Krish Dholakia
784eb18366
Merge pull request #14558 from iabhi4/fix-14536
...
fix(proxy): Correctly parse multi-part MCP server aliases from URL paths
2025-09-15 21:05:22 -07:00
Ishaan Jaff
8e22cf5d65
[Fix] /responses API - add cancel endpoint + allow non-admins to use this as an llm api endpoint ( #14594 )
...
* fix: ensure /responses/cancel works for non admins
* test: cancel endpoint
* fix responses API cancel endpoint
* test fix
* TestGoogleAIStudioResponsesAPITest
2025-09-15 18:49:54 -07:00
Ishaan Jaff
cebacd65cf
[Bug Fix] SCIM v2 - ensure group PUSH and PUT ops allow creating non-existent members ( #14581 )
...
* fix: scim handle non existent members
* test - scim v2
* test fix
* fix: NewUserResponse
2025-09-15 11:27:05 -07:00
iabhi4
4ba3a21042
fix(proxy): Correctly parse multi-part MCP server aliases from URL paths
2025-09-14 15:17:08 -07:00
iabhi4
dc27bccb45
feat(proxy): Assign default budget to auto-generated JWT teams
2025-09-14 12:04:43 -07:00
Krrish Dholakia
2c6481fa33
fix: remove incorrect test
2025-09-14 09:34:31 -07:00
Krish Dholakia
11822e63f1
Merge pull request #14519 from uc4w6c/feat/add_tools_permission_guardrail
...
feat: add tool-permission guardrail
2025-09-13 23:22:31 -07:00
Ishaan Jaff
6172145014
fix: org budget update fix ( #14541 )
2025-09-13 16:34:26 -07:00
Ishaan Jaff
252ec8e1ae
test_normal_router_call_tpm_v3
2025-09-13 12:04:56 -07:00
Krish Dholakia
38efd358eb
Merge pull request #14401 from Noma-Security/noma_non_blocking_monitor_mode
...
Noma non blocking monitor mode & anonymize input support
2025-09-13 09:41:41 -07:00
Krish Dholakia
663dbc6080
Merge pull request #14477 from BerriAI/litellm_dev_09_11_2025_p2
...
`/v1/messages` - don't send content block after message w/ finish reason + usage block + `/key/unblock` - support hashed tokens
2025-09-12 19:51:44 -07:00
Yuta Saito
1de7f076ac
feat: add tool-permission guardrail
2025-09-13 07:34:29 +09:00
Ishaan Jaff
18372f9ebe
Revert "fix vertex ai file upload" ( #14501 )
2025-09-12 12:02:24 -07:00
Boopesh Shanmugam
8b338a4d8c
User Headers X LiteLLM Users Mapping feature ( #14485 )
...
* Draft commit.
* user header mapping feature with backward compatibility with user_header_name field.
* user header mapping feature with backward compatibility with user_header_name field optimizations.
* Added unit tests.
2025-09-12 11:49:37 -07:00
Krish Dholakia
113d2a8c5a
Merge pull request #14459 from holzman/fix-provider-budget
...
Fix provider budgets
2025-09-12 00:34:52 -07:00
Krrish Dholakia
0c8b311155
test: add unit testing for both flows on key unblock
2025-09-11 19:15:15 -07:00
Burt Holzman
e9e548d797
Fix provider budgets
2025-09-11 12:08:43 -05:00
Sameer Kankute
090e0fddf4
fix vertex ai file upload
2025-09-11 22:20:54 +05:30
Tom Alon
b83b497d38
PR fixes
2025-09-11 13:38:06 +03:00
Tom Alon
b473344f70
Implement anonymization logic
2025-09-11 11:47:19 +03:00
Tom Alon
f6bc4d0bf9
Noma non blocking on monitor mode
2025-09-10 13:35:17 +03:00
Krrish Dholakia
bdd7255bab
test: remove redundant tests - moved to parallel_request_limiter_v3.py
2025-09-09 21:35:50 -07:00
pinkgu
285b14bd69
Fix/gcp model armor ( #14381 )
...
* chore: fix model armor always success
Signed-off-by: bjorn <bjornjee95@gmail.com>
* chore: fix sanitisation field extraction
Signed-off-by: bjorn <bjornjee95@gmail.com>
---------
Signed-off-by: bjorn <bjornjee95@gmail.com>
2025-09-09 09:18:37 -07:00
Krish Dholakia
54c3ae15c8
Merge pull request #14312 from mubashir1osmani/main
...
fix: spend tags endpoint returns 500
2025-09-08 19:05:13 -07:00
mubashir1osmani
d9bbbc10a6
added tests
2025-09-07 10:17:28 -04:00
Krish Dholakia
fbc0ec98b6
Merge pull request #12438 from jasonpnnl/fix-customer-update
...
Fix 500 error in `/customer/update` endpoint when updating with `budget_id`
2025-09-06 22:12:30 -07:00
Ishaan Jaff
c9ab104445
[Fix] Perf fix: Heavy RAM Usage over time when using Passthrough Routes ( #14305 )
...
* Implement pass-through route registration and removal to prevent duplicates and memory leaks
* fix MYPY linting
* fix InitPassThroughEndpointHelpers
* fix test_aaparallel_function_call
---------
Co-authored-by: Jugal Bhatt <jugalbhatt3@gmail.com>
2025-09-06 19:22:25 -07:00
Ishaan Jaff
7f5460465c
unit test oai pass through
2025-09-06 14:54:34 -07:00
Sameer Kankute
07ba3ff036
[Feat] Add pass through image gen and image editing on OpenAI ( #14292 )
...
