Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion .release-please-manifest.json
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
{
".": "2.24.0"
".": "2.25.0"
}
4 changes: 2 additions & 2 deletions .stats.yml
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
configured_endpoints: 148
openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-6bfe886b5ded0fe3bf37ca672698814e16e0836a093ceef65dac37ae44d1ad6b.yml
openapi_spec_hash: 6b1344a59044318e824c8d1af96033c7
openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-4432c056f89389d4d43b695cbdf44f97df8169f63bbae2c15fc079a5766ced6e.yml
openapi_spec_hash: cbf649cc2c944fb3f77450ec752ab1e9
config_hash: 7f49c38fa3abe9b7038ffe62262c4912
14 changes: 14 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,19 @@
# Changelog

## 2.25.0 (2026-02-27)

Full Changelog: [v2.24.0...v2.25.0](https://github.com/openai/openai-python/compare/v2.24.0...v2.25.0)

### Features

* **api:** remove prompt_cache_key param from responses, phase field from message types ([44fb382](https://github.com/openai/openai-python/commit/44fb382698872d98d5f72c880b47846c7b594f4f))


### Bug Fixes

* **api:** manual updates ([9fc323f](https://github.com/openai/openai-python/commit/9fc323f4da6cfca9de194e12c1486a3cd1bfa4b5))
* **api:** readd phase ([1b27b5a](https://github.com/openai/openai-python/commit/1b27b5a834f5cb75f80c597259d0df0352ba83bd))

## 2.24.0 (2026-02-24)

Full Changelog: [v2.23.0...v2.24.0](https://github.com/openai/openai-python/compare/v2.23.0...v2.24.0)
Expand Down
2 changes: 1 addition & 1 deletion pyproject.toml
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
[project]
name = "openai"
version = "2.24.0"
version = "2.25.0"
description = "The official Python library for the openai API"
dynamic = ["readme"]
license = "Apache-2.0"
Expand Down
2 changes: 1 addition & 1 deletion src/openai/_version.py
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.

__title__ = "openai"
__version__ = "2.24.0" # x-release-please-version
__version__ = "2.25.0" # x-release-please-version
8 changes: 6 additions & 2 deletions src/openai/types/responses/easy_input_message.py
Original file line number Diff line number Diff line change
Expand Up @@ -30,8 +30,12 @@ class EasyInputMessage(BaseModel):
One of `user`, `assistant`, `system`, or `developer`.
"""

phase: Optional[Literal["commentary", "final_answer"]] = None
"""The phase of an assistant message.
phase: Optional[Literal["commentary"]] = None
"""
Labels an `assistant` message as intermediate commentary (`commentary`) or the
final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when
sending follow-up requests, preserve and resend phase on all assistant messages
— dropping it can degrade performance. Not used for user messages.

Use `commentary` for an intermediate assistant message and `final_answer` for
the final assistant message. For follow-up requests with models like
Expand Down
8 changes: 6 additions & 2 deletions src/openai/types/responses/easy_input_message_param.py
Original file line number Diff line number Diff line change
Expand Up @@ -31,8 +31,12 @@ class EasyInputMessageParam(TypedDict, total=False):
One of `user`, `assistant`, `system`, or `developer`.
"""

phase: Optional[Literal["commentary", "final_answer"]]
"""The phase of an assistant message.
phase: Optional[Literal["commentary"]]
"""
Labels an `assistant` message as intermediate commentary (`commentary`) or the
final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when
sending follow-up requests, preserve and resend phase on all assistant messages
— dropping it can degrade performance. Not used for user messages.

Use `commentary` for an intermediate assistant message and `final_answer` for
the final assistant message. For follow-up requests with models like
Expand Down
8 changes: 6 additions & 2 deletions src/openai/types/responses/response_output_message.py
Original file line number Diff line number Diff line change
Expand Up @@ -35,8 +35,12 @@ class ResponseOutputMessage(BaseModel):
type: Literal["message"]
"""The type of the output message. Always `message`."""

phase: Optional[Literal["commentary", "final_answer"]] = None
"""The phase of an assistant message.
phase: Optional[Literal["commentary"]] = None
"""
Labels an `assistant` message as intermediate commentary (`commentary`) or the
final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when
sending follow-up requests, preserve and resend phase on all assistant messages
— dropping it can degrade performance. Not used for user messages.

Use `commentary` for an intermediate assistant message and `final_answer` for
the final assistant message. For follow-up requests with models like
Expand Down
8 changes: 6 additions & 2 deletions src/openai/types/responses/response_output_message_param.py
Original file line number Diff line number Diff line change
Expand Up @@ -35,8 +35,12 @@ class ResponseOutputMessageParam(TypedDict, total=False):
type: Required[Literal["message"]]
"""The type of the output message. Always `message`."""

phase: Optional[Literal["commentary", "final_answer"]]
"""The phase of an assistant message.
phase: Optional[Literal["commentary"]]
"""
Labels an `assistant` message as intermediate commentary (`commentary`) or the
final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when
sending follow-up requests, preserve and resend phase on all assistant messages
— dropping it can degrade performance. Not used for user messages.

Use `commentary` for an intermediate assistant message and `final_answer` for
the final assistant message. For follow-up requests with models like
Expand Down