Add performance optimizations and LRU caching

[benzntech]

Summary

This PR implements three key performance optimizations to improve response times and reduce API quota consumption:

1. LRU Response Cache (src/utils/responseCache.ts)

• Implements LRU caching for Gemini API responses
• 30-minute TTL ensures fresh data
• 10MB max cache size with automatic eviction
• Near-instant responses for repeated queries
• Significant reduction in API quota usage

2. Eliminate Code Duplication (src/utils/geminiExecutor.ts)

• Introduced buildGeminiArgs() helper function
• DRY principle for CLI argument construction
• Shared between main execution and Flash model fallback
• Reduces maintenance burden and potential bugs
• Added GeminiCLIOptions interface for type safety

3. Array Buffer Performance (src/utils/commandExecutor.ts)

• Replaced O(n²) string concatenation with O(n) array buffers
• Significant performance improvement for large command outputs
• More efficient memory usage during streaming operations

Additional Improvements

• Enhanced CLI flag support in constants.ts
• Updated tools (ask-gemini.tool.ts, brainstorm.tool.ts) to use new options interface
• Dependency cleanup in package.json and package-lock.json

Testing

• All existing functionality remains backward compatible
• Tested with MCP inspector and Playwright
• Verified caching behavior and eviction policies
• Confirmed Flash model fallback still works correctly

Performance Impact

• Response time: Near-instant for cached queries (vs. 2-5s for API calls)
• API quota: Significantly reduced for repeated queries
• Memory: Efficient with 10MB cap and automatic eviction
• Large outputs: O(n) performance vs. previous O(n²)

Files Changed

• src/utils/responseCache.ts (new file)
• src/utils/geminiExecutor.ts (refactored)
• src/utils/commandExecutor.ts (optimized)
• src/constants.ts (enhanced flags)
• src/tools/ask-gemini.tool.ts (updated interface)
• src/tools/brainstorm.tool.ts (updated interface)
• src/index.ts (minor cleanup)
• package.json & package-lock.json (dependencies)

All changes maintain backward compatibility while significantly improving performance.

[gemini-code-assist]

Summary of Changes

Hello @benzntech, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances the application's performance and efficiency by implementing a robust LRU caching mechanism for Gemini API responses, streamlining CLI argument construction to reduce code duplication, and optimizing command output processing with array buffers. These changes aim to improve response times, lower API quota consumption, and provide a more flexible and maintainable codebase.

Highlights

• LRU Response Caching: Introduced a new LRU cache (lru-cache dependency) for Gemini API responses, providing near-instant replies for repeated queries, reducing API quota usage, and featuring a 30-minute TTL and 10MB max size.
• Code Duplication Elimination: Refactored geminiExecutor.ts by introducing a buildGeminiArgs() helper function and GeminiCLIOptions interface, centralizing CLI argument construction and improving maintainability.
• Array Buffer Performance: Optimized commandExecutor.ts by replacing inefficient O(n²) string concatenation with O(n) array buffers for handling large command outputs, leading to significant performance and memory efficiency gains.
• Enhanced CLI Flags: Expanded constants.ts with new CLI flags and default values for features like YOLO mode, approval modes, output formats, and directory inclusion, enhancing the flexibility of Gemini CLI interactions.
• Tool Interface Updates: Updated ask-gemini.tool.ts and brainstorm.tool.ts to utilize the new GeminiCLIOptions interface, ensuring consistency and type safety across tool arguments.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces significant performance optimizations and improves code structure. The addition of an LRU cache for API responses is a great feature to reduce latency and quota usage. The implementation in src/utils/responseCache.ts is solid. The refactoring in src/utils/geminiExecutor.ts to use a helper function and an options object greatly improves maintainability and readability. The optimization in src/utils/commandExecutor.ts to use array buffers instead of string concatenation for command output is a correct and effective performance enhancement. I've found a couple of areas for improvement, one related to correctness in commandExecutor.ts and a minor refinement in responseCache.ts.