Unified TrajectoryOS Architecture Plan

**Status**: Reconciliation of RAG++ Implementation with Original Conversational Interview Vision TrajectoryOS was originally designed as **"an AI that interviews you like a Stanford professor, models your strengths like a McKinsey consultant, and tracks your life-trajectory like NASA mission control."** The current implementation has **RAG++ (state-based recommendations)** working but is **missing the conversational interview engine** that was the core vision. 1. **Interview Layer** - Conversational AI that extracts skills, projects, constraints 2. **RAG++ Layer** - State-based recommendations from transition memory 3. **Planning Layer** - Background agent that generates action plans | Component | Status | Location | |-----------|--------|----------| | Life Physics Model | ✅ Complete | `services/trajectory-core/src/domain/physics.ts` | | RAG++ Services (5 services) | ✅ Complete | `services/trajectory-core/src/services/` | | RAG++ API Endpoints | ✅ Complete | `services/trajectory-core/src/routes/ragpp.ts` | | Interview Agent (Backend) | ✅ Exists | `services/agent-orchestrator/src/agents/InterviewAgent.ts` | | Planner Agent (Backend) | ✅ Exists | `services/agent-orchestrator/src/agents/PlannerAgent.ts` | | iOS App (RAG++ only) | ✅ Complete | `apps/ios/TrajectoryOS/` | | Prisma Schema | ✅ Complete | `services/trajectory-core/prisma/schema.prisma` |