DEVELOPER TOOLS

LiteLLM’s LTS patch fixes large MCP results and duplicate guardrail checks

By IDAKIM Digital · Published

Version 1.108.3 addresses three operational failures involving Bedrock configuration, streamed MCP output and model-level post-call guardrails.

The project’s November 7 release notes list a Bedrock fix for deployments configured with an empty api_base, where requests had failed with 500 or 400 responses. They also repair MCP tool results larger than one MiB that could end with an SSE stream ended without a response error, described as broken since v1.103.0. A third fix stops model-level post_call guardrails from checking a response twice and calling the moderation provider twice. The maintainers label the release LTS and say no upgrade action is needed. The notes provide image-signature verification instructions, but IDAKIM Digital has not pulled, installed or independently tested the images. Operators should assess the patch against their own routing and guardrail configuration rather than assuming the release note proves their complete workload works.

Why it matters

If your gateway uses MCP tools that return large documents, include a result above the reported threshold in staging. Check moderation call counts and error handling alongside successful inference. Signature verification and functional testing answer different questions; retain both in a normal managed update process.

Source: LiteLLM maintainers · November 7, 2026

Product claims are attributed to the linked publisher. IDAKIM Digital has not independently tested these claims.

Read the full edition