- Switch from Python to Go for smaller images (~10MB vs ~150MB)
- Add fsnotify for hot reload of secrets without pod restart
- Update status from Proposed to Accepted
- Add Prometheus metrics endpoint
- Update resource limits (32Mi vs 128Mi)
- Mark repository creation as complete
- Add AGENT-ONBOARDING.md for AI agents
- Add ARCHITECTURE.md with full system overview
- Add TECH-STACK.md with complete technology inventory
- Add DOMAIN-MODEL.md with entities and bounded contexts
- Add CODING-CONVENTIONS.md with patterns and practices
- Add GLOSSARY.md with terminology reference
- Add C4 diagrams (Context and Container levels)
- Add 10 ADRs documenting key decisions:
- Talos Linux, NATS, MessagePack, Multi-GPU strategy
- GitOps with Flux, KServe, Milvus, Dual workflow engines
- Envoy Gateway
- Add specs directory with JetStream configuration
- Add diagrams for GPU allocation and data flows
Based on analysis of homelab-k8s2 and llm-workflows repositories
and kubectl cluster-info dump data.