Ishaan Jaff and GitHub
e73d053de3
[Fix] Proxy Auth - Ensure LLM_API_KEYs can access pass through routes ( #15115 )
...
* test_virtual_key_llm_api_routes_allows_registered_pass_through_endpoints
* fix: is_registered_pass_through_route
* docs fix
2025-10-01 14:09:01 -07:00
Sameer Kankute and GitHub
7ec7e5332c
Add generateContent cost tracking ( #15014 )
2025-10-01 09:03:45 -07:00
Krish Dholakia and GitHub
1503435d91
Merge pull request #15029 from henryhwang/gemini-adapter-fixes
...
feat(gemini): Add full support for native Gemini API translation
2025-09-30 21:19:18 -07:00
Ishaan Jaff and GitHub
73bfef1a1f
Revert "[Feature]: Replace HTTPException with ParallelRequestLimitError in pa…" ( #15095 )
...
This reverts commit 71b9b58fa9 .
2025-09-30 21:17:04 -07:00
Henry Wang
acc23b9757
fix issue from pr review
2025-10-01 11:57:10 +08:00
Henry H Wang and GitHub
7c4439ba0a
Merge branch 'BerriAI:main' into gemini-adapter-fixes
2025-10-01 09:53:51 +08:00
Krish Dholakia and GitHub
c475723c67
Merge pull request #15044 from BerriAI/litellm_dev_09_29_2025_p1
...
MCP - enforce server permissions on call tools + Teams - add model specific tpm/rpm limits to teams on LiteLLM
2025-09-30 15:32:53 -07:00
Krish Dholakia and GitHub
5619d350b6
Merge pull request #15074 from Jetemple/custom-logo-fix
...
Make UI theme settings publicly accessible for custom branding
2025-09-30 15:26:00 -07:00
Ishaan Jaff and GitHub
0476a33d9f
[Bug Fix] Passthrough API Endpoints - Ensure query params are forwarded from origin url to downstream request ( #15087 )
...
* test_pass_through_request_query_params_forwarding
* fix: pass_through_request
* test_azure_openai_assistants_e2e_operations_stream
* test_azure_openai_assistants_e2e_operations_stream
2025-09-30 15:01:38 -07:00
Ishaan Jaff and GitHub
69a464fc97
[Fix Security] Ensure OCI secret fields not shared on /models and /v1/models endpoints ( #15085 )
...
* fix: remove_sensitive_info_from_deployment
* fix: remove_sensitive_info_from_deployment
* test_model_info_v1_oci_secrets_not_leaked
2025-09-30 14:55:54 -07:00
71b9b58fa9
[Feature]: Replace HTTPException with ParallelRequestLimitError in parallel_request_limiter_v3 ( #15033 )
...
* Initial plan
* Implement ParallelRequestLimitError custom exception to replace HTTPException
Co-authored-by: ishaan-jaff <29436595+ishaan-jaff@users.noreply.github.com >
* Add ParallelRequestLimitError to litellm main module exports
Co-authored-by: ishaan-jaff <29436595+ishaan-jaff@users.noreply.github.com >
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com >
Co-authored-by: ishaan-jaff <29436595+ishaan-jaff@users.noreply.github.com >
2025-09-30 13:57:14 -07:00
Krrish Dholakia
0cd61a6a6a
fix: simplify testing
2025-09-30 12:37:25 -07:00
Jack Temple
7212116d8c
test: add UI theme settings retrieval and update tests
2025-09-30 10:01:44 -05:00
Henry Wang
d838c96ffb
fix test issues from pr review
2025-09-30 16:05:17 +08:00
f22fd4cddd
Fix: Add /v1/messages/count_tokens to Anthropic routes for non-admin user access ( #15034 )
...
* Initial plan
* Fix: Add /v1/messages/count_tokens to Anthropic routes for user access
Co-authored-by: ishaan-jaff <29436595+ishaan-jaff@users.noreply.github.com >
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com >
Co-authored-by: ishaan-jaff <29436595+ishaan-jaff@users.noreply.github.com >
2025-09-29 18:16:52 -07:00
ebf72f5eb9
[Fix] Parallel Request Limiter v3 - use well known redis cluster hashing algorithm ( #15052 )
...
