Implementation:Openai Openai python Response Reasoning Text Done

Knowledge Sources	Openai_Openai_python OpenAI API Reference
Domains	API_Types, Responses_API
Last Updated	2026-02-15 00:00 GMT

Overview

Concrete type for representing an event emitted when a reasoning text content part is fully completed during streaming, provided by the openai-python SDK.

Description

ResponseReasoningTextDoneEvent is a Pydantic model representing the response.reasoning_text.done streaming event. It is emitted when the model has finished generating a reasoning content part. The event includes the complete text of the reasoning content, content_index identifying the part, item_id, output_index, and sequence_number.

Usage

Import this type when you need to capture the finalized reasoning text after all deltas have been streamed for a particular content part.

Code Reference

Source Location

• Repository: openai-python
• File: src/openai/types/responses/response_reasoning_text_done_event.py

Signature

class ResponseReasoningTextDoneEvent(BaseModel):
    """Emitted when a reasoning text is completed."""

    content_index: int
    item_id: str
    output_index: int
    sequence_number: int
    text: str
    type: Literal["response.reasoning_text.done"]

Import

from openai.types.responses import ResponseReasoningTextDoneEvent

I/O Contract

Fields

Name	Type	Required	Description
content_index	int	Yes	The index of the reasoning content part.
item_id	str	Yes	The ID of the item this reasoning text is associated with.
output_index	int	Yes	The index of the output item this reasoning text is associated with.
sequence_number	int	Yes	The sequence number of this event.
text	str	Yes	The full text of the completed reasoning content.
type	Literal["response.reasoning_text.done"]	Yes	The type of the event. Always response.reasoning_text.done.

Usage Examples

import openai

client = openai.OpenAI()

stream = client.responses.create(
    model="o3-mini",
    input="Prove that there are infinitely many prime numbers.",
    stream=True,
)

for event in stream:
    if event.type == "response.reasoning_text.done":
        print(f"Reasoning part [{event.content_index}] complete: {event.text[:100]}...")

Related Pages

• Environment:Openai_Openai_python_Python_3_9_Plus