5d516aace1
* Add tests for function calling support in LiteLLM proxy models - Introduced a new test script `test_proxy_function_calling.py` to validate function calling capabilities for both direct and proxied models. - Created a comprehensive test suite in `tests/litellm_utils_tests/test_proxy_function_calling.py` using pytest, covering various model configurations and edge cases. - Implemented parameterized tests to ensure consistency between direct and proxied model function calling support. - Added tests for specific proxy models, edge cases, and import verification for the `supports_function_calling` function. - Included a demonstration test to highlight the current issue with proxy model resolution. * feat: add fallback handling for litellm_proxy models in model info retrieval * feat: enhance proxy function calling tests with custom model name handling and documentation * fix: add type ignore comments for custom logger callback initialization * fix: remove styling diff * fix: style * fix(utils.py): remove outdated comment regarding litellm_proxy models * feat(utils.py): add proxy model handling for underlying model extraction * feat(utils.py): enhance model name handling for litellm_proxy integration * refactor(utils.py): remove unused _handle_proxy_model_names function |
||
|---|---|---|
| .. | ||
| basic_proxy_startup_tests | ||
| batches_tests | ||
| code_coverage_tests | ||
| documentation_tests | ||
| enterprise | ||
| guardrails_tests | ||
| image_gen_tests | ||
| litellm_utils_tests | ||
| litellm-proxy-extras | ||
| llm_responses_api_testing | ||
| llm_translation | ||
| load_tests | ||
| local_testing | ||
| logging_callback_tests | ||
| mcp_tests | ||
| multi_instance_e2e_tests | ||
| old_proxy_tests/tests | ||
| openai_endpoints_tests | ||
| otel_tests | ||
| pass_through_tests | ||
| pass_through_unit_tests | ||
| proxy_admin_ui_tests | ||
| proxy_security_tests | ||
| proxy_unit_tests | ||
| router_unit_tests | ||
| scim_tests | ||
| spend_tracking_tests | ||
| store_model_in_db_tests | ||
| test_litellm | ||
| windows_tests | ||
| __init__.py | ||
| 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_entrypoint.py | ||
| test_fallbacks.py | ||
| test_health.py | ||
| test_keys.py | ||
| test_logging.conf | ||
| test_models.py | ||
| 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 | ||
| 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.