scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-17 23:51:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 67
32579 commits 2515 branches 1410 tags 3 GiB
Commit graph

32579 commits

This branch
This branch
All branches
Author SHA1 Message Date
Julio Quinteros Pro
bf157acccc fix: restore pytest-xdist to CI workflow 
- Add pytest-xdist back to pip install line (required for -n flag)
- Was accidentally removed when removing pytest-retry
- Without pytest-xdist, all CI jobs fail with 'unrecognized option -n'
 2026-02-17 16:08:24 -03:00
Julio Quinteros Pro
bd9b239ed7 fix(ci): address Greptile review feedback 
- Remove pytest-retry to avoid duplicate retry mechanisms (only use pytest-rerunfailures)
- Remove --dist loadgroup flag (no tests use xdist_group marker)
- Remove unused LITELLM_CI environment variable
- Remove sequential test step with error masking
- Simplify workflow for clarity

This fixes the issue where tests could be retried 60+ times due to
duplicate retry plugins (pytest-retry with retries=20 + pytest-rerunfailures
with --reruns 2-3).

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-17 15:58:33 -03:00
Julio Quinteros Pro
e9929d2798 fix: replace deprecated asyncio.iscoroutinefunction with inspect.iscoroutinefunction 
- Replace asyncio.iscoroutinefunction() with inspect.iscoroutinefunction()
- Add inspect import
- Fixes deprecation warning in Python 3.16

The asyncio.iscoroutinefunction is deprecated and will be removed in Python 3.16.
Using inspect.iscoroutinefunction is the recommended approach.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-17 15:48:09 -03:00
Julio Quinteros Pro
7a097ae97f fix(ci): reduce parallelism and add retry logic 
- Reduce workers from 4 to 2 to avoid race conditions
  - Add --reruns with 2-3 retries per test group
  - Increase timeout from 15 to 20 minutes
  - Add better test isolation
 2026-02-17 15:43:43 -03:00
Krrish Dholakia
4930babace docs(release_cycle.md): document enterprise support 2026-02-17 10:15:17 -08:00
Krrish Dholakia
bf824dec55 docs: remove references to unused var 2026-02-17 10:15:17 -08:00
Krrish Dholakia
e936f88f15 refactor: remove old doc 2026-02-17 10:15:17 -08:00
jquinter
cd20dde199
Merge pull request #21390 from BerriAI/fix/lint-too-many-statements-route-llm 
fix(lint): suppress PLR0915 too many statements in route_request
 2026-02-17 14:41:25 -03:00
Julio Quinteros Pro
289341d948 fix(lint): suppress PLR0915 in route_request function 
Add noqa comment for "too many statements" lint error in route_request().
The function has 60 statements (limit is 50) but refactoring it properly
would be a significant undertaking requiring careful testing.

The function handles routing for 50+ different request types and contains
complex logic that should be addressed in a dedicated refactoring effort,
not as part of a lint fix.

