NousResearch/hermes-agent

openai-codex provider empty response.output reports

Cluster 5674 · agent. Data as of

Nothing open on GitHub. Fix attempted, not merged.

The short answer

0open issues
0open PRs
7items grouped
Known?
Yes. 7 related items grouped here, 6 issues already closed.
Fix event
No fix has been merged to main. 1 PR closed without merging; see the attempts below.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
Nothing open on GitHub.

Most members describe the openai-codex provider (notably with gpt-5.x models) returning an empty or malformed response.output, or a 'no output items' error, even when streamed text or tool-call events were delivered. One member is a code change proposing to use the terminal event response when the final response has empty output; the exact cause is not established across members.

Open issues0

No open issues.

Open PRs0

No open pull requests.

1 PR closed without merging

From the close comments: duplicate 1

  • #6026 fix(codex): use terminal event response when get_final_response has empty output · duplicate → #5720
Closed issues · 6
  • Closed#5674[Bug]: codex suddenly reporting "emtpy/malformed response"
  • Closed#5678[Bug]: openai-codex provider fails with 'Responses API returned no output items' when output[] is empty but streaming delivered text (gpt-5.4)
  • Closed#5732[Bug]: Codex Responses stream completes with empty output after tool-call events, forcing fallback
  • Closed#5736[Bug] openai-codex provider returns empty response.output from agent loop on multiple gpt-5.x models (works in isolated direct call)
  • Closed#5879openai-codex provider always returns response.output is empty — DEFAULT_CODEX_BASE_URL endpoint broken
  • Closed#5883GPT-5.4 via openai-codex fails in normal mode with 'Empty/malformed response' fallback
How this cluster was grouped
  • Link evidence (partly structural links): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.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 0.20: 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
Closed issues
6
Attempts
1 PR closed without merging

For your agent

The same facts, typed.