Флэш-память Gemini 3.7 теперь доступна. Попробуйте!

Эта страница переведена с помощью Cloud Translation API.

Gemini Triggers API

Триггеры позволяют планировать выполнение агентов по расписанию cron, обеспечивая автоматизацию и повторяющиеся задачи.

Просмотреть в формате Markdown Просмотреть спецификацию OpenAPI

CreateTrigger

ссылка: https://generativelanguage.googleapis.com/v1beta/triggers

Создает новый триггер, который будет запускать указанный агент по заданному расписанию cron.

Текст запроса
Ответ

Текст запроса

Тело запроса содержит данные следующей структуры:

display_name строка (необязательно)

Необязательно. Отображаемое имя триггера.

environment_id строка (необязательно)

Необязательно. Идентификатор среды для выполнения триггера.

execution_timeout_seconds — целое число (необязательно)

Необязательно. Время ожидания выполнения для инициированного взаимодействия.

Методы взаимодействия CreateAgentInteractionParams или CreateModelInteractionParams (обязательно)

Обязательно. Шаблон запроса на взаимодействие, который будет выполнен.

max_consecutive_failures целое число (необязательно)

Необязательно. Максимально допустимое количество последовательных сбоев до автоматической приостановки срабатывания триггера (статус меняется на ERROR).

строка расписания (обязательно)

Обязательно. Расписание cron, по которому должен запускаться триггер. Стандартный формат cron.

строка time_zone (обязательно)

Обязательно. Часовой пояс, в котором следует интерпретировать расписание.

Ответ

В случае успеха тело ответа содержит данные следующей структуры:

consecutive_failure_count целое число (необязательно)

Только вывод. Количество последовательных сбоев, произошедших с момента последнего успешного выполнения.

create_time string (необязательно)

Только вывод. Время создания триггера.

display_name строка (необязательно)

Необязательно. Отображаемое имя триггера.

environment_id строка (необязательно)

Необязательно. Идентификатор среды для выполнения триггера.

execution_timeout_seconds — целое число (необязательно)

Необязательно. Время ожидания выполнения для инициированного взаимодействия.

строка идентификатора (необязательно)

Обязательно. Только для вывода. Идентификатор. Идентификатор триггера.

Взаимодействие (необязательно )

Обязательно. Шаблон запроса на взаимодействие, который будет выполнен.

Поля

агент AgentOption (необязательно)

Имя агента, использованного для генерации взаимодействия.

Возможные значения

deep-research-pro-preview-12-2025
Агент по глубоким исследованиям компании Gemini
deep-research-preview-04-2026
Агент по глубоким исследованиям компании Gemini
deep-research-max-preview-04-2026
Gemini Deep Research Max Agent
antigravity-preview-05-2026
Используйте управляемый агент Antigravity для выполнения многоэтапных задач, требующих логического мышления, работы с файлами и использования инструментов.

объект agent_config (необязательно)

Параметры конфигурации для взаимодействия с агентом.

Возможные типы

Полиморфный дискриминатор: type

AntigravityAgentConfig

Настройки среды выполнения агента Antigravity. Обеспечивают управление средой выполнения агента и конфигурацией инструментов на стороне сервера.

max_total_tokens строка (необязательно)

Максимальное общее количество токенов для выполнения задания агентом.

строка модели (необязательно)

Модель, используемая для рассуждений агента.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте режим "antigravity" .

CodeMenderAgentConfig

Настройки агента CodeMender.

find_request FindRequest (необязательно)

Параметры для поиска уязвимостей.

Поля

строка описания (необязательно)

Дополнительный контекст или пользовательские инструкции, предоставленные пользователем для проведения анализа уязвимостей.

finding_id строка (необязательно)

Идентификатор конкретной уязвимости, подлежащей проверке. В основном используется в режиме ПРОВЕРКИ (VERIFY) для того, чтобы сосредоточить проверку агента на выполнении на одной конкретной уязвимости.

режим перечисления (строка) (необязательно)

Режим работы поисковой сессии.

