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

{
Multimodal embedding translation across proxy boundaries requires coordinating request-shape handling, image normalization, provider capability detection, error paths, and regression coverage. The streaming discrepancy is more likely isolated to Azure model-specific response adaptation and stream-mode handling, with narrower scope and lower integration risk.
}
https://github.com/berriai/litellm/issues/31178 3:1 https://github.com/berriai/litellm/issues/29995