NousResearch/hermes-agent
GLM-5 reasoning model stale-timeout floor fix
Cluster 89241 · agent. 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.
Next step: read the attempts below. Your case may extend or revive that work.
Pick up a Lab taskThese issues and PRs concern a stale-detection timeout that was too short (90s) for GLM-5 and GLM-4.6 reasoning models, which always think and thus require longer floors (300s). The members describe the problem and proposed fixes to raise the timeout threshold.
Open issues1
- Issue#89241GLM-5 reasoning models killed by 90s non-stream stale detector (GLM-5.3 always thinks; Coding endpoint reroutes glm-5.2 to 5.3)
Open PRs1
- PR#90024fix(timeouts): add GLM-5 family to reasoning stale-timeout floor (#89241)
2 PRs closed without merging
From the close comments: closed without comment 1 · other 1
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structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 0.36.1.00means 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 LabAt a glance
- Subsystem
- agent
- Closed issues
- 0
- Attempts
- 2 PRs closed without merging