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
44733 commits 2357 branches 1407 tags 2.7 GiB
Commit graph

13345 commits

Author SHA1 Message Date
Krrish Dholakia
d4cc748b40 feat(openrouter.py): add image generation via google on openrouter support 
Closes https://github.com/BerriAI/litellm/pull/14151
 2025-09-01 18:39:41 -07:00
Krrish Dholakia
4b8f2dc051 test: update tests 2025-09-01 18:20:46 -07:00
Krrish Dholakia
0fbcc01173 feat(types/utils.py): support 'images' field in output 
Compatible with Openrouter response format

 Closes https://github.com/BerriAI/litellm/pull/14151
 2025-09-01 18:05:16 -07:00
Ishaan Jaff
8e72f991cc test_model_alias_map 2025-09-01 17:59:40 -07:00
Krrish Dholakia
4a422ca897 fix: support logging dynamic metadata values to braintrust 2025-09-01 17:38:15 -07:00
Ishaan Jaff
4c7b3e10ed
[Bug Fix] Gemini Tool Calling - fix gemini empty enum property (#14155) 
* fix: _convert_schema_types

* fix recursive detector

* test_convert_schema_types_type_array_conversion

* fix: DEFAULT_NUM_WORKERS_LITELLM_PROXY

* add _fix_enum_empty_strings

* test_tool_call_with_empty_enum_property

* test_fix_enum_empty_strings

* fix _fix_enum_empty_strings
 2025-09-01 17:05:01 -07:00
Ishaan Jaff
7656cb3d6e test fix 2025-09-01 17:04:47 -07:00
Ishaan Jaff
2331fb45d5
[Bug]: Gemini 2.5 Pro – schema validation fails with OpenAI-style type arrays in tools (#14154) 
* fix: _convert_schema_types

* fix recursive detector

* test_convert_schema_types_type_array_conversion

* fix: DEFAULT_NUM_WORKERS_LITELLM_PROXY
 2025-09-01 16:53:20 -07:00
Byron Grogan
736bee813e fix: Support AWS_BEDROCK_RUNTIME_ENDPOINT on bedrock passthrough, make work for URLs with a base path 2025-09-01 17:47:26 -06:00
Ishaan Jaff
98d57b5d27
[Feat] Allow using x-litellm-stream-timeout header for stream timeout in requests (#14147) 
* fix: allow passing stream_timeout header

* fix: _get_stream_timeout_from_request

* test_add_litellm_data_to_request_with_stream_timeout_header

* docs: LiteLLM Headers

* test_add_litellm_data_to_request_with_stream_timeout_header
 2025-09-01 15:59:14 -07:00
Ishaan Jaff
58b713d19d
[Bug fix] Misclassified 500 error on invalid image_url in /chat/completions request (#14149) 
* add ImageFetchError

* docs ImageFetchError

* fix ImageFetchError

* test_completion_with_invalid_image_url
 2025-09-01 15:26:27 -07:00
Sameer Kankute
c51665ec9c
fix xai cost calculation (#14127) 2025-09-01 11:31:56 -07:00
Ivan Krakhmaliuk
76dd9d8110 GPT-5: Test for unsupported params 2025-09-01 20:30:43 +03:00
retanoj
002c2f16dc fix token count error when proxy gemini cli to openai like model 2025-09-01 20:02:53 +08:00
Krish Dholakia
fd0f47d48d Merge pull request #14005 from moshemorad/bedrock_fix_structure_output 
Bedrock fix structure output
 2025-09-01 14:50:08 +03:00
TomeHirata
1ac7f875c9 fix test 2025-09-01 17:21:47 +09:00
TomeHirata
e334f48699 Add supported text field to anthropic citation response 2025-09-01 16:46:54 +09:00
TomeHirata
ca6d77b479 fix citation field name 2025-09-01 16:41:35 +09:00
onlylhf
bfed4e0a6a Add a complete URL generation method for embedding Volcengine API and optimize request and response processing logic; Delete redundant test files and refactor integration testing to improve readability and maintainability. 2025-09-01 13:18:19 +08:00
Krrish Dholakia
2ad77d9bf6 feat(ollama/completion): output parse thinking content on streaming + non-streaming for ollama completion calls 
Completes 'thinking' param support for ollama
 2025-08-31 21:17:10 -07:00
iabhi4
75e698feef bug(auth): support for ES256/ES384/ES512 and EdDSA JWT verification 2025-08-31 15:58:26 -07:00
Dharamendra Kumar
4278c3b596 feat: Add dependency injection support to BaseLLMAIOHTTPHandler 
- Add optional client_session, transport, and connector parameters to constructor
- Implement session ownership tracking to prevent closing user-provided sessions
- Add comprehensive session resolution hierarchy (dynamic > instance > create new)
- Include transport control for advanced HTTP stack management
- Add 29 comprehensive tests covering all injection scenarios
- Maintain backward compatibility with existing code

This enhancement allows users to inject their own configured aiohttp sessions,
transports, and connectors for fine-grained control over connection pooling,
SSL settings, proxy configurations, and other HTTP stack parameters.
 2025-08-31 11:14:19 -07:00
Yuta Saito
d83c420d48 feat: Add guardrail for the Anthropic API endpoint 2025-08-31 16:44:01 +09:00
Krrish Dholakia
b6f6dc5c1c feat(vertex_ai.py): support parsing thinking content into gemini format 
allows function calls with thought signatures to be sent back to gemini

  Closes https://github.com/BerriAI/litellm/pull/13842
 2025-08-30 18:49:34 -07:00
Krrish Dholakia
51c73dc60b fix(vertex_and_google_ai_studio_gemini.py): bubble up thoughtsignature back to client 2025-08-30 17:26:18 -07:00
John Lathouwers
cf5a695571
Merge branch 'BerriAI:main' into main 2025-08-30 22:03:39 +01:00
gotsysdba
07d9d14b49
Update OCIResposeClass 2025-08-30 22:02:00 +01:00
Ishaan Jaff
34275ab273 Revert "Merge pull request #14005 from moshemorad/bedrock_fix_structure_output" 
This reverts commit 75c327cb9e, reversing
changes made to afa687182a.
 2025-08-30 13:37:10 -07:00
Ishaan Jaff
48d3aad68f test_caching_with_models_v2 2025-08-30 13:21:14 -07:00
John Lathouwers
d137371026
Merge branch 'BerriAI:main' into main 2025-08-30 21:17:28 +01:00
gotsysdba
1ae5466daf
Test Case 2025-08-30 21:15:54 +01:00
Ishaan Jaff
c9b86775a7 test_system_message_with_no_user_message 2025-08-30 13:09:25 -07:00
Ishaan Jaff
7ff93cd1b1 Revert "Merge pull request #12865 from aholmberg/holmberg/default-reasoning" 
This reverts commit 68f4847659, reversing
changes made to df39320889.
 2025-08-30 13:07:33 -07:00
gotsysdba
a27604b67a
Fixes #14090 2025-08-30 20:57:57 +01:00
Ishaan Jaff
3cb8e23dfe Revert "Merge pull request #14026 from TomeHirata/citation-supported-text" 
This reverts commit afa687182a, reversing
changes made to 55186dad4c.
 2025-08-30 11:23:18 -07:00
Ishaan Jaff
dc6161535a fix for supports_reasoning check added in 68f4847659 2025-08-30 11:06:02 -07:00
Ishaan Jaff
de6b08e76e test_supports_tool_choice 2025-08-30 10:35:16 -07:00
Ishaan Jaff
3fc2198d27 fix: test_gemini_image_generation_async_stream 2025-08-30 10:33:23 -07:00
Ishaan Jaff
efebf7ec7b test_gemini_image_generation_async 2025-08-30 10:29:24 -07:00
Ishaan Jaff
fd39f22e3e test_completion_openrouter_reasoning_content 2025-08-30 09:27:37 -07:00
Krish Dholakia
8b11452d9e
Merge branch 'main' into add-vercel-ai-gateway-provider 2025-08-29 22:27:08 -07:00
Krish Dholakia
ead7e7259b
Merge pull request #13152 from betterthanbreakfast/bug-openmeter-user-id-from-token 
[Bug]: Set user from token user_id for OpenMeter integration
 2025-08-29 22:21:26 -07:00
Krish Dholakia
75c327cb9e
Merge pull request #14005 from moshemorad/bedrock_fix_structure_output 
Bedrock fix structure output
 2025-08-29 22:04:51 -07:00
Krish Dholakia
afa687182a
Merge pull request #14026 from TomeHirata/citation-supported-text 
Add supported text field to anthropic citation response
 2025-08-29 22:02:18 -07:00
Ishaan Jaff
562790cb31 fix: /v1/realtime check 2025-08-29 18:38:14 -07:00
Ishaan Jaff
37d885e46a
[Fix] LiteLLM does not support new web_search tool (Responses API) (#14083) 
* test_basic_openai_responses_with_websearch

* fix: ResponsesAPIResponse

* fix: StandardBuiltInToolCostTracking
 2025-08-29 18:33:52 -07:00
frankzye1
75a7b39700 pass function tool description for databricks provider 
Signed-off-by: frankzye1 <frankzye@qq.com>
 2025-08-30 09:27:39 +08:00
Ishaan Jaff
5ee7a675f2
[Bug]: grok-4 does not support frequency_penalty, litellm should drop this param for grok-4 (#14078) 
* fix: _supports_frequency_penalty

* _supports_frequency_penalty

* test_xai_grok_4_frequency_penalty_not_supported
 2025-08-29 17:31:48 -07:00
Ishaan Jaff
607f425cc6
[Bug]: Fix Can't set reasoning_effort for DeepSeek-V3.1 on DeepInfra by default (#14053) 
* fix DeepInfraConfig

* track supports reasoning

* fix: get_supported_openai_params

* test_deepseek_supported_openai_params
 2025-08-29 13:15:43 -07:00
Oscar Craviotto
323cabb98d
fix: ensure Gemini calls include a user message (fixes #9733) 
When a Gemini model supports system messages, messages with the
system role get filtered out from the list of messages, so never
appended to the content (and passed as system_instructions instead).

This causes a 400 error, as both generateContent and streamGenerateContent
require contents (the systemInstruction object is optional).

This is a quick fix that does not check whether there was a system msg
or if the model supports it. It simply makes sure that if the list
of messages passed to  _gemini_convert_messages_with_history()
yields no contents, that there is at least a single (empty space)
user message set to prevent the call from failing.

The potential side effect of this is that we will not fail
a call lacking any message at all, but if that needs to be checked
(and AFAIU the OpenAI spec messages are required) it should be done
elsewhere (e.g. validate_and_fix_openai_messages() @ litellm/utils.py).

PS: Applied `make format` (`poetry run black [file changed]`) only to
files changed by me. The `make lint` command identified a bunch of
files requiring formatting that I am not modifying as I did not touch
them.
 2025-08-29 20:41:58 +03:00