mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-16 23:41:43 +00:00
8efb70e7a0
Root cause: get_sanitized_user_information_from_key() passed user_api_key_dict.metadata (which contains the raw 'logging' key with langfuse_secret_key, api keys, etc.) directly into user_api_key_auth_metadata. This dict then propagated to every logger integration via StandardLoggingUserAPIKeyMetadata without ever being scrubbed. Structural fixes (three layers of defense): 1. _safe_key_metadata() in litellm_pre_call_utils.py: strips 'logging' and 'callback_settings' from key metadata before it becomes user_api_key_auth_metadata. Credentials are now removed at the earliest possible point — before scatter. 2. langfuse.py _log_langfuse_v2: add 'user_api_key_auth_metadata' to the clean_metadata exclusion list, alongside 'user_api_key_auth'. Belt-and-suspenders for Langfuse. 3. langfuse.py: use standard_logging_object['model_parameters'] (OpenAI-spec whitelist) instead of raw optional_params for modelParameters. Structurally prevents any callback credential from reaching modelParameters regardless of future key types. These fixes are general: they protect against leaking any credential type (LLM api keys, virtual keys, etc.), not just langfuse_secret_key. |
||
|---|---|---|
| .. | ||
| agent_tests | ||
| audio_tests | ||
| basic_proxy_startup_tests | ||
| batches_tests | ||
| code_coverage_tests | ||
| documentation_tests | ||
| enterprise | ||
| guardrails_tests | ||
| image_gen_tests | ||
| litellm | ||
| litellm-proxy-extras | ||
| litellm_core_utils | ||
| litellm_utils_tests | ||
| llm_responses_api_testing | ||
| llm_translation | ||
| load_tests | ||
| local_testing | ||
| logging_callback_tests | ||
| mcp_tests | ||
| multi_instance_e2e_tests | ||
| ocr_tests | ||
| old_proxy_tests/tests | ||
| openai_endpoints_tests | ||
| otel_tests | ||
| pass_through_tests | ||
| pass_through_unit_tests | ||
| proxy_admin_ui_tests | ||
| proxy_e2e_anthropic_messages_tests | ||
| proxy_e2e_azure_batches_tests | ||
| proxy_security_tests | ||
| proxy_unit_tests | ||
| router_unit_tests | ||
| scim_tests | ||
| search_tests | ||
| spend_tracking_tests | ||
| store_model_in_db_tests | ||
| test_litellm | ||
| unified_google_tests | ||
| vector_store_tests | ||
| windows_tests | ||
| __init__.py | ||
| gettysburg.wav | ||
| large_text.py | ||
| openai_batch_completions.jsonl | ||
| README.MD | ||
| test_budget_management.py | ||
| test_callbacks_on_proxy.py | ||
| test_config.py | ||
| test_debug_warning.py | ||
| test_default_encoding_non_root.py | ||
| test_end_users.py | ||
| test_entrypoint.py | ||
| test_fallbacks.py | ||
| test_gpt5_azure_temperature_support.py | ||
| test_health.py | ||
| test_keys.py | ||
| test_litellm_proxy_responses_config.py | ||
| test_logging.conf | ||
| test_models.py | ||
| test_openai_endpoints.py | ||
| test_organizations.py | ||
| test_otel_thread_leak.py | ||
| test_passthrough_endpoints.py | ||
| test_presidio_latency.py | ||
| test_proxy_server_non_root.py | ||
| test_ratelimit.py | ||
| test_resource_cleanup.py | ||
| test_service_logger_otel.py | ||
| test_spend_logs.py | ||
| test_team.py | ||
| test_team_logging.py | ||
| test_team_members.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/test_litellm
This folder can only run mock tests.