Collected sources and patterns will appear here. Add from search or the patterns library.
LLMRequest -> LLMResponse
Detect primary LLM provider HTTP errors and dynamically rewrite routing targets to a configured fallback endpoint or backup provider.
Problem it solves
Rate limits, model deprecation, or unexpected outages at a single LLM provider break downstream applications.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.