Cairn

MCP poll loop TimeoutError spin causing gateway OOM

NousResearch/hermes-agent · cluster 63892 · mcp

Data as of

Nothing open on GitHub. Fix merged in #67183. Check it covers your case.

The short answer

0open issues
0open PRs
6items grouped
Known?
Yes. 6 related items grouped here, 1 issue already closed.
Fix event
A fix was merged to main in PR #67183. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this resolved, deciding PR #67183. That is separate from the fix event.
Still open
Nothing open on GitHub.

Multiple fixes targeting an MCP poll loop bug where a completed future's real TimeoutError is mistaken for a poll timeout, causing infinite spinning and significant memory leakage. Several approaches to stopping the spin and surfacing the correct error are represented.

Open issues0

No open issues.

Open PRs0

No open pull requests.

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

  • #67183 fix(mcp): stop gateway OOM from poll loop swallowing a completed future's real TimeoutError (supersedes #63918, #64072, #63903, #66039)

    merged to main

    files: tests/tools/test_mcp_poll_loop_oom_integration.py, tests/tools/test_mcp_tool.py, tools/mcp_tool.py

4 PRs closed without merging

From the close comments: done elsewhere 2 · merged via another change 1 · superseded by another PR 1

  • #63903 fix(mcp): resolve completed future in poll loop to stop TimeoutError spin (#63892) · done elsewhere → #67183
  • #63918 fix(mcp): propagate stored timeouts from completed futures · merged via another change → #67183
  • #64072 fix(mcp): surface completed future's real TimeoutError instead of spinning (_run_on_mcp_loop, #63892) · done elsewhere → #67183
  • #66039 fix: prevent OOM from MCP poll loop swallowing real TimeoutError (#63892) · superseded by another PR → #67183, #63892
Closed issues · 1
  • Closed#63892gateway OOM: MCP poll loop mistakes a completed future's real TimeoutError for a poll timeout (Py>=3.8 alias) and spins, leaking ~108MB/s of traceback
How this cluster was grouped
  • Link evidence (structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
  • Pairwise link density 0.33: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. 1.00 means every pair is linked.

Pick up a Lab task

Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.

Open the Lab

At a glance

Subsystem
mcp
Merged PRs
#67183
Closed issues
1
Attempts
4 PRs closed without merging
Fix link checked
18 Jul 2026

For your agent

The same facts, typed.

cluster/63892.json
cluster/63892.md