litellm

History

Krish Dholakia 1a4ad8bf18 Update mistral 'supports_response_schema' field + Fix ollama embedding (#12024 ) * build(model_prices_and_context_window.json): update all mistral models (besides codestral-mamba) to indicate support for response schema Closes https://github.com/BerriAI/litellm/issues/12012 * fix(route_llm_request.py): if llm router is not initialized, go straight through to litellm sdk Fixes https://github.com/BerriAI/litellm/issues/12008 * test: add unit test * fix(ollama_embeddings): fix unecessary await Fixes https://github.com/BerriAI/litellm/issues/11997 * test: update ollama embedding tests		2025-06-25 07:20:13 -07:00
..
basic_proxy_startup_tests
batches_tests
code_coverage_tests	docs(litellm_logging_code_coverage.py): fix check	2025-06-18 21:36:03 -07:00
documentation_tests
enterprise	test_internal_user_endpoints.py	2025-06-21 16:45:14 -07:00
guardrails_tests	[Bug Fix] Bedrock Guardrail - Don't raise exception on intervene action (#11875 )	2025-06-23 19:59:44 -07:00
image_gen_tests	[Fix]: Add cost tracking for image edits endpoint [OpenAI, Azure] (#11186 )	2025-05-27 17:52:15 -07:00
litellm_utils_tests	Update enduser spend and budget reset date based on budget duration (#8460 )	2025-06-08 08:39:14 -07:00
litellm-proxy-extras
llm_responses_api_testing	[Feat] Add Azure Codex Models on LiteLLM + new /v1 preview Azure OpenAI API (#11934 )	2025-06-20 18:08:44 -07:00
llm_translation	Anthropic `/v1/messages` - Custom LLM Server support (#12016 )	2025-06-24 22:00:44 -07:00
load_tests
local_testing	Minor Fixes (#11868 )	2025-06-18 14:12:59 -07:00
logging_callback_tests	[Feat] Add OpenAI Search Vector Store Operation (#12018 )	2025-06-24 15:52:43 -07:00
mcp_tests	[Feat] MCP - Allow connecting to MCP with authentication headers + Allow clients to specify MCP headers (#11890 ) (#11891 )	2025-06-19 20:07:08 -07:00
multi_instance_e2e_tests
old_proxy_tests/tests
openai_endpoints_tests	set flaky tests as flaky	2025-06-14 13:51:52 -07:00
otel_tests	set flaky tests as flaky	2025-06-14 13:51:52 -07:00
pass_through_tests	test_anthropic_basic_completion_with_headers	2025-06-14 13:56:06 -07:00
pass_through_unit_tests	[Bug Fix] Cost tracking and logging via the /v1/messages API are not working when using Claude Code (#11928 )	2025-06-20 18:08:35 -07:00
proxy_admin_ui_tests	test(test_sso_sign_in.py): update test	2025-06-03 21:46:34 -07:00
proxy_security_tests
proxy_unit_tests	Squashed commit of the following:	2025-06-20 23:11:53 -07:00
router_unit_tests	Support env var vertex credentials for passthrough + ignore space id on watsonx deployment (throws Json validation errors) (#11527 )	2025-06-07 20:31:05 -07:00
scim_tests
spend_tracking_tests
store_model_in_db_tests	fix test MCP	2025-06-20 12:09:45 -07:00
test_litellm	Update mistral 'supports_response_schema' field + Fix ollama embedding (#12024 )	2025-06-25 07:20:13 -07:00
vector_store_tests	[Feat] OpenAI/Azure OpenAI - Add support for creating vector stores on LiteLLM (#12021 )	2025-06-24 20:46:48 -07:00
windows_tests
__init__.py
gettysburg.wav
large_text.py
openai_batch_completions.jsonl
README.MD
test_budget_management.py	Update enduser spend and budget reset date based on budget duration (#8460 )	2025-06-08 08:39:14 -07:00
test_callbacks_on_proxy.py
test_config.py
test_debug_warning.py
test_end_users.py
test_entrypoint.py
test_fallbacks.py	Ollama Chat - parse tool calls on streaming (#11171 )	2025-05-27 16:14:49 -07:00
test_health.py
test_keys.py
test_logging.conf
test_models.py	Add model access groups on UI (#11719 )	2025-06-13 21:20:25 -07:00
test_openai_endpoints.py
test_organizations.py
test_passthrough_endpoints.py
test_ratelimit.py
test_spend_logs.py
test_team_logging.py
test_team_members.py
test_team.py	build: publish new litellm-proxy-extras file	2025-05-27 17:44:23 -07:00
test_users.py	test: fix imports	2025-05-26 22:06:53 -07:00

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.