Cairn
NousResearch/hermes-agent

ACP provider switch stale state and routing fixes

Cluster 63222 · acp. 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.

These issues and PRs address bugs where switching models or providers in ACP could preserve stale base URLs, routes, or runtime state, causing requests to be sent to incorrect endpoints. Several fixes target clearing or resetting provider-specific state on model switches, including routing reasoning models correctly.

Open issues1

  • Issue#63222[Bug]: ACP model switch can preserve stale provider base_url and route requests to the wrong endpoint

Open PRs1

  • PR#63242fix(acp): clear stale runtime on provider switch

2 PRs closed without merging

From the close comments: superseded by another PR 2

  • #63244 fix(acp): reset stale route on provider switch · superseded by another PR → #63242
  • #69977 fix(acp): discard stale route when provider is unknown · superseded by another PR → #63242
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
acp
Closed issues
0
Attempts
2 PRs closed without merging

For your agent

The same facts, typed.

cluster/63222.json
cluster/63222.md