Response quality: greeting/goodbye/meta handlers, slang routing, lexical variety, last-verified badge, markdown norm, crisis variants

V4.4 Tier 2: safety-pipeline UI visualization, paper results section, demo script, mobile CSS, HIPAA + privacy docs

V4.1: fix repetition/scroll/topbar, add PDF export, counselor-assist note

V4: streaming, controlled paraphrasing, support plan, voice, sweeps

Add LLM plan-and-rephrase layer with Groq + Anthropic providers

Add stage-aware listening planner and F-1 student awareness

Polish MVP support experience

Prepare Core dataset intake and resource registry

Add live demo decision console

Polish peer helper and scope handling

Add Core safety metadata and eval summaries

Implement EmpathRAG Core hybrid router

Start V2.5 support navigator hardening

Checkpoint V2 curated support navigator

Add curated corpus integration scaffold

Start v2 safety hardening

Add conversation memory, fix Gradio stack, improve SYSTEM_PROMPT, log human eval turns

feat: Gradio demo app, DeBERTa Colab notebook, updated smoke test results (Day 13)