- Split edge service into dedicated modules (control_command, node_command, run_dispatch, status_provider) - Separate OpenAI handlers (chat_handler, ollama_passthrough, routes, stream, strict_output, types) - Archive completed milestone documents (02_edge_service_split, 03+02_openai_surface_split) - Update architecture refactor foundation milestone
- Add field bootstrap user test documentation - Update serving-routing-optimization phase and milestone - Update edge runtime bootstrap and openai server implementation - Add edge/node binaries build script updates - Update config structures and tests - Update architecture and deploy docs - Archive agent task logs for completed sub-tasks
- Add streaming support and load balancing in OpenAI edge server - Enhance Ollama adapter with runtime event handling and health checks - Add new runtime event types for model loading/unloading - Update e2e test script for OpenAI-Ollama flow
필드 테스트를 위해 edge OpenAI-compatible 경로와 node adapter 설정을 확장하고, Jenkins 바이너리 빌드 및 control-plane/web compose 배포 구성을 함께 정리한다.
