AIWHYS

Technology

model gateway

2 synchronized stories carry this tag.

Agents & toolsShipped

LiteLLM 1.100.1 fixes retry-history retention in stable routing

LiteLLM 1.100.1 patches the stable 1.100 line so retry breadcrumbs stop retaining every earlier request and removes spend-attribution backports from that branch. The signed release retains 1.100's governed routing, agent-registry search, access-group budgets, MCP toolset enforcement, guardrail logging and job-ownership controls.

Why it matters: The patch narrows unnecessary request-history retention in retry paths and changes which spend-attribution fixes operators can assume are present on the stable line.

Read storyOriginal source · github.com
InfrastructureShipped

LiteLLM 1.98 adds deprecation alerts and gateway security controls

LiteLLM 1.98 added proactive model-retirement alerts and a deprecations endpoint, stripped callback credentials from request metadata, scoped file pagination to the caller, introduced deployment-specific failure and cooldown policies, and published signed-container verification instructions.

Why it matters: The release addresses lifecycle visibility, credential leakage, tenant isolation, fallback behavior, and supply-chain verification at a shared model-gateway boundary.

Read storyOriginal source · github.com