# NousResearch/hermes-agent · GLM-5.3 medium effort mapping for China endpoint

## Open now

- 1 issue, 1 PR open on GitHub.
- #96222: \[Bug\]: GLM-5.3 medium reasoning_effort rejected by China endpoint (open.bigmodel.cn), silent fallback every turn
- PR #96228: fix(zai): GLM-5.3 on the China endpoint accepts low/high/max only

These items address a bug where the China endpoint (open.bigmodel.cn) only accepts low/high/max reasoning effort values, rejecting 'medium' and causing silent fallback. The fix maps medium effort to high for bigmodel.cn compatibility.

## TL;DR

- 2 member(s): 1 open issue(s), 0 closed issue(s), 1 open PR(s), 0 merged PR(s), 0 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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 `0.67`: 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.

## Open related issues

- #96222: \[Bug\]: GLM-5.3 medium reasoning_effort rejected by China endpoint (open.bigmodel.cn), silent fallback every turn

## Prior & competing PRs

- **#96226: fix(providers/zai): map GLM-5.3 medium effort to high for bigmodel.cn compatibility (#96222)**. closed without merge
  - maintainer direction: category `silent_close`; implication `active`
  - files: `agent/reasoning_effort.py`, `tests/plugins/model_providers/test_zai_profile.py`
- **#96228: fix(zai): GLM-5.3 on the China endpoint accepts low/high/max only**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `#91789`
  - files: `agent/reasoning_effort.py`, `plugins/model-providers/zai/__init__.py`, `tests/plugins/model_providers/test_zai_profile.py`

## Fix status

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