v1.71.3-rc #11292

krrishdholakia announced in Announcements

krrishdholakia
May 31, 2025
Maintainer

What's Changed

feat: Make gemini accept the openai parameter parallel_tool_calls by @aholmberg in feat: Make gemini accept the openai parameter parallel_tool_calls #11125
Fix [Bug]: docker-compose healthcheck test uses curl but curl is not in the image #9295 docker-compose healthcheck test uses curl but curl is not in the image by @agajdosi in Fix #9295 docker-compose healthcheck test uses curl but curl is not in the image #9737
[Feat] Add /image/edits support for Azure by @ishaan-jaff in [Feat] Add /image/edits support for Azure #11160
Fix deprecation_date value for llama groq models by @kiriloman in Fix deprecation_date value for llama groq models #11151
[Fix] Rollback to httpx==0.27.0 by @ishaan-jaff in [Fix] Rollback to httpx==0.27.0 #11146
Doc update for azure openai by @ketangangal in Doc update for azure openai #11161
Litellm fix GitHub action testing by @krrishdholakia in Litellm fix GitHub action testing #11163
[Feat - Contributor PR] Add Video support for Bedrock Converse by @ishaan-jaff in [Feat - Contributor PR] Add Video support for Bedrock Converse #11166
[Fixes] Aiohttp transport fixes - add handling for aiohttp.ClientPayloadError and ssl_verification settings by @ishaan-jaff in [Fixes] Aiohttp transport fixes - add handling for aiohttp.ClientPayloadError and ssl_verification settings #11162
prevent leaking sensitive keys to langfuse + support forwarding /sso/key/generate to the server root path url by @krrishdholakia in prevent leaking sensitive keys to langfuse + support forwarding /sso/key/generate to the server root path url #11165
[Fix] - Duplicate maxTokens parameter being sent to Bedrock/Claude model with thinking by @ishaan-jaff in [Fix] - Duplicate maxTokens parameter being sent to Bedrock/Claude model with thinking #11181
Integration with Nebius AI Studio added by @Aktsvigun in Integration with Nebius AI Studio added #11143
Codestral - return litellm latency overhead on /v1/completions + Add 'contains' support for ChatCompletionDeltaToolCall by @krrishdholakia in Codestral - return litellm latency overhead on /v1/completions + Add '__contains__' support for ChatCompletionDeltaToolCall #10879
Ollama Chat - parse tool calls on streaming by @krrishdholakia in Ollama Chat - parse tool calls on streaming #11171
[Fix] Prometheus Metrics - Do not track end_user by default + expose flag to enable tracking end_user on prometheus by @ishaan-jaff in [Fix] Prometheus Metrics - Do not track end_user by default + expose flag to enable tracking end_user on prometheus #11192
[Fix]: Add cost tracking for image edits endpoint [OpenAI, Azure] by @ishaan-jaff in [Fix]: Add cost tracking for image edits endpoint [OpenAI, Azure] #11186
VertexAI - codeExecution tool support + anyOf handling by @krrishdholakia in VertexAI - codeExecution tool support + anyOf handling #11195
Add Pangea provider to Guardrails hook by @ryanmeans in Add Pangea provider to Guardrails hook #10775
Return anthropic thinking blocks on streaming + VertexAI Minor Fixes & Improvements (Thinking, Global regions, Parallel tool calling) by @krrishdholakia in Return anthropic thinking blocks on streaming + VertexAI Minor Fixes & Improvements (Thinking, Global regions, Parallel tool calling) #11194
Azure OIDC provider improvements + OIDC audience bug fix by @nikoizs in Azure OIDC provider improvements + OIDC audience bug fix #10054
[Feat] Add well known MCP servers to LiteLLM by @ishaan-jaff in [Feat] Add well known MCP servers to LiteLLM #11209
Add missing request_kwargs to get_available_deployment call by @Nitro963 in Add missing request_kwargs to get_available_deployment call #11202
feat: Allow Adding MCP Servers Through LiteLLM UI by @ishaan-jaff in feat: Allow Adding MCP Servers Through LiteLLM UI #11208
Add price for gpt4o mini audio preview without date by @Jacobh2 in Add price for gpt4o mini audio preview without date #11207
Put "all proxy models" if no models are selected by @NANDINI-star in Put "all proxy models" if no models are selected #11187
Removed teamInfo call and used existing teamsList call by @NANDINI-star in Removed teamInfo call and used existing teamsList call #11051
build(deps): bump next from 14.2.26 to 15.2.4 in /ui/litellm-dashboard by @dependabot in build(deps): bump next from 14.2.26 to 15.2.4 in /ui/litellm-dashboard #11216
Improve display of model tags on Keys, Teams and Org page by @NANDINI-star in Improve display of model tags on Keys, Teams and Org page #11022
Update mistral-medium prices and context sizes by @regismesquita in Update mistral-medium prices and context sizes #10729
Add sentry sample rate by @Vinnie-Singleton-NN in Add sentry sample rate #10283
[Feat] Permission management vector stores on LiteLLM Key, Team, Orgs by @ishaan-jaff in [Feat] Permission management vector stores on LiteLLM Key, Team, Orgs #11213
Fix: Remove duplicate object_permission field in LiteLLM_TeamTable by @trashhalo in Fix: Remove duplicate object_permission field in LiteLLM_TeamTable #11219
[UI] SCIM fixes SCIM token exposed on UI by @ishaan-jaff in [UI] SCIM fixes SCIM token exposed on UI #11220
[Debug] Fix - debug langfuse clients started by @ishaan-jaff in [Debug] Fix - debug langfuse clients started #11221
Helicone base url support + fix for embedding cache hits on str input by @krrishdholakia in Helicone base url support + fix for embedding cache hits on str input #11211
fix(utils.py): support non default params for audio transcription + fix calling azure o_series models by @krrishdholakia in fix(utils.py): support non default params for audio transcription + fix calling azure o_series models #11212
Add 'supports_parallel_function_calling' to all gemini models by @krrishdholakia in Add 'supports_parallel_function_calling' to all gemini models #11225
fix the litellm CLA reference by @emmanuel-ferdman in fix the litellm CLA reference #11230
Update docker_quick_start.md – Replace gpt-3.5-turbo with gpt-4o in Proxy Getting Started Guide by @VigneshwarRajasekaran in Update docker_quick_start.md – Replace gpt-3.5-turbo with gpt-4o in Proxy Getting Started Guide #11223
fix: bedrock ai21 jamba models will work now by @AnilAren in fix: bedrock ai21 jamba models will work now #11233
Fix syntax error in Python example code in LiteLLM docs by @fadil4u in Fix syntax error in Python example code in LiteLLM docs #11242
[Feat]: Add Bedrock InvokeAgents as a /chat/completions route on LiteLLM by @ishaan-jaff in [Feat]: Add Bedrock InvokeAgents as a /chat/completions route on LiteLLM #11239
[Feat]: Guardrails - Add streaming for bedrock post guard by @ishaan-jaff in [Feat]: Guardrails - Add streaming for bedrock post guard #11247
[Fix] Responses API - Session management by @ishaan-jaff in [Fix] Responses API - Session management #11254
Support dropping non-openai params when specified in additional_drop_params + Add VertexAI Anthropic support on /v1/messages by @krrishdholakia in Support dropping non-openai params when specified in additional_drop_params + Add VertexAI Anthropic support on /v1/messages #11246
Anthropic - Files API w/ form-data support on passthrough + File ID support on /chat/completion by @krrishdholakia in Anthropic - Files API w/ form-data support on passthrough + File ID support on /chat/completion #11256
[Feat] UI - show vector store permissions for Key, Team, Org by @ishaan-jaff in [Feat] UI - show vector store permissions for Key, Team, Org #11277
[Fix] Bedrock Guard Auth Param Persistence by @ishaan-jaff in [Fix] Bedrock Guard Auth Param Persistence #11270
Streamline session expiration in UI by @whitfin in Streamline session expiration in UI #11279
[Chore] Only run init mcp servers if the mcp pip is available by @ishaan-jaff in [Chore] Only run init mcp servers if the mcp pip is available #11282
[Feat] Enforce Vector Store Access Controls on LiteLLM Auth by @ishaan-jaff in [Feat] Enforce Vector Store Access Controls on LiteLLM Auth #11281
[Bug]: Performance Fix Max langfuse clients reached: 20 is greater than 20 by @ishaan-jaff in [Bug]: Performance Fix Max langfuse clients reached: 20 is greater than 20 #11285
Wrong parameter mapping for "frequency_penalty" to "repeat_penalty" by @VigneshwarRajasekaran in Wrong parameter mapping for "frequency_penalty" to "repeat_penalty" #11284
fix(secret-managers): Break AzureCredentialType restriction on AZURE_CREDENTIAL by @hcoona in fix(secret-managers): Break AzureCredentialType restriction on AZURE_CREDENTIAL #11272
Swap Cohere and Cohere Chat provider by @keyute in Swap Cohere and Cohere Chat provider #11173
Increase timeout by @SmartManoj in Increase timeout #11288
Make gemini stream thinking as reasoning_content by @aholmberg in Make gemini stream thinking as reasoning_content #11290
[Fix] QA Fixes - Vector Store Object Permissions by @ishaan-jaff in [Fix] QA Fixes - Vector Store Object Permissions #11291
feat(parallel_request_limiter_v2.py): add sliding window logic by @krrishdholakia in feat(parallel_request_limiter_v2.py): add sliding window logic #11283

