NousResearch/hermes-agent

MCP OAuth mtime=0 causes spurious re-init loop

Cluster 77369 · mcp. Data as of

2 open items. Fix attempted, not merged.

The short answer

1open issue
1open PR
4items grouped
Known?
Yes. 4 related items grouped here, 0 issues 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
1 issue and 1 PR.

A zero value for last_mtime_ns is incorrectly treated as an external refresh rather than a first observation, triggering repeated re-initialization of remote MCP servers. The fix seeds the mtime baseline on first read to prevent this spurious invalidation.

Open issues1

  • Issue#77369MCP OAuth: a never-read mtime (0) is treated as an external refresh, forcing a re-init loop that eventually parks remote servers

Open PRs1

  • PR#78176fix(mcp): seed OAuth mtime baseline on first read to prevent spurious invalidation (#77369)

2 PRs closed without merging

From the close comments: duplicate 1 · superseded by another PR 1

  • #77415 fix(mcp): treat mtime=0 as first observation, not external refresh (#77369) · duplicate → #39569
  • #78272 fix(mcp): treat last_mtime_ns=0 as first observation, not external refresh (#77369) · superseded by another PR → #39569
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 0.50: 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
0
Attempts
2 PRs closed without merging

For your agent

The same facts, typed.