* add pass through image gen and image editing on OpenAI
* fix lint
2025-09-05 12:25:49 -07:00
Ishaan Jaff
379b0dbf14
[Fix] Ensure team_id is a required field for generating service account keys ( #14270 )
...
* generate_service_account_key_fn
* fix validate_team_id_used_in_service_account_request
* fix types
* test_validate_team_id_used_in_service_account_request_requires_team_id
2025-09-04 18:14:38 -07:00
Sameer Kankute
5f79e8aac6
Litellm passthrough cost tracking chat completion ( #14256 )
...
* feat: add structured output for sdk
* Add support for cost tracking for chat completion in passthrough
* remove not required changes
2025-09-04 09:57:48 -07:00
Krish Dholakia
a8cce5fbf3
Merge pull request #14237 from yeahyung/fix/tpm_limit_bug
...
Fixes #14204 TPM Rate Limit Bug
2025-09-04 07:29:47 -07:00
22mSqRi
25afa67616
fix: Key Budget not resets at expectable times
2025-09-04 09:04:01 +00:00
yeahyung
7829de2948
( #14204 ) add test code
2025-09-04 16:41:29 +09:00
Ishaan Jaff
23ae7170d1
[Feat] Allow using Veo Video Generation through LiteLLM Pass through routes ( #14228 )
...
* fix: add follow_redirects=True,
* test_pass_through_with_httpbin_redirect
* cook book veo video
* docs Veo Video Generation with Google AI Studio
* add veo-3.0-generate-preview cost tracking details
* track vertex_video_models
2025-09-03 18:25:43 -07:00
Ishaan Jaff
beb300abae
[Fix] SCIM - Bug fixes for handling SCIM Group Memberships ( #14226 )
...
* Feat: add better SCIM debugging
* fix _get_scim_member_display
* fix patch_group
* test_update_group_e2e
* test_get_scim_member_value
2025-09-03 16:15:51 -07:00
kayoch1n
76555cad81
Format code
2025-09-03 11:20:52 +08:00
kayoch1n
ffbe5cd899
Add a testcase
2025-09-03 11:08:23 +08:00
Ishaan Jaff
128d9a3488
[Feature]: Add header support for spend_logs_metadata ( #14186 )
...
* fix: allow settings spend_logs_metadata
* fix add_litellm_data_for_backend_llm_call
* fix: add add_litellm_metadata_from_request_headers
* fix add_litellm_metadata_from_request_headers
* test_add_litellm_metadata_from_request_headers
* add_litellm_metadata_from_request_headers
* docs Tracking Spend with custom metadata
* add_litellm_metadata_from_request_headers
* add_litellm_metadata_from_request_headers
2025-09-02 15:13:15 -07:00
Krish Dholakia
d2c519f005
Merge pull request #14133 from retanoj/fix/gemini-token-count
...
Fix token count error for gemini cli
2025-09-01 22:39:51 -07:00
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
retanoj
002c2f16dc
fix token count error when proxy gemini cli to openai like model
2025-09-01 20:02:53 +08:00
Ishaan Jaff
37a599932d
[Bug Fix] Virtual keys with llm_api type cause Internal Server Error when using /anthropic/* and other llm passthrough routes ( #14046 )
...
* fix route checks passthrough_routes_wildcard
* refactor check_route_access
* test_virtual_key_llm_api_route_includes_passthrough_prefix
2025-08-28 15:14:09 -07:00
Krish Dholakia
10816a44d4
Merge pull request #13160 from pangeacyber/aidr-update
...
Update Pangea Guardrail to support new AIDR endpoint
2025-08-27 22:15:32 -07:00
Xingyao Wang
9acf80b8ad
Fix issue #13995 : Handle None metadata in batch requests ( #13996 )
...
* Fix issue #13995 : Handle None metadata in batch requests
- Added null check in add_key_level_controls method to prevent NoneType error
- Updated type hint to Optional[dict] for better type safety
- Added comprehensive test suite to verify the fix works correctly
- All existing tests pass, confirming no regression
Fixes #13995
Co-authored-by: openhands <openhands@all-hands.dev>
* Move test file to tests/test_litellm/proxy/ directory
- Moved test_batch_metadata_none_fix.py from tests/ to tests/test_litellm/proxy/
- Updated import structure to match existing test patterns
- This ensures the test runs in GitHub Actions as requested by @krrishdholakia
Co-authored-by: openhands <openhands@all-hands.dev>
---------
Co-authored-by: openhands <openhands@all-hands.dev>
2025-08-27 14:51:09 -07:00
Krish Dholakia
45f465d84f
Merge pull request #13572 from Noma-Security/noma-security-guardrails-support
...
Add Noma Security guardrail support
2025-08-26 23:15:17 -07:00
Krish Dholakia
9df6f4ef08
Merge branch 'main' into litellm_dev_08_20_2025_p1
2025-08-23 12:09:53 -07:00
Krrish Dholakia
b23e35f75e
test: update tests
2025-08-23 12:09:19 -07:00
Ishaan Jaff
825d6b08f0
test fix location of encode bedrock runtime modelid arn
2025-08-22 17:34:09 -07:00
Jugal D. Bhatt
3c1dcb64cc
fix by adding init lock ( #13666 )
2025-08-22 11:42:43 -07:00
