update startup welcome/splash screen messages with new STUP policy details

restore main application app.py (replace maintenance stub)

maintenance: refactor stub to Flask (remove Gradio dependency)

maintenance: show stub page until STUP enrollment window opens

docs: enhance README with comprehensive features, diagrams, and live demo link

Update expert mode to use diffusiongemma model and include read_b64 helper

Update expert mode LLM to mistral-medium-3.5-128b with reasoning effort

Update expert mode routing for sarvam-m

Fix keyring module not found and add model name to metrics

Manual update to nvidia_llm

Update language switch and note in index.html

Untrack extraneous files to comply with minimalist deployment

Remove PDF from tracking to adhere to minimalist deployment

Update documentation to reflect splash screen and copy button features

Improve copy button design

Add copy buttons to QA responses

Update splash screen text

Add formatted program overview to UI message area

UI tweak for feedback area and fix token usage metrics extraction

Implement Dual LLM Toggle: Expert and Assistant modes

Update nvidia_llm to use google/diffusiongemma-26b-a4b-it via requests

Fix IndentationError in graph_store.py

Fix Kuzu graph write lock error and suppress pip/transformer warnings

Update nvidia_llm to use minimaxai/minimax-m2.7 and new sampling params

Update nvidia_llm model, endpoint, stream=False, and remove hardcoded API key

Fix NameError in crew.py and add AI disclaimer to index.html

Fix nvidia_llm httpx connection leaks and improve crew.py retrieval logging

Replace gen_llm with nvidia_llm and add frontend test

Update feedback UI layout and add thank you message

Update gitignore to exclude strategic documents for minimalist deployment

Remove excess documentation and CLI scripts to keep HF repo lean

Update docs and PDFs

Update feedback UI: relocate to bottom, add 5-star rating, and immediate capture

Fix OOM crash causing missing jobs by limiting PyTorch concurrency

Update docs with feedback and resumability features

Add feedback UI and capture to nitdaa_summary.json

Fix multiuser concurrency bottleneck and update HF deployment docs

Fix UI 404 by applying async job queue client logic to actual index.html template

Refactor RAG query architecture to async job queue to fix mobile background disconnects

Fix: Handle mobile UI disconnects during LLM query via SSE keep-alives and UI alerts

Docs: Add minimalist deployment rule

Update architecture design with project intelligence

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub