scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-14 23:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 102
28599 commits 2357 branches 1407 tags 2.7 GiB
Commit graph

28599 commits

This branch
This branch
All branches
Author SHA1 Message Date
Cesar Garcia
6a3e6465ea
fix(completion): transform image content in tool results for Responses API (#17799) 
When using litellm.completion() with model="openai/responses/...", images
in tool message content were not being transformed from Chat Completion
format to Responses API format.

Chat Completion format: {"type": "image_url", "image_url": {"url": "..."}}
Responses API format: {"type": "input_image", "image_url": "..."}

This caused OpenAI to reject the request with error 400 since "image_url"
is not a valid type for function_call_output content.
 2025-12-11 08:21:05 -08:00
Cesar Garcia
2e303bf556
fix(anthropic): capture web_search_tool_result in streaming for multi-turn conversations (#17798) 
This fix addresses two issues with Anthropic web search streaming:

1. Fix trailing {} in tool call arguments
   - web_search_tool_result blocks have input_json_delta events that were
     incorrectly emitted as tool calls
   - Added current_content_block_type tracking to only emit tool calls for
     tool_use and server_tool_use blocks

2. Capture web_search_tool_result for multi-turn
   - The web_search_tool_result content comes ALL AT ONCE in content_block_start
   - Now captured in provider_specific_fields.web_search_results
   - stream_chunk_builder combines these for final message
   - Allows multi-turn conversations to work with streaming web search
 2025-12-11 08:19:23 -08:00
YutaSaito
13df50830d
chore: prefer standard trace id for Langfuse logging (#17791) 2025-12-11 08:18:45 -08:00
CyrusTC
5d326386fb
feat(bedrock): add serviceTier support for Converse API (#17810) 
Add support for the Bedrock Converse API serviceTier parameter to allow
specifying processing tier (priority, default, or flex).

Changes:
- Add ServiceTierBlock type in litellm/types/llms/bedrock.py
- Add serviceTier to CommonRequestObject
- Add serviceTier to get_config_blocks() in AmazonConverseConfig
- Add comprehensive tests for serviceTier functionality
- Add documentation for serviceTier usage

This allows users to configure service tier via:
- litellm_params in proxy config
- optional_params in SDK calls
 2025-12-11 08:16:32 -08:00
Cesar Garcia
97be0da0d2
fix(azure_ai): Remove unsupported params from Azure AI Anthropic requests (#17822) 
* fix(azure_ai): Remove unsupported params from Azure AI Anthropic requests

Azure AI Anthropic endpoint rejects max_retries and stream_options parameters
with "Extra inputs are not permitted" error. These are LiteLLM-internal
parameters that should not be sent to the API.

Fixes 400 Bad Request error when using azure_ai/claude-sonnet-4-5 and other
Azure AI Anthropic models.

* test(azure_ai): Add test for unsupported params removal in Azure AI Anthropic

Verifies that max_retries, stream_options, and extra_body are properly
removed from the request before sending to Azure AI Anthropic endpoint.
 2025-12-11 08:09:13 -08:00
Ashton Sidhu
a514313540
Add Hiddenlayer Guardrail Hooks (#17728) 
* Core logic working, need to add tests

* Re add removed files

* Remove mistaken files

* one more file

* Add deployment params

* Add tests

* Remove unused imports

* Update docs from feedback

* Update guardrails
 2025-12-11 07:43:26 -08:00
Sameer Kankute
3de46889bb
Merge pull request #17805 from BerriAI/litellm_fix_azure_anthropic_model_map 
Fix llm provider for azure_ai in model map
 2025-12-11 16:04:11 +05:30
Sameer Kankute
51065295ba Fix llm provider for azure_ai in model map 2025-12-11 11:36:56 +05:30
Sameer Kankute
8942053c8b
Merge pull request #17700 from BerriAI/litellm_batches_passthrough_cost_tracking 
Add anthropic retrieve batches and retreive file content support
 2025-12-11 10:31:54 +05:30
Sameer Kankute
1107febf05
Merge pull request #17803 from BerriAI/litellm_preserve_system_instructions 
fix: Preserve systemInstructions for vertex ai generate content request
 2025-12-11 10:31:08 +05:30
Sameer Kankute
9344d29a15 fix: Preserve systemInstructions for vertex ai generate content request 2025-12-11 09:52:32 +05:30
Sameer Kankute
2ea855d225
Merge pull request #17707 from raghav-stripe/raghav-fix-responsesapi-rl 
fix: responses api not applying tpm rate limits on api keys
 2025-12-11 08:57:16 +05:30
Shivam Rawat
9d7a255d55
made litellm proxy and sdk difference cleaner in overview (#17790) 2025-12-10 19:14:49 -08:00
Cesar Garcia
b2e3f56f69
feat(models): add Mistral Codestral 2508, Devstral 2512, and Labs Devstral Small 2512 (#17801) 
Add newly released Mistral coding models:
- mistral/codestral-2508: 256K context, $0.30/$0.90 per M tokens
- mistral/devstral-2512: 256K context, $0.40/$2.00 per M tokens
- mistral/labs-devstral-small-2512: 256K context, $0.10/$0.30 per M tokens
 2025-12-10 19:14:02 -08:00
Ishaan Jaff
4a7437ba5f
[Feat] Agent Gateway - allow adding langgraph, bedrock agent core agents (#17802) 
* fix: langgraph bridge streaming

