Adding custom httpx client for streamable mcp connection #2966
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @calvinbrown085, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request enhances the MCP client session by allowing users to inject their own httpx.AsyncClient for streamable HTTP connections. This provides greater flexibility for advanced configurations and custom behaviors of the underlying HTTP client, without breaking existing functionality.
Highlights
- Custom HTTPX Client Support: Introduced the ability to pass a custom
httpx.AsyncClientinstance to theStreamableHTTPConnectionParams, allowing users to configure their HTTP client with specific settings. - Backward Compatibility: The changes are designed to be fully backward compatible, meaning existing implementations that do not provide a custom client will continue to function as before.
- Pydantic Model Configuration: Updated
StreamableHTTPConnectionParamsto usepydantic.ConfigDict(arbitrary_types_allowed=True)to correctly handle thehttpx.AsyncClienttype. - Test Coverage: Added a new unit test to verify that the
StreamableHTTPConnectionParamscorrectly initializes and stores a providedhttpx.AsyncClient.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in pull request comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
There was a problem hiding this comment.
Code Review
This pull request effectively adds the capability to use a custom httpx client, which is a valuable enhancement for users needing more control over HTTP configurations. The implementation is straightforward and includes necessary tests. I've provided one suggestion to refactor a small part of the code to improve its conciseness and maintainability by reducing code duplication. Overall, this is a solid contribution.
| elif isinstance(self._connection_params, StreamableHTTPConnectionParams): | ||
| client = streamablehttp_client( | ||
| url=self._connection_params.url, | ||
| headers=merged_headers, | ||
| timeout=timedelta(seconds=self._connection_params.timeout), | ||
| sse_read_timeout=timedelta( | ||
| seconds=self._connection_params.sse_read_timeout | ||
| ), | ||
| terminate_on_close=self._connection_params.terminate_on_close, | ||
| ) | ||
| if self._connection_params.httpx_client: | ||
| client = streamablehttp_client( | ||
| url=self._connection_params.url, | ||
| headers=merged_headers, | ||
| timeout=timedelta(seconds=self._connection_params.timeout), | ||
| sse_read_timeout=timedelta( | ||
| seconds=self._connection_params.sse_read_timeout | ||
| ), | ||
| terminate_on_close=self._connection_params.terminate_on_close, | ||
| httpx_client_factory=self._connection_params.httpx_client, | ||
| ) | ||
| else: | ||
| client = streamablehttp_client( | ||
| url=self._connection_params.url, | ||
| headers=merged_headers, | ||
| timeout=timedelta(seconds=self._connection_params.timeout), | ||
| sse_read_timeout=timedelta( | ||
| seconds=self._connection_params.sse_read_timeout | ||
| ), | ||
| terminate_on_close=self._connection_params.terminate_on_close, | ||
| ) |
There was a problem hiding this comment.
There's significant code duplication between the if and else blocks. All arguments to streamablehttp_client are the same except for httpx_client_factory. You can make the code more concise and easier to maintain by creating a dictionary of common arguments and conditionally adding httpx_client_factory before calling the function with keyword argument unpacking.
kwargs = {
"url": self._connection_params.url,
"headers": merged_headers,
"timeout": timedelta(seconds=self._connection_params.timeout),
"sse_read_timeout": timedelta(
seconds=self._connection_params.sse_read_timeout
),
"terminate_on_close": self._connection_params.terminate_on_close,
}
if self._connection_params.httpx_client:
kwargs["httpx_client_factory"] = self._connection_params.httpx_client
client = streamablehttp_client(**kwargs)
Hopefully resolves #2963
I'm not the most fluent in Python so if there's a better way to accomplish this, please let me know!
The goal was to allow a user to pass their own client into the MCP client session instead of using the default mcp one. This should still support that and be backwards compatible if folks would like to keep using that.