Ishaan Jaff
2746064686
fixes: expose flag to disable token counter ( #11344 )
...
* fixes: expose flag to disable token counter
* fix add disable_token_counter
2025-06-02 21:54:24 -07:00
Ishaan Jaff
68d1cb1769
[Perf] - Add Async + Batched S3 Logging ( #11340 )
...
* fix: add s3 v2 async
* fix: add s3 v2 async
* fix: add s3 v2 async
* test: s3 v2 logging
* fixes: s3 logging
* fixes: s3 logging use max upload batch size
* fixes: s3 logging tests
* fixes: s3 logging tests
* fixes: s3 logging tests
2025-06-02 21:54:16 -07:00
Ishaan Jaff
2ce41815f5
[Feat] DD Trace - Add instrumentation for streaming chunks ( #11338 )
...
* fix: add tracing for litellm.completion
* fix: NULL span add trace
* fix: add tracing for litellm.completion streaming
* fix: add tracing for litellm.completion streaming
* fix: use a constant for str
2025-06-02 21:54:08 -07:00
Krish Dholakia
a40b81cd6b
Rate Limiting: Check all slots on redis, Reduce number of cache writes ( #11299 )
...
* fix(base_routing_strategy.py): compress increments to redis - reduces write ops
* fix(base_routing_strategy.py): make get and reset in memory keys atomic
* fix(base_routing_strategy.py): don't reset keys - causes discrepency on subsequent requests to instance
* fix(parallel_request_limiter.py): retrieve values of previous slots from cache
more accurate rate limiting with sliding window
* fix: fix test
* fix: fix linting error
2025-05-31 18:32:13 -07:00
AyrennC
8ae79178ae
feat: Add audio parameter support to gemini tts models ( #11287 )
...
* feat: Add Gemini TTS audio parameter support
- Add is_model_gemini_audio_model() method to detect TTS models
- Include 'audio' parameter in supported params for TTS models
- Map OpenAI audio parameter to Gemini speechConfig format
- Add _extract_audio_response_from_parts() method to transform audio
output to openai format
* updated unit-test to use pcm16
* - created typedict for speechconfig
- simplified gemini tts model detection
- moved gemini_tts test to test_litellm
* simplified is_model_gemini_audio_model more
2025-05-31 16:20:19 -07:00
Krish Dholakia
06484f6e5a
Xai, VertexAI, Google AI Studio - live web search support in OpenAI format ( #11251 )
...
* build(model_prices_and_context_window.json): fix 'supports_web_search' flag - openai only supports it on 2 models - gpt-4o-search-preview and gpt-4o-mini-search-preview
* feat(xai/chat): add xai web search options param support
* test: add max tokens to test
xai output very verbose
* build(xai/): add web search support for all xai models
* build(model_prices_and_cost.json): add gemini-2.0 supports web search
* feat(gemini/): map openai 'web_search_options' to google's 'googlesearch' tool
* build(model_prices_and_context_window.json): add supports_web_search for vertex_ai/gemini-2 models
* fix: fix circular reference error
* fix(convert_dict_to_response.py): handle scenario where xai returns finish reason as 'stop' for tool calls
* fix: reduce function size
* fix: import session handling
* Revert "fix: import session handling"
This reverts commit deb257dc10#11247 )
* feat: add streaming for bedrock post guard
* fix: bedrock guardrails
* fix: add clear comments
* Update litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix: clean up bedrock guardrails
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* [Fix] Responses API - Session management (#11254 )
* fix: import session handling
* fix: imports for session handler
* tests: tests for session handler
* Update enterprise/litellm_enterprise/enterprise_callbacks/session_handler.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* bump: bump litellm enterprise
* fixes: test_create_user_default_budget
* fix(xai/): filter 'strict' on tool call
* test: update test for new error string
* fix(utils.py): default to None if not set in model cost map
ensures consistent usage of 'supports_[x]' flags
* fix(fireworks_ai/): support fireworks ai document inlining on pdf's sent via openai 'file' message type
* test: update test
* test: name filter_value_from_dict
* fix(fireworks_ai/): handle cache control flag in messages
* fix(xai/chat): fix check
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-05-31 14:26:16 -07:00
Ishaan Jaff
16efb8db67
Revert "Make gemini stream thinking as reasoning_content ( #11290 )"
...
