fix(codex): recover stream output after SDK null output

[liran29]

Summary

• recover Codex Responses streams when the OpenAI SDK crashes on response.completed.output = null
• reuse already-collected response.output_item.done items or streamed text deltas instead of failing the turn
• add a regression test for the SDK TypeError path

Root Cause

The ChatGPT Codex backend can stream valid output items and then emit a terminal response.completed event whose response.output is null. OpenAI SDK 2.24 raises TypeError("'NoneType' object is not iterable") while parsing that terminal event, before Hermes reaches the existing empty-output recovery path.

Test

• venv/bin/python -m pytest tests/run_agent/test_run_agent_codex_responses.py -q

[alt-glitch]

Duplicate of merged #32963 — same Codex null-output stream recovery (TypeError guard on response.completed.output = null). Fix already on main.

[teknium1]

Thanks for this — closing as already fixed on main.

The Codex null-output crash (response.completed with output: null from the chatgpt.com backend → TypeError: 'NoneType' object is not iterable → surfaced as "non-retryable HTTP None") is resolved by commits already on main:

• cb38ce28c — drop the SDK responses.stream() helper and consume events directly, rebuilding output from response.output_item.done events so the null terminal-event output is never iterated (refactor(codex): drop SDK responses.stream() helper; consume events directly #33042).
• 43a3f119f — recover Codex streams with null output.
• dc9d677d5 — classify TypeError('NoneType … not iterable') as a retryable provider-shape error so retry/fallback runs instead of killing the turn.

Your fix targets the same path that's now hardened upstream, so there's nothing left to merge here. Your authorship is preserved in your branch; I'm crediting your report in the umbrella issue #33932 (now closed). Appreciate the contribution.