Fix quadratic time reading large stdio responses

[guptaishaan]

Fixes #3699

Motivation and Context

stdio_client took quadratic time to receive a large response. stdout_reader did (buffer + chunk).split("\n") for every chunk, so one big JSON line was re-copied once per chunk.

Now chunks without a newline are collected in a list and joined once when the line ends. Thanks to the reporter of #3699 for the diagnosis and the proposed change.

Real client and server over pipes (the issue's script), 16 MB reply: 6.29 s before, 0.19 s after. 32 MB: 22.86 s before, 0.39 s after.

How Has This Been Tested?

• New test in tests/client/test_stdio.py feeds an 8 MB line in 1 KB chunks to the fake process. It times out (5 s) without the fix and passes in about 0.08 s with it.
• tests/client/test_stdio.py and tests/interaction/transports/test_stdio.py pass (38 tests). ruff check and ruff format --check are clean.
• Linux only. Not run on Windows or macOS. Full suite and coverage gate not run. The new test is wall-clock based, with a wide margin.

Breaking Changes

None.

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update

Checklist

• I am assigned to the linked issue (or it is labeled help wanted, or I'm a maintainer)
• I have disclosed any AI assistance and can explain the change in my own words
• I have read the MCP Documentation
• My code follows the repository's style guidelines
• New and existing tests pass locally
• I have added appropriate error handling
• I have added or updated documentation as needed

Additional context

AI disclosure: this change was written and tested by an automated Claude agent run, not by hand.

[github-actions]

This PR has been closed automatically. This repo only keeps pull requests open when they come from a maintainer, or from a contributor a maintainer has assigned to the linked issue, and you aren't currently assigned to #3699.

If a maintainer assigns you to #3699, this PR reopens on its own and there's nothing more you need to do here. Assignment is a maintainer call based on capacity; comments that only ask to be assigned don't factor in. What does help is engaging on the issue itself by confirming the repro, explaining why it matters for your use case, or describing the approach you'd take.

You're welcome to keep pushing commits here (just avoid force-pushing, since GitHub can't reopen a rewritten branch), but that on its own won't get the PR reviewed or the issue assigned, and realistically most auto-closed PRs stay closed. There's no need to open a new PR either way.

CONTRIBUTING.md has the full reasoning, but in short:

• We're a small team with very little capacity to review community PRs right now.
• Many recent PRs are AI-generated with little human review, and reviewing one carefully still costs a maintainer as much time as it ever did. A well-described issue is usually more useful to us than the code.

Maintainers: reopen, remove missing-issue-link, or add bypass-issue-check to override.