[nikolas-sapa]

Summary

Closes #3709.

When a synchronous prompt function returns an awaitable (coroutine, Task, or Future), Prompt.render() previously ran the sync callable in a worker thread via anyio.to_thread.run_sync(), but did not await the returned awaitable. This resulted in the coroutine object being serialized as fallback JSON/string representation:

Left contains one more item: Message(role='user', content=TextContent(type='text', text='"<coroutine object ...>"'))

PromptResult explicitly allows Awaitable[SyncPromptResult]. This PR awaits any awaitable returned by the prompt callable before validating and converting messages.

Root Cause

Prompt.render() ran result = await anyio.to_thread.run_sync(...) for non-async callables, but did not check inspect.isawaitable(result).

Fix

Added if inspect.isawaitable(result): result = await result immediately after running the prompt callable in src/mcp/server/mcpserver/prompts/base.py.

Test Plan

• Added regression test test_prompt_render_awaits_awaitable_returned_by_sync_callback in tests/server/mcpserver/prompts/test_base.py.
• Verified test fails RED on base and passes GREEN with fix.
• Ran all 22 prompt tests in test_base.py: 22 passed.
• ruff check, ruff format --check, and pyright: 0 errors.

[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 #3709.

If a maintainer assigns you to #3709, 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.