# NousResearch/hermes-agent · Prevent reasoning_effort sent to unsupported models

## Open now

- 1 issue, 2 PRs open on GitHub.
- #59660: Bug: CustomProfile (Ollama fallback) forwards reasoning_effort to non-reasoning models, causing HTTP 400 'does not support thinking'
- PR #81574: fix(ollama): clamp reasoning for non-thinking local models
- PR #95854: fix(ollama): omit reasoning_effort for local models without thinking

These issues and fixes address a bug where reasoning_effort parameters are incorrectly forwarded to models that do not support thinking/reasoning, causing HTTP 400 errors. The work involves gating or clamping reasoning settings to only known reasoning-capable models.

## TL;DR

- 4 member(s): 1 open issue(s), 0 closed issue(s), 2 open PR(s), 0 merged PR(s), 1 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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 `0.50`: 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.

## Open related issues

- #59660: Bug: CustomProfile (Ollama fallback) forwards reasoning_effort to non-reasoning models, causing HTTP 400 'does not support thinking'

## Prior & competing PRs

- **#59678: fix(custom-profile): gate reasoning_effort on known reasoning-capable models (#59660)**. closed without merge
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `#59678`
- **#81574: fix(ollama): clamp reasoning for non-thinking local models**. open
  - maintainer direction: category `silent_close`; implication `active`
  - files: `plugins/model-providers/custom/__init__.py`, `run_agent.py`, `tests/plugins/model_providers/test_custom_profile.py`, `tests/run_agent/test_run_agent.py`
- **#95854: fix(ollama): omit reasoning_effort for local models without thinking**. open
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#86197`, `#63315`, `#81574`, `#59660`
  - files: `plugins/model-providers/custom/__init__.py`, `run_agent.py`, `tests/agent/transports/test_chat_completions.py`, `tests/plugins/model_providers/test_custom_profile.py`, `tests/run_agent/test_run_agent.py`

## Fix status

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