Sorting LiteLLM GitHub issues by difficulty to implement. Higher = harder.

{
The left task has broader cross-provider request-normalization implications, involving interception behavior, tool-selection semantics, and compatibility testing. The right task is comparatively localized to endpoint construction and regression coverage.
}
https://github.com/berriai/litellm/issues/30822 3:1 https://github.com/berriai/litellm/issues/25748