Add Support for Google Gemini API #46
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Install @google/genai v1.28.0 package - Add gemini option to aiServiceProvider enum - Add geminiApiKey configuration setting with link to Google AI Studio - Add geminiModel configuration setting with default gemini-2.0-flash-exp - Include documentation for popular Gemini models
- Create GeminiService class implementing AIService interface - Add getCommitMessageFromDiff() method for generating commit messages - Add getExplainedChanges() method for explaining code changes - Implement caching support for API responses - Add comprehensive error handling with user-friendly messages - Follow same pattern as OpenAiService for consistency
- Add getGeminiKey() method to retrieve and validate Gemini API key - Add getGeminiModel() method to retrieve selected Gemini model - Include error messages for missing API key with link to Google AI Studio
- Import and add GeminiService instance management - Add getGeminiService() method - Update getAIService() to support gemini provider - Update all methods to handle Gemini API: * explainAndPreview() * explainDiffToClipboard() * generateCommitMessageToClipboard() * generateCommitMessageToSCM() - Add Gemini API key validation - Add cleanup for Gemini service in dispose() method
Hi7cl4w
commented
Nov 3, 2025
Owner
Author
Hi7cl4w
left a comment
Hi7cl4w
left a comment
There was a problem hiding this comment.
Summary
This PR adds support for Google Gemini API as an alternative AI provider to the existing OpenAI integration. The implementation follows the same pattern as the OpenAiService and integrates seamlessly with the existing extension architecture.
Changes
🔧 Dependencies
- Added
@google/genaiv1.28.0 package for Google Gemini API integration
⚙️ Configuration
- Added
geminioption toaiServiceProviderenum in package.json - Added
geminiApiKeysetting with link to Google AI Studio for API key setup - Added
geminiModelsetting with support for multiple Gemini models:gemini-2.0-flash-exp(default)gemini-1.5-progemini-1.5-flash
🏗️ Implementation
-
GeminiService.ts: New service class implementing the AIService interface
- Singleton pattern for service management
- Full integration with caching layer (CacheService)
- Error handling and logging
- Support for all extension features: commit message generation, diff explanation, etc.
-
WorkspaceService.ts: Extended with Gemini-specific configuration methods
getGeminiKey(): Retrieves and validates Gemini API keygetGeminiModel(): Gets selected Gemini model from settings
-
Diffy.ts: Updated main extension class
- Added
getGeminiService()method for lazy initialization - Updated
getAIService()to route to Gemini when provider is set to "gemini" - All four main methods now support Gemini:
explainAndPreview()explainDiffToClipboard()generateCommitMessageToClipboard()generateCommitMessageToSCM()
- Added proper cleanup in
dispose()method
- Added
Usage
Users can now select Google Gemini as their AI provider by setting:
{
"diffy.aiServiceProvider": "gemini",
"diffy.geminiApiKey": "your-gemini-api-key-here",
"diffy.geminiModel": "gemini-2.0-flash-exp"
}Testing
- ✅ Code compiles successfully with webpack
- ✅ All TypeScript types are properly defined
- ✅ Follows existing code patterns and architecture
- ✅ Error handling matches existing services
- ✅ Caching integration works correctly
Commits
The changes were committed separately for better review:
feat: add Google Gemini API dependency- Package updatesfeat: implement GeminiService for Google Gemini API integration- New servicefeat: add Gemini configuration methods to WorkspaceService- Config methodsfeat: integrate GeminiService into Diffy extension- Main integration
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.