This reverts commit e0daa3da68
2025-05-31 13:29:51 -07:00
Ishaan Jaff
3b930f6736
fix: aiohttp handle transfer encoding errors gracefully
2025-05-31 13:02:07 -07:00
Ishaan Jaff
236975a742
fix: allow users to disable aiohttp transport
2025-05-31 12:32:24 -07:00
Ishaan Jaff
f95754c67f
(UI) new build
2025-05-31 12:25:29 -07:00
Ishaan Jaff
7b4fb48bd1
ui new build
2025-05-31 12:08:48 -07:00
Krish Dholakia
39849627f7
feat(parallel_request_limiter_v2.py): add sliding window logic ( #11283 )
...
* feat(parallel_request_limiter_v2.py): add sliding window logic
allows rate limiting to work across minutes
* fix(parallel_request_limiter_v2.py): decrement usage on rate limit error
* fix(base_routing_strategy.py): fix merge from redis - preserve values in in-memory cache during gap b/w push to redis and read from redis
* fix(base_routing_strategy.py): catch the delta change during redis sync
ensures values are kept in sync
* fix(parallel_request_limiter_v2.py): update tpm tracking to use slot key logic
* fix: fix linting error
* test: update testing
* test: update tests
* test: skip on rate limit or internal server errors
* test: use pytest fixture instead
* test: bump mistral model
2025-05-31 10:06:42 -07:00
Ishaan Jaff
68fd17d15e
[Fix] QA Fixes - Vector Store Object Permissions ( #11291 )
...
* fix: QA for key,team,org permissions
* fix: add_vector_store_to_registry
* fix: refactor bedrock guard
* fix: refactor using us east 1 with vector stores
* fix: code QA checks
* fix: testing for mgmt endpoints
2025-05-31 09:41:05 -07:00
Adam Holmberg
e0daa3da68
Make gemini stream thinking as reasoning_content ( #11290 )
...
When "Thought": True, return text as reasoning_content instead of
content.
fixes #10563
fixes #11000
2025-05-31 09:13:00 -07:00
Krrish Dholakia
51f716c762
build(VLLM-Passthrough-with-loadbalancing-support-(enables-using-model-list-for-VLLM-/classify-endpoint)): Closes #11205
2025-05-31 09:00:04 -07:00
Shuai Zhang
712e042aa4
fix(secret-managers): Break AzureCredentialType restriction on AZURE_CREDENTIAL ( #11272 )
2025-05-31 01:03:08 -07:00
VigneshwarRajasekaran
9df61ef08b
Wrong parameter mapping for "frequency_penalty" to "repeat_penalty" in Ollama/completion/transformation.py ( #11284 )
2025-05-31 00:58:19 -07:00
Ishaan Jaff
15ea80d2cf
ui new build
2025-05-30 23:08:07 -07:00
Ishaan Jaff
310d97c982
fix: fix linting error
2025-05-30 22:51:10 -07:00
Ishaan Jaff
d7f19bbfe3
[Bug]: Performance Fix Max langfuse clients reached: 20 is greater than 20 ( #11285 )
...
* fix: initializing langfuse clients
* fix: initializing langfuse clients
* tests: tests for langfuse cache
2025-05-30 22:34:39 -07:00
Ishaan Jaff
7e49b4e2a0
[Feat] Enforce Vector Store Access Controls on LiteLLM Auth ( #11281 )
...
* fix LiteLLM_ObjectPermissionTable
* fix include object_permission for list key
* fix key list to inclue obj permissions
* fix object permissions for vector stores on key info
* add key edit view with vector stores
* allow editing vector stores permissions
* fixes obj permissions
* feat: add obj permission on UI
* fix: add object_permission:true
* ui show org vector stores on org info
* fix: show object permissions on /org/info
* feat: allow updating obj permissions for keys
* fixes: key object permissions
* fixes: team object permissions
* fixes: org object permissions
* fix vector store selector for Orgs
* feat: add auth checks for vector store permissions
* feat: working auth checks for vector store permissions
* test vector stores auth checks
* Update litellm/proxy/_types.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix: linting
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-05-30 22:20:11 -07:00
Ishaan Jaff
2f8eb1dcc3
fix: dont require mcp pip for proxy ( #11282 )
2025-05-30 22:19:53 -07:00
Ishaan Jaff
a9d23f5d4a
[Fix] Bedrock Guard Auth Param Persistence ( #11270 )
...