* add public/agents/fields

* test_a2a_completion_bridge_non_streaming

* TestA2AStreamingTransformation

* AgentCredentialFieldMetadata

* add new logo

* refactor add agent

* fix add dynamic fields

* feat allow adding langgraph agent

* add langgraph provider

* stash

* add AgentCreateInfo

* agent_create_fields

* fix fields

* test_a2a_completion_bridge_bedrock_agentcore

* test_a2a_completion_bridge_bedrock_agentcore

* add public endpoints

* fix a2a endpoints

* fix dynamic fields
 2025-12-10 19:13:50 -08:00
Sameer Kankute
ad5d94a82f
Merge pull request #17771 from BerriAI/litellm_db_videos_issue 
fix: respect videos content db creds
 2025-12-11 08:27:43 +05:30
Sameer Kankute
44d57b695a remove print statment 2025-12-11 08:22:22 +05:30
Ishaan Jaff
059fedbed5
[Feat] Agent Gateway - Track agent_id in SpendLogs (#17795) 
* add agent_id in metadata in spend logs

* add agent_id in SpendLogsPayload

* add agent_id in SpendLogsPayload

* add _set_agent_id_on_logging_obj

* add agent id tracking in SpendLogs

* add agent id in spend logs

* fix create_a2a_client

* test_asend_message_passes_agent_id_to_callback

* test_get_logging_payload_includes_agent_id_from_kwargs

* test_asend_message_streaming_triggers_callbacks

* fix asend_message_streaming

* asend_message_streaming

* A2AStreamingIterator

* _handle_stream_message

* test_asend_message_streaming_propagates_metadata
 2025-12-10 16:09:56 -08:00
Ishaan Jaff
5d456bcdc3
[Feat] UI SSO - allow fetching role from generic SSO provider (Keycloak) (#17787) 
* fix ui SSO

* TestGenericResponseConvertorUserRole

* Assigning User Roles via SSO
 2025-12-10 13:09:28 -08:00
Alexsander Hamir
439bb5bfe3
fix: suggest Gunicorn instead of uvicorn when using max_requests_before_restart (#17788) 2025-12-10 13:09:00 -08:00
Ishaan Jaff
7ad2a58dcd
[Feat] A2a Gateway - allow using bedrock agentcore, langgraph agents with A2a Gateway (#17786) 
* init LANGGRAPH

* init LangGraphConfig

* init LangGraphConfig types

* init langgraph

* init getting api base and key

* init transform langgraph

* fix SSE issues

* test_langgraph_acompletion_non_streaming

* add LangGraph to docs

* docs: Setting Up a Local LangGraph Server

* fix langgraph SSE

* fix import uuid

* init A2A to LiteLLM Completion Bridge

* add send message for bridge

* test_a2a_completion_bridge_non_streaming

* add A2ACompletionBridgeTransformation

* add a2a send message support

* init a2a bridge
 2025-12-10 13:08:43 -08:00
Ishaan Jaff
49b91c4a35
[Feat] A2a gateway - Add cost per token pricing (#17780) 
* fix calculate_a2a_cost

* add cost_per_query

* add test_asend_message_uses_cost_per_query

* fix: _initialize_slack_alerting_jobs

* feat: add token tracking for agents invoke

* add A2ARequestUtils

* add _set_usage_on_logging_obj

* test_asend_message_token_tracking

* add _handle_a2a_response_logging

* test_asend_message_streaming_token_tracking

* add A2AStreamingIterator

* add cost calculator for agents

* test_asend_message_uses_input_output_cost_per_token

* docs gix
 2025-12-10 13:08:15 -08:00
Alexsander Hamir
ccb6cd880a
[Perf] - Cut memory leak in half (#17784) 
Stop passing references to large objects to fire-and-forget tasks.
 2025-12-10 12:31:58 -08:00
Ishaan Jaff
5ee32167c0
[Feat] New Provider - add langgraph (#17783) 
* init LANGGRAPH

* init LangGraphConfig

* init LangGraphConfig types

* init langgraph

* init getting api base and key

* init transform langgraph

* fix SSE issues

* test_langgraph_acompletion_non_streaming

* add LangGraph to docs

* docs: Setting Up a Local LangGraph Server

* fix langgraph SSE

* fix import uuid
 2025-12-10 12:30:35 -08:00
Ishaan Jaff
115a14891d
[Feat] Agent Gateway - Add token counting non streaming + streaming (#17779) 
* fix calculate_a2a_cost

