Commit graph

25148 commits

Author SHA1 Message Date
Krish Dholakia
661a42b626
Merge pull request #14698 from BerriAI/litellm_contributor_prs_09_18_2025_p1
Litellm contributor prs 09 18 2025 p1
2025-09-18 18:32:51 -07:00
Alexsander Hamir
60800698f2
feature: generic object pool (#14702)
* add: generic object pool & tests

Introduced a reusable object pool that can be applied across the codebase.
Note: memory growth is managed via eviction settings—using a hard cap could
reduce performance, so eviction is the preferred safeguard.

* fix: simpler tests
2025-09-18 18:32:45 -07:00
Krish Dholakia
7b53edec7e
Merge pull request #14701 from ARajan1084/bedrock-guardrail-view
NEW Amazon Bedrock Guardrail Info View in Logs
2025-09-18 18:02:53 -07:00
=
7cfdc6069a upgraded build script to node 20 2025-09-18 18:01:47 -07:00
Ishaan Jaffer
114d077cc9 fix: model cost map check 2025-09-18 17:52:56 -07:00
Krish Dholakia
ccb817d16c
Merge pull request #14699 from ARajan1084/bedrock-guardrail-view
NEW Amazon Bedrock Guardrail Info View in Logs
2025-09-18 17:52:19 -07:00
=
90bd1927e2 Update config.yml 2025-09-18 17:50:55 -07:00
=
61d1fabb6e upgraded vitest 2025-09-18 17:39:53 -07:00
=
4f89675267 upgraded to node 20 2025-09-18 17:38:56 -07:00
Ishaan Jaffer
c1a967992f fix: model cost map check 2025-09-18 17:37:09 -07:00
Ishaan Jaffer
0626affa11 fix: model cost map check 2025-09-18 17:25:28 -07:00
Krish Dholakia
c7af9d1b7e
Merge pull request #14696 from ARajan1084/bedrock-guardrail-view
NEW Amazon Bedrock Guardrail Info View in Logs
2025-09-18 17:22:17 -07:00
Alexsander Hamir
59409429d4
fix: reduced __inits__ overhead in 7% (#14689)
* fix: avoid redundant __init__ calls on hot path

Previously, imports on the request hot path caused __init__ to run
excessively for every request. This change ensures initialization
happens once, reducing cpu overhead.

* fix: remove redundant __init__ import

The current implementation no longer requires an import at the top of the function.

* fix: placed on core utils for future reuse

* test: add coverage & remove inline import

A general import-checking tool across all endpoints would be a large PR.
This commit focuses on a smaller, targeted fix for the discussed case.

* added import check to CI
2025-09-18 17:18:05 -07:00
Ishaan Jaff
4c983f985a
[Feat] Add Bedrock Twelve Labs embedding provider support (#14697)
* fix: add 12 labs to bedrock embedding

* fix: get_bedrock_embedding_provider

* test: test_text_embedding

* fix: 12 labs embedding transform

* fix: refactor 12 labs transform logic

* fix: test_e2e_bedrock_embedding

* fix: test_e2e_bedrock_embedding

* feat: add bedrock twelvelabs pricing

* DOCS: docs bedrock embedding

* DOCS: 12 labs bedrock overview

* fix: bedrock embeddings 12 labs
2025-09-18 17:16:45 -07:00
=
f80660acd9 vitests for GuardrailViewer components 2025-09-18 16:57:22 -07:00
katsuhiro muto
ec61a7152a
Support for is_streamed_request widh datadog (#14673) 2025-09-18 15:55:16 -07:00
Mubashir Osmani
a7a6381926
fix: flaky passthrough tests (#14692)
* fix: flaky passthrough tests

* Revert "fix: flaky passthrough tests"

This reverts commit ffe692e017.

* fix: serialize prisma objects
2025-09-18 15:35:14 -07:00
=
78cb8c71fd prelim changes for new Bedrock guardrail info view 2025-09-18 15:09:10 -07:00
Ishaan Jaff
c6e37bb0bb
fix: BadRequestError cohere (#14691) 2025-09-18 12:32:54 -07:00
Ishaan Jaffer
e733b619db fix: test_user_email_in_all_required_metrics 2025-09-18 11:23:13 -07:00
Sameer Kankute
36bedc69ff
Add TwelveLabs marengo model (#14674) 2025-09-18 11:21:35 -07:00
Sameer Kankute
d213a2e066
correct the gaurdcontent name (#14684)
* correct the gaurdcontent name