Возможные значения:

scan
Быстрое сканирование с использованием только исходного классификатора.
verify
Проводит классификацию с последующим детальным исследованием.

массив source_files (FileContent) (необязательно)

Список исходных файлов, которые необходимо предоставить в качестве контекста для сканирования.

Поля

строка содержимого (необязательно)

Содержимое файла, закодированное в UTF-8.

строка пути (необязательно)

Относительный путь к файлу относительно корневого каталога проекта.

fix_request FixRequest (необязательно)

Параметры для устранения уязвимостей.

Поля

строка описания (необязательно)

Дополнительный контекст или пользовательские инструкции, предоставленные пользователем для управления процессом создания патча.

finding_id строка (необязательно)

Идентификатор конкретной уязвимости, подлежащей устранению. Этот идентификатор соответствует ранее обнаруженной уязвимости.

массив source_files (FileContent) (необязательно)

Список исходных файлов, предоставляющих контекст для устранения проблемы. Как правило, это файлы, содержащие выявленную уязвимость.

Поля

строка содержимого (необязательно)

Содержимое файла, закодированное в UTF-8.

строка пути (необязательно)

Относительный путь к файлу относительно корневого каталога проекта.

строка модели (необязательно)

Название модели, используемой для агента CodeMender. Одна сессия CodeMender будет использовать только одну модель.

session_config SessionConfig (необязательно)

Дополнительные параметры конфигурации, специфичные для каждой сессии, позволяют переопределить поведение агента по умолчанию.

Поля

max_rounds — целое число (необязательно)

Максимальное количество раундов взаимодействия, которое агент может выполнить до истечения тайм-аута.

session_id строка (необязательно)

Параметр для группировки нескольких взаимодействий, относящихся к одной и той же сессии CodeMender.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "code-mender" .

DeepResearchAgentConfig

Настройки агента Deep Research.

collaborative_planning логическое значение (необязательно)

Включает планирование с участием человека для агента Deep Research. Если установлено значение true, агент Deep Research предоставит план исследования в своем ответе. Затем агент продолжит работу только в том случае, если пользователь подтвердит план на следующем ходу.

enable_bigquery_tool boolean (необязательно)

Включает инструмент BigQuery для агента Deep Research.

thinking_summaries ThinkingSummaries (необязательно)

Стоит ли включать в ответ краткое изложение мыслей?

Возможные значения

auto
Краткие обзоры автоматического мышления.
none
Никаких кратких изложений мысли.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "deep-research" .

перечисление визуализации (строка) (необязательно)

Стоит ли включать визуализации в ответ.

Возможные значения:

off
Не включайте визуализации.
auto
Автоматическое добавление визуализаций.

DynamicAgentConfig

Настройка для динамических агентов.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "dynamic" .

созданная строка (необязательно)

Только вывод. Время создания ответа в формате ISO 8601 (ГГГГ-ММ-ДДЧч:мм:ссЗ).

среда EnvironmentConfig или строка (необязательно)

Конфигурация среды для взаимодействия. Может представлять собой объект, указывающий на удаленные источники среды, или строку, ссылающуюся на существующий идентификатор среды.

Поля

environment_id строка (необязательно)

Необязательный параметр. Идентификатор среды для взаимодействия. Если указан, запрос обновит существующую среду вместо создания новой.

network EnvironmentNetworkEgressAllowlist или enum (строка) (необязательно)

Настройка сети для данной среды.

Возможные типы

объект

Настройки исходящей сети для песочницы. При указании ограничивает доступ песочницы к внешним доменам. Полное исключение позволяет разрешить весь исходящий трафик без внедрения заголовков.

Массив разрешенных записей (AllowlistEntry) (необязательно)

Список разрешенных исходящих доменов. Разрешены только запросы к перечисленным доменам. Используйте [{'domain': '*'}], чтобы разрешить все домены, но при этом добавить заголовки только к определенным из них.

Поля

строка домена (необязательно)

Домен, разрешающий исходящие запросы. Поддерживаются подстановочные знаки (например, '*.googleapis.com'). Используйте '*' для разрешения всех доменов.

