Wire through parallel_tool_calls to Responses API

Signed-off-by: Anastas Stoyanovsky <astoyano@redhat.com>
This commit is contained in:
Anastas Stoyanovsky 2025-11-11 08:54:02 -05:00
parent 7093978754
commit 7a9b7ecdc2
9 changed files with 159 additions and 20 deletions

View file

@ -6723,9 +6723,12 @@ components:
type: array
title: Output
parallel_tool_calls:
type: boolean
title: Parallel Tool Calls
default: false
type: boolean
default: true
description: >-
(Optional) Whether to allow more than one function tool call generated
per turn.
previous_response_id:
anyOf:
- type: string
@ -6835,12 +6838,14 @@ components:
title: Input
type: object
required:
- created_at
- id
- model
- output
- status
- input
- created_at
- id
- model
- object
- output
- status
- text
- input
title: OpenAIResponseObjectWithInput
description: OpenAI response object extended with input context information.
OpenAIResponseOutput:
@ -7122,9 +7127,12 @@ components:
- type: 'null'
title: OpenAIResponsePrompt
instructions:
type: string
anyOf:
- type: string
- type: 'null'
parallel_tool_calls:
type: boolean
previous_response_id:
anyOf:
- type: string
@ -7253,7 +7261,10 @@ components:
parallel_tool_calls:
type: boolean
title: Parallel Tool Calls
default: false
default: true
description: >-
(Optional) Whether to allow more than one function tool call generated
per turn.
previous_response_id:
anyOf:
- type: string
@ -7325,11 +7336,11 @@ components:
- type: 'null'
type: object
required:
- created_at
- id
- model
- output
- status
- created_at
- id
- model
- output
- status
title: OpenAIResponseObject
description: Complete OpenAI response object containing generation results and metadata.
OpenAIResponseContentPartOutputText: