Remove 'Safely' from main heading

Add expandable practice goal examples

Fix broken Sarah Peyton attachment quiz link

Move simulation setup from sidebar to main page

Add prominent mobile menu instruction at top of page

Fix |aI| pronoun: only for AI self-reference, not user scripts

Add |aI| pronoun requirement to debrief prompt

Fix debrief bug: capture conversation before clearing state

Update sidebar welcome text with ARI framing

Fix 404 error: Update model from deprecated claude-3-opus to claude-sonnet-4

Update setup instructions to be clear for both mobile and desktop users

Update welcome message to be more mobile-friendly

Change arrow direction back to pointing left

Change arrow direction to point to sidebar

Add scroll instruction to welcome text

Clear conversation state when entering debrief mode

Fix debrief message format and remove duplicate bubbles

Fix debrief initialization order to prevent NameError

Fix duplicate chat bubble in debrief initialization

Update debrief functionality with new therapeutic reflection prompt

Remove debug messages from API initialization

fix: Simplify Anthropic client initialization and downgrade package version

fix: Update Anthropic client initialization to fix proxies parameter error

Update to use Anthropic API instead of OpenAI

ported over new wip app. note - its using gpt4o not claude

switch model to gpt4o and fix readme

Update app configuration and documentation for Hugging Face deployment

Add personal website link to author name in header

Update system prompt with new protocols and improve app interface. Changes include: - Add Firearms Protocol - Add Homicidal Mentions Protocol - Add System Interruption Protocol - Update Try It Out section with detailed explanation - Convert we language to I language throughout

Load system prompt from file during chat session initialization; added error handling for file not found and other exceptions.

Initial commit