* test_keyslot_for_redis_cluster
* fix _is_redis_cluster
* Update litellm/proxy/hooks/parallel_request_limiter_v3.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
2025-09-29 18:12:44 -07:00
Ishaan Jaffer
f303860881
Revert "test_keyslot_for_redis_cluster"
...
This reverts commit 52de33787b .
2025-09-29 16:42:15 -07:00
Ishaan Jaffer
52de33787b
test_keyslot_for_redis_cluster
2025-09-29 16:41:32 -07:00
Krrish Dholakia
9ed83d44e3
test: remove unnecessary test
2025-09-29 13:35:34 -07:00
Sameer Kankute and GitHub
3ab1c31e4e
(Feat) Add cost tracking for Vertex AI Passthrough /predict endpoint ( #15019 )
...
* Add cost tracking for passthrough for predict endpoint
* restore file
2025-09-29 13:19:04 -07:00
Krrish Dholakia
bc6e6e7a28
fix(auth_checks.py): add auth checks to mcp server on call tools
2025-09-29 13:13:10 -07:00
Henry Wang
99a884019b
test(gemini): Add unit tests for Google GenAI adapter
...
This commit adds a comprehensive suite of unit tests for the Google GenAI adapter to ensure compliance with the project's contribution guidelines.
The new tests cover four main areas:
- Request parameter translation
- Streaming response handling
- Router methods for Google GenAI
- Proxy endpoints for Google GenAI
Additionally, this commit includes minor formatting and linting fixes identified during development.
2025-09-29 18:51:35 +08:00
Krish Dholakia and GitHub
0d738b2899
Merge pull request #14986 from uc4w6c/fix/remove-servername-prefix-mcp_tools-tests
...
Fix/remove servername prefix mcp tools tests
2025-09-28 18:00:23 -07:00
Krrish Dholakia
f32b0364c4
fix: fix tests
2025-09-28 17:55:46 -07:00
Yuta Saito
dae7d08ff2
Revert "Revert "Merge pull request #14720 from uc4w6c/feat/remove-servername-prefix-mcp_tools""
...
This reverts commit a88d774f94 .
2025-09-29 07:12:24 +09:00
Krish Dholakia and GitHub
c328b4a036
Merge pull request #15002 from BerriAI/litellm_dev_09_27_2025_p3
...
MCP - specify forwardable headers, specify allowed/disallowed tools for MCP servers
2025-09-28 09:21:52 -07:00
Krrish Dholakia
53d0cbb1b7
fix: update tests + logic for passing multiple headers
2025-09-28 09:09:11 -07:00
Krrish Dholakia
526156ed9d
feat(mcp/): allows admin to prevent llm's from accidentally deleting github repo's even if user is allowed to do this
2025-09-27 19:36:11 -07:00
Ishaan Jaffer
35c14f7178
Revert "Merge pull request #14821 from hazyone/fix-13380"
...
This reverts commit 37ea89eff0 , reversing
changes made to aede742db5 .
2025-09-27 18:52:59 -07:00
Krrish Dholakia
0ff7177373
feat(user_api_key_auth_mcp.py): pass extra headers from clientside straight through - allow multiple clientside headers
...
Closes LIT-952
2025-09-27 17:11:06 -07:00
Krish Dholakia and GitHub
3e3e3837a1
Merge branch 'main' into litellm_dev_09_24_2025_p1
2025-09-27 11:21:07 -07:00
Krrish Dholakia
5cdeb63cdd
test: fix tests
2025-09-27 11:09:25 -07:00
Krrish Dholakia
7278ae5305
test: fix tests
2025-09-27 10:03:54 -07:00
Krrish Dholakia
ac09d29c0e
test(tests/): add unit test to confirm oauth2 headers forwarded on receipt
2025-09-27 09:30:07 -07:00
Ishaan Jaff and GitHub
36cc98254c
[Fix] Parallel Request Limiter v3 - ensure Lua scripts can execute on redis cluster ( #14968 )
...
