Cairn
NousResearch/hermes-agent

Fix latency estimates for local model recommendations

Cluster 109606 · hermes cli. 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 address a bug where local model speed recommendations ignored prompt prefill time, which accounts for the majority of wall-clock time per agent turn. Fixes aim to stop recommending models with misleadingly slow real-world performance.

Open issues1

  • Issue#109606[Bug]: Local Models speed gate models decode only — the prompt prefill it omits is 87-93% of an agent turn's wall clock

Open PRs1

  • PR#109630fix(local-runtime): stop recommending models with multi-minute prompt waits

1 PR closed without merging

From the close comments: other 1

  • #109618 fix(local-runtime): price recommendations by turn latency · other → 2cbf4bf, 3569e84, #109606, #109618
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
hermes cli
Closed issues
0
Attempts
1 PR closed without merging

For your agent

The same facts, typed.

cluster/109606.json
cluster/109606.md