Krish Dholakia
79d071c25c
Merge pull request #15022 from BerriAI/litellm_gemini_tool_search
...
Ignore type param for gemini tools
2025-09-29 21:57:50 -07:00
Copilot
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
Ishaan Jaff
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
Alexsander Hamir
d4830e34e5
fix: remove router inefficiencies (from O(M*N) to O(1)) - 62.5% faster P99 latency ( #15046 )
...
* fix: remove redundant deep copy
set_model_list already does the deep copy at the beginning of the call.
* fix: remove unused model_list arguments
The `model_list` parameter was being passed to classes that did not use it.
* fix: reduce per-request memory and time from O(N×M) to O(N)
No need to create a whole array for a simple look up.
* add: missing test
* fix: remove unused parameter
2025-09-29 15:49:46 -07:00
Krrish Dholakia
9ed83d44e3
test: remove unnecessary test
2025-09-29 13:35:34 -07:00
Sameer Kankute
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
Ishaan Jaff
4dc23e8079
Revert "feat: improve vertex AI/gemini api_base handling for proxy services (…" ( #15042 )
...
This reverts commit ff2d19e4ca
2025-09-29 13:03:46 -07:00
Zero Clover
ff2d19e4ca
feat: improve vertex AI/gemini api_base handling for proxy services ( #15039 )
2025-09-29 12:12:32 -07:00
Shubham Pathak
3f312d0527
Added test
2025-09-29 21:43:31 +05:30
Sameerlite
58955a0348
Ignore type param for gemini tools
2025-09-29 16:32:21 +05:30
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
anthony-liner
9ca73d5504
fix: set usage_details.total in langfuse integration
2025-09-29 16:30:44 +09:00
Krish Dholakia
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
TobiMayr
3c99d2236a
feature/add max requests env var
2025-09-28 19:18:56 +01:00
Krish Dholakia
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 37ea89eff0aede742db5
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
Krrish Dholakia
0560cb5cfe
fix(openai/image_edit/transformation.py): fix passing multiple images to openai
2025-09-27 16:03:17 -07:00
Krrish Dholakia
4e283aa13b
fix: fix linting errors
2025-09-27 14:25:05 -07:00
Krrish Dholakia
e644953c0f
fix: fix linting errors
2025-09-27 14:19:11 -07:00
Krrish Dholakia
c9f29dd0c5
fix: fix linting errors
2025-09-27 14:02:27 -07:00
Krrish Dholakia
a6c8a40c86
fix: fix linting errors
2025-09-27 13:26:27 -07:00
Krrish Dholakia
5cbfa42bb4
fix: fix linting error
2025-09-27 13:02:32 -07:00
Krish Dholakia
f5cad14282
Merge branch 'main' into litellm_ci_cd_linting_fixes_09_29_2025_p2
2025-09-27 12:48:23 -07:00
Krrish Dholakia
f00a32d04c
fix: fix linting errors
2025-09-27 12:47:13 -07:00
Ishaan Jaffer
c27beb74b9
test fix
2025-09-27 12:40:34 -07:00
Krrish Dholakia
d0725d97a5
fix: fix linting errors
2025-09-27 11:25:01 -07:00
Krish Dholakia
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
cf1ed225d7
fix: fix vllm test
2025-09-27 10:01:48 -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
Krish Dholakia
0350a44ab1
Merge pull request #14965 from Maximgitman/issue-14962-anthropic-streaming-id
...
Fix Anthropic streaming IDs (#14962 )
2025-09-27 07:36:48 -07:00
Ishaan Jaff
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
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
Maximgitman
f2d7c1c14d
Fix Anthropic streaming IDs
2025-09-26 18:31:10 -04:00
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
Alex Shoop
914844122c
Fix: revert fastuuid optional dependency, always use fastuuid in .__uid helper ( #14941 )
...
* always use fastuuid
* rm from proxy extras since its now default
* poetry lock
2025-09-26 09:14:20 -07:00
Krish Dholakia
f2f75bf911
Merge pull request #14893 from vertexcover-io/fix/openai-image-edit-support-images
...
🐛 Fix a bug where openai image edit siltently ignores multiple images
2025-09-25 23:37:52 -07:00
Ritesh Kadmawala
af0cb7c277
🐛 Fix a bug where openai image edit siltently ignores multiple images
2025-09-26 10:56:06 +05:30
Sameer Kankute
1681bf7175
(Feat) Add BitBucket Integration for Prompt Management ( #14882 )
...
* Add bitbucket integration for prompt management
* remove not needed file
* remove not needed file
* Add the correct readme
* Add the correct readme
* fix test for bitbucket
* fix test for bitbucket
2025-09-25 15:51:00 -07:00
Alexsander Hamir
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
