Add HANA klatchat credentials for BrainForge Security (4090 x1-3)

Add Mistral.ai provider and checkbox-style settings menu

Strip thinking content from all LLM responses and skip redundant role generation

Restyle sidebar with Neon card layout, refine buttons and labels

Add AI-completed vs exact role generation style toggle

Simplify model selection: single-click to reuse, replace oldest on overflow

Add response timing, chat stats, and role prompt viewer to settings

Rebrand UI with Neon.ai header, sidebar styling, expert personas, and UX improvements

Add speed-priority setting with 5s racing fallback for faster responses

Remove debug instrumentation

Increase accordion body max-height deduction to prevent bottom overflow clipping

Make accordion body scrollable with viewport-relative max-height

Keep height:100vh scroll containment at all breakpoints to fix HF iframe

Add responsive design for phone and tablet screens

Replace orchestrator modal with sub-menu to fix backdrop-filter containment bug

Fix accordion overflow clipping and install itsdangerous for local dev

Fix sidebar model name overflow with ellipsis truncation and flex-shrink protection

Fix API_BASE to allow empty string for same-origin Docker deployment

Add HuggingFace Spaces deployment with OAuth and rate limiting

Add freeform persona input mode with file upload and Developer menu toggle

Add Developer menu with orchestrator picker, download buttons, and LLMChats2-style dropdown

Initial commit: LLMChats3 - LLM conversation app with React + FastAPI, persona config, orchestrated conversation lifecycle, collapsible sidebar accordions, stop button, and export capabilities