Cairn
NousResearch/hermes-agent

Kanban respawn guard and stale rate-limit error text

Cluster 126190 · cron. Data as of

2 open items. Fix attempted, not merged.

The short answer

1open issue
1open PR
3items grouped
Known?
Yes. 3 related items grouped here, 0 issues already closed.
Fix event
No fix has been merged to main. 1 PR 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.

These items all concern the Kanban respawn guard and stale rate-limit text left in last_failure_error, which one bug report links to a task staying in ready after dependency promotion. The two fix-titled items appear to address this by using run outcomes instead of error prose and by clearing stale text when recompute_ready promotes a card.

Open issues1

  • Issue#126190[Bug]: Kanban task stuck in ready forever: stale rate-limit text in last_failure_error trips respawn guard blocker_auth after dependency promotion

Open PRs1

  • PR#126212fix(kanban): clear stale rate-limit text when recompute_ready promotes a card

1 PR closed without merging

From the close comments: stale or abandoned 1

  • #142737 fix(kanban): respawn guard decides from run outcomes, never from error prose · stale or abandoned
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
cron
Closed issues
0
Attempts
1 PR closed without merging

For your agent

The same facts, typed.

cluster/126190.json
cluster/126190.md