преобразование массива (объекта) или объекта (необязательно)

Заголовки для добавления во все исходящие запросы, соответствующие этому домену. Принимает один словарь или список словарей. Исходящий прокси добавляет их автоматически.

нить

Отключает всю сеть.

Возможные значения

disabled
Отключает всю сеть.

массив источников (Источник) (необязательно)

Описание отсутствует.

Поля

строка содержимого (необязательно)

Встроенное содержимое, если `type` имеет значение `INLINE`.

строка кодировки (необязательно)

Дополнительная кодировка для встроенного контента (например, `base64`).

исходная строка (необязательно)

Источник среды. Для Cloud Storage это путь к Cloud Storage. Для GitHub это путь к GitHub.

Целевая строка (необязательно)

Где должен отображаться исходный код в окружающей среде.

тип перечисления (строка) (необязательно)

Описание отсутствует.

Возможные значения:

gcs
Сегмент облачного хранилища.
inline
Встроенный контент.
repository
Универсальный репозиторий. Префикс протокола в URL-адресе источника идентифицирует поставщика (например, github://, gcs://).
skill_registry
Ресурс навыков из службы регистрации навыков. Навык: projects/{project}/locations/{location}/skills/{skill} Ревизия навыка: projects/{project}/locations/{location}/skills/{skill}/revisions/{revision} Поддерживается подключение всех навыков в рамках проекта: projects/{project}/locations/{location}/skills.

тип объекта (необязательно)

Описание отсутствует.

Всегда устанавливайте значение "remote" .

environment_id строка (необязательно)

Только для вывода. Идентификатор среды для взаимодействия. Заполняется только в том случае, если в запросе задана конфигурация среды.

массив ошибок (Ошибка) (необязательно)

Только вывод. Диагностические ошибки / ошибки платформы, зафиксированные во время взаимодействия.

Поля

строка кода (необязательно)

URI, определяющий тип ошибки.

строка сообщения (необязательно)

Удобочитаемое сообщение об ошибке.

строка идентификатора (необязательно)

Обязательно. Только для вывода. Уникальный идентификатор завершения взаимодействия.

По умолчанию:

Входные данные: Content или массив (Content) или массив (Step) или строка (необязательно)

Входные данные для взаимодействия.

объект меток (необязательно)

Метки с заданными пользователем метаданными для запроса.

модель ModelOption (необязательно)

Название модели, использованной для генерации взаимодействия.

Возможные значения

gemini-2.5-flash
Наша первая гибридная модель рассуждений, поддерживающая контекстное окно в 1 миллион токенов и имеющая бюджеты мышления.
gemini-2.5-pro
Наша передовая многоцелевая модель, превосходно справляющаяся с задачами программирования и сложным логическим мышлением.
gemma-4-26b-a4b-it
Джемма 4 26B A4B IT
gemma-4-31b-it
Джемма 4 31B IT
gemini-flash-latest
Последняя версия Gemini Flash
gemini-flash-lite-latest
Новейшая версия фонарика Gemini Flash-Lite
gemini-pro-latest
Последняя версия Gemini Pro
gemini-2.5-flash-lite
Наша самая компактная и экономичная модель, предназначенная для масштабного использования.
gemini-2.5-flash-image
Наша собственная модель генерации изображений, оптимизированная для скорости, гибкости и контекстного понимания. Стоимость ввода и вывода текста такая же, как у 2,5-дюймовой версии Flash.
gemini-3-flash-preview
Наша самая интеллектуальная модель, созданная для скорости, сочетает в себе передовые методы разведки с превосходными возможностями поиска и посадки на землю.
gemini-3.1-pro-preview
Наша новейшая, передовая модель логического мышления с беспрецедентной глубиной и детализацией, а также мощными возможностями многомодального понимания и кодирования.
gemini-3.1-pro-preview-customtools
Gemini 3.1 Pro Preview оптимизирован для использования пользовательских инструментов.
gemini-3.1-flash-lite
Наша наиболее экономичная модель, оптимизированная для выполнения больших объемов агентских задач, перевода и простой обработки данных.
gemini-3-pro-image
Изображение Gemini 3 Pro
nano-banana-pro-preview
Предварительный просмотр изображения Gemini 3 Pro
gemini-3.1-flash-image
Изображение Gemini 3.1 Flash.
gemini-3.5-flash
Наша наиболее интеллектуальная модель для достижения устойчиво высоких результатов в задачах, связанных с агентным программированием и кодированием.
gemini-3.6-flash
Наша наиболее интеллектуальная модель для достижения устойчиво высоких результатов в задачах, связанных с агентным программированием и кодированием.
gemini-3.7-flash
Наша наиболее интеллектуальная модель для достижения устойчиво высоких результатов в задачах, связанных с агентным программированием и кодированием.
lyria-3-clip-preview
Наша модель генерации музыки с низкой задержкой оптимизирована для высококачественных аудиоклипов и точного контроля ритма.
lyria-3-pro-preview
Наша передовая генеративная модель, способная обрабатывать целые композиции и обладающая глубоким пониманием композиции, оптимизирована для точного структурного контроля и сложных переходов между различными музыкальными стилями.
gemini-robotics-er-1.6-preview
Gemini Robotics-ER 1.6 Preview
gemini-robotics-er-2-preview
Предварительный обзор Gemini Robotics Embodied Reasoning 2

