Cairn
NousResearch/hermes-agent

Gate reasoning.effort to compatible models only

Cluster 76255 · agent. Data as of

Nothing open on GitHub. Fix merged in #115765 on 19 Sep 2026. Check it covers your case.

The short answer

0open issues
0open PRs
4items grouped
Known?
Yes. 4 related items grouped here, 1 issue already closed.
Fix event
A fix was merged to main in PR #115765. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this resolved, deciding PR #115765. That is separate from the fix event.
Still open
Nothing open on GitHub.

These items address a bug where the openai-api provider unconditionally sends reasoning.effort, breaking non-reasoning models like gpt-4o-mini and gpt-4.1-mini. The work involves centralizing model capability detection and conditionally applying reasoning parameters.

Open issues0

No open issues.

Open PRs0

No open pull requests.

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

  • #115765 fix(codex): reasoning_effort none is sent on OpenAI Responses, gpt-4o/4.1 no longer 400 on openai-api, ACP honors reasoning config (#75227, #76255, #85153, salvage #85164)

    merged to main

    files: acp_adapter/session.py, agent/auxiliary_client.py, agent/curator.py, agent/model_metadata.py, agent/transports/codex.py, contributors/emails/[redacted:email], gateway/slash_commands_session.py, plugins/platforms/feishu/feishu_comment.py, tests/acp_adapter/test_session_reasoning_config.py, tests/agent/test_auxiliary_client.py, tests/agent/test_curator.py, tests/agent/test_error_classifier.py, tests/agent/transports/test_codex_transport.py, tests/gateway/test_compress_command.py, tests/gateway/test_feishu_comment.py, website/docs/user-guide/configuration.md

2 PRs closed without merging

From the close comments: merged via another change 1 · superseded by another PR 1

  • #76299 fix(codex): centralize openai_model_supports_reasoning and gate auxiliary path · superseded by another PR
  • #76301 fix(openai-api): gate reasoning.effort for non-reasoning models (#76255) · merged via another change → 80009fb, #115765, #75227, #76255, #85153, #85164
Closed issues · 1
  • Closed#76255openai-api provider always sends reasoning.effort, breaks non-reasoning models (gpt-4o-mini, gpt-4.1-mini)
How this cluster was grouped
  • Link evidence (structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
  • Pairwise link density 0.50: the share of item 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.

Pick up a Lab task

Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.

Open the Lab

At a glance

Subsystem
agent
Merged PRs
#115765
Closed issues
1
Attempts
2 PRs closed without merging
Fix link checked
19 Sep 2026

For your agent

The same facts, typed.

cluster/76255.json
cluster/76255.md