mirror of
https://github.com/openai/codex.git
synced 2026-11-07 20:30:33 +00:00
Support audio input
This commit is contained in:
@@ -997,6 +997,26 @@
|
||||
],
|
||||
"title": "InputImageFunctionCallOutputContentItem",
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"properties": {
|
||||
"input_audio": {
|
||||
"$ref": "#/definitions/InputAudio"
|
||||
},
|
||||
"type": {
|
||||
"enum": [
|
||||
"input_audio"
|
||||
],
|
||||
"title": "InputAudioFunctionCallOutputContentItemType",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"input_audio",
|
||||
"type"
|
||||
],
|
||||
"title": "InputAudioFunctionCallOutputContentItem",
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -1111,6 +1131,21 @@
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
"InputAudio": {
|
||||
"properties": {
|
||||
"data": {
|
||||
"type": "string"
|
||||
},
|
||||
"format": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"data",
|
||||
"format"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
"ListMcpServerStatusParams": {
|
||||
"properties": {
|
||||
"cursor": {
|
||||
|
||||
+42
@@ -9137,6 +9137,26 @@
|
||||
],
|
||||
"title": "InputImageFunctionCallOutputContentItem",
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"properties": {
|
||||
"input_audio": {
|
||||
"$ref": "#/definitions/v2/InputAudio"
|
||||
},
|
||||
"type": {
|
||||
"enum": [
|
||||
"input_audio"
|
||||
],
|
||||
"title": "InputAudioFunctionCallOutputContentItemType",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"input_audio",
|
||||
"type"
|
||||
],
|
||||
"title": "InputAudioFunctionCallOutputContentItem",
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -9925,6 +9945,21 @@
|
||||
],
|
||||
"type": "string"
|
||||
},
|
||||
"InputAudio": {
|
||||
"properties": {
|
||||
"data": {
|
||||
"type": "string"
|
||||
},
|
||||
"format": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"data",
|
||||
"format"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
"InputModality": {
|
||||
"description": "Canonical user-input modality tags advertised by a model.",
|
||||
"oneOf": [
|
||||
@@ -9941,6 +9976,13 @@
|
||||
"image"
|
||||
],
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"description": "Audio content included in tool payloads.",
|
||||
"enum": [
|
||||
"audio"
|
||||
],
|
||||
"type": "string"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
+42
@@ -5526,6 +5526,26 @@
|
||||
],
|
||||
"title": "InputImageFunctionCallOutputContentItem",
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"properties": {
|
||||
"input_audio": {
|
||||
"$ref": "#/definitions/InputAudio"
|
||||
},
|
||||
"type": {
|
||||
"enum": [
|
||||
"input_audio"
|
||||
],
|
||||
"title": "InputAudioFunctionCallOutputContentItemType",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"input_audio",
|
||||
"type"
|
||||
],
|
||||
"title": "InputAudioFunctionCallOutputContentItem",
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -6474,6 +6494,21 @@
|
||||
"title": "InitializeParams",
|
||||
"type": "object"
|
||||
},
|
||||
"InputAudio": {
|
||||
"properties": {
|
||||
"data": {
|
||||
"type": "string"
|
||||
},
|
||||
"format": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"data",
|
||||
"format"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
"InputModality": {
|
||||
"description": "Canonical user-input modality tags advertised by a model.",
|
||||
"oneOf": [
|
||||
@@ -6490,6 +6525,13 @@
|
||||
"image"
|
||||
],
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"description": "Audio content included in tool payloads.",
|
||||
"enum": [
|
||||
"audio"
|
||||
],
|
||||
"type": "string"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -17,6 +17,13 @@
|
||||
"image"
|
||||
],
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"description": "Audio content included in tool payloads.",
