# NousResearch/hermes-agent · Ollama/GLM stop-to-length heuristic false positive fixes

## Open now

- Nothing open on GitHub.

These issues and pull requests address false triggers in the stop-to-length continuation heuristic for Ollama and GLM backends, particularly when responses end with emoji, carets, or are short but complete. Multiple fixes aim to narrow when spurious continuation retries are initiated.

## TL;DR

- 5 member(s): 0 open issue(s), 1 closed issue(s), 0 open PR(s), 0 merged PR(s), 4 PR(s) closed without merging.
- No fix has been merged to main; one or more PRs were attempted (see below).
- **Recommended:** review the prior/competing PR(s) below. A fix was attempted but not merged; your case may extend or revive that work.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
- Pairwise link density `0.40`: the share of member 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.

## Closed / duplicate issues

- #14572: \[Bug\]: Ollama/GLM stop-to-length heuristic false-triggers on responses ending with emoji sign-offs

## Prior & competing PRs

- **#15363: fix(agent): recognize emoji as natural response endings in stop-to-length heuristic (#14572)**. closed without merge · fix tier `suggested`
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `#14574`, `#14572`
  - _suggested-tier fix detail withheld; re-request with `?tier=all` to include it._
- **#25991: fix(agent): prevent GLM stop-to-length heuristic false positives (#14572)**. closed without merge · fix tier `suggested`
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `#14574`
  - _suggested-tier fix detail withheld; re-request with `?tier=all` to include it._
- **#14574: fix(agent): accept emoji sign-offs as natural endings**. closed without merge
  - maintainer direction: category `implemented_elsewhere`; implication `superseded`; refs `#14572`
- **#15463: fix(agent): prevent GLM stop-to-length heuristic false positives (#14572)**. closed without merge
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#14574`, `#14572`, `#15363`

## Fix status

- No merged fix on record.
- Subsystem: `agent`