Error: proxy/route_llm_request.py:145:11: PLR0915 Too many statements (60 > 50)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-02-17 14:38:17 -03:00
Sameer Kankute
809838042e
Merge pull request #21382 from BerriAI/litellm_vllm_e2e_testing 
Add vllm e2e test for embedding
 2026-02-17 22:32:42 +05:30
Sameer Kankute
811ffff0b8 move e2e to llm translation 2026-02-17 21:14:44 +05:30
Sameer Kankute
ec573ee2b0
Merge pull request #21375 from BerriAI/litellm_evals_api 
[feat] Add support for Openai Evals API
 2026-02-17 21:01:36 +05:30
Sameer Kankute
1c9cee0630 Fix doc 2026-02-17 20:57:38 +05:30
Sameer Kankute
842d5a0762 Fix mypy issues 2026-02-17 20:51:51 +05:30
Sameer Kankute
3af90d6e81
Merge pull request #21383 from BerriAI/litellm_fix_mock_tests 
Update poetry.lock
 2026-02-17 20:40:38 +05:30
Sameer Kankute
791cef6d99 fix test_chat_completion 2026-02-17 20:26:28 +05:30
Sameer Kankute
288f7b860c fix test_allow_access_by_email 2026-02-17 20:19:39 +05:30
Sameer Kankute
1ced47c612 fix tests/test_litellm/proxy/_experimental/mcp_server/test_mcp_server.py 2026-02-17 20:14:56 +05:30
Sameer Kankute
550bb621f7 fix llm tests 2026-02-17 20:13:23 +05:30
Sameer Kankute
fe20e66a1d Fix : test_exception_without_scanners 2026-02-17 20:12:02 +05:30
Sameer Kankute
8374b4d939 Fix : test_exception_without_scanners 2026-02-17 20:11:20 +05:30
Sameer Kankute
7a35116148 Fix : test_video_content_handler_uses_get_for_openai 2026-02-17 20:06:08 +05:30
Sameer Kankute
cd7fc38d21 Update poetry.lock 2026-02-17 19:51:59 +05:30
Sameer Kankute
211d6e9d30 Add vllm e2e test for embedding 2026-02-17 19:42:46 +05:30
Sameer Kankute
90be817b32 Add support for evals via sdk 2026-02-17 19:32:15 +05:30
Sameer Kankute
59408387ef Add eval run endpoints 2026-02-17 19:32:15 +05:30
Sameer Kankute
b246c3c56c Add eval run endpoints and methods 2026-02-17 19:32:15 +05:30
Sameer Kankute
8b75979fdc Add eval run endpoints methods 2026-02-17 19:32:15 +05:30
Sameer Kankute
782b048372 Update tests/test_litellm/llms/openai/evals/test_openai_evals_transformation.py 
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
 2026-02-17 19:30:58 +05:30
Sameer Kankute
ea72ffb03b Update litellm/llms/custom_httpx/llm_http_handler.py 
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
 2026-02-17 19:30:58 +05:30
Sameer Kankute
590b98630d Update litellm/llms/custom_httpx/llm_http_handler.py 
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
 2026-02-17 19:30:58 +05:30
Sameer Kankute
32263deb02 Add tests for openai evals 2026-02-17 19:30:58 +05:30
Sameer Kankute
71385a4e12 Add openai evals in base http handler 2026-02-17 19:30:58 +05:30
Sameer Kankute
5cc0036c87 Add openai evals endpoints and routing 2026-02-17 19:30:58 +05:30
Sameer Kankute
6b95bdeb12 Add OpenAIEvalsConfig 2026-02-17 19:30:58 +05:30
Sameer Kankute
a4eae1bc53 Add Evals API operations 2026-02-17 19:30:58 +05:30
Sameer Kankute
357a2b640e Add Evals API operations 2026-02-17 19:30:58 +05:30
Sameer Kankute
525acaf755 Add BaseEvalsAPIConfig for openai evals 2026-02-17 19:30:58 +05:30
Sameer Kankute
f4b79fa635
Merge pull request #21368 from TomeHirata/databricks/response-schema 
Add Databricks to supported LLM providers for response schema
 2026-02-17 14:04:18 +05:30
Tomu Hirata
43ba7d0a07 Add test case for Databricks Meta LLaMA 3.1 70B instruct model in content parsing tests 
Signed-off-by: Tomu Hirata <tomu.hirata@gmail.com>
 2026-02-17 15:36:00 +09:00
Tomu Hirata
3053fedad2 Add Databricks to supported LLM providers for response schema 
Signed-off-by: Tomu Hirata <tomu.hirata@gmail.com>
 2026-02-17 15:21:55 +09:00
yuneng-jiang
69ee2c21ea
Merge pull request #21362 from BerriAI/litellm_default_key_fix 
[Fix] Key Expiry Default Duration
 2026-02-16 21:09:23 -08:00
yuneng-jiang
8576683f39
Update tests/test_litellm/proxy/management_endpoints/test_key_management_endpoints.py 
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
 2026-02-16 21:09:13 -08:00
yuneng-jiang
ee5120bfc2 fix default duration 2026-02-16 20:54:10 -08:00
yuneng-jiang
96d7585ea4
Merge pull request #21353 from BerriAI/litellm_gh_server_root_test 
[Infra] Add Server Root Test to GitHub Actions
 2026-02-16 20:16:25 -08:00
yuneng-jiang
3b5096d142
Merge pull request #21357 from BerriAI/release_feb16_copy 
[Infra] v1.81.13-nightly Change Copy to main
 2026-02-16 20:15:57 -08:00
yuneng-jiang
3669d547f6 fixing regen key tests 2026-02-16 20:14:40 -08:00
yuneng-jiang
aa7bc6ae3b Adding bedrock thinking budget tokens to docs 2026-02-16 20:14:26 -08:00
yuneng-jiang
45e6440b0a fixing test_basic_openai_responses_api 2026-02-16 20:14:06 -08:00
yuneng-jiang
23219d9217 fixing container tests 2026-02-16 20:13:55 -08:00