Block a user
DGR-047: Adapt the upstream V4 mHC boundary for ranged ownership
DGR-048: Carry token-ID sideband through the first three hash-routed layers
DGR-039: Pass local two-process dense acceptance
DGR-041: Register native Shard capabilities without redesigning Meshnet
DGR-040: Add node-side native worker supervision
DGR-042: Carry native frames through direct and existing relay seams
DGR-044: Pin the DeepSeek V4 Flash target contract
DGR-043: Expose GGUF compatibility and measured cost inputs to existing routing
DGR-045: Inventory V4 GGUF tensors and layer ownership
DGR-032: Implement deterministic fake
ShardEngine
DGR-033: Build a standalone fake C++ gRPC Shard worker
DGR-034: Implement dense-Llama range-aware GGUF ownership
DGR-035: Implement dense architecture boundary input/output
DGR-038: Implement isolated shard-local Hot KV State
DGR-036: Prove dense fixture and real-model range parity
DGR-037: Bind llama.cpp to the standalone worker
DGR-025: Define exact artifact and runtime recipe identity
DGR-026: Provision exact split-GGUF artifacts outside /home
DGR-027: Add exact llama.cpp provenance manifest and fetch workspace
DGR-028: Implement numbered patch-stack apply and verification