* use hashtag slots for rate limiting logic
* redis_startup_nodes fix
* test_execute_redis_batch_rate_limiter_script_cluster_compatibility
* async_increment_tokens_with_ttl_preservation
2025-09-26 18:15:57 -07:00
Ishaan Jaff and GitHub
628cd13755
[Feat] UI - Allow scheduling key rotations when creating virtual keys ( #14960 )
...
* fix design of key reset interval
* fix: LiteLLM_VerificationToken
* fix key manager
* add key_rotation_at
* ui fix
* fix ui view
* set key_rotation_at on creation
* add key_rotation_at
* fix info
* fix: _set_key_rotation_fields
* fix KeyRotationManager
* fix key edit view
* test_update_key_fn_auto_rotate_enable
* fix KeyRotationManager
2025-09-26 16:24:40 -07:00
Ishaan Jaff
ea8d0bb7d5
fix: re-add scheduled rotations
2025-09-26 11:40:46 -07:00
Ishaan Jaffer
539d10f9cb
test fix
2025-09-26 11:06:26 -07:00
Alexsander Hamir and GitHub
eaa04cd8ce
fix: use fastuuid helper ( #14903 )
...
* fix: use fastuuid helper across the codebase
First batch of changes, simple drop in replacement.
* second batch of changes
* fixed: script mistake on helper file
2025-09-25 15:47:01 -07:00
Arshdeep Singh
471f011ae5
fix: add return type annotation for full mypy compliance
2025-09-25 12:52:12 -04:00
Arshdeep Singh
8193f56876
fix: remove print statement to pass ruff linting checks
2025-09-25 12:39:49 -04:00
Arshdeep Singh
39683cc3d8
fix: remove unused custom_recognizers variable to pass linting
2025-09-25 12:31:08 -04:00
Arshdeep Singh
8364da014f
style: format code with black
2025-09-25 12:23:44 -04:00
Arshdeep Singh
82ec42993f
fix(presidio): enable custom PII entities with Union type
2025-09-25 12:16:22 -04:00
Ishaan Jaffer
b1e56c55ad
merge
2025-09-24 22:11:37 -07:00
Ishaan Jaff and GitHub
ded823a3a3
[Feat] Initial support for scheduled key rotations ( #14877 )
...
* add KeyRotationSettings
* add KeyRotationManager
* add key rotation manager
* add KeyRotationManager
* fix _initialize_spend_tracking_background_jobs
* fix add_key_rotation_fields
* fixes
* new fields in schema
* update schema
* fix fixes for init key rotation manager
* fixes for init key rotation manager
* fix KeyRotationManager
* tests for key rotation
* fix key_rotation_settings
* fix KeyRotationManager
* fix LITELLM_KEY_ROTATION_CHECK_INTERVAL_SECONDS
* fix fixes for init key rotation manager
* ruff check fix
* fix LITELLM_KEY_ROTATION_CHECK_INTERVAL_SECONDS
* fix _initialize_spend_tracking_background_jobs
* docs fix
* docs auto rotate
* schema fix
* bump proxy extras
* fix config.yml
2025-09-24 21:37:56 -07:00
Krish Dholakia and GitHub
37ea89eff0
Merge pull request #14821 from hazyone/fix-13380
...
Fix: support claude code auth via subscription (anthropic)
2025-09-23 22:52:32 -07:00
Krish Dholakia and GitHub
d59dec39d0
Merge pull request #14826 from Jetemple/sso-clear-button-fix
...
fix: SSO "Clear" button writes empty values instead of removing SSO config
2025-09-23 22:49:47 -07:00
Ishaan Jaff and GitHub
f4ecf3ca72
[Feat] Fixes for LiteLLM Proxy CLI to Auth to Gateway ( #14836 )
...
* fix: error msg from updating key
* fix _create_new_cli_key
* fix validate_key_team_change
* fix interface for chat
* ruff fix
* fix auth for keys
* get_litellm_gateway_api_key
* fix chat
* test fix
* linting fix
* fix mypy
* test_validate_key_team_change_with_member_permissions
2025-09-23 19:43:32 -07:00
Ishaan Jaffer
a48273740d
test fix
2025-09-23 17:46:09 -07:00