Ashwin Bharambe 1e81056a22 feat(tests): enable MCP tests in server mode (#4146) ... We would like to run all OpenAI compatibility tests using only the openai-client library. This is most friendly for contributors since they can run tests without needing to update the client-sdks (which is getting easier but still a long pole.) This is the first step in enabling that -- no using "library client" for any of the Responses tests. This seems like a reasonable trade-off since the usage of an embeddeble library client for Responses (or any OpenAI-compatible) behavior seems to be not very common. To do this, we needed to enable MCP tests (which only worked in library client mode) for server mode.		2025-11-13 07:23:23 -08:00
..
recordings	fix(responses): fix subtle bugs in non-function tool calling (#3817)	2025-10-15 13:57:37 -07:00
test_builtin_tools.py	feat(tools)!: substantial clean up of "Tool" related datatypes (#3627)	2025-10-02 15:12:03 -07:00
test_mcp.py	feat(tests): enable MCP tests in server mode (#4146)	2025-11-13 07:23:23 -08:00
test_mcp_json_schema.py	chore: Stack server no longer depends on llama-stack-client (#4094)	2025-11-07 09:54:09 -08:00
test_registration.py	chore: Stack server no longer depends on llama-stack-client (#4094)	2025-11-07 09:54:09 -08:00