* fix: using bedrock guard
* fix: bedrock guard param persistence
2025-05-30 17:24:03 -07:00
Ishaan Jaff
ea841eeb9b
[Feat] UI - show vector store permissions for Key, Team, Org ( #11277 )
...
* fix LiteLLM_ObjectPermissionTable
* fix include object_permission for list key
* fix key list to inclue obj permissions
* fix object permissions for vector stores on key info
* add key edit view with vector stores
* allow editing vector stores permissions
* fixes obj permissions
* feat: add obj permission on UI
* fix: add object_permission:true
* ui show org vector stores on org info
* fix: show object permissions on /org/info
* feat: allow updating obj permissions for keys
* fixes: key object permissions
* fixes: team object permissions
* fixes: org object permissions
* fix vector store selector for Orgs
2025-05-30 17:23:50 -07:00
Ishaan Jaff
b13d1b3ff1
ci/cd: run again
2025-05-30 09:06:03 -07:00
Krish Dholakia
44a69421ea
Anthropic - Files API w/ form-data support on passthrough + File ID support on /chat/completion ( #11256 )
...
* fix(anthropic/chat): support passing 'file_id' param to anthropic
Partial fix for LIT-200
* feat(anthropic/chat): use correct anthropic content block based on file object
* fix(anthropic/chat): fix file id for container_upload message type
* fix(anthropic/chat/transformation.py): fix check for adding code execution to tool calls - needed for 'container_upload' message type
* fix(llm_passthrough_endpoints.py): support reading form data for anthropic passthrough
* refactor(llm_passthrough_endpoints.py): refactor block into function for easier testing
* test: add unit test
* fix: don't pass in empty tools list
* [Fix] Responses API - Session management (#11254 )
* fix: import session handling
* fix: imports for session handler
* tests: tests for session handler
* Update enterprise/litellm_enterprise/enterprise_callbacks/session_handler.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* bump: bump litellm enterprise
* fixes: test_create_user_default_budget
* fix: fix linting error
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-05-29 23:54:24 -07:00
Krish Dholakia
5d4ae9aa4d
Support dropping non-openai params when specified in additional_drop_params + Add VertexAI Anthropic support on /v1/messages ( #11246 )
...
* feat(utils.py): support dropping non-openai params when specified via additional drop params
Closes https://github.com/BerriAI/litellm/issues/11205
* fix(utils.py): fix linting error
* refactor(handler.py): add custom llm provider to anthropic messages provider config exception
* feat: initial commit adding vertex ai anthropic support on `/v1/messages`
* test: add working unit test
* test(vertex_ai_partner_models/anthropic): add /v1/messages support for anthropic api
Adds vertex ai auth
* feat(vertex_ai/anthropic): return correct url when calling via `/v1/messages`
* fix: more alignment to expected anthropic request format
* fix: fix ruff linting check
* Removed syntax error from docs (#11242 )
* [Feat]: Add Bedrock InvokeAgents as a /chat/completions route on LiteLLM (#11239 )
* feat: init structure for bedrock AGENTs
* feat: add basic routing for bedrock AGENTs
* feat: add basic transforms for bedrock AGENTs
* fix: url for bedrock agent runtime
* fix: working agents request
* feat: working agents non-streaming request
* feat: bedrock agents
* feat: add streaming for bedrock agents
* feat: add cost tracking for bedrock agents
* docs litellm with bedrock agents
* fix: linting errors
* test: invoke agents tests
* fix: import session handling
* Revert "fix: import session handling"
This reverts commit deb257dc10#11247 )
* feat: add streaming for bedrock post guard
* fix: bedrock guardrails
* fix: add clear comments
* Update litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix: clean up bedrock guardrails
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* [Fix] Responses API - Session management (#11254 )
* fix: import session handling
* fix: imports for session handler
* tests: tests for session handler
* Update enterprise/litellm_enterprise/enterprise_callbacks/session_handler.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* bump: bump litellm enterprise
* fixes: test_create_user_default_budget
* fix: fix linting error
* fix: fix linting error
---------
Co-authored-by: Fadil Rahman <87557055+fadil4u@users.noreply.github.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-05-29 23:42:48 -07:00
Ishaan Jaff
c9062ac044
fixes: test_create_user_default_budget
2025-05-29 21:12:28 -07:00
Ishaan Jaff
7fcbb38d91
[Fix] Responses API - Session management ( #11254 )
...