New Contributors

@agajdosi made their first contribution in Fix #9295 docker-compose healthcheck test uses curl but curl is not in the image #9737
@ketangangal made their first contribution in Doc update for azure openai #11161
@Aktsvigun made their first contribution in Integration with Nebius AI Studio added #11143
@ryanmeans made their first contribution in Add Pangea provider to Guardrails hook #10775
@nikoizs made their first contribution in Azure OIDC provider improvements + OIDC audience bug fix #10054
@Nitro963 made their first contribution in Add missing request_kwargs to get_available_deployment call #11202
@Vinnie-Singleton-NN made their first contribution in Add sentry sample rate #10283
@trashhalo made their first contribution in Fix: Remove duplicate object_permission field in LiteLLM_TeamTable #11219
@VigneshwarRajasekaran made their first contribution in Update docker_quick_start.md – Replace gpt-3.5-turbo with gpt-4o in Proxy Getting Started Guide #11223
@AnilAren made their first contribution in fix: bedrock ai21 jamba models will work now #11233
@fadil4u made their first contribution in Fix syntax error in Python example code in LiteLLM docs #11242
@whitfin made their first contribution in Streamline session expiration in UI #11279
@hcoona made their first contribution in fix(secret-managers): Break AzureCredentialType restriction on AZURE_CREDENTIAL #11272

Full Changelog: v1.71.1-stable...v1.71.3-rc

This discussion was created from the release v1.71.3-rc.

Replies: 0 comments

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment