mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
2a1983aa37
Previously, _get_mcp_tools_from_manager() hardcoded mcp_auth_header=None and mcp_server_auth_headers=None when calling _get_tools_from_mcp_servers(). This meant that x-mcp-auth and x-mcp-<server>-* headers from the HTTP request were never forwarded during tool list fetching, causing MCP servers that require authentication to fail with 424 (Failed Dependency). The auth headers were already correctly forwarded for tool execution (call_tool) but were missing from the tool discovery path. Changes: - _get_mcp_tools_from_manager: Accept and forward mcp_auth_header, mcp_server_auth_headers, oauth2_headers, raw_headers parameters - _process_mcp_tools_without_openai_transform: Thread auth headers through to _get_mcp_tools_from_manager - _process_mcp_tools_to_openai_format: Thread auth headers through - aresponses_api_with_mcp (responses/main.py): Extract MCP auth headers from secret_fields BEFORE tool list retrieval, not just for auto-execute - acompletion_with_mcp (chat_completions_handler.py): Same fix - extract headers early and pass to tool processing Tests: - test_get_mcp_tools_from_manager_forwards_auth_headers - test_process_mcp_tools_without_openai_transform_forwards_auth_headers Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| 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_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.