如何实现自定义LogCollector，将GRPC请求的时间，ip地址,模型名，推理时间记录到文件中。 不仅要给出C++代码，更要给出如何build镜像的完整流程，并且给出最方便快捷build镜像，搭建开发环境的... - #1

• Analyzed existing TensorFlow Serving logging infrastructure
• Studied LogCollector abstract interface and registration pattern
• Examined existing test implementations for reference
• Create custom FileLogCollector class that extends LogCollector
• Implement CollectMessage to log GRPC request details (timestamp, IP, model name, inference time)
• Add factory registration for the custom log collector
• Create corresponding BUILD file entries
• Add unit tests for the custom log collector
• Update log collector config proto if needed
• Create Docker build instructions and development setup guide
• Test the complete implementation

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.