You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
# Some parameter documentations has been truncated, see
52
41
# {OpenAI::Models::Responses::ResponseOutputMessage} for more details.
53
42
#
@@ -59,8 +48,6 @@ class ResponseOutputMessage < OpenAI::Internal::Type::BaseModel
59
48
#
60
49
# @param status [Symbol, OpenAI::Models::Responses::ResponseOutputMessage::Status] The status of the message input. One of `in_progress`, `completed`, or
61
50
#
62
-
# @param phase [Symbol, OpenAI::Models::Responses::ResponseOutputMessage::Phase, nil] The phase of an assistant message.
63
-
#
64
51
# @param role [Symbol, :assistant] The role of the output message. Always `assistant`.
65
52
#
66
53
# @param type [Symbol, :message] The type of the output message. Always `message`.
@@ -95,24 +82,6 @@ module Status
95
82
# @!method self.values
96
83
# @return [Array<Symbol>]
97
84
end
98
-
99
-
# The phase of an assistant message.
100
-
#
101
-
# Use `commentary` for an intermediate assistant message and `final_answer` for
102
-
# the final assistant message. For follow-up requests with models like
103
-
# `gpt-5.3-codex` and later, preserve and resend phase on all assistant messages.
104
-
# Omitting it can degrade performance. Not used for user messages.
# @param model [Symbol, String, OpenAI::Models::Responses::ResponseCompactParams::Model, nil] Model ID used to generate the response, like `gpt-5` or `o3`. OpenAI offers a wi
0 commit comments