# NousResearch/hermes-agent · Ollama Cloud GLM truncation false-positive and partial propagation

## Open now

- Nothing open on GitHub.

A bug where \`_should_treat_stop_as_truncated\` incorrectly flags Ollama Cloud GLM responses as truncated, along with a related issue where \`partial\` status is not propagated through SSE session streams. The members include the bug report and associated fix attempts.

## TL;DR

- 4 member(s): 0 open issue(s), 1 closed issue(s), 0 open PR(s), 1 merged PR(s), 2 PR(s) closed without merging.
- A fix was merged to main in PR #100924. Verify it addresses your case.
- **Recommended:** read PR #100924 (and any competing PRs below) before filing. Confirm the merged change covers your symptom.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `resolved` · deciding PR(s): `pr-100924`. 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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 `0.50`: 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

- #72316: \[Bug\]: \`_should_treat_stop_as_truncated\` false-positives on Ollama Cloud GLM + SSE session stream doesn't propagate \`partial\` status

## Prior & competing PRs

- **#100924: fix(agent): GLM on Ollama Cloud no longer falsely truncated (#72316, #98406)**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`
  - files: `gateway/platforms/api_server.py`, `run_agent.py`, `tests/run_agent/test_run_agent.py`
- **#72332: fix: exclude Ollama Cloud from stop->length false-positive and propagate partial SSE status (#72316)**. closed without merge
  - maintainer direction: category `partial_fix`; implication `needs_llm`; refs `#73223`, `#13971`
- **#73223: fix(gateway): exclude Ollama Cloud from GLM truncation detection; propagate partial flag (#72316)**. closed without merge
  - maintainer direction: category `partial_fix`; implication `needs_llm`; refs `5360886f54b`

## Fix status

- Merged to main in PR #100924 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-09-02`.
- Subsystem: `agent`