Skip to content

fix(codex): recover from null-output stream snapshots - #32924

Closed
PeterBerthelsen wants to merge 1 commit into
NousResearch:mainfrom
PeterBerthelsen:fix/codex-responses-null-output
Closed

fix(codex): recover from null-output stream snapshots#32924
PeterBerthelsen wants to merge 1 commit into
NousResearch:mainfrom
PeterBerthelsen:fix/codex-responses-null-output

Conversation

@PeterBerthelsen

Copy link
Copy Markdown

Summary

  • recover Codex Responses streams when the OpenAI SDK crashes parsing a terminal response snapshot with output=None
  • reuse collected response.output_item.done items or streamed text instead of failing over through every model
  • add a regression test for the SDK TypeError path

Validation

  • /home/peter/.hermes/hermes-agent/venv/bin/python -m pytest -o addopts="-m 'not integration'" tests/run_agent/test_run_agent_codex_responses.py::test_run_codex_stream_recovers_when_completed_snapshot_has_null_output tests/run_agent/test_run_agent_codex_responses.py::test_run_codex_stream_fallback_parses_create_stream_events -q
  • Real Hermes Codex one-shot returned OK locally after patch

@alt-glitch alt-glitch added type/bug Something isn't working P3 Low — cosmetic, nice to have comp/agent Core agent runtime: loop, agent_init, prompt builder, context-compression, responses endpoint provider/openai OpenAI / Codex Responses API codex duplicate This issue or pull request already exists labels May 27, 2026
@alt-glitch

Copy link
Copy Markdown
Collaborator

Duplicate of #32884 — same Codex Responses null output recovery. Root cause tracked in #11179.

@teknium1

Copy link
Copy Markdown
Contributor

Closing as duplicate — the Codex null-output fix has been merged via #32963 (cherry-picked from @carltonawong's PR #32890, the one Gille reviewed). Thanks for jumping on the outage so quickly; appreciate the help. Closes #11179.

@teknium1 teknium1 closed this May 27, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

codex comp/agent Core agent runtime: loop, agent_init, prompt builder, context-compression, responses endpoint duplicate This issue or pull request already exists P3 Low — cosmetic, nice to have provider/openai OpenAI / Codex Responses API type/bug Something isn't working

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants