NousResearch/hermes-agent

MCP stdio transport fail-fast on session/process death

Cluster 81995 · mcp. Data as of

Nothing open on GitHub. Fix attempted, not merged.

The short answer

0open issues
0open PRs
3items grouped
Known?
Yes. 3 related items grouped here, 1 issue already closed.
Fix event
No fix has been merged to main. 2 PRs closed without merging; see the attempts below.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
Nothing open on GitHub.

These items address a bug where in-flight MCP tool calls remain attached to a dead stdio subprocess or restarted transport session until a full timeout expires, rather than failing immediately. The fixes introduce fail-fast behavior when the subprocess dies or the transport session restarts.

Open issues0

No open issues.

Open PRs0

No open pull requests.

2 PRs closed without merging

From the close comments: duplicate 1 · superseded by another PR 1

  • #82071 fix(mcp): fail RPCs when transport sessions restart · duplicate → #48069
  • #82219 fix(mcp): fail-fast in-flight tool calls when stdio subprocess dies (#81995) · superseded by another PR → #48069, #81995, #82071
Closed issues · 1
  • Closed#81995[Bug]: Stalled stdio MCP cold-spawn leaves in-flight tool call attached to dead subprocess for full 300s timeout — no fail-fast on supervisor respawn
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 0.67: 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
Closed issues
1
Attempts
2 PRs closed without merging

For your agent

The same facts, typed.