* fix: import session handling
* fix: imports for session handler
* tests: tests for session handler
* Update enterprise/litellm_enterprise/enterprise_callbacks/session_handler.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-05-29 20:36:02 -07:00
Ishaan Jaff
f24d8919c4
[Feat]: Guardrails - Add streaming for bedrock post guard ( #11247 )
...
* feat: add streaming for bedrock post guard
* fix: bedrock guardrails
* fix: add clear comments
* Update litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix: clean up bedrock guardrails
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-05-29 20:01:44 -07:00
Ishaan Jaff
0d4c85c419
Revert "fix: import session handling"
...
This reverts commit deb257dc10
2025-05-29 17:54:24 -07:00
Ishaan Jaff
deb257dc10
fix: import session handling
2025-05-29 17:48:34 -07:00
Ishaan Jaff
5e6f6ddc52
[Feat]: Add Bedrock InvokeAgents as a /chat/completions route on LiteLLM ( #11239 )
...
* feat: init structure for bedrock AGENTs
* feat: add basic routing for bedrock AGENTs
* feat: add basic transforms for bedrock AGENTs
* fix: url for bedrock agent runtime
* fix: working agents request
* feat: working agents non-streaming request
* feat: bedrock agents
* feat: add streaming for bedrock agents
* feat: add cost tracking for bedrock agents
* docs litellm with bedrock agents
* fix: linting errors
* test: invoke agents tests
2025-05-29 16:48:55 -07:00
AnilAren
9a82a69593
fix: bedrock ai21 jamba models will work now ( #11233 )
2025-05-29 08:31:05 -07:00
Krrish Dholakia
077b69eafa
fix(key_management_endpoints.py): allow master key rotations for OSS users
...
Closes https://github.com/BerriAI/litellm/issues/11210
2025-05-28 22:56:25 -07:00
Krish Dholakia
8fb2779c9e
build(model_prices_and_context_window.json): add supports parallel function calling to all gemini models ( #11225 )
2025-05-28 22:32:02 -07:00
Krish Dholakia
1995c7aad5
fix(utils.py): support non default params for audio transcription ( #11212 )
...
* fix(utils.py): support non default params for audio transcription
allows passing provider specific params straight through on transcription calls
* fix(gpt_transformation.py): fix o_series model routing
call _transform_request on async event
* refactor: refactor tests
* test(test_azure_chat_o_series_transformation.py): add unit test for azure o series error
* test: update test
* test: update json
* fix: fix mutiple keyword error
2025-05-28 22:24:02 -07:00
Krish Dholakia
ba39f9e360
Helicone base url support + fix for embedding cache hits on str input ( #11211 )
...
* fix(helicone.py): add helicone api base support
Fixes https://github.com/BerriAI/litellm/issues/10825
* test: add unit test for cache hit response on embedding calls
* fix(caching_handler.py): fix handling cache hit on embedding when input is string
Fixes LIT-197
* docs(helicone_integration.md): document new helicone api base param
2025-05-28 22:02:55 -07:00
Ishaan Jaff
2372492237
test: fix test_user_email_metrics
2025-05-28 21:30:47 -07:00
Ishaan Jaff
edf85f2394
fix: code QA check
2025-05-28 21:16:17 -07:00
Ishaan Jaff
745d9acdc3
fix: code QA check
2025-05-28 21:03:33 -07:00
Ishaan Jaff
68a2466f3d
fix debug langfuse clients started ( #11221 )
2025-05-28 19:16:52 -07:00
Ishaan Jaff
df76b8c7b9
ui new build
2025-05-28 18:53:37 -07:00
Stephen Solka
3960e08dd7
Fix: Remove duplicate object_permission field in LiteLLM_TeamTable ( #11219 )
...
