litellm/tests
Krish Dholakia 2ed593e052
Updated cohere v2 passthrough (#9997)
* Add cohere `/v2/chat` pass-through cost tracking support (#8235)

* feat(cohere_passthrough_handler.py): initial working commit with cohere passthrough cost tracking

* fix(v2_transformation.py): support cohere /v2/chat endpoint

* fix: fix linting errors

* fix: fix import

* fix(v2_transformation.py): fix linting error

* test: handle openai exception change
2025-04-14 19:51:01 -07:00
..
basic_proxy_startup_tests
batches_tests VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
code_coverage_tests fix(cost_calculator.py): handle custom pricing at deployment level fo… (#9855) 2025-04-09 22:13:10 -07:00
documentation_tests
image_gen_tests get_base_image_generation_call_args 2025-04-02 21:04:06 -07:00
litellm [UI QA checklist] (#9957) 2025-04-12 20:41:50 -07:00
litellm_utils_tests [Feat] Add litellm.supports_reasoning() util to track if an llm supports reasoning (#9923) 2025-04-11 17:56:04 -07:00
llm_responses_api_testing test_openai_o1_pro_response_api_streaming 2025-03-20 13:04:49 -07:00
llm_translation fix(transformation.py): correctly translate 'thinking' param for lite… (#9904) 2025-04-11 23:25:13 -07:00
load_tests fix vertex embedding perf test 2025-03-26 10:25:50 -07:00
local_testing Updated cohere v2 passthrough (#9997) 2025-04-14 19:51:01 -07:00
logging_callback_tests [Feat] Add litellm.supports_reasoning() util to track if an llm supports reasoning (#9923) 2025-04-11 17:56:04 -07:00
mcp_tests test fixes 2025-03-29 18:34:58 -07:00
multi_instance_e2e_tests (e2e testing) - add tests for using litellm /team/ updates in multi-instance deployments with Redis (#8440) 2025-02-10 19:33:27 -08:00
old_proxy_tests/tests
openai_endpoints_tests test_bad_request_bad_param_error 2025-03-13 16:02:21 -07:00
otel_tests [Team Member permissions] - Fixes (#9945) 2025-04-12 11:17:51 -07:00
pass_through_tests [Bug Fix] Add support for UploadFile on LLM Pass through endpoints (OpenAI, Azure etc) (#9853) 2025-04-09 15:29:20 -07:00
pass_through_unit_tests use new anthropic interface 2025-03-31 14:31:09 -07:00
proxy_admin_ui_tests [Team Member permissions] - Fixes (#9945) 2025-04-12 11:17:51 -07:00
proxy_security_tests (Security fix) - remove code block that inserts master key hash into DB (#8268) 2025-02-05 17:25:42 -08:00
proxy_unit_tests [Feat] Emit Key, Team Budget metrics on a cron job schedule (#9528) 2025-04-10 16:59:14 -07:00
router_unit_tests fix(router.py): support reusable credentials via passthrough router (#9758) 2025-04-04 18:40:14 -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 test_chat_completion_bad_model_with_spend_logs 2025-02-28 20:19:43 -08:00
gettysburg.wav
large_text.py
openai_batch_completions.jsonl
README.MD add bedrock llama vision support + cohere / infinity rerank - 'return_documents' support (#8684) 2025-02-20 21:23:54 -08:00
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: fix test 2025-03-10 22:00:50 -07:00
test_health.py
test_keys.py
test_logging.conf
test_models.py fix(model_management_endpoints.py): fix allowing team admins to update team models (#9697) 2025-04-01 22:28:15 -07:00
test_openai_endpoints.py test string checked for model access control 2025-03-10 20:04:18 -07:00
test_organizations.py Add remaining org CRUD endpoints + support deleting orgs on UI (#8561) 2025-02-15 15:48:06 -08:00
test_passthrough_endpoints.py
test_ratelimit.py
test_spend_logs.py (feat) - track org_id in SpendLogs (#8253) 2025-02-04 21:08:05 -08:00
test_team_logging.py
test_team_members.py
test_team.py fix(team_endpoints.py): ensure 404 raised when team not found (#9038) 2025-03-06 22:04:36 -08:00
test_users.py

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.