output_audio AudioContent (необязательно)

Последний аудиофайл, сгенерированный моделью в ответ на текущий запрос. Примечание: эта информация добавляется SDK.

Поля

каналы целое число (необязательно)

Количество аудиоканалов.

строка данных (необязательно)

Аудиоконтент.

перечисление mime_type (строка) (необязательно)

MIME-тип аудиофайла.

Возможные значения:

audio/wav
аудиоформат WAV
audio/mp3
аудиоформат MP3
audio/aiff
аудиоформат AIFF
audio/aac
аудиоформат AAC
audio/ogg
Аудиоформат OGG
audio/flac
аудиоформат FLAC
audio/mpeg
аудиоформат MPEG
audio/m4a
аудиоформат M4A
audio/l16
аудиоформат L16
audio/opus
Аудиоформат OPUS
audio/alaw
Аудиоформат ALAW
audio/mulaw
Аудиоформат MULAW

sample_rate — целое число (необязательно)

Частота дискретизации аудиосигнала.

тип объекта (необязательно)

Описание отсутствует.

Всегда устанавливайте значение "audio" .

строка URI (необязательно)

URI аудиофайла.

output_image ImageContent (необязательно)

Последнее изображение, сгенерированное моделью в ответ на текущий запрос. Примечание: оно добавляется SDK.

Поля

строка данных (необязательно)

Содержание изображения.

перечисление mime_type (строка) (необязательно)

MIME-тип изображения.

Возможные значения:

image/png
формат изображения PNG
image/jpeg
формат изображения JPEG
image/webp
формат изображений WebP
image/heic
формат изображения HEIC
image/heif
формат изображения HEIF
image/gif
формат изображения GIF
image/bmp
формат изображения BMP
image/tiff
формат изображения TIFF

разрешение MediaResolution (необязательно)

Разрешение средств массовой информации.

Возможные значения

low
Низкое разрешение.
medium
Среднее разрешение.
high
Высокое разрешение.
ultra_high
Сверхвысокое разрешение.

тип объекта (необязательно)

Описание отсутствует.

Всегда устанавливайте значение "image" .

строка URI (необязательно)

URI изображения.

output_text строка (необязательно)

Конкатенированный текст из последнего результата работы модели в ответ на текущий запрос. Примечание: этот текст добавляется SDK.

output_video Видеоконтент (необязательно)

Последнее видео, сгенерированное моделью в ответ на текущий запрос. Примечание: оно добавляется SDK.

Поля

строка данных (необязательно)

Видеоконтент.

перечисление mime_type (строка) (необязательно)

Тип MIME видео.

Возможные значения:

video/mp4
видеоформат MP4
video/mpeg
видеоформат MPEG
video/mpg
видеоформат MPG
video/mov
видеоформат MOV
video/avi
видеоформат AVI
video/x-flv
видеоформат FLV
video/webm
видеоформат WebM
video/wmv
видеоформат WMV
video/3gpp
видеоформат 3GPP

Обработка медиафайлов или перечисление (строка) (необязательно)

Как модель обрабатывает это видео для понимания.

разрешение MediaResolution (необязательно)

Разрешение средств массовой информации.

Возможные значения

low
Низкое разрешение.
medium
Среднее разрешение.
high
Высокое разрешение.
ultra_high
Сверхвысокое разрешение.

тип объекта (необязательно)

Описание отсутствует.

Всегда устанавливайте значение "video" .

строка URI (необязательно)

URI видео.

previous_interaction_id строка (необязательно)

Идентификатор предыдущего взаимодействия, если таковое имелось.

response_format Формат ответа или массив (ResponseFormat) (необязательно)

Обеспечивает, чтобы сгенерированный ответ представлял собой объект JSON, соответствующий схеме JSON, указанной в этом поле.

Возможные типы

AudioResponseFormat

Настройка формата вывода звука.

bit_rate — целое число (необязательно)

Битрейт в битах в секунду (бит/с). Применимо только для сжатых форматов (MP3, Opus).

перечисление доставки (строка) (необязательно)

Режим вывода аудиосигнала.

Возможные значения:

inline
Аудиоданные возвращаются непосредственно в ответе.
uri
Аудиоданные возвращаются в виде URI.

перечисление mime_type (строка) (необязательно)

MIME-тип аудиовыхода.

Возможные значения:

audio/mp3
Аудиоформат MP3.
audio/ogg_opus
Аудиоформат OGG Opus.
audio/l16
Необработанный аудиоформат PCM (L16).
audio/wav
Аудиоформат WAV.
audio/alaw
Аудиоформат A-law.
audio/mulaw
Аудиоформат Mu-law.

sample_rate — целое число (необязательно)

Частота дискретизации в Гц.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "audio" .

ImageResponseFormat

Настройки формата вывода изображения.

aspect_ratio enum (string) (optional)

Соотношение сторон выходного изображения.

Возможные значения:

1:1
Соотношение сторон 1:1.
2:3
Соотношение сторон 2:3.
3:2
Соотношение сторон 3:2.
3:4
Соотношение сторон 3:4.
4:3
Соотношение сторон 4:3.
4:5
Соотношение сторон 4:5.
5:4
Соотношение сторон 5:4.
9:16
Соотношение сторон 9:16.
16:9
Соотношение сторон 16:9.
21:9
Соотношение сторон 21:9.
1:8
Соотношение сторон 1:8.
8:1
Соотношение сторон 8:1.
1:4
Соотношение сторон 1:4.
4:1
Соотношение сторон 4:1.

перечисление доставки (строка) (необязательно)

Способ доставки изображения на выходе.

Возможные значения:

inline
Данные изображения возвращаются непосредственно в ответе.
uri
Данные изображения возвращаются в виде URI.

Перечисление image_size (строка) (необязательно)

Размер выходного изображения.

Возможные значения:

512
Размер изображения: 512 пикселей.
1K
Размер изображения 1K.
2K
Размер изображения 2K.
4K
Размер изображения 4K.

перечисление mime_type (строка) (необязательно)

MIME-тип выходного изображения.

Возможные значения:

image/jpeg
Формат изображения JPEG.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "image" .

TextResponseFormat

Настройка формата текстового вывода.

перечисление mime_type (строка) (необязательно)

MIME-тип выходного текстового файла.

Возможные значения:

application/json
Формат вывода JSON.
text/plain
Формат вывода в виде простого текста.

Объект схемы (необязательно)

JSON-схема, которой должен соответствовать выходной файл. Применимо только в том случае, если mime_type имеет значение application/json.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "text" .

