🚀 New Features & Enhancements

Translation UI Improvements

• Target Language Display: Added target language tag in translation panel header, showing which language the text was actually translated to
• Enhanced Language Logic: Improved detected language and target language logic with robust alternative language support
• Better Newline Handling: Fixed newline formatting in translation output for proper text structure preservation

User Experience

• Model Picker Fix: Fixed model selector initialization to prevent loading state on first render
• Scrollable Text Areas: Added vertical scrollbars to translated text area for better handling of long translations
• Consistent UI Styling: Enhanced visual consistency with matching language tags in both text panels

Technical Improvements

• Enhanced Logging: Improved error handling and logging across all translation services (Azure, OpenAI, Ollama)
• Backend Updates: Updated backend to return comprehensive target language information to frontend
• Code Quality: Fixed all Rust clippy warnings and improved overall code quality
• Alternative Language Logic: Enhanced prompt instructions and backend logic for better language detection and alternative language selection

🔧 Bug Fixes

• Fixed detected language only showing when valid (not 'unknown' variants)
• Resolved target language display issues in translation panel
• Improved translation service error handling and response parsing
• Enhanced newline character handling in translation output

🏗️ Development

• Updated to version 1.3.2 across all configuration files
• Comprehensive code formatting and linting
• All clippy warnings resolved
• Clean build verification

📦 Installation

• Windows Installer (NSIS): GPTranslate_1.3.2_x64-setup.exe

This release significantly improves the translation experience with better UI feedback, enhanced language handling, and more robust error handling across all supported translation services.

🐛 Bug Fixes:
• Fixed target language recording in translation history

🔧 Technical:
• Added fix_target_language_in_history function to correct existing history entries
• Code formatting improvements
• Cleaned up unused files and manifests

🚀 Major Azure OpenAI Support & Model Management Improvements

✨ New Features

Enhanced Azure OpenAI Support

• Full o1/o3 Reasoning Model Support: Native support for Azure OpenAI o1, o1-mini, o3, and o3-mini models
• Smart Parameter Detection: Automatically uses max_completion_tokens instead of max_tokens for reasoning models
• Developer Role Support: Proper handling of system vs developer roles for different model types
• Enhanced Endpoint Parsing: Improved Azure endpoint URL parsing and validation
• Auto-Model Addition: Automatically extracts and adds models from pasted Azure endpoint URLs

Modular Settings UI

• Component-Based Architecture: Refactored settings into modular Svelte components
• Improved Model Management: Dedicated model management interface with add/remove/toggle functionality
• Real-Time Updates: Model changes instantly reflect in the main window dropdown
• Better Organization: Tabbed settings interface for better user experience

Live Model Management

• Dynamic Model Updates: Added/removed models appear immediately without app restart
• Config State Management: Centralized configuration management with reactive updates
• Auto-Save: Model changes are automatically saved and synchronized
• No Default Models: Clean slate approach - only shows user-configured models

🐛 Bug Fixes

Azure OpenAI Fixes

• Temperature Parameter: Fixed temperature parameter errors for o1/o3 reasoning models
• Token Limits: Resolved max_tokens vs max_completion_tokens parameter conflicts
• API Key Validation: Improved Azure API key validation and error handling
• Endpoint Compatibility: Better support for both Cognitive Services and Models API endpoints

UI/UX Improvements

• Svelte Ownership Warnings: Fixed prop mutation warnings in ModelSelector component
• TypeScript Errors: Resolved all TypeScript compilation issues
• Model Refresh: Fixed model dropdown not updating after settings changes

🔧 Technical Improvements

Backend Enhancements

• Conditional Parameters: Smart parameter inclusion based on model type
• Better Error Handling: Enhanced error messages and logging for Azure configurations
• Model Detection Logic: Automatic reasoning model detection and parameter adjustment

Frontend Architecture

• Component Modularity: Improved code organization with reusable components
• State Management: Better prop passing and state synchronization
• Event-Driven Updates: Reactive model management with immediate UI updates

📈 Performance & Reliability

• Reduced Build Errors: Eliminated TypeScript and compilation issues
• Improved Validation: Better input validation and error prevention
• Enhanced Logging: More detailed logging for debugging and troubleshooting

This release significantly improves Azure OpenAI compatibility, especially for the latest reasoning models (o1, o3 series), while providing a much better user experience for model management and configuration.

📋 GPTranslate v1.2.1 - Changes Summary

🐛 Bug Fixes

Fixed Ollama Newline Formatting Issue:

• Problem: When typing text in the "Original Text" field, Ollama translations returned literal /n instead of actual newlines
• Root Cause: Problematic prompt instruction asking Ollama to "properly escape newlines" caused confusion
• Solution:
  • Updated prompt to "Preserve line breaks and formatting in the translated text"
  • Added defensive response processing to handle various escape formats (\n, /n, \r\n, \r)

This is a minor bugfix release that specifically addresses the Ollama newline formatting issue while adding valuable automation tools for future releases.

GPTranslate v1.2.0

🎉 Major Updates

✨ Free Local Translation with Ollama

GPTranslate now supports Ollama for completely free, offline translations!

• No API costs - Run completely offline
• No internet required - Perfect for private/secure environments
• Complete privacy - Your data never leaves your machine
• Unlimited usage - Translate as much as you want
• Professional quality - Use modern AI models like Llama, Mistral, and more

🔥 New Features

• Full Ollama Integration: Connect to local Ollama instance for translations
• Local Model Support: Use a variety of free, local AI models
• Enhanced Privacy: Translate sensitive content without sending data to cloud services
• Offline Capability: Translate anytime, anywhere - no internet connection required

📝 Setup Guide for Free Translation

1. Install Ollama: Download from ollama.com
2. Pull a model: Run ollama pull llama3.2:latest (or any preferred model)
3. Start Ollama: The service should start automatically
4. Configure GPTranslate:
   • In Settings, select "Ollama" as provider
   • Set the server URL (default: http://localhost:11434)
   • Choose your downloaded model name

🧠 Recommended Ollama Models

• llama3.2:latest - Great general-purpose model
• mistral:latest - Excellent for European languages
• codellama:latest - Good for technical content
• dolphin-mistral:latest - Optimized for instruction following

🛠️ Other Improvements

• Simplified API Setup: Clearer configuration options for all providers
• Updated Cost Analysis: Added comprehensive comparison including free options
• Enhanced Documentation: Expanded usage guides and model recommendations
• Updated Configuration: Added new options for Ollama URL and model selection
• Refactored Settings: Better organization of provider options

📋 Updated Planned Features

• Model management, allowing users to select and switch between different models
• Better history management, including search and filtering

📌 Note to Users

This update makes GPTranslate entirely free to use with Ollama! Cloud-based options remain available through OpenAI and Azure OpenAI for those who prefer them.

📋 Changes Since Last Commit

🐛 Bug Fixes

• 🔧 Azure API compatibility: Fixed "error sending request" issue by properly handling different Azure endpoint formats
• 🔧 URL parsing: Robust parsing of Azure URLs with proper error handling
• 🔧 Model flexibility: Removed restrictions that prevented using custom/newer models

🎯 Key Improvements

1. Better Azure Support: Now handles both Cognitive Services and Models API endpoints seamlessly
2. User Experience: Real-time feedback when pasting Azure URLs with automatic extraction
3. Visual Design: Professional header with larger SVG logo and better typography
4. Flexibility: Removed hardcoded model restrictions, allowing any model name
5. Error Handling: Comprehensive validation with clear error messages
6. Icon update: Icon has been updated

Initial release!

Tested and working, please report any bugs that you might find.

• Download the .msi for system scope install
• Download the .exe for user scope install