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

{
Vertex-specific work spans two substantial capabilities, requiring provider integration, request metadata propagation, API-surface compatibility, and broader testing. The search-key feature is complex but more contained and can reuse existing routing, cooldown, and failover infrastructure.
}
https://github.com/berriai/litellm/issues/32225 3:2 https://github.com/berriai/litellm/issues/32118