ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
34,378 Commits 9 Branches 7 Tags 935 MiB
dd183a7fcb
Commit Graph

34378 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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
f1f9f2a594 fix: fix linting error 2025-09-01 17:52:22 -07:00
Krrish Dholakia
5d6532419f refactor: remove unused function 2025-09-01 17:46:38 -07:00
Krrish Dholakia
c54c41f726 fix: fix ruff errors 2025-09-01 17:38:39 -07:00
Krrish Dholakia
4a422ca897 fix: support logging dynamic metadata values to braintrust 2025-09-01 17:38:15 -07:00
Ishaan Jaff
e17bed715e DEFAULT_NUM_WORKERS_LITELLM_PROXY 2025-09-01 17:08:03 -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
Mubashir Osmani
58ac3ecf84
openrouter: added gpt 4.1 model family (#14101) 2025-09-01 15:36:17 -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
Ishaan Jaff
2985915357
[Perf] LiteLLM Proxy: +400 RPS when using correct amount of CPU cores (#14153) 
* bump: DEFAULT_NUM_WORKERS_LITELLM_PROXY

* fix: DEFAULT_NUM_WORKERS_LITELLM_PROXY
 2025-09-01 15:26:16 -07:00
Krish Dholakia
9e947fce19
Merge pull request #14087 from zainhas/main 
update together models
 2025-09-01 15:07:58 -07:00
Abhinav
b6c26c3365
helm(chart): add optional PodDisruptionBudget for litellm proxy (#14062) (#14093) 2025-09-01 12:21:44 -07:00
Krish Dholakia
a6f8808b0b
Merge pull request #14134 from BerriAI/back-to-logs 
Back to Keys should say Back to Logs
 2025-09-01 12:01:47 -07:00
Sameer Kankute
c51665ec9c
fix xai cost calculation (#14127) 2025-09-01 11:31:56 -07:00
tanjiro
735af5bf36
success tooltip added (#14132) 2025-09-01 11:08:58 -07:00
tanjiro
ca70b689af
Logs page screen size fixed (#14135) 
* width fixed

* tailwind css instead of inline css

* minor width fixes

* time button fixed

* fixed width for the "showing..." part
 2025-09-01 11:08:09 -07:00
Ivan Krakhmaliuk
76dd9d8110 GPT-5: Test for unsupported params 2025-09-01 20:30:43 +03:00
Ivan Krakhmaliuk
2622a0634a
GPT-5: Remove params unsupported with reasoning models 2025-09-01 19:51:54 +03:00
mubashir1osmani
2626123aca added litellm_spend_metric 2025-09-01 11:33:34 -04:00
mubashir1osmani
5649c0f0b9 Revert "feat: add persistence and management for guardrails on virtual keys" 
This reverts commit 6cd5afa8b1.
 2025-09-01 10:45:46 -04:00
mubashir1osmani
a6790ac158 Revert "feat: add UI support for displaying and managing guardrails on virtual keys" 
This reverts commit 83654c5608.
 2025-09-01 10:45:44 -04:00
mubashir1osmani
31cfe1fe0a Revert "fix: import verbose_proxy_logger to resolve undefined name errors" 
This reverts commit a8f2ebed9c.
 2025-09-01 10:45:38 -04:00
mubashir1osmani
8de65e8448 fix: added prometheus missing metrics 2025-09-01 10:36:51 -04:00
mubashir1osmani
af2f447698 added prometheus metrics 2025-09-01 10:28:48 -04:00
retanoj
e05ffcfb4c fix back 2025-09-01 20:09:19 +08:00
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
cf676e7aef fix mypy 2025-09-01 17:51:24 +09:00
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
e312c23533 Refactoring: Remove the transform-REquest and transform-REsponse methods, and directly implement the response transformation logic in transform_ embedding-REsponse; Enhance environment validation to ensure the validity of api_key 2025-09-01 13:29:06 +08:00
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
mubashir1osmani (aider)
a8f2ebed9c fix: import verbose_proxy_logger to resolve undefined name errors 2025-09-01 01:17:46 -04:00
mubashir1osmani (aider)
83654c5608 feat: add UI support for displaying and managing guardrails on virtual keys 2025-09-01 01:17:08 -04:00
mubashir1osmani (aider)
6cd5afa8b1 feat: add persistence and management for guardrails on virtual keys 2025-09-01 00:56:22 -04:00
Krrish Dholakia
0c9051abba docs(docker_quick_start.md): add docker compose to quick start 2025-08-31 21:24:30 -07:00
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
Krrish Dholakia
e6429f6565 feat(ollama_chat/transformation.py): handle thinking content on streaming for ollama chat models 
Output parse correctly to 'reasoning_content'
 2025-08-31 20:55:01 -07:00
Krrish Dholakia
90bd89c7fd feat(ollama_chat/): add 'think' param support + output parse '<think>' content into 'reasoning_content' 
Ensures consistent use of thinking
 2025-08-31 20:38:52 -07:00
Krrish Dholakia
3a68ca5140 fix(ollama/chat): add 'think' param support 2025-08-31 20:29:21 -07:00
Krrish Dholakia
130c1dd4fc fix(types/openai.py): add default none values to responsesapiresponse object 
Fixes https://github.com/BerriAI/litellm/issues/14061
 2025-08-31 20:25:12 -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
tanjiro
15baaf68db back to logs added conditionally 2025-08-31 17:09:11 +09:00