tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-07-19 04:20:26 +00:00
Code Issues Packages Projects Releases Wiki Activity
27,510 Commits 2,072 Branches 1,425 Tags
6fc7397ddef18ebabe3bbd5c79c8b2ca0b3760bd
Commit Graph
4185 Commits
Author SHA1 Message Date
Sameer KankuteandGitHub 6fc7397dde Add Vertex AI Image Edit Support (#16828) 
* Add vertex ai image edit support

* Fix lint errors
 2025-11-19 18:39:28 -08:00
idola9andGitHub e1005cb9d3 Use LiteLLM key alias as fallback Noma applicationId in NomaGuardrail (#16832) 
* Use auth key name if there are no app id in in headers or in extra_data

* use key alias instead of key name

* Fix

* last priority key alias

* Fix

* Add tests
 2025-11-19 17:44:23 -08:00
Sameer KankuteandGitHub 9622829fa1 Fix vector store create issue (#16804) 2025-11-19 16:53:20 -08:00
Ishaan JaffandGitHub c7cf18cf67 [Feat] Prompt Management - Allow storing prompt version in DB (#16848) 
* test_dotprompt_auto_detection_with_model_only

* fix _auto_detect_prompt_management_logger

* test_dotprompt_with_prompt_version

* add v1, v2 tests

* add _compile_prompt_helper

* fix _compile_prompt_helper

* test_dotprompt_with_prompt_version

* test_dotprompt_with_prompt_version, test_get_prompt_with_version

* add version in schema

* feat add _get_prompt_spec_for_db_prompt

* add _get_prompt_spec_for_db_prompt

* feat add _get_prompt_spec_for_db_prompt

* update prompt table

* add version in prompt DB

* test_get_prompt_spec_for_db_prompt_with_versions
 2025-11-19 13:19:56 -08:00
NakiandGitHub 98dd866b26 feat(github-copilot): Add Responses API support for gpt-5.1-codex model (#16845) 
- Implement GithubCopilotResponsesAPIConfig for /responses endpoint
- Add support for models requiring responses API (e.g., gpt-5.1-codex)
- Auto-detect vision requests and set X-Initiator header
- Follow OpenAI Responses API compatibility pattern
- Add comprehensive unit tests (16 tests passing)

Fixes #16820
 2025-11-19 13:17:19 -08:00
Ishaan JaffandGitHub 3ebe489082 [Feat] Prompt Management - Add support for versioning prompts (#16836) 
* test_dotprompt_auto_detection_with_model_only

* fix _auto_detect_prompt_management_logger

* test_dotprompt_with_prompt_version

* add v1, v2 tests

* add _compile_prompt_helper

* fix _compile_prompt_helper

* test_dotprompt_with_prompt_version

* test_dotprompt_with_prompt_version, test_get_prompt_with_version
 2025-11-19 13:16:03 -08:00
Ishaan JaffandGitHub 1f8fe007a1 [Feat] Prompt Management - Allow specifying just prompt_id in a request to a model (#16834) 
* test_dotprompt_auto_detection_with_model_only

* fix _auto_detect_prompt_management_logger

* test_dotprompt_auto_detection_with_model_only
 2025-11-19 10:20:58 -08:00
Alan PonnachanandGitHub b92cc2b2f9 fix(bedrock): Ensure consistent chunk IDs in Bedrock streaming responses (#16596) 
* ensure consistent chunk IDs in streaming responses

* use native conversationId for consistent stream chunk IDs
 2025-11-18 20:37:21 -08:00
Sameer KankuteandGitHub 34cc532d8d Make sure that user inherits team permissions (#16639) 2025-11-18 20:14:42 -08:00
Alexsander HamirandGitHub 2e007505da fix(spend-logs): trim logged response strings (#16654) 
* fix(spend-logs): trim logged response strings

- route spend-log responses through the existing string sanitizer so oversized base64/text fields are truncated before persistence
- add unit tests covering the truncation path and the feature flag

Note: embeddings-specific truncation (numeric vectors) is still pending and will be handled separately.

