Change8

v1.82.rc.1

📦 litellmView on GitHub →
18 features🐛 29 fixes1 deprecations🔧 34 symbols

Summary

This release focuses heavily on UI enhancements, particularly around Projects management and access control (RBAC), alongside numerous performance optimizations and bug fixes across model integrations and proxy functionality. Key additions include new model support and improved tracing capabilities.

Migration Steps

  1. If using older xAI models grok-2-vision-1212 or grok-3-mini, plan migration as deprecation dates have been added.

✨ New Features

  • Added support for gemini-3.1-flash-image-preview model on Vertex AI.
  • Added v1 transformation for Anthropic responses.
  • Enabled local file support for OCR.
  • Implemented Access group CRUD with bidirectional team/key synchronization.
  • Added gpt-audio-1.5 and gpt-realtime-1.5 to the model cost map.
  • Added OpenRouter native models to the model cost map.
  • Included timestamps in /project/list response.
  • Introduced UI for Projects with list and create flows.
  • Added Prometheus in_flight_requests metric to /health/backlog endpoint and Prometheus.
  • Added Agent RBAC Permission Fix to ensure internal users cannot create agents.
  • Added ability to trace metrics to Datadog.
  • Added duplicate issue detection and auto-close bot to CI.
  • Added Litellm health check tokens.
  • Added Litellm presidio stream v3 support.
  • Added secret scan test and CI job.
  • Added UI for Project Details Page.
  • Added project keys table and project dropdown to key create/edit UI.
  • Added UI for deleting projects.

🐛 Bug Fixes

  • Fixed converse handling for parallel_tool_calls.
  • Preserved forwarding server side called tools.
  • Fixed free models working correctly from the UI.
  • Added ChatCompletionImageObject in OpenAIChatCompletionAssistantMessage.
  • Fixed poetry lock issues.
  • Stripped stale mcp-session-id to prevent 400 errors across proxy workers.
  • Fixed function calling for PublicAI Apertus models.
  • Fixed Claude code plugin schema.
  • Added missing migration for LiteLLM_ClaudeCodePluginTable in the database.
  • Restored parallel_tool_calls mapping in map_openai_params for Bedrock.
  • Updated test mocks for renamed filter_server_ids_by_ip_with_info.
  • Added PROXY_ADMIN role to system user for key rotation.
  • Populated user_id and user_info for admin users in /user/info.
  • Fixed LLMClientCache._remove_key to store task references.
  • Propagated extra_headers to Upstream for image generation.
  • Passed MCP auth headers from request into tool fetch for /v1/responses and chat completions.
  • Shortened guardrail benchmark result filenames for Windows long path support.
  • Set default available_on_public_internet to true for MCP.
  • Filtered internal json_tool_call when mixed with real tools for Bedrock.
  • Fixed OIDC discovery URLs, roles array handling, and dot-notation error hints for JWT.
  • Fixed TTS metrics issues.
  • Fixed update_price_and_context_window workflow from running in forks.
  • Removed duplicate env key in scan_duplicate_issues workflow.
  • Suppressed PLR0915 in complex transform methods during linting.
  • Implemented atomic RPM rate limiting in model rate limit check.
  • Isolated get_config failures from the model sync loop in the proxy.
  • Fixed CI issue handling inline table in pyproject.toml for proxy-extras version check.
  • Bumped litellm-proxy-extras to 0.4.50 and fixed 3 failing tests.
  • Resolved flaky UI tests related to leaked @tremor/react Tooltip timer.

Affected Symbols

⚡ Deprecations

  • Added deprecation dates for xAI grok-2-vision-1212 and grok-3-mini models.