- Updated system prompts for all services to enforce 'ITERATIVE MODIFICATIONS' behavior
- Instructed AI to maintain design structure and only apply requested changes
- Added 'Change Log' requirement for text responses
- Modified AIAssist.tsx to preserve raw code in history for AI context
- Updated UI rendering to hide code tags while keeping them in context
- Added 'Applying surgical edits...' status feedback
- Added 'Same as source' to translations in EN, RU, HE
- Updated 'Number of Slides' dropdown to include 'Same as source' (value 0)
- Updated Qwen, Ollama, and Z.AI services to handle 0 slide count by instructing AI to match source structure
- Replaced qwen-coder-plus (which failed with 400) with qwen2.5-coder-32b-instruct
- Updated available models list with qwen2.5-coder series
- Corrected store defaults
- Fixed generateAIAssistStream to call Qwen API directly
- Uses getEffectiveEndpoint() and getRequestHeaders() for proper auth
- Added better error logging for debugging
- Fixed listModels to use getAvailableModels()
- This fixes the 'Stream request failed' error
- Added text-slate-100 dark:text-slate-100 to input for visible text on dark bg
- Updated Qwen models to use valid names: qwen-coder-plus, qwen-turbo, etc
- Set qwen-coder-plus as default model for best coding assistance
- Added GoogleAdsGenerator component with comprehensive keyword research and ad copy generation.
- Updated Sidebar and Home page for navigation.
- Added necessary UI components (Badge, Tabs) and dependencies.
- Added custom animations for progress indicators.