* remove unnecessary comment

* add: sanitization unit test for embeddings

* fix: simplify sanatization logic

I overcomplicated a simple change for lack of understanding, fixed.
 2025-11-18 20:12:49 -08:00
Sameer KankuteandGitHub 9e93d65ee2 Add extra_body support for response api params from chat completion (#16765) 2025-11-18 20:05:47 -08:00
Cesar GarciaandGitHub 5e70c78b94 fix(cost-tracking): support base_model lookup in litellm_metadata for Responses API (#16778) 
Cost tracking was failing for Responses API when using custom deployment names
with base_model configuration. The issue occurred because:

- Chat Completions API stores model_info in 'metadata'
- Responses API stores model_info in 'litellm_metadata'
- Cost calculator only checked 'metadata', missing Responses API costs

Changes:
- Updated _get_base_model_from_metadata() to check both metadata locations
- Added comprehensive unit tests covering all scenarios
- Maintains backward compatibility (metadata takes precedence)

Fixes #16772
 2025-11-18 19:53:18 -08:00
yuneng-jiangandGitHub fe05e33723 Fix e2e ui playwright test (#16799) 2025-11-18 17:56:40 -08:00
Ishaan JaffandGitHub c3c6cef6d8 [Fix] Fixes Swagger UI resolver errors for chat completion endpoints caused by Pydantic v2 $defs not being properly exposed in the OpenAPI schema. (#16784) 
* fix add_request_body_to_paths

* test_move_defs_to_components
 2025-11-18 17:39:28 -08:00
Ishaan JaffandGitHub 2880cb45a2 [Fix] AI Gateway Auth - Ensure Team Tags works when using JWT Auth (#16797) 
* fix setting team_metadata

* test_team_metadata_with_tags_flows_through_jwt_auth
 2025-11-18 17:36:38 -08:00
Ishaan JaffandGitHub e2fc225201 [Feat] SSO - Ensure role from SSO provider is used when a user is inserted onto LiteLLM (#16794) 
* test_apply_user_info_values_sso_role_takes_precedence

* fix SSO
 2025-11-18 15:35:38 -08:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 		97bb899f52 Bump js-yaml in /tests/proxy_admin_ui_tests/ui_unit_tests (#16755) 
Bumps [js-yaml](https://github.com/nodeca/js-yaml) from 3.14.1 to 3.14.2.
- [Changelog](https://github.com/nodeca/js-yaml/blob/master/CHANGELOG.md)
- [Commits](https://github.com/nodeca/js-yaml/compare/3.14.1...3.14.2)

---
updated-dependencies:
- dependency-name: js-yaml
  dependency-version: 3.14.2
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-11-18 11:38:54 -08:00
Sameer KankuteandGitHub f3344a0d07 Fix videos tagging (#16770) 2025-11-18 11:37:05 -08:00
yuneng-jiangandGitHub f9ec353b80 [Feature] UI - Allow setting base_url in API reference docs (#16674) 
* Allow setting base_url in API reference docs

* Add logic to change base url for test key page
 2025-11-18 11:27:28 -08:00
Sameer KankuteandGitHub acf206bec6 Add Day 0 gemini-3-pro-preview support (#16719) 
* Add thinking signature support for gemini

* Add docs related to thinking signature

* remove double base64 import

* fix mypy errors

* fix litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py mypy

* Add new gemini 3 model and features

* Add docs related to gemini 3

* Update gemini 3 pricing

* fix llm translation tests

* fix mapped tests
 2025-11-18 09:44:45 -08:00
AndreyGitHubmubashir1osmaniMubashir OsmaniKrish Dholakiamogith-pn
 		4dbbec233c Snowflake provider support: added embeddings, PAT, account_id (#15727) 
* added oauth mcp to docs

* added azure ai/grok-4 model family

* Revert "added oauth mcp to docs"

This reverts commit 950b7cef44f14b2db1429f6fbd32548a7c95d325.

* fix: arize ui integration

* need to remove a file

This reverts commit d6c877b73ac763464f204b77135f3786342373b7.

