Add demo trio personas and polish empty-state panel UX.

Load cross-project shared.env before project .env for local dev.

Harden Expert Persona builder and add model suggestion.

Build credentials during Phase 1 and streamline human participant setup.

perf(orchestrator): prefetch human-phase opinions and tighten context budget

fix(personas): surface Neon HANA persona prompts in the sidebar

perf(orchestrator): parallel phases, streaming, early table summaries

feat(conversation): pluggable structures + decision methods (Robert's Rules, ranked-choice, majority)

feat(resilience): multi-tier participant failure recovery + Response-priority toggle

feat: human participant turns + credential intake redesign

chore: remove HANA Security verification probe

test: probe BrainForge/Security via standard HANA path

rename: 'CCAI Vibe Demo' -> 'Collaborative Conversational AI (CCAI) Demo'

feat(transparency): add "View current chat prompts" to settings

feat(participants): add "Select N Automatically" option

feat(limits): expose repetition / failsafe limits in settings menu

data: replace personal_health_diet demo prompt with four_day_workweek

Surface Credential Summary in settings + exports

Tighten CCAI conversation flow and visual threading

Build CCAI Vibe Demo on top of LLMChats3 baseline

Import LLMChats3 master as CCAI baseline