitHub_Trending/co/comet-llmMode:new | update | maintainLanguage:Python | TypeScriptPattern:method-patching | proxy | callback | OTel exporterEntrypoint:track_name(...)Library version prepared:What was done创建/修改的文件——按 integration / tests / docs 分组准备动作依赖安装、版本固定、fixtures/envVerificationMCP:project 名 读回的 trace ids或 not verified — 原因Tests:N passing — 列出用例; ruff/mypy clean | issuesFlows supported test coverageFlowImplementedTestMCP-verifiedchat.complete(sync, non-stream)✅test_name_complete__happyflow✅ traceidchat.complete_async✅test_name_complete_async__happyflow—chat.stream(sync)✅test_name_stream__happyflow✅ traceidchat.stream_async✅/❌……nested undertrack✅/❌……error →error_infologged✅test_name__error...—token usage captured✅asserted in above✅customproject_name✅/❌param case—Whats NOT supported / limitations有意不打补丁的方法、已实现但未测试的流程、已知缺口、provider 不在 LLMProvider 的注意点、env/后端阻塞Follow-ups建议的下一步更多方法、TS 对应实现、PR 拆分等How to use最小代码片段【免费下载链接】comet-llmDebug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.项目地址: https://gitcode.com/GitHub_Trending/co/comet-llm创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考