* add cost_per_query

* add test_asend_message_uses_cost_per_query

* fix: _initialize_slack_alerting_jobs

* feat: add token tracking for agents invoke

* add A2ARequestUtils

* add _set_usage_on_logging_obj

* test_asend_message_token_tracking

* add _handle_a2a_response_logging

* test_asend_message_streaming_token_tracking

* add A2AStreamingIterator
 2025-12-10 11:45:28 -08:00
Krish Dholakia
8bc5e2ca7f
Add /v1/messages/count_tokens endpoint documentation (#17772) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2025-12-10 11:34:11 -08:00
Krish Dholakia
7a773b738b
Add docstring to add_new_model endpoint (#17778) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2025-12-10 11:25:07 -08:00
Krrish Dholakia
4ea758767a build: update poetry.lock 2025-12-10 11:09:28 -08:00
Ishaan Jaff
7a33579af6
[Feat] Agent Gateway - Add cost per query for agent invocations (#17774) 
* fix calculate_a2a_cost

* add cost_per_query

* add test_asend_message_uses_cost_per_query

* fix: _initialize_slack_alerting_jobs
 2025-12-10 10:43:52 -08:00
saisurya237
f3ead2c153
add a new feature fix to expose the team alias when authenticating th… (#17725) 
* CLI SSO: show team aliases in team selection

* temp poetry lock fix

* add poetry.lock to gitignore

* Revert proxy_server background job refactor

* Revert proxy_server background job refactor

* rever gitignore and poetry lock file
 2025-12-10 10:10:28 -08:00
yuneng-jiang
ba554a86b9
Merge pull request #16843 from BerriAI/litellm_allow_custom_mount_paths 
[Feature] Allow Root Path to Redirect when Docs not on Root Path
 2025-12-10 09:52:30 -08:00
Sameer Kankute
15e5a8251e fix: respect videos content db creds 2025-12-10 23:00:01 +05:30
Sameer Kankute
dea62e3f60
Merge pull request #17769 from BerriAI/litellm_test_fix 
Fix nvdia and geminin tests
 2025-12-10 22:29:04 +05:30
Sameer Kankute
ad45fc7cce
Merge pull request #17770 from BerriAI/litellm_deepseek_v3.2 
Add DeepSeek-V3.2 model support
 2025-12-10 22:28:50 +05:30
Sameer Kankute
4c78c1afc8
Merge pull request #17756 from BerriAI/litellm_add_gemini_computer_use 
Add support for computer use for gemini
 2025-12-10 22:28:37 +05:30
Sameer Kankute
05a82ae570 Add support for deepseek v3.2 2025-12-10 22:21:04 +05:30
Sameer Kankute
ec30032bc3 Fix nvdia and geminin tests 2025-12-10 22:05:11 +05:30
Sameer Kankute
0f99517170 Fix lint error 2025-12-10 18:28:29 +05:30
Sameer Kankute
9e3a04a725 Add batch passthrough endpoint cost tracking for anthropic 2025-12-10 18:24:31 +05:30
Sameer Kankute
ad87aa1926 fix code quality qa 2025-12-10 17:24:16 +05:30
Sameer Kankute
a69384598c Fix:Argument llm_provider 2025-12-10 17:21:15 +05:30
Sameer Kankute
b9d3d7c059 Add tests for file and batch feat for anthropic 2025-12-10 17:14:47 +05:30
Sameer Kankute
ec3c9191f3 Transform anthropic file content to openai file content 2025-12-10 17:07:00 +05:30
Sameer Kankute
854183e3b9 Revert batch utils with original logic 2025-12-10 17:01:21 +05:30
Sameer Kankute
0d2f8ce931
Merge pull request #17711 from BerriAI/litellm_add_additional_drop_params_support 
feat: Add nested field removal support to additional_drop_params
 2025-12-10 15:37:39 +05:30
Lucas Sugi
c7fd8fabdb
fix: Avoid error when we have just the tool_calls in input (#17753) 
* fix: Avoid error when we have just the tool_calls in input

* fix: Remove the tool call validation

* feat: Add unit test
 2025-12-09 22:59:59 -08:00
Krish Dholakia
b0a5a4b81d
Arize Phoenix OSS - Prompt Management Integration (#17750) 
* docs(prompt_management.md): document how to onboard prompts to litellm

* feat(arize_phoenix_prompt_manager.py): support new prompt management integration

allows users to connect arize phoenix prompt manager to litellm

* fix(proxy/utils.py): remove prompt variables to avoid re-processing prompt

* docs(arize_phoenix_prompts.md): document new prompt management integration
 2025-12-09 22:53:42 -08:00
Sameer Kankute
bcac9e41f6 Add support for computer use for gemini 2025-12-10 10:34:08 +05:30
Ishaan Jaff
e546f0e021
[Fix] UI SSO - allow up-serting user role when SSO provider role changes (#17754) 
* use _build_sso_user_update_data

* test_build_sso_user_update_data_with_valid_role
 2025-12-09 19:16:10 -08:00
Peter Chanthamynavong
539ce89d4e
fix(guardrails): mask all regex pattern matches, not just first (#17727) 
Before: search() + replace() only replaced first match
After: sub() replaces all matches of each pattern

Closes #17687
 2025-12-09 18:51:28 -08:00