feat: add observability budget telemetry and canary analytics

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

Add operator auth modes with risk warnings and session login

Add control presets, runtime profiles, signed operator actions, and observability analytics

Implement VX04 per-user voice preference profiles

Implement JX05 personality preview controls with rollback

Implement VX05 STT confidence diagnostics

Add live operator conversation trace panel and API

Add operator control schema endpoint and explicit sleep control

Harden operator API auth and persist runtime control styles

Require inbound webhook token and sanitize operator/inbound payload logs

Improve operator SSE stream and skills tool gating behavior

Harden audit retention, skills state persistence, and operator/config safeguards

Add operator console, observability, skills, and resilience/security hardening