Cairn
NousResearch/hermes-agent

MCP server reconnection and process tracking fixes, including cron sessions

Cluster 26042 · cron. Data as of

Nothing open on GitHub. Fix attempted, not merged.

The short answer

0open issues
0open PRs
5items grouped
Known?
Yes. 5 related items grouped here, 1 issue already closed.
Fix event
No fix has been merged to main. 4 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.

Most members concern MCP server lifecycle: lazily reconnecting or restarting when a session is stale or a transport errors, including an issue about ECONNREFUSED in cron jobs. Two others are about tracking descendant or grandchild processes of shell-wrapper MCP servers, which is a related but distinct theme.

Open issues0

No open issues.

Open PRs0

No open pull requests.

4 PRs closed without merging

From the close comments: superseded by another PR 2 · closed without comment 1 · done elsewhere 1

  • #26125 fix(mcp): lazy reconnect on dead session + transport errors for cron jobs · superseded by another PR → #23540
  • #26304 fix(mcp): lazy restart MCP server on tool call when session is stale (#26042) · superseded by another PR → #23540
  • #27516 fix(mcp): track grandchildren of shell-wrapper MCP servers · done elsewhere → a29d64e, #24003, #17692
  • #40110 fix(mcp): recursive descendant PID tracking for shell-wrapper MCP servers · closed without comment
Closed issues · 1
  • Closed#26042MCP servers unavailable in cron sessions — ECONNREFUSED when accessing MCP tools from scheduled jobs
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 0.40: 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
cron
Closed issues
1
Attempts
4 PRs closed without merging

For your agent

The same facts, typed.

cluster/26042.json
cluster/26042.md