LiteLLM: Jev-driven context compaction and pass-through

The LiteLLM proxy scores older tool results with Jev and replaces low-relevance ones with short removal notices before the request reaches the LLM; a TypeSafe pass-through endpoint is documented too.

Notes

Docs; defaults: threshold 0.2, minimum 200 characters per result.

source-backed — Public repository, docs or live artifact. About this label

Destinations

Filed under

• #litellm
• #compaction
• #proxy

In collections

• Agent harnesses →