|
||||
"enum": [
|
||||
"audio"
|
||||
],
|
||||
"type": "string"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
+35
@@ -140,6 +140,26 @@
|
||||
],
|
||||
"title": "InputImageFunctionCallOutputContentItem",
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"properties": {
|
||||
"input_audio": {
|
||||
"$ref": "#/definitions/InputAudio"
|
||||
},
|
||||
"type": {
|
||||
"enum": [
|
||||
"input_audio"
|
||||
],
|
||||
"title": "InputAudioFunctionCallOutputContentItemType",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"input_audio",
|
||||
"type"
|
||||
],
|
||||
"title": "InputAudioFunctionCallOutputContentItem",
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -150,6 +170,21 @@
|
||||
],
|
||||
"type": "string"
|
||||
},
|
||||
"InputAudio": {
|
||||
"properties": {
|
||||
"data": {
|
||||
"type": "string"
|
||||
},
|
||||
"format": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"data",
|
||||
"format"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
"LocalShellAction": {
|
||||
"oneOf": [
|
||||
{
|
||||
|
||||
@@ -199,6 +199,26 @@
|
||||
],
|
||||
"title": "InputImageFunctionCallOutputContentItem",
|
||||
"type": "object"
|
||||
},
|
||||
{
|
||||
"properties": {
|
||||
"input_audio": {
|
||||
"$ref": "#/definitions/InputAudio"
|
||||
},
|
||||
"type": {
|
||||
"enum": [
|
||||
"input_audio"
|
||||
],
|
||||
"title": "InputAudioFunctionCallOutputContentItemType",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"input_audio",
|
||||
"type"
|
||||
],
|
||||
"title": "InputAudioFunctionCallOutputContentItem",
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -209,6 +229,21 @@
|
||||
],
|
||||
"type": "string"
|
||||
},
|
||||
"InputAudio": {
|
||||
"properties": {
|
||||
"data": {
|
||||
"type": "string"
|
||||
},
|
||||
"format": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"data",
|
||||
"format"
|
||||
],
|
||||
"type": "object"
|
||||
},
|
||||
"LocalShellAction": {
|
||||
"oneOf": [
|
||||
{
|
||||
|
||||
+2
-1
@@ -2,9 +2,10 @@
|
||||
|
||||
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
|
||||
import type { ImageDetail } from "./ImageDetail";
|
||||
import type { InputAudio } from "./InputAudio";
|
||||
|
||||
/**
|
||||
* Responses API compatible content items that can be returned by a tool call.
|
||||
* This is a subset of ContentItem with the types we support as function call outputs.
|
||||
*/
|
||||
export type FunctionCallOutputContentItem = { "type": "input_text", text: string, } | { "type": "input_image", image_url: string, detail?: ImageDetail, };
|
||||
export type FunctionCallOutputContentItem = { "type": "input_text", text: string, } | { "type": "input_image", image_url: string, detail?: ImageDetail, } | { "type": "input_audio", input_audio: InputAudio, };
|
||||
|
||||
@@ -0,0 +1,5 @@
|
||||
// GENERATED CODE! DO NOT MODIFY BY HAND!
|
||||
|
||||
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
|
||||
|
||||
export type InputAudio = { data: string, format: string, };
|
||||
@@ -5,4 +5,4 @@
|
||||
/**
|
||||
* Canonical user-input modality tags advertised by a model.
|
||||
*/
|
||||
export type InputModality = "text" | "image";
|
||||
export type InputModality = "text" | "image" | "audio";
|
||||
|
||||
@@ -36,6 +36,7 @@ export type { ImageDetail } from "./ImageDetail";
|
||||
export type { InitializeCapabilities } from "./InitializeCapabilities";
|
||||
export type { InitializeParams } from "./InitializeParams";
|
||||
export type { InitializeResponse } from "./InitializeResponse";
|
||||
export type { InputAudio } from "./InputAudio";
|
||||
export type { InputModality } from "./InputModality";
|
||||
export type { InternalSessionSource } from "./InternalSessionSource";
|
||||
export type { LocalShellAction } from "./LocalShellAction";
|
||||
|
||||
Reference in New Issue
Block a user