Skip to content

fix(responses): guard against null item/text in stream accumulator and output_text #3628

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Xsidz wants to merge 2 commits into
base: main
Choose a base branch
from
+7 −4
Open

fix(responses): guard against null item/text in stream accumulator and output_text #3628

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b9961b6
fix(responses): guard against null item/text in stream accumulator an…
Xsidz Aug 16, 2026
fe0ebbe
fix(types): make ResponseOutputItemAddedEvent.item Optional to match …
Xsidz Aug 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion src/openai/lib/streaming/responses/_responses.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -328,7 +328,9 @@ def accumulate_event(self, event: RawResponseStreamEvent) -> ParsedResponseSnaps
return self._create_initial_response(event)

if event.type == "response.output_item.added":
if event.item.type == "function_call":
if event.item is None:
pass
Comment on lines +331 to +332

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 16, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Preserve output indexes when an item is null

When a compatible provider emits a null item and then continues with another output item, this pass leaves snapshot.output one element shorter than the server's output indexes. Subsequent response.content_part.added, text-delta, or function-call-delta events index this list using event.output_index, so they can raise IndexError or update the wrong item. Preserve the missing slot's index or track and ignore dependent events by server index rather than shifting later outputs.

Useful? React with 👍 / 👎.

elif event.item.type == "function_call":
snapshot.output.append(
construct_type_unchecked(
type_=cast(Any, ParsedResponseFunctionToolCall), value=event.item.to_dict()
Expand Down
2 changes: 1 addition & 1 deletion src/openai/types/beta/beta_response_output_item_added_event.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ class Agent(BaseModel):
class BetaResponseOutputItemAddedEvent(BaseModel):
"""Emitted when a new output item is added."""

item: BetaResponseOutputItem
item: Optional[BetaResponseOutputItem] = None
"""The output item that was added.

For reasoning items, `encrypted_content` may be incomplete while the item is in
Expand Down
2 changes: 1 addition & 1 deletion src/openai/types/responses/response.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -486,7 +486,7 @@ def output_text(self) -> str:
for output in self.output:
if output.type == "message":
for content in output.content:
if content.type == "output_text":
if content.type == "output_text" and content.text is not None:
texts.append(content.text)
Comment on lines +489 to 490

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 16, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Guard null text before structured parsing

For callers using responses.parse(..., text_format=...) or responses.stream(..., text_format=...), parse_response() processes the response before this property can be used and still calls parse_text(item.text, ...) unconditionally. The same output_text block with text: null therefore passes None to Pydantic's JSON parser and raises, so the affected response remains unusable in structured-output paths; skip parsing or normalize null text in parse_response() as well.

Useful? React with 👍 / 👎.


return "".join(texts)
3 changes: 2 additions & 1 deletion src/openai/types/responses/response_output_item_added_event.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
# File generated from our OpenAPI spec by Castiron. See CONTRIBUTING.md for details.

from typing import Optional
from typing_extensions import Literal

from ..._models import BaseModel
Expand All @@ -11,7 +12,7 @@
class ResponseOutputItemAddedEvent(BaseModel):
"""Emitted when a new output item is added."""

item: ResponseOutputItem
item: Optional[ResponseOutputItem] = None
"""The output item that was added.

For reasoning items, `encrypted_content` may be incomplete while the item is in
Expand Down