litellm/tests at 071c8a2e26fce00851161a79eda99bf82ca14872 - litellm - Gitea: Git with a cup of tea

tiennm99/litellm

mirror of https://github.com/tiennm99/litellm.git synced 2026-07-09 01:08:05 +00:00

Files

T

History

Krish Dholakia 552b7e4013 Add customer + model per key level multi-instance tpm/rpm limiting (#10518 )

* fix(redis_cache.py): handle multiple event loops

* fix(parallel_request_limiter_v2.py): add customer tpm limiting

* fix(parallel_request_limiter.py): add customer rpm limiting

* fix(parallel_request_limiter_v2.py): add model per key + customer tpm/rpm limiting

* fix(parallel_request_limiter_v2.py): make error more informative

* fix: fix ruff error

* fix: generate new poetry lock

2025-05-03 10:28:55 -07:00

..

basic_proxy_startup_tests

…

VertexAI non-jsonl file storage support (#9781 )

2025-04-09 14:01:48 -07:00

code_coverage_tests

Handle more gemini tool calling edge cases + support bedrock 'stable-image-core' (#10351 )

2025-04-28 14:22:29 -07:00

documentation_tests

…

Add customer + model per key level multi-instance tpm/rpm limiting (#10518 )

2025-05-03 10:28:55 -07:00

image_gen_tests

[Bug Fix] Add Cost Tracking for gpt-image-1 when quality is unspecified (#10247 )

2025-04-23 15:16:40 -07:00

[Feat] Show Vector Store / KB Request on LiteLLM Logs Page (#10514 )

2025-05-02 16:14:09 -07:00

litellm_utils_tests

fix(token_counter.py): handle empty lists

2025-05-02 08:07:08 -07:00

litellm-proxy-extras

Prisma Migrate - support setting custom migration dir (#10336 )

2025-04-26 12:05:06 -07:00

llm_responses_api_testing

test: handle internal server errors

2025-05-01 16:47:30 -07:00

llm_translation

Add vertex ai meta llama 4 support + handle tool call result in content for vertex ai (#10492 )

2025-05-01 22:47:06 -07:00

test: bump limit on flaky load test

2025-05-02 12:10:22 -07:00

UI - allow reassigning team to other org (#10527 )

2025-05-03 08:44:43 -07:00

logging_callback_tests

[QA] Bedrock Vector Stores Integration - Allow using with registry + in OpenAI API spec with tools (#10516 )

2025-05-03 08:30:38 -07:00

test fixes

2025-03-29 18:34:58 -07:00

multi_instance_e2e_tests

…

old_proxy_tests/tests

test: update tests to new deployment model (#10142 )

2025-04-18 14:22:12 -07:00

openai_endpoints_tests

# expect an error when getting the response again since

2025-04-25 09:42:35 -07:00

Refactor budget assertions in tests to improve clarity and accuracy. Updated remaining hours check to ensure positive values and adjusted budget reset time validation for better range checks. (#10500 )

2025-05-02 09:02:02 -07:00

pass_through_tests

test: add more debug logs

2025-04-29 15:40:18 -07:00

pass_through_unit_tests

fix test_anthropic_messages_litellm_router_streaming_with_logging

2025-05-03 09:34:32 -07:00

proxy_admin_ui_tests

Playwright test for team admin (#10366 ) (#10470 )

2025-05-03 08:20:00 -07:00

proxy_security_tests

…

proxy_unit_tests

Refactor budget assertions in tests to improve clarity and accuracy. Updated remaining hours check to ensure positive values and adjusted budget reset time validation for better range checks. (#10500 )

2025-05-02 09:02:02 -07:00

router_unit_tests

test_init_responses_api_endpoints

2025-04-24 21:43:59 -07:00

[Feat SSO] Add LiteLLM SCIM Integration for Team and User management (#10072 )

2025-04-16 19:21:47 -07:00

spend_tracking_tests

test_long_term_spend_accuracy_with_bursts

2025-03-31 21:09:29 -07:00

store_model_in_db_tests

fix(router.py): handle edge case where user sets 'model_group' inside… (#10191 )

2025-04-21 16:17:45 -07:00

gettysburg.wav

…

large_text.py

…

openai_batch_completions.jsonl

…

README.MD

…

test_callbacks_on_proxy.py

…

test_config.py

…

test_debug_warning.py

…

test_end_users.py

test: run test earlier to catch error

2025-03-27 23:08:52 -07:00

test_entrypoint.py

…

test_fallbacks.py

…

test_health.py

…

test_keys.py

Support x-litellm-api-key header param + allow key at max budget to call non-llm api endpoints (#10392 )

2025-04-29 18:57:57 -07:00

test_logging.conf

…

test_models.py

Litellm UI improvements 04 26 2025 p1 (#10346 )

2025-04-26 18:24:49 -07:00

test_openai_endpoints.py

…

test_organizations.py

UI - fix adding vertex models with reusable credentials + fix pagination on keys table + fix showing org budgets on table (#10528 )

2025-05-03 08:16:53 -07:00

test_passthrough_endpoints.py

…

test_ratelimit.py

…

test_spend_logs.py

…

test_team_logging.py

…

test_team_members.py

…

test_team.py

…

test_users.py

…

README.MD

In total litellm runs 1000+ tests

[02/20/2025] Update:

To make it easier to contribute and map what behavior is tested,

we've started mapping the litellm directory in tests/litellm

This folder can only run mock tests.