* correct the gaurdcontent name

* fix model required error in test

* Add correct model
2025-09-18 11:00:19 -07:00
Ishaan Jaffer
e0bbc3f46b fix: test_cohere_request_body_with_allowed_params 2025-09-18 10:56:45 -07:00
Ishaan Jaffer
8296bfb866 fix: test metrics 2025-09-18 10:25:22 -07:00
Ishaan Jaffer
c6afa904bb fix: test_completion_with_no_model 2025-09-18 10:17:09 -07:00
Ishaan Jaffer
1e1d174733 fix: test_completion_with_no_model 2025-09-18 10:13:32 -07:00
Ishaan Jaffer
706b9214c0 fix: test_init_kwargs_for_pass_through_endpoint_basic 2025-09-18 07:59:05 -07:00
Ishaan Jaffer
3018c66867 fix: test_awesome_otel_with_message_logging_off 2025-09-18 07:49:39 -07:00
Ishaan Jaffer
09d63a00e2 fix: cohere generate api is deprecated 2025-09-18 07:40:28 -07:00
Ishaan Jaffer
da95e208da fix: BedrockCountTokensHandler 2025-09-18 07:32:33 -07:00
Ishaan Jaffer
7b5dd5c7d1 fix: cohere generate api is deprecated 2025-09-18 07:29:11 -07:00
Ishaan Jaff
759bb6cff5
fix: cohere generate api is deprecated (#14676) 2025-09-18 07:27:51 -07:00
Krish Dholakia
bfaab8ad7e
Merge pull request #14557 from timelfrink/fix/issue-14478-bedrock-count-tokens-endpoint
Implement AWS Bedrock CountTokens API support
2025-09-17 23:51:06 -07:00
Krish Dholakia
ff36dfdc76
Merge pull request #14637 from akraines/feature/middle-truncate-spend-logs
feat: implement middle-truncation for spend log payloads
2025-09-17 23:47:04 -07:00
Krish Dholakia
e7bc700b20
Merge pull request #14640 from Sameerlite/litellm_gardrail_default_latest_message
[Feat]Add last message as default in gaurdrail
2025-09-17 23:42:40 -07:00
Tim Elfrink
7538fc0def Fix mypy type annotations in transformation.py
- Add explicit type annotation for transformed_message dict
- Resolves mypy errors while maintaining functionality
- All tests continue to pass
2025-09-18 08:34:05 +02:00
Tim Elfrink
c234b13275 Apply code formatting and linting fixes
- Apply Black formatting to all Bedrock CountTokens files
- Clean up imports and remove unused variables in tests
- Fix indentation and simplify test structure
- Fix pyright type error with type ignore annotation
- All tests continue to pass after cleanup
2025-09-18 08:28:17 +02:00
Tim Elfrink
e74ac35b5d Add comprehensive tests for Bedrock CountTokens functionality
- Add endpoint integration test in test_proxy_token_counter.py
- Add unit tests for transformation logic in bedrock/count_tokens/
- Test model extraction from request body vs endpoint path
- Test input format detection (converse vs invokeModel)
- Test request transformation from Anthropic to Bedrock format
- All tests follow existing codebase patterns and pass successfully
2025-09-18 08:16:56 +02:00
Sameerlite
edf95966c9 Handle consecutive user messages 2025-09-18 10:35:25 +05:30
Alexsander Hamir
8d96626044
fix: iscoroutine removed from hot path +50 RPS (#14649)
* fix: iscoroutine removed from hot path

* fix: replace all instances & separate concerns

1. Replaced all instances of iscoroutine with is_async_callable
2. Place the coroutine checker in its own file

* fix: PR comment changes

* fix: missing config setting declaration

* fix: revert non-performance related changes

* fix: revert to initial implementation

* fix: remove dead const
2025-09-17 19:01:43 -07:00
Krrish Dholakia
00d8dedd16 test: update test 2025-09-17 17:44:14 -07:00
Krish Dholakia
44e0c730b9
Merge pull request #14653 from ARajan1084/in-memory-guardrail-fix
fix: In Memory Guardrail fails to update
2025-09-17 17:42:23 -07:00
=
268b984cb6 added test for updating in memory guardrails 2025-09-17 17:16:49 -07:00
Mubashir Osmani
8b804303ed
fix: ci/cd tests + lint errors (#14646)
* fix: lint errors + tests

* fixed ci tests

* fixed tests

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
2025-09-17 17:06:43 -07:00
Ishaan Jaffer
e2be7e0b1f docs fix posthog 2025-09-17 17:02:23 -07:00
Krish Dholakia
f51003538a
Merge pull request #14650 from BerriAI/litellm_dev_09_17_2025_p1
Bedrock Guardrails - support setting bedrock runtime endpoint + Protect `/health/test_connect` to prevent users without model creation permissions from calling it
2025-09-17 16:55:53 -07:00
Krrish Dholakia
1954bbffc0 test: fix test on ci/cd 2025-09-17 16:53:07 -07:00
=
66202d0ab7 updates in memory custom guardrail liteLLM params 2025-09-17 16:28:05 -07:00
Krish Dholakia
895c41efa3
Merge pull request #14619 from BerriAI/litellm_dev_09_16_2025_p1
UI - allow team member to view service account keys they create + Anthropic - include cache creation tokens in prompt token total (separate out during cost tracking)
2025-09-17 15:43:04 -07:00
Krrish Dholakia
d96e397de5 fix(_health_endpoints.py): protect /health/test_connection - only allow users who are allowed to create models, to call this endpoint
Closes LIT-989
2025-09-17 15:28:35 -07:00