●Change8

v1.90.0-rc.1

📦 litellmView on GitHub →
✨ 14 features🐛 23 fixes🔧 6 symbols

Summary

This release introduces Docker image signing via cosign for enhanced security and adds significant features like standardized rate limit errors and Claude Fable 5 support. Numerous bug fixes were applied across the UI, MCP handling, and various provider integrations.

Migration Steps

  1. If you use Docker, verify your image signature using the provided cosign commands, preferably using the pinned commit hash for maximum security.

✨ New Features

  • All LiteLLM Docker images are now signed with cosign; verification instructions provided.
  • Forward strict and additionalProperties to Converse toolSpec for Bedrock.
  • Added budget duration to edit team member form in the UI.
  • Standardized rate limit errors to include category, rate_limit_type, model, and llm_provider fields.
  • Added models and repository layers to LiteLLM core.
  • Included internal routes in the dashboard's generated OpenAPI types.
  • Published /v2/model/info in Swagger OpenAPI spec for the proxy.
  • Added health check support for UI callback test for Galileo.
  • Added opt-in fallback to DB team on unresolved JWT claim for JWT authentication.
  • Added organization metadata inclusion in Vantage FOCUS Tags export.
  • Added MAI-Image-2.5 image generation support for Azure AI.
  • Extended response headers hook to streaming, TTS, image generation, and pass-through in the proxy.
  • Added admin flag to disable in-product UI nudges for everyone.
  • Added Claude Fable 5 support across Anthropic, Bedrock, Vertex AI, and Azure AI.

🐛 Bug Fixes

  • Mapped system-only chat request to system input item in responses bridge.
  • Highlighted MCP cards red when the logged-in user is missing per-user environment variables.
  • Made workflow runs page fill full width in the UI.
  • Defaulted guardrails page to the Guardrails tab in the UI.
  • Kept create guardrail modal open on outside click in the UI.
  • Labeled default key type as "Full Access" on the key edit page in the UI.
  • Unified migrated-route URLs and migrated the API Reference page in the UI.
  • Allowed non-creator users to OAuth into OBO-mode MCP servers from the Tools page.
  • Allowed deleting a BYOK model after its team is deleted.
  • Prevented blocking /team/update on unchanged team budget.
  • Enabled tool calling for glm-5p1 in the Fireworks model cost map.
  • Propagated Vertex AI metadata in streaming success callbacks.
  • Showed team projects to internal users on key creation in the UI.
  • Deleted a team's BYOK models when the team is deleted.
  • Read CrowdStrike AIDR identity from both metadata bags in guardrails.
  • Mirrored upstream token lifetime instead of forcing a 1h OBO expiry for MCP.
  • Loaded MCP tool configuration tools via the OBO/passthrough-aware GET path.
  • Reserved team budget raises for proxy admins on /team/update.
  • Reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (UI/MCP).
  • Allowed team access-group grants in OAuth authorize/token access check.
  • Authorized batch files using upload target_model_names (LIT-3593) in the proxy.
  • Restored stored prompt_tokens on embedding cache hits instead of recomputing.
  • Self-healed startup/reload prisma reads on engine disconnect in the proxy.

Affected Symbols

Converse toolSpec/v2/model/infopyjwtwsCrowdStrike AIDR identitytarget_model_names