Cairn
NousResearch/hermes-agent

Output token limits causing empty responses on gateways

Cluster 108558. Data as of

Nothing open on GitHub. Fix attempted, not merged.

The short answer

0open issues
0open PRs
3items grouped
Known?
Yes. 3 related items grouped here, 1 issue 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
Nothing open on GitHub.

These items address a bug where reasoning models produce empty responses when hitting output token caps on OpenAI-compatible gateways, plus related fixes and a feature for context-aware output token defaults for custom providers.

Open issues0

No open issues.

Open PRs0

No open pull requests.

2 PRs closed without merging

From the close comments: superseded by another PR 1 · other 1

  • #108559 fix(agent): short-circuit empty-response ladder on proven output-cap starvation · superseded by another PR → #108558, #1, #2
  • #108574 feat(agent): context-aware output-token default for custom providers · other → #108558
Closed issues · 1
  • Closed#108558[Bug]: Reasoning models starve to empty responses on OpenAI-compatible gateways with internal output caps
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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

Closed issues
1
Attempts
2 PRs closed without merging

For your agent

The same facts, typed.

cluster/108558.json
cluster/108558.md