Mark VII

API & Usage Management

• API Usage Screen: Introduced a dedicated API Usage screen for tracking personal API key limits.
• Quota Warnings & Portal Links: Added proactive quota warnings and direct links to API usage portals (Gemini AI Studio, Groq Console, OpenRouter Activity).
• Key Verification Feedback: Improved UI feedback during API key verification processes.

UI/UX & Onboarding Refinements

• UI Polish: Polished onboarding flows and refined various app UI surfaces for a cleaner experience.
• Top Bar UI Fix: Fixed a visual bug in the main chat screen where scrollable chat messages were improperly overlapping the top app bar and system status bar.
• App Icon Update: Updated the main application icon.

Authentication & Settings

• Auth Screen & Email Flow: Added a dedicated Authentication screen and implemented an email authentication flow.
• Copy Refinements: Refined the textual copy across the settings page and retry dialogs for improved clarity.

Groq AI Provider (v3.3.0)

• Added Groq as a third AI provider alongside Gemini and OpenRouter.
• Support for ultra-fast models (Llama 3, Mixtral, Gemma, etc.).
• Dynamic model fetching from /models endpoint (no hardcoding).
• SSE streaming with conversation context (last 6 messages).
• Firebase-managed API key with optional user override.
• Integrated into model selector and settings UI.

Retry UX & Traceability (v3.3.1)

• Retry actions linked to original prompts.
• "Retried From" tag with quick navigation to source prompt.
• Source prompt highlight animation for visibility.
• Cleaner retry context without stale responses.

Performance & Rendering

• Throttled streaming updates (~60 FPS) for smoother UI.
• Introduced StreamingMarkdown for low-flicker live rendering.
• Full markdown rendering with code copy after stream completion.
• Optimized haptic feedback handling.
• Improved mic waveform rendering using single Canvas.
• Refined auto-scroll behavior.

Sessions & Stability

• Per-user local session caching.
• Cache-first session loading with Firestore sync.
• Improved IO threading to reduce UI blocking.
• Stabilized drawer recomposition and callbacks.

Fixes & Improvements

• Added Groq tab in model selector, increased dropdown width.
• Enabled Groq models in retry selector.
• Added warning for unsupported image retries with Groq.
• Fixed duplicate prompt issue in OpenRouter requests.

User API Key Management

• Personal API Keys: Introduced UserApiPreferences system allowing users to add and manage their own Gemini and OpenRouter API keys.
• API Key Verification: Added real-time API key verification with loading states, error handling, and visual feedback in Settings.
• Key Priority System: User-provided API keys now take priority over app default keys when enabled, with seamless fallback support.
• Settings UI Enhancement: New UserApiConfigItem component for API key input, toggle enable/disable, and verification.
• Persistent Storage: API keys and enabled states are stored securely using SharedPreferences with reactive StateFlow updates.

Documentation & Visuals

• README Enhancement: Added OpenRouter model visuals and comprehensive usage examples.
• Documentation Assets: Added visual assets for v3.1.0 feature documentation.

• New Explore UI with animation and quick actions.
• Guest users get a New Chat option.
• Chat list and top bar now have smooth gradients.
• Fixed keyboard overlap issue.
• Smaller action buttons and smoother onboarding animation.

• Custom Speech Recognition Engine: Fully redesigned voice input with 60-bar moving waveform, RMS-based amplitude detection, animated mic button, and zero system toasts.
• Multilingual Text-to-Speech (15+ Languages): MLKit-powered language detection with automatic TTS switching for Chinese, Japanese, Korean, Arabic, Hindi, and more.
• Dynamic Theme System & UI Overhaul: New light/dark/system themes, smoother animations, improved layouts, clickable GitHub link, and polished Material 3 visuals.
• Chat Sessions + Cloud Sync: Google Sign-In, persistent Firestore chat sessions, and full session management (create, rename, delete, switch).
• Dual API Support (OpenRouter + Gemini): Seamless model switching, provider-specific error handling, and expanded support for 40+ AI models.
• Real-Time Streaming Responses: Live token streaming with haptics, stop-generation control, and optimized high-FPS rendering.
• PDF Export System: Export conversations with syntax highlighting, timestamps, and formatting for professional use.
• Performance & Stability Improvements: Auto model correction, refined error handling, faster timeouts, memory optimizations, and smoother UI transitions.

• Added model switcher.
• Redesigned prompt text box.
• New send and image picker animated logo added.
• Added custom text (ttfs).
• Added chat screen background and info card.
• Added developer's social media handles.

• Custom designed splash screen.
• Smooth UI animation integrated.
• Google gemini-1.5-flash-8b NLP model used as default.
• Added an option for image search.
• Added Android Monet theme in the app.
• Automatically changes theme according to your android theme.