feat: add Anthropic Claude provider support with flexible authentication

[nicdaCosta]

Added support for Anthropic models, thus making the current availability OpenAI, Gemini, OLlama, and Anthropic.

I have added support for a new model provider, as well as multiple authentication methods for Anthropic to work for various setups, including the usage of 3rd party key providers like Portkey.ai. The reason for the multiple auth options is to allow for various setups to work, from personal to enterprise solutions.

[greptile-apps]

Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.

[gemini-code-assist]

Summary of Changes

Hello @nicdaCosta, 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 system's LLM capabilities by integrating Anthropic Claude models. The primary goal was to provide robust and flexible support for Anthropic, ensuring compatibility with different user setups, from individual developers using direct API keys to enterprise environments leveraging proxy services or existing Claude Code CLI configurations. This broadens the range of powerful models available for both orchestrator and cypher generation tasks, making the system more versatile and accessible to a wider user base.

Highlights

• Anthropic Claude Integration: Added comprehensive support for Anthropic Claude models as a new LLM provider, expanding the system's capabilities beyond OpenAI, Gemini, and Ollama.
• Flexible Authentication: Implemented multiple authentication methods for Anthropic, including direct API keys, automatic detection from ~/.claude/settings.json (for Claude Code CLI users), and support for proxy services like Portkey via custom HTTP headers.
• Configuration and Documentation Updates: Updated .env.example and README.md with detailed instructions and examples for configuring Anthropic models and their various authentication options. New environment variables for Anthropic API key, base URL, and custom headers were introduced.
• Extensible Provider Architecture: Enhanced the core model provider system to accommodate custom HTTP headers, making it more flexible for integrating with various LLM gateways and enterprise solutions.
• New Utility and Tests: Introduced a new utility module (codebase_rag/utils/claude_settings.py) to read Claude Code settings and added extensive unit tests for the new Anthropic provider and its configuration loading mechanisms.

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 adds support for Anthropic Claude models, including flexible authentication methods like direct API keys, proxy services via custom headers, and automatic configuration from Claude Code settings. The implementation is well-structured, with a new AnthropicProvider class, corresponding configuration options, and thorough tests. The documentation in README.md and .env.example is also updated clearly.

My review focuses on a small area of code duplication for parsing custom headers, which can be refactored into a shared utility function for better maintainability. I've also suggested adding a comment to clarify the use of a broad exception catch, in line with the project's coding practices. Additionally, I've ensured that the suggested utility function adheres to the project's rule against docstrings. Overall, this is a great addition that significantly expands the tool's capabilities.