* snowflake support PAT, account_id and embeddings

* format

* test embeddings

* format

* complete test

* fix: add arize from ui

* updated clarifai functions to openai compatible (#15615)

* fix: npm build errors

* update tests

* SnowflakeBaseConfig moved to utils

* rename pat_key => api_ke

* key_type=PAT => 'pat/key'

* fix if api_key is None

* doc update

* doc update

---------

Co-authored-by: mubashir1osmani <mubashir.osmani777@gmail.com>
Co-authored-by: Mubashir Osmani <ilikewafflesomcuh@gmail.com>
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
Co-authored-by: mogith-pn <143642606+mogith-pn@users.noreply.github.com>
 2025-11-17 20:27:46 -08:00
YutaSaitoandGitHub 86ada061ec fix: prompt injection not working (#16701) 2025-11-17 20:04:57 -08:00
pnookala-godaddyandGitHub 52337961dc fix(openai-video): inherit BaseVideoConfig to enable async content response (#16708) 2025-11-17 20:04:10 -08:00
John LathouwersandGitHub d93e13be36 OCI Provider - Add oci_endpoint_id Parameter for OCI Dedicated Endpoints #16723 2025-11-17 19:59:34 -08:00
BradleyandGitHub d0c880e555 Add support for strict parameter in Anthropic tool schemas (#16725) 
* support anthropic strict tools

* correct comment from copy-paste
 2025-11-17 19:57:13 -08:00
mmandic-coatueandGitHub 355eff8723 fix haiku-4-5 bedrock configs (#16732) 2025-11-17 19:52:01 -08:00
Ishaan JaffandGitHub bdb1e16dcf [Feat] AI Gateway Auth - Allow using JWTs for signing in with Proxy CLI (#16756) 
* fix auth

* get_cli_jwt_auth_token

* fix linting

* test fixes

* docs

* test fixes

* fix refactor
 2025-11-17 19:47:29 -08:00
Sameer KankuteandGitHub 7cebc151b0 Add managed files support for responses API (#16733) 
* Fix responses api with managed files

* fix litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py mypy

* fix litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py mypy

* fix mypy errors
 2025-11-17 18:41:26 -08:00
Ishaan JaffandGitHub 83ea037bc9 [Feat] AI Gateway - Allow admins to disable, dynamic callback controls (#16750) 
* add flag to allow_dynamic_callback_disabling

* fix EnterpriseCallbackControls

* test controls

* add docs on dynamic logging
 2025-11-17 18:29:07 -08:00
Ishaan JaffandGitHub 08e115ecff [Feat] Add SSML Support for Azure Text-to-Speech (AVA) (#16747) 
* detect SSML in input

* transform_text_to_speech_request

* test_litellm_speech_with_ssml_passthrough

* add Passing Raw SSML

* fix is_ssml_input
 2025-11-17 15:41:22 -08:00
YutaSaitoandGitHub 0b586d26fc refactor: drop MCPClient.connect and use run_with_session lifecycle (#16696) 
Surface detailed connection errors by handling HTTP failures
 2025-11-15 17:54:27 -08:00
Ishaan JaffandGitHub 25cb873467 [UI] expose backend endpoint for callbacks settings (#16698) 
* init json for

* add SQS fields

* fix params

* return callbacks configs

* test_get_callback_configs

* test_get_callback_configs

* vercel build fix
 2025-11-15 16:44:17 -08:00
yuneng-jiangandGitHub 00ecb99f3e [Fix] UI MCP Tool Test Regression (#16695) 
* Fix UI MCP testing tool regression

* Fixed linting
 2025-11-15 15:31:04 -08:00
Ishaan JaffandGitHub 06eeb28c8f Litellm ci cd fixes 2 (#16693) 
* litellm_proxy_unit_testing_part1

* test proxy unit test

* litellm_proxy_unit_testing_key_generation

* test_async_call_with_key_over_model_budget

* test_aasync_call_with_key_over_model_budget
 2025-11-15 14:12:44 -08:00
Sameer KankuteGitHubIshaan Jaffer
 		a2e3b942dc Vector store files Stable Release (#16643) 
* Add support for vector store files endpoints (#16490)

