Kotlin Multiplatform ViewModels and reactive state management

Reference implementation of Application Management Framework for demand-driven orchestration based on Kubernetes and ROS 2

Large Result Offloading (LRO) -- a token-aware strategy for managing large tool outputs in LLM context windows. Includes empirical evaluation and formal specification.

Large Result Offloading for MCP servers. Writes oversized tool responses to JSONL files, returning compact descriptors with extraction recipes.