mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-15 23:31:29 +00:00
b0908d5345
The call_tool and list_tools mock tests seeded a tool's owning-server set from every id in the registry. That holds only while the fixture has exactly one server; adding a second would make the tool look multi-owned and resolve as ambiguous, failing the test for an unrelated reason. Each site now derives the id from the server it actually loaded, matching the pattern already used in the alias-prefixing tests and the logging tests. |
||
|---|---|---|
| .. | ||
| test_configs | ||
| conftest.py | ||
| mcp_e2e_upstream_server.py | ||
| mcp_server.py | ||
| test_aresponses_api_with_mcp.py | ||
| test_mcp_auth_header_extraction.py | ||
| test_mcp_auth_priority.py | ||
| test_mcp_chat_completions.py | ||
| test_mcp_client_unit.py | ||
| test_mcp_guardrails.py | ||
| test_mcp_hooks.py | ||
| test_mcp_litellm_client.py | ||
| test_mcp_logging.py | ||
| test_mcp_server.py | ||
| test_oauth2_mcp_config.yaml | ||
| test_openapi_spec_path_url.py | ||
| test_per_user_oauth_cache.py | ||
| test_proxy_mcp_e2e.py | ||
| test_semantic_tool_filter_e2e.py | ||