litellm/tests/test_litellm
Jugal D. Bhatt b8fe5f7b17
[MCP Gateway] LiteLLM Fix MCP gateway key auth (#13630)
* Fix - add safe divide by 0 for most places to prevent crash

* Enhance MCPRequestHandler to support permission inheritance and intersection logic for access groups. Added integration tests to verify behavior when keys have no permissions and when both keys and teams have overlapping permissions.

* Remove redundant assertions for permission checks in test_user_api_key_auth_mcp.py to streamline test logic.

* Refactor integration tests for MCPRequestHandler to simplify mocking. Replace complex database mocks with direct function mocks for permission inheritance and intersection scenarios, improving test clarity and maintainability.

* Revert "Fix - add safe divide by 0 for most places to prevent crash"

This reverts commit 265d40e39051e148996b9fb7f354730c57ff23ac.
2025-08-14 16:32:18 -07:00
..
caching Add GCS bucket caching support (#13122) 2025-08-04 16:09:33 -07:00
completion_extras/litellm_responses_transformation fix: handle reasoning parameters and response in responses bridge (#12433) 2025-07-10 18:06:45 -07:00
enterprise/enterprise_callbacks [Feat] Backend - Add support for disabling callbacks in request body (#12762) 2025-07-19 10:10:30 -07:00
experimental_mcp_client [MCP Gateway] Allow using stdio MCPs with LiteLLM (#12530) 2025-07-11 20:21:02 -07:00
google_genai [Bug Fix] Gemini-CLI - The Gemini Custom API request has an incorrect authorization format (#13098) 2025-07-29 13:46:43 -07:00
integrations Update mlflow logger usage span attributes (#13561) 2025-08-14 15:20:50 -07:00
litellm_core_utils Revert "Revert "Fix - add safe divide by 0 for most places to prevent crash"" 2025-08-14 14:23:06 -07:00
llms [LLM Translation] Fix Realtime API endpoint for no intent (#13476) 2025-08-14 16:24:14 -07:00
passthrough
proxy [MCP Gateway] LiteLLM Fix MCP gateway key auth (#13630) 2025-08-14 16:32:18 -07:00
responses [Feat] Working e2e flow for Responses API session management with media (#13456) 2025-08-08 18:28:10 -07:00
router_strategy fix mapped test 2025-07-25 07:24:42 -07:00
router_utils
secret_managers Added handling for pwd protected cert files in AOAI CertificateCredential auth (#12995) 2025-07-28 21:34:54 -07:00
types [LLM Translation] Fix Model Usage not having text tokens (#13234) 2025-08-04 21:06:49 +05:30
vector_stores
__init__.py
conftest.py
log.txt
readme.md
test_constants.py
test_cost_calculation_log_level.py Enhance logging in cost calculation tests to ensure DEBUG level captures are accurate. Updated tests to set logger level before assertions and restored original logger level after execution. This improves reliability of log level checks in both cost and batch cost calculation tests. 2025-08-14 14:21:22 -07:00
test_cost_calculator.py test: update test 2025-07-16 09:15:05 -07:00
test_logging.py [Bug Fix] StandardLoggingPayload on cache_hits should track custom llm provider + DD LLM Obs span type (#12652) 2025-07-16 15:43:15 -07:00
test_lowest_latency_zero_tokens.py fix(lowest_latency.py): Handle ZeroDivisionError with zero completion tokens (#12734) 2025-07-18 15:19:47 -07:00
test_main.py Fix async retryer on .acompletion() + forward clientside headers - filter out content-type from clientside request (causes llm api call to hang) (#12886) 2025-07-22 19:50:05 -07:00
test_router.py Litellm dev 08 07 2025 p1 (#13418) 2025-08-09 16:30:04 -07:00
test_utils.py Merge pull request #13590 from BerriAI/litellm_bedrock_api_header 2025-08-14 11:32:18 -07:00

Testing for litellm/

This directory 1:1 maps the the litellm/ directory, and can only contain mocked tests.

The point of this is to:

  1. Increase test coverage of litellm/
  2. Make it easy for contributors to add tests for the litellm/ package and easily run tests without needing LLM API keys.

File name conventions

  • litellm/proxy/test_caching_routes.py maps to litellm/proxy/caching_routes.py
  • test_<filename>.py maps to litellm/<filename>.py