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 38: proactive dedupe hardening and runtime decomposition

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

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

Add phased soak and personality A/B drift harness

Decompose runtime helpers and expand eval contract coverage

Decompose services into domain handlers and expand eval contract coverage

Complete remaining Jarvis roadmap: proactive, trust, planner, integrations, and deployment tracks