feat: Add Qwen AI provider integration and update model support

Author: gianged

CLAUDE.md

@@ -6,9 +6,11 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 **Universal Commit Assistant** is a VS Code extension that generates AI-powered commit messages using multiple AI providers. The extension supports 8 languages and follows modern TypeScript development practices with automated release workflows.
 
-## Latest Updates (January 2025)
+## Latest Updates (November 2025)
 
-- **DeepSeek Provider Added**: Integration with DeepSeek-V3.1 models including deepseek-chat (fast general purpose) and deepseek-reasoner (thinking mode for complex tasks)
+- **Qwen Provider Added**: Integration with Alibaba Cloud DashScope API supporting Qwen Max, Qwen Plus, and Qwen Turbo models
+- **GPT-5.1 Models**: Updated OpenAI provider with GPT-5.1, GPT-5.1 Codex, and GPT-5.1 Codex Mini
+- **Gemini 3 Models**: Updated Google Gemini provider with Gemini 3 Pro (flagship) and preview models
 - **Enhanced Model Support**: Updated to support latest AI models from all major providers
 
 ## Development Commands
@@ -36,7 +38,7 @@ npm run release:dry-run  # Test release process without publishing
 
 ## Architecture Overview
 
-This is a VS Code extension called Universal Commit Assistant that generates AI-powered commit messages using multiple AI providers and supports 8 languages. As of January 2025, it supports 8 providers including the newly added DeepSeek provider.
+This is a VS Code extension called Universal Commit Assistant that generates AI-powered commit messages using multiple AI providers and supports 8 languages. As of November 2025, it supports 9 providers including OpenAI, Anthropic, Gemini, Mistral, DeepSeek, Qwen, OpenRouter, Ollama, and LM Studio.
 
 ### Core Architecture Pattern
 
@@ -65,7 +67,7 @@ All AI providers inherit from **BaseProvider** abstract class and implement:
 
 Provider types:
 
-- **Cloud providers** (OpenAI, Anthropic, Gemini, Mistral, DeepSeek, OpenRouter) - require API keys stored in VS Code secrets
+- **Cloud providers** (OpenAI, Anthropic, Gemini, Mistral, DeepSeek, Qwen, OpenRouter) - require API keys stored in VS Code secrets
 - **Local providers** (Ollama, LM Studio) - require running local servers, configurable base URLs
 
 Each provider implements standardized error handling and configuration validation to ensure robust operation.
@@ -91,14 +93,15 @@ src/
 ├── providers/            # AI provider implementations
 │   ├── aiProviderFactory.ts   # Factory for creating provider instances
 │   ├── baseProvider.ts        # Abstract base class
-│   ├── anthropicProvider.ts   # Claude 3.5 Haiku/Sonnet
+│   ├── anthropicProvider.ts   # Claude 4.5 Haiku/Sonnet/Opus
 │   ├── deepseekProvider.ts    # DeepSeek V3.1 models
-│   ├── geminiProvider.ts      # Google Gemini models
+│   ├── geminiProvider.ts      # Google Gemini 3 models
 │   ├── lmstudioProvider.ts    # Local LM Studio integration
 │   ├── mistralProvider.ts     # Mistral AI models
 │   ├── ollamaProvider.ts      # Local Ollama integration
-│   ├── openaiProvider.ts      # OpenAI GPT models
-│   └── openrouterProvider.ts  # OpenRouter proxy service
+│   ├── openaiProvider.ts      # OpenAI GPT-5.1 models
+│   ├── openrouterProvider.ts  # OpenRouter proxy service
+│   └── qwenProvider.ts        # Alibaba Qwen models
 ├── services/
 │   ├── gitCommitService.ts    # Main workflow orchestration
 │   ├── gitService.ts          # Git operations wrapper
@@ -146,34 +149,44 @@ Users configure the extension through VS Code settings UI or JSON. Core settings
 
 Provider-specific settings use nested structure:
 
-- Cloud providers: `universal-commit-assistant.openai.model`, `universal-commit-assistant.anthropic.model`, `universal-commit-assistant.deepseek.model`
+- Cloud providers: `universal-commit-assistant.openai.model`, `universal-commit-assistant.anthropic.model`, `universal-commit-assistant.deepseek.model`, `universal-commit-assistant.qwen.model`
 - Local providers: `universal-commit-assistant.ollama.baseUrl`, `universal-commit-assistant.lmstudio.model`
 
-### Latest AI Model Updates (September 2025)
+### Latest AI Model Updates (November 2025)
 
