Add LLM memory quality eval gate and promote OpenAI-agent readiness updates

feat: add fault chaos permutations and operator UX contracts

feat: complete wave 113 no-hardware reliability expansion

refactor: close waves 108-112 runtime and reliability hardening

Wave 37: add multimodal grounding, context-aware nudges, and repeatable soak cycles

Wave 36: add proactive triage, preference learning, and operator guidance

Add release-readiness tooling and persistent expansion state