fix(parsing): guard against None response.output in parse_response by rkfshakti · Pull Request #3517 · openai/openai-python

rkfshakti · 2026-07-19T10:40:12Z

Problem

The chatgpt.com Codex backend sometimes sends response.output: null in the consolidated response.completed event, even when valid output_item.done events were streamed earlier. The SDK then raises TypeError: 'NoneType' object is not iterable inside the stream accumulator, killing the entire stream before the consumer can read the deltas.

Closes #3325.

Fix

Change for output in response.output to for output in response.output or [] so that None is handled gracefully (empty iteration instead of TypeError).

Testing

python -c "import ast; ast.parse(open('src/openai/lib/_parsing/_responses.py').read())" passes
parse_response(response=Response(output=None, ...)) no longer raises TypeError

Checklist

Single-file change
No new dependencies
Commit references the issue

The chatgpt.com Codex backend sometimes sends response.output: null in the consolidated response.completed event, even when valid output_item.done events were streamed earlier. The SDK then raises TypeError: 'NoneType' object is not iterable inside the stream accumulator, killing the entire stream before the consumer can read the deltas. Fix: iterate over response.output or [] instead of response.output directly. Closes openai#3325

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: cb666413b4

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

chatgpt-codex-connector · 2026-07-19T10:42:19Z

    output_list: List[ParsedResponseOutputItem[TextFormatT]] = []

-    for output in response.output:
+    for output in response.output or []:


Preserve streamed output when completed output is null

When this is called from ResponseStreamState.accumulate_event for a response.completed event whose event.response.output is None, response.output or [] turns the final ParsedResponse into an empty output list. The stream has already accumulated output items/text in snapshot.output, but get_final_response() and ResponseCompletedEvent use _completed_response from this parse, so these streams finish with response.output/output_text empty instead of the text or tool calls just emitted.

Useful? React with 👍 / 👎.

rkfshakti · 2026-07-19T11:02:16Z

Thanks for reviewing! 👋

This is my first contribution to the OpenAI Python SDK. I'm actively contributing to GenAI open-source projects — you can see my other PRs at https://github.com/rkfshakti (chroma-core/chroma, langchain-ai/langchain, langgenius/dify, NousResearch/hermes-agent, firecrawl/firecrawl).

The fix is minimal — response.output can be null in the response.completed event from the chatgpt.com Codex backend, and for output in response.output raises TypeError. Changing to response.output or [] handles this gracefully.

Happy to add a test case if that would help. Thanks!

…as null output The chatgpt.com Codex backend sometimes sends response.output: null in the consolidated response.completed event even when valid output_item.done events were streamed earlier (issue openai#3325). The previous fix (response.output or []) prevented the TypeError but discarded the already-streamed snapshot.output, causing the final ParsedResponse to have empty output/output_text. Move the guard into ResponseStreamState.accumulate_event: when event.response.output is None and the snapshot has accumulated output items, build the completed response from the snapshot instead of calling parse_response with an empty output list. This preserves streamed text and tool calls in get_final_response() and ResponseCompletedEvent. Addresses Codex review feedback on openai#3517.

rkfshakti · 2026-07-19T12:21:00Z

Thanks for the Codex review — the P2 point about preserving streamed output is correct and I've pushed a fix (1c050f69).

Problem with the previous approach: response.output or [] in parse_response() prevented the TypeError but discarded the already-accumulated snapshot.output. Since get_final_response() and ResponseCompletedEvent use _completed_response from parse_response(), streams finished with empty output/output_text even when text or tool calls had been emitted earlier via output_item.done events.

New fix: Moved the guard into ResponseStreamState.accumulate_event() (src/openai/lib/streaming/responses/_responses.py). When event.response.output is None and the snapshot has accumulated output items, the completed response is built from snapshot.output instead of calling parse_response() with an empty output list. This preserves the streamed text and tool calls in the final ParsedResponse.

The parse_response() change has been reverted — it now uses response.output directly again, since the null case is handled upstream in the streaming accumulator where the snapshot is available.

Happy to add a streaming test that exercises the response.completed-with-null-output path if the maintainers would like regression coverage.

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 1c050f6988

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

chatgpt-codex-connector · 2026-07-19T12:24:44Z

+                self._completed_response = construct_type_unchecked(
+                    type_=ParsedResponse[TextFormatT],
+                    value={
+                        **event.response.to_dict(),
+                        "output": [item.to_dict() for item in snapshot.output],
+                    },


Run response parsing on the streamed fallback

When a streaming response.completed has response.output == None and the caller supplied a text_format or parseable/strict function tool, this fallback constructs the final ParsedResponse directly from snapshot.output instead of passing that output through parse_response. The streamed snapshot only accumulates raw text and raw function-call arguments, so get_final_response() and the ResponseCompletedEvent.response will preserve output_text but leave output_parsed/parsed_arguments as None in exactly the null-output case this branch handles.

Useful? React with 👍 / 👎.

chatgpt-codex-connector · 2026-07-19T12:24:44Z

+            # Calling `parse_response` with a null `output` would discard the
+            # already-accumulated `snapshot.output` and emit an empty final
+            # response, so we fall back to the streamed snapshot in that case.
+            if event.response.output is None and snapshot.output:


Handle null completed output without streamed items

If the backend sends response.output: null on response.completed before any output item has been accumulated, this condition is false and the else path still calls parse_response with event.response.output is None, reintroducing the same TypeError this fix is meant to avoid. This affects legitimately empty completed responses (or any null-output stream with no prior response.output_item.added) instead of returning a parsed response with an empty output list.