* Add base code for vector store integration

* fix azure related tests and linting error

* fix mypy errors

* Add vector store files documentation

* fix mapped tests

* Add bytedance and ideogram support in fal ai (#16636)

* Add fal ai flux pro v1.1 support (#16578)

* Add fal ai flux pro v1.1 support

* Add tests and docs

---------

Co-authored-by: Ishaan Jaffer <ishaanjaffer0324@gmail.com>
 2025-11-15 13:00:33 -08:00
Sameer KankuteGitHubIshaan Jaffer
 		59d17cc468 Litellm anthropic contex management param support (#16528) 
* Add support for anthropic context_management param

* Add support for anthropic context_management param

* Add context management in response

* fix review changes

---------

Co-authored-by: Ishaan Jaffer <ishaanjaffer0324@gmail.com>
 2025-11-15 13:00:09 -08:00
Ishaan Jaffer 4eaa95a55f fix build and test 2025-11-15 11:21:45 -08:00
Krish DholakiaandGitHub 586f126395 Prometheus - make OSS (#16689) 
* refactor: remove enterprise license from prometheus metrics

* refactor: complete refactoring imports

* refactor: complete prometheus refactoring

* bump: version 1.80.0 → 1.80.1

* bump: version 1.80.1 → 1.80.2

* build: update litellm lock file

* docs(enterprise.md): cleanup enterprise docs

* docs: more docs cleanup

* docs: doc cleanup

* fix: fix imports

* fix: fix linting error
 2025-11-15 11:06:34 -08:00
Ishaan Jaffer 2bc122302f fix build and test 2025-11-15 10:41:15 -08:00
Ishaan Jaffer c587aeaf3a test_async_rate_limit 2025-11-15 10:34:24 -08:00
Ishaan Jaffer abe3fcc7e7 test_ui_view_spend_logs_with_team_id 2025-11-15 10:12:47 -08:00
Ishaan Jaffer 95b1608970 test_get_valid_models_with_custom_llm_provider 2025-11-15 09:43:10 -08:00
Ishaan Jaffer 666913f76d test_async_call_with_key_over_model_budget 2025-11-15 09:26:29 -08:00
Ishaan Jaffer 0699430206 test logging tests + mcp server QA checks 2025-11-15 08:58:46 -08:00
Cesar GarciaandGitHub cc72037cec feat(openai): Add verbosity parameter support for GPT-5 family models (#16660) 
OpenAI's GPT-5 model family supports a verbosity parameter to control
the length and detail of responses. This parameter accepts three values:
'low', 'medium', or 'high'.

Changes:
- Added verbosity parameter to completion() and acompletion() signatures
- Added verbosity to DEFAULT_CHAT_COMPLETION_PARAM_VALUES in constants.py
- Added verbosity to get_optional_params() in utils.py
- Added verbosity to GPT-5 supported params list
- Updated OpenAI docs with verbosity usage examples
- Added comprehensive test for verbosity parameter

Supported models: gpt-5, gpt-5.1, gpt-5-mini, gpt-5-nano, gpt-5-codex, gpt-5-pro
 2025-11-14 19:38:27 -08:00
Luka PečnikandGitHub d84e97f211 fix: preserve $defs for Anthropic tools input schema (#16648) 
* fix: preserve $defs for Anthropic tools input schema

* fix: preserve $defs for Anthropic tools input schema

* fix: preserve $defs for Anthropic tools input schema
 2025-11-14 19:35:27 -08:00
pnookala-godaddyandGitHub f599a462c1 openai(video): use GET for /videos/{id}/content by returning empty params; add tests to assert GET (#16672) 2025-11-14 19:33:37 -08:00
Ishaan Jaffer 63994e302e test_call_with_key_over_model_budget 2025-11-14 19:05:00 -08:00
Ishaan Jaffer 39c1a970a1 fix 2025-11-14 18:56:30 -08:00
Ishaan Jaffer 11cf22e7b8 add "provider_specific_fields": null 2025-11-14 18:49:35 -08:00