This fixes a mypy error where 'object_permission' was already defined on line 1267.
🤖 Generated with [Claude Code](https://claude.ai/code )
Co-authored-by: Stephen Solka <stephen@standd.io>
Co-authored-by: Claude <noreply@anthropic.com>
2025-05-28 18:40:45 -07:00
Ishaan Jaff
4e6c4beef8
[Feat] Permission management vector stores on LiteLLM Key, Team, Orgs ( #11213 )
...
* fix: init commit for object permissions
* fix: init commit for object permissions
* fix: add vector_store_id to permissions
* fix vector store selector
* feat:add vector store permission mgmt
* feat: ui add allowed vector stores dropdown
* feat: add new vector store object permissions
* testing: key mgmt
* fix: stor vector store permissions on team
* ui select vector store for teams
* ui add vector store settings for orgs
* feat: allow setting org vector store permissions
* test: adding team permissions for vector stores
2025-05-28 16:58:53 -07:00
Vinnie-Singleton-NN
178a614d4a
Add sentry sample rate ( #10283 )
...
* Add SENTRY_API_SAMPLE_RATE configuration option for Sentry SDK
* removed print line
* Update Sentry documentation with sample rate information
---------
Co-authored-by: Vinnie <vinnie@Vinnies-MacBook-Pro.local>
2025-05-28 16:44:10 -07:00
Regis David Souza Mesquita
56c32ef503
Update mistral-medium prices and context sizes ( #10729 )
...
* Update mistral-medium prices and context sizes
While testing the Mistral model, I noticed a discrepancy in the pricing shown on the logs screen. After reviewing the code, I confirmed that the pricing values were incorrect.
This PR corrects the input and output token pricing for the latest Mistral model and adds the newly released mistral-medium-2505 version.
* Adds tool calling flag to mistral-medium
* Adds mistral-medium price updates to the main model price file
* Update model_prices_and_context_window_backup.json
sets mistral medium alias to the old values as it probably points to the old version.
* Update model_prices_and_context_window.json
* Update model_prices_and_context_window_backup.json
* Update model_prices_and_context_window.json
2025-05-28 16:42:28 -07:00
Ishaan Jaff
9a6d5c119e
feat: Allow Adding MCP Servers Through LiteLLM UI ( #11208 )
...
* feat: MCP Servers with CRUD operations (#10699 )
* feat: mcp CRUD operations with authn/authz
* feat: mcp server UI
* mcp server page with overview, mcp tools, and settings page
* Adding MCP Server flow
* prisma generate before test
* UI callbacks add/remove with api server refetch
* test fix: poetry run prisma
* feat: mcp server db and config connection
* fix: MCPTool filter on description when not present
* feat: mcp on UI and integrated with list tools
* feat: Update mcp server endpoint
* tests: Unit and integration tests for mcp management endpoints
* fix: docs and ensuring global_mcp_manage up to date
* ui: remove the mcp tools view
* fix: ruff lint
* fix: unit -> integration test area
* fix(ui): remove left nav menu of previous tools
---------
Co-authored-by: wagnerjt <wagnerjt@github.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
* fix: sync DB MCP tools with in memory
* fix: sync DB MCP tools with in memory
* fix: stop using prisma.models
* fix: code qa check
* fix: import MCP
* fix: code QA checks
* fix: code QA checks
* fixes - only list tools for the specific MCP server
* fix: only list MCP tools for selected server
* fix linting error
---------
Co-authored-by: Tyler Wagner <wagnerjt@users.noreply.github.com>
Co-authored-by: wagnerjt <wagnerjt@github.com>
2025-05-28 16:29:27 -07:00
Krrish Dholakia
cc780ecf5a
fix(vertex_llm_base.py): handle default vertex location
2025-05-28 11:33:39 -07:00
Adnan Alkattan
18f7316b08
Add missing request_kwargs to function call ( #11202 )
2025-05-28 10:55:41 -07:00