 **OpenAI Latest Models:**
 
-- **GPT-5 Mini** (gpt-5-mini) - Fast and cost-effective, released August 2025, 400K context window
-- **GPT-5** (gpt-5) - Flagship model with state-of-the-art reasoning and coding capabilities
+- **GPT-5.1** (gpt-5.1) - Latest model balancing intelligence and speed, released November 2025
+- **GPT-5.1 Codex** (gpt-5.1-codex) - Optimized for coding tasks
+- **GPT-5.1 Codex Mini** (gpt-5.1-codex-mini) - Fast coding model
+- **GPT-5 Mini** (gpt-5-mini) - Fast and cost-effective, 400K context window
+- **GPT-5** (gpt-5) - Full capability flagship model
 
 **Anthropic Latest Models:**
 
 - **Claude Haiku 4.5** (claude-haiku-4-5-20251001) - Fast and cost-effective, released October 2025, 200K context window
 - **Claude Sonnet 4.5** (claude-sonnet-4-5-20250929) - Enhanced reasoning and coding capabilities, released September 2025
 - **Claude Opus 4.1** (claude-opus-4-1-20250805) - Most capable model with extended thinking, released August 2025
 
-**DeepSeek Latest Models (January 2025):**
+**Google Gemini Latest Models:**
+
+- **Gemini 3 Pro** (gemini-3-pro) - Latest flagship model with 1M context window, released November 2025
+- **Gemini 3 Pro Preview** (gemini-3-pro-preview-11-2025) - Preview version of Gemini 3
+- **Gemini 2.5 Flash** (gemini-2.5-flash) - Fast and cost-effective
+- **Gemini 2.5 Pro** (gemini-2.5-pro) - Advanced reasoning with thinking mode
+
+**DeepSeek Latest Models:**
 
 - **deepseek-chat** - DeepSeek-V3.1 Non-thinking Mode, fast general purpose model, 128K context
 - **deepseek-reasoner** - DeepSeek-V3.1 Thinking Mode, advanced reasoning for complex tasks, 128K context
-- **Pricing**: Competitive rates with cache hit/miss optimization
 - **API**: OpenAI-compatible API at https://api.deepseek.com
 
-**Google Gemini Latest Models:**
+**Qwen Latest Models (November 2025):**
 
-- **Gemini 2.5 Flash** - Most recent stable model with thinking capabilities
-- **Gemini 2.5 Pro** - State-of-the-art reasoning model leading in math and science benchmarks
-- **Gemini 2.5 Flash Image** - Advanced image generation and editing capabilities
+- **Qwen Plus** (qwen-plus) - Balanced performance and cost (recommended)
+- **Qwen Max** (qwen-max) - Most capable model
+- **Qwen Turbo** (qwen-turbo) - Fastest model with 1M context
+- **API**: OpenAI-compatible API at https://dashscope-intl.aliyuncs.com/compatible-mode/v1
 
 ## Development Best Practices
 

README.md

@@ -1,24 +1,30 @@
 # Universal Commit Assistant
 
-[📦 VS Code Marketplace](https://marketplace.visualstudio.com/items?itemName=gianged.universal-commit-assistant) • [⭐ Rate & Review](https://marketplace.visualstudio.com/items?itemName=gianged.universal-commit-assistant&ssr=false#review-details) • [🐛 Report Issues](https://github.com/gianged/universal-commit-assistant/issues)
+[VS Code Marketplace](https://marketplace.visualstudio.com/items?itemName=gianged.universal-commit-assistant) | [Rate & Review](https://marketplace.visualstudio.com/items?itemName=gianged.universal-commit-assistant&ssr=false#review-details) | [Report Issues](https://github.com/gianged/universal-commit-assistant/issues)
 
-**Stop writing commit messages manually.** Let AI generate perfect commit messages for you instantly, with support for 8 AI providers and 8 languages, directly in VS Code.
+**Stop writing commit messages manually.** Let AI generate perfect commit messages for you instantly, with support for 9 AI providers and 8 languages, directly in VS Code.
+
+---
 
 ## Why Universal Commit Assistant?
 
-🚀 **Save Time**: Generate commit messages in seconds instead of minutes
-🎯 **Always Consistent**: Follow conventional commit standards automatically
-🌍 **Your Language**: Support for 8 languages including English, Chinese, Spanish, French, Russian, Japanese, Korean, Vietnamese
-🔒 **Privacy First**: Use local AI models (Ollama, LM Studio) or secure cloud providers
+- **Save Time**: Generate commit messages in seconds instead of minutes
+- **Always Consistent**: Follow conventional commit standards automatically
+- **Your Language**: Support for 8 languages including English, Chinese, Spanish, French, Russian, Japanese, Korean, Vietnamese
+- **Privacy First**: Use local AI models (Ollama, LM Studio) or secure cloud providers
+
+---
 
 ## Quick Start
 
-1. **Install** → Search "Universal Commit Assistant" in VS Code Extensions
-2. **Configure** → Choose your AI provider and add API key (or setup local model)
-3. **Generate** → Click the ✨ button in Source Control panel
+1. **Install** - Search "Universal Commit Assistant" in VS Code Extensions
+2. **Configure** - Choose your AI provider and add API key (or setup local model)
+3. **Generate** - Click the sparkle button in Source Control panel
 
 That's it! Your commit messages will be professionally written and consistent.
 
+---
+
 ## Smart Commit Generation
 
 - **Context-Aware**: Analyzes your actual code changes to understand what you did
@@ -29,40 +35,45 @@ That's it! Your commit messages will be professionally written and consistent.
 - **Flexible Context**: Works with staged changes, unstaged changes, or both
 - **Customizable**: Adjust AI creativity, message length, and add custom prompts
 
+---
+
 ## AI Provider Options
 
 Choose the provider that fits your needs and budget:
 
-### ☁️ Cloud Providers (API Key Required)
+### Cloud Providers (API Key Required)
 
-| Provider          | Best For              | Latest Models                          |
-| ----------------- | --------------------- | -------------------------------------- |
-| **OpenAI**        | General purpose       | GPT-5, GPT-5 Mini                      |
-| **Anthropic**     | Code understanding    | Claude Haiku 4.5, Sonnet 4.5, Opus 4.1 |
-| **Google Gemini** | Fast responses        | Gemini 2.5 Flash, Gemini 2.5 Pro       |
-| **Mistral**       | European compliance   | Mistral Small, Mistral Large           |
-| **DeepSeek**      | Cost-effective        | DeepSeek-V3.1 Chat & Reasoner          |
-| **OpenRouter**    | Access to 100+ models | Meta Llama, Claude, GPT, and more      |
+| Provider          | Best For              | Latest Models                                |
+| ----------------- | --------------------- | -------------------------------------------- |
+| **OpenAI**        | General purpose       | GPT-5.1, GPT-5.1 Codex, GPT-5                |
+| **Anthropic**     | Code understanding    | Claude Haiku 4.5, Sonnet 4.5, Opus 4.1       |
+| **Google Gemini** | Fast responses        | Gemini 3 Pro, Gemini 2.5 Flash               |
+| **Mistral**       | European compliance   | Mistral Small, Mistral Large                 |
+| **DeepSeek**      | Cost-effective        | DeepSeek-V3.1 Chat & Reasoner                |
+| **Qwen**          | Alibaba Cloud         | Qwen Max, Qwen Plus, Qwen Turbo              |
+| **OpenRouter**    | Access to 100+ models | Meta Llama, Claude, GPT, and more            |
 
-### 🏠 Local Providers (Privacy First)
+### Local Providers (Privacy First)
 
 | Provider      | Best For         | Setup                            |
 | ------------- | ---------------- | -------------------------------- |
 | **Ollama**    | Complete privacy | Install Ollama + download models |
 | **LM Studio** | Easy local setup | Download LM Studio + any model   |
 
-## Configuration Made Simple
+---
+
+## Configuration
 
-Access via `Settings` → `Extensions` → `Universal Commit Assistant`:
+Access via `Settings` > `Extensions` > `Universal Commit Assistant`:
 
 ### Essential Settings
 
 - **Provider**: Select your preferred AI service
 - **Message Style**:
-  - `conventional` → feat: add new feature
-  - `concise` → add new feature
-  - `detailed` → Multi-line with explanations
-  - `custom` → Your own template
+  - `conventional` - feat: add new feature
+  - `concise` - add new feature
+  - `detailed` - Multi-line with explanations
+  - `custom` - Your own template
 - **Language**: Choose from 8 supported languages
 - **Include Unstaged**: Analyze uncommitted changes too
 
@@ -74,6 +85,8 @@ Access via `Settings` → `Extensions` → `Universal Commit Assistant`:
 - **Detect First Commit**: Automatically detect and generate appropriate initial commit messages (default: enabled)
 - **Custom Prompt**: Override default instructions
 
+---
+
 ## Example Outputs
 
 **Conventional Style:**
@@ -103,27 +116,33 @@ This commit introduces a comprehensive authentication system for the application
 - Follows industry best practices
 ```
 
+---
+
 ## Commands
 
 Access these via Command Palette (`Ctrl+Shift+P`):
 
-- **Generate Universal Commit Message** → Main functionality
-- **Show API Key Status** → Check which providers are configured
-- **Clear All API Keys** → Remove stored credentials
-- **Open Settings** → Quick access to configuration
+- **Generate Universal Commit Message** - Main functionality
+- **Show API Key Status** - Check which providers are configured
+- **Clear All API Keys** - Remove stored credentials
+- **Open Settings** - Quick access to configuration
+
+---
 
 ## Multi-Language Support
 
 Generate commit messages in your preferred language:
 
-- 🇺🇸 English (default)
-- 🇨🇳 Chinese (Simplified)
-- 🇪🇸 Spanish
-- 🇫🇷 French
-- 🇷🇺 Russian
-- 🇯🇵 Japanese
-- 🇰🇷 Korean
-- 🇻🇳 Vietnamese
+- English (default)
+- Chinese (Simplified)
+- Spanish
+- French
+- Russian
+- Japanese
+- Korean
+- Vietnamese
+
+---
 
 ## Token Cost Analysis
 
@@ -143,51 +162,60 @@ Universal Commit Assistant is designed to be cost-effective while providing high
 
 Based on enhanced analysis (~2,500 input tokens + 150 output tokens average):
 
-| Provider | Model | Cost per Commit | Cost per 100 Commits |
-|----------|-------|-----------------|---------------------|
-| **OpenAI** | GPT-5 Mini | ~$0.0005 | ~$0.05 |
-| **OpenAI** | GPT-5 | ~$0.008 | ~$0.80 |
-| **Anthropic** | Claude Haiku 4.5 | ~$0.003 | ~$0.30 |
-| **Anthropic** | Claude Sonnet 4.5 | ~$0.010 | ~$1.00 |
-| **DeepSeek** | deepseek-chat | ~$0.0009 | ~$0.09 |
-| **Gemini** | 2.5 Flash | ~$0.0003 | ~$0.03 |
-| **Ollama/LM Studio** | Local Models | **FREE** | **FREE** |
+| Provider             | Model              | Cost per Commit | Cost per 100 Commits |
+| -------------------- | ------------------ | --------------- | -------------------- |
+| **OpenAI**           | GPT-5.1            | ~$0.0008        | ~$0.08               |
+| **OpenAI**           | GPT-5.1 Codex      | ~$0.005         | ~$0.50               |
+| **Anthropic**        | Claude Haiku 4.5   | ~$0.003         | ~$0.30               |
+| **Anthropic**        | Claude Sonnet 4.5  | ~$0.010         | ~$1.00               |
+| **DeepSeek**         | deepseek-chat      | ~$0.0009        | ~$0.09               |
+| **Gemini**           | Gemini 3 Pro       | ~$0.0003        | ~$0.03               |
+| **Qwen**             | Qwen Plus          | ~$0.0006        | ~$0.06               |
+| **Ollama/LM Studio** | Local Models       | **FREE**        | **FREE**             |
 
 ### Cost Optimization Tips
 
-1. **Use Cost-Effective Providers**: Gemini Flash, DeepSeek, and GPT-5 Mini offer excellent quality at low cost
+1. **Use Cost-Effective Providers**: Gemini 3 Pro, DeepSeek, Qwen, and GPT-5.1 offer excellent quality at low cost
 2. **Adjust Max Diff Length**: Reduce `maxDiffLength` to 2000 for simpler commits
 3. **Local Models**: Use Ollama or LM Studio for completely free operation
 4. **Smart Defaults**: The extension uses intelligent truncation to minimize tokens while preserving context
 
 **Bottom Line**: Even with premium models, most users spend less than $1/month on commit message generation.
 
+---
+
 ## Requirements
 
 - **VS Code**: Version 1.95.0 or higher
 - **Git Repository**: With changes to commit
 - **AI Provider**: API key (cloud) or running server (local)
 
+---
+
 ## Privacy & Security
 
 - **Secure Storage**: API keys stored in VS Code's encrypted secret storage
 - **No Data Retention**: Your code never leaves your machine with local providers
 - **Optional Analytics**: Usage tracking can be disabled (no sensitive data collected)
 - **Open Source**: Full transparency with MIT license
 
+---
+
 ## Need Help?
 
-- 📖 **Documentation**: See configuration examples above
-- 🐛 **Issues**: [Report bugs on GitHub](https://github.com/gianged/universal-commit-assistant/issues)
-- 💡 **Feature Requests**: [Suggest improvements](https://github.com/gianged/universal-commit-assistant/issues)
-- ⭐ **Rate & Review**: Help others discover this extension
+- **Documentation**: See configuration examples above
+- **Issues**: [Report bugs on GitHub](https://github.com/gianged/universal-commit-assistant/issues)
+- **Feature Requests**: [Suggest improvements](https://github.com/gianged/universal-commit-assistant/issues)
+- **Rate & Review**: Help others discover this extension
+
+---
 
 ## License
 
 MIT License - see [LICENSE](LICENSE) file for details.
 
 ---
 
-**Made with ❤️ for developers who value their time**
+**Made for developers who value their time**
 
 _Save hours every week on commit messages. Install now and never write another commit message manually._