how to customize llm api

[fcakyon]

Currently, HyperChat supports the OpenAI version of the Claude and Gemini APIs. However, OpenAI version of these APIs doesn't support caching. They say use the official API for caching: https://docs.anthropic.com/en/api/openai-sdk

How can I update the source code so that HyperChat works with official SDKs? Can you guide me? I am also open to make a contribution to your project 👍🏻

cc: @laopo001

[laopo001]

Hi @fcakyon,

Thank you for bringing up this important feature request!

Good news - HyperChat 2.0 has already implemented this functionality! We've migrated to the official SDKs using the Vercel AI SDK, which provides native support for caching with Claude, Gemini, and other providers' official APIs.

However, please note that 2.0 is currently in alpha status and under active development. The architecture has been significantly refactored (largely rebuilt with Claude Code assistance), so there are substantial changes from v1.x.

Current development:

• Main development branch:
• We welcome contributions and testing!
• The new implementation should address your caching requirements

If you're interested in contributing or testing the 2.0 alpha, please feel free to check out the branch and let us know your feedback.

Thank you for your willingness to contribute to the project! 🙏