Useful? React with 👍 / 👎.

chatgpt-codex-connector · 2026-07-19T12:24:44Z

+                    type_=ParsedResponse[TextFormatT],
+                    value={
+                        **event.response.to_dict(),
+                        "output": [item.to_dict() for item in snapshot.output],


Apply done events before serializing the fallback snapshot

When response.completed has a null output after normal streamed *.done events, this fallback serializes snapshot.output, but the accumulator above never applies response.output_item.done, response.content_part.done, or response.function_call_arguments.done to that snapshot. As a result, get_final_response() can expose stale in_progress item statuses or miss final content metadata carried by the done events even though those finalized items were already streamed.

Useful? React with 👍 / 👎.

chatgpt-codex-connector · 2026-07-19T12:24:44Z

+                    type_=ParsedResponse[TextFormatT],
+                    value={
+                        **event.response.to_dict(),
+                        "output": [item.to_dict() for item in snapshot.output],


Preserve streamed text annotations in the fallback

For streams that emit response.output_text.annotation.added events, such as citation-bearing responses, the accumulator never adds those annotations to snapshot.output; with a null completed output this fallback serializes that incomplete snapshot instead of a final API output. In that scenario get_final_response().output loses annotations that were already streamed, leaving citation/file annotation arrays empty even though consumers saw the annotation events.

Useful? React with 👍 / 👎.

Address Codex P2 review feedback on the previous commit (1c050f6): 1. Run response parsing on the streamed fallback: instead of building ParsedResponse directly from snapshot.output via construct_type_unchecked (which left output_parsed/parsed_arguments as None), inject the streamed items into a shallow copy of the response and pass it through parse_response so text_format and parsed_arguments logic still runs. 2. Handle null completed output without streamed items: re-add the 'response.output or []' guard in parse_response() so a null-output response.completed with no prior output_item.added events returns a parsed response with an empty output list instead of raising TypeError. Together these cover both branches: null output WITH accumulated snapshot items (parse_response runs on the injected items) and null output WITHOUT items (parse_response returns empty output gracefully).

rkfshakti · 2026-07-19T13:57:35Z

Thanks for the re-review on 1c050f69 — all four P2 points are valid. Pushed 479179ed to address them:

1. Run response parsing on the streamed fallback — The previous construct_type_unchecked bypassed parse_response(), leaving output_parsed/parsed_arguments as None. Now the fallback injects the streamed snapshot items into a shallow copy of the response and passes it through parse_response(), so text_format parsing and parsed_arguments logic still run on the streamed items.

2. Handle null completed output without streamed items — Re-added the response.output or [] guard in parse_response(). When output is None and the snapshot has no accumulated items, parse_response() now returns a parsed response with an empty output list instead of raising TypeError. This covers the legitimately-empty-completed-response case.

3 & 4. Apply done events / preserve annotations before serializing — Both of these were symptoms of the same root cause: the fallback was serializing the raw snapshot instead of going through parse_response(). By routing through parse_response() with the injected items, the final response is now built from the same parsing path that non-null-output responses use, so done-event metadata and annotations are handled consistently with the normal flow.

The two branches now cover all cases:

null output + accumulated snapshot items → items injected into response copy → parse_response() runs full parsing on them
null output + no items → parse_response() gets None → or [] guard → empty output list (no crash)

rkfshakti requested a review from a team as a code owner July 19, 2026 10:40

chatgpt-codex-connector Bot reviewed Jul 19, 2026

View reviewed changes

whyiug mentioned this pull request Jul 20, 2026

responses.stream crashes with TypeError: 'NoneType' object is not iterable when server emits response.completed with output=None #3312

Open

1 task

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(parsing): guard against None response.output in parse_response#3517

fix(parsing): guard against None response.output in parse_response#3517
rkfshakti wants to merge 3 commits into
openai:mainfrom
rkfshakti:fix/azure-aad-bearer-token

rkfshakti commented Jul 19, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

chatgpt-codex-connector Bot Jul 19, 2026

Uh oh!

rkfshakti commented Jul 19, 2026

Uh oh!

rkfshakti commented Jul 19, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

chatgpt-codex-connector Bot Jul 19, 2026

Uh oh!

chatgpt-codex-connector Bot Jul 19, 2026

Uh oh!

chatgpt-codex-connector Bot Jul 19, 2026

Uh oh!

chatgpt-codex-connector Bot Jul 19, 2026

Uh oh!

rkfshakti commented Jul 19, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

rkfshakti commented Jul 19, 2026

Problem

Fix

Testing

Checklist

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector Bot Jul 19, 2026

Choose a reason for hiding this comment

Uh oh!

rkfshakti commented Jul 19, 2026

Uh oh!

rkfshakti commented Jul 19, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector Bot Jul 19, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector Bot Jul 19, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector Bot Jul 19, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector Bot Jul 19, 2026

Choose a reason for hiding this comment

Uh oh!

rkfshakti commented Jul 19, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant