BerriAI shipped LiteLLM v1.103.2 on 2026-10-01 (PyPI ~06:20Z; 17 commits vs 1.103.1): forward Claude Code safeguards / dangerous-tool-use beta unchanged to Anthropic, Bedrock, Vertex, and Azure AI Foundry so auto mode works behind the proxy; attribute CLI session spend to a per-user cli-session alias for daily activity BI; restore pre-config-wins for pass-through endpoints.

Key Takeaways

  • ✓Release v1.103.2 at 2026-10-01T06:37:31Z; 17 commits vs v1.103.1
  • ✓Forward Claude Code safeguards + dangerous-tool-use beta to Anthropic/Bedrock/Vertex/Azure Foundry so auto mode returns safeguard_results
  • ✓CLI session spend attributed to per-user cli-session alias for daily activity BI (#40541/#43642/#43656)
  • ✓Restore pass-through pre-config-wins (#43962); verify Docker with cosign
  • ✓pip install 'litellm==1.103.2'; https://docs.litellm.ai/docs/ ; https://pypi.org/project/litellm/1.103.2/
🧭

Finished reading? Explore benchmark rankings & pricing

Real-world SWE-bench scores & $20/mo vs API cost break-even calculator

🔬

In-Depth Technical Analysis

Background

Teams point Claude Code at LiteLLM Proxy. v1.103.1 stripped safeguards, breaking auto mode; CLI session keys appeared as hashes in daily activity BI; pass-through pre-config priority regressed.

What shipped

v1.103.2 (17 commits vs 1.103.1) forwards safeguards + dangerous-tool-use beta to Anthropic/Bedrock/Vertex/Azure Foundry; attributes CLI spend to per-user cli-session; restores pass-through pre-config-wins; cosign-signed Docker.

Benchmarks

No TTFT/SWE numbers—stable-line compatibility patch. Anchors: GitHub 2026-10-01T06:37:31Z; PyPI ~06:20Z.

Get started

pip install 'litellm==1.103.2'. Docs: https://docs.litellm.ai/docs/ ; https://pypi.org/project/litellm/1.103.2/