# NousResearch/hermes-agent · OpenAI non-reasoning models rejecting Responses reasoning/include parameters

## Open now

- 0 issues, 3 PRs open on GitHub.
- PR #23460: fix(transports/codex): remove unsupported include parameter for standard OpenAI Chat Completions API
- PR #23734: fix(agent): only upgrade to codex_responses for models that require it
- PR #24234: fix: only send reasoning.encrypted_content include for supported models

Members report HTTP 400 errors such as "Encrypted content is not supported with this model" when Hermes uses GPT-4o, GPT-4o-mini, or GPT-4.1. Related pull requests propose gating reasoning or \`include\` parameters, or choosing the API mode, based on model capability.

## TL;DR

- 9 member(s): 0 open issue(s), 3 closed issue(s), 3 open PR(s), 0 merged PR(s), 3 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evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.
- Members outside that structural core may belong to a different underlying problem.
- Pairwise link density `0.19`: 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

- #23450: \[Bug\]: \[Bug\]: Hermes v0.13.0 sends unsupported \`include\` parameter causing "Encrypted content is not supported with this model" error with OpenAI GPT-4o
- #46516: \[Bug\]: \[OpenAI API\] HTTP 400 for gpt-4.1 and gpt-4o-mini on Hermes 0.16.0 (Windows) while direct API calls work
- #52023: \[Bug\]: GPT-4o-mini and GPT-4.1 (and more) fail with "Encrypted content is not supported with this model" after clean install

## Prior & competing PRs

- **#23460: fix(transports/codex): remove unsupported include parameter for standard OpenAI Chat Completions API**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `b6ca56f651505d6a8ec2489f1048da3d2c07d12e`
  - files: `agent/transports/codex.py`, `gateway/platforms/whatsapp.py`, `tests/agent/transports/test_codex_transport.py`, `tests/tools/test_file_tools.py`, `tools/file_tools.py`
- **#23734: fix(agent): only upgrade to codex_responses for models that require it**. open
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#23460`, `#23450`
  - files: `run_agent.py`
- **#24234: fix: only send reasoning.encrypted_content include for supported models**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `agent/auxiliary_client.py`, `agent/model_metadata.py`, `agent/transports/codex.py`, `tests/agent/test_encrypted_content_support.py`
- **#46550: fix(agent): omit Responses reasoning param for non-reasoning OpenAI models**. closed without merge
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `#46516`
- **#47820: fix(openai): model-aware api_mode for direct api.openai.com (GPT-4.1/4o use Chat Completions)**. closed without merge
  - maintainer direction: category `implemented_elsewhere`; implication `superseded`; refs `77e2992020`, `#23450`, `#76255`, `#23460`, `#24234`, `#23734`
- **#52047: fix(codex): gate reasoning params on model capability (#52023)**. closed without merge
  - maintainer direction: category `silent_close`; implication `active`

## Fix status

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