Add Automated Tests for src/mcp/client/sse.py and src/mcp/server/sse.py

[apappascs]

The files src/mcp/client/sse.py and src/mcp/server/sse.py implement the client and server functionalities for SSE transport, but there are no tests in the repository to verify their behavior.

Relevant Links: PR: https://github.com/modelcontextprotocol/python-sdk/pull/83 Related Discussion: https://github.com/jlowin/fastmcp/issues/69 Related Issue: https://github.com/modelcontextprotocol/python-sdk/issues/101

[windcandle]

Please help me!

[Harsimran-19]

Can I work on this issue?

[windcandle]

@Harsimran-19 you can?

[Pan-Binghong]

I'm having the same problem. Did you solve it? @windcandle

[AI-Surfing]

similar question！ The error messages as followed:

pydantic_core._pydantic_core.ValidationError: 1 validation error for Xinference
client
  Field required [type=missing, input_value={'server_url': 'http://0....Tl', 'model_kwargs': {}}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.9/v/missing

how to solve it?

[spark-ws]

same problem here!

[fz5400]

pip install langchain_community==0.2 problem solved

[jsli]

In package 'lanchain_community.llms.xinference', make client: Optional[Any] = None optional, then ok. langchain-community==0.3.9 @spark-ws @AI-Surfing @windcandle @Pan-Binghong

[bigfool]

In package 'lanchain_community.llms.xinference', make client: Optional[Any] = None optional, then ok. langchain-community==0.3.9 @spark-ws @AI-Surfing @windcandle @Pan-Binghong

can you show me the code?thanks

[leo-liu-83]

In package 'lanchain_community.llms.xinference', make client: Optional[Any] = None optional, then ok. langchain-community==0.3.9 @spark-ws @AI-Surfing @windcandle @Pan-Binghong

can you show me the code?thanks

same problem. It works for me.

[dosubot[bot]]

Hi, @windcandle. I'm Dosu, and I'm helping the LangChain team manage their backlog. I'm marking this issue as stale.

Issue Summary

• The issue involves a ValidationError when initializing Xinference due to a missing "client" field.
• Several users, including @Pan-Binghong, @AI-Surfing, and @spark-ws, reported the same problem.
• @jsli suggested making the client field optional, which resolved the issue, confirmed by @leo-liu-83.
• A temporary workaround was downgrading to langchain_community==0.2, as suggested by @fz5400.

Next Steps

• Please confirm if this issue is still relevant to the latest version of the LangChain repository by commenting here.
• If there is no further activity, this issue will be automatically closed in 7 days.

Thank you for your understanding and contribution!