Prompt cache, finally typed: shipping llm-ports 0.1.0-alpha.19
The llm-ports library has released version 0.1.0-alpha.19, introducing a unified interface for prompt caching across different LLM providers like Anthropic, OpenAI, and Gemini. This new version standardizes how developers interact with caching mechanisms, which vary significantly between providers. The update also includes a breaking change with the renaming of `cost.cacheDiscountUSD` to `cost.cacheSavingsUSD` to better reflect the nature of cost savings from cache hits. AI
IMPACT Simplifies prompt caching implementation for developers working with multiple LLM providers.