[DivyaNarahari97]

_aggregate_components treated an empty prompt/resource/tool sweep as "the server gave us nothing" and deleted the session's exit stack.

On the connect_with_session path no stack is ever registered, so the del raised a bare KeyError and the connection failed outright. On the connect_to_server path the stack was removed without being closed, so disconnect_from_server had nothing left to tear down and the transport stayed open until the whole group exited.

The premise was wrong in the first place: the group never calls list_resource_templates, so a server whose entire surface is a resource template also looks componentless to aggregation.

Fixes #3384

[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 #3384.

If a maintainer assigns you to #3384, 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.