# NousResearch/hermes-agent · Clamp reasoning effort for non-gpt-5.6 providers

## Open now

- Nothing open on GitHub.

These issues and fixes address a crash caused by unsupported 'ultra' or 'max' reasoning effort values being sent to non-gpt-5.6 model providers, returning HTTP 422 errors. The proposed fix clamps those values down to 'high' for incompatible providers.

## 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 #90330. Verify it addresses your case.
- **Recommended:** read PR #90330 (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: `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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 `0.50`: 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

- #80242: Custom providers crash with /reasoning ultra (HTTP 422: unknown variant)

## Prior & competing PRs

- **#90330: fix: reasoning effort 'ultra' no longer 400s on non-Anthropic wires (#89503 class, salvage #89509)**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`
  - files: `agent/auxiliary_client.py`, `agent/transports/chat_completions.py`, `agent/transports/codex.py`, `plugins/model-providers/copilot/__init__.py`, `plugins/model-providers/custom/__init__.py`, `tests/agent/test_reasoning_effort_wire_translation.py`, `tests/agent/transports/test_reasoning_effort_sibling_sites.py`
- **#80291: fix(agent): clamp reasoning effort ultra/max to high for non-gpt-5.6 providers**. closed without merge
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `#90330`
- **#80435: fix: clamp reasoning_effort ultra/max to high for non-gpt-5.6 models**. closed without merge
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `#80291`, `#80242`

## Fix status

- Merged to main in PR #90330 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-08-19`.
- Subsystem: `agent`