Cairn
NousResearch/hermes-agent

Copilot model routing lost after gateway restart

Cluster 113701 · gateway. Data as of

1 open item. Fix attempted, not merged.

The short answer

0open issues
1open PR
3items grouped
Known?
Yes. 3 related items grouped here, 1 issue 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
0 issues and 1 PR.

A bug where Copilot model routing configuration is not preserved across gateway restarts, causing requests to be sent to the wrong API endpoint and silently falling back to a different model. The accompanying fixes address rehydration of model overrides and routing resolution on restart.

Open issues0

No open issues.

Open PRs1

  • PR#70184fix: pass target_model to resolve_runtime_provider in model override rehydration

1 PR closed without merging

From the close comments: other 1

  • #113709 fix(gateway): preserve Copilot model routing on restart · other → 931b5ff
Closed issues · 1
  • Closed#113701[Bug]: After a gateway restart, a chat-completions-only Copilot model (gemini-3.8-flash) is sent to the Responses API and fails with HTTP 400, then silently falls back to a different model
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
gateway
Closed issues
1
Attempts
1 PR closed without merging

For your agent

The same facts, typed.

cluster/113701.json
cluster/113701.md