VideoResponseFormat

Настройки формата видеовыхода.

aspect_ratio enum (string) (optional)

Соотношение сторон видеовыходного изображения.

Возможные значения:

16:9
Соотношение сторон 16:9.
9:16
Соотношение сторон 9:16.

перечисление доставки (строка) (необязательно)

Режим вывода видеосигнала.

Возможные значения:

inline
Видеоданные возвращаются непосредственно в ответе.
uri
Видеоданные возвращаются в виде URI.

строка продолжительности (необязательно)

Продолжительность видеовывода.

строка gcs_uri (необязательно)

URI облачного хранилища для сохранения видеоданных. Необходимо для Vertex, если режим доставки — URI.

Перечисление разрешений (строка) (необязательно)

Разрешение видеовыхода. По умолчанию — 720p.

Возможные значения:

360p
Разрешение 360p.
720p
Разрешение 720p.
1080p
Разрешение 1080p.
4k
Разрешение 4K.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "video" .

массив safety_settings (SafetySetting) (необязательно)

Настройки безопасности для взаимодействия.

Поля

метод перечисления (строка) (необязательно)

Необязательный параметр. Способ блокировки контента. Если не указан, по умолчанию используется оценка вероятности.

Возможные значения:

severity
Метод блокировки вреда использует как вероятностные оценки, так и оценки тяжести последствий.
probability
Метод блокировки вреда использует показатель вероятности.

пороговое значение перечисления (строка) (необязательно)

Обязательно. Пороговое значение для блокировки контента. Если вероятность причинения вреда превысит этот порог, контент будет заблокирован.

Возможные значения:

block_low_and_above
Блокируйте контент с низкой или высокой вероятностью причинения вреда.
block_medium_and_above
Блокируйте контент со средней или высокой вероятностью причинения вреда.
block_only_high
Блокируйте контент с высокой вероятностью причинения вреда.
block_none
Не блокируйте никакой контент, независимо от вероятности его нанесения вреда.
off
Полностью отключите защитный фильтр.

тип HarmCategory (необязательно)

Обязательно. Категория вреда, подлежащая блокировке.

Возможные значения

hate_speech
Контент, пропагандирующий насилие или разжигающий ненависть к отдельным лицам или группам на основе определенных признаков.
dangerous_content
Контент, который пропагандирует, способствует или поощряет опасные действия.
harassment
Оскорбительный, угрожающий контент, направленный на запугивание, мучение или высмеивание.
sexually_explicit
Контент, содержащий материалы сексуального характера.
civic_integrity
Устарело: фильтр выборов больше не поддерживается. Категория причинения вреда — гражданская неприкосновенность.
image_hate
Изображения, содержащие разжигающие ненависть высказывания.
image_dangerous_content
Изображения, содержащие опасный контент.
image_harassment
Изображения, содержащие элементы домогательств.
image_sexually_explicit
Изображения, содержащие материалы сексуального характера.
jailbreak
Подсказки, предназначенные для обхода защитных фильтров.

service_tier ServiceTier (необязательно)

Уровень обслуживания для данного взаимодействия.

Возможные значения

flex
Гибкий уровень обслуживания.
standard
Стандартный уровень обслуживания.
priority
Приоритетный уровень обслуживания.
deferred
Отложенный уровень обслуживания.

перечисление статуса (строка) (необязательно)

Обязательный параметр. Только вывод. Статус взаимодействия.

Возможные значения:

in_progress
Взаимодействие продолжается.
requires_action
Для взаимодействия требуется действие/ввод данных от пользователя.
completed
Взаимодействие завершено.
failed
Взаимодействие не удалось.
cancelled
Встреча была отменена.
incomplete
Взаимодействие завершено, но результаты неполные (например, достигнуто значение max_tokens).
budget_exceeded
Взаимодействие было прервано из-за превышения лимита токенов.
queued
Взаимодействие поставлено в очередь и ожидает обработки.

массив шагов (Шаг) (необязательно)

Только вывод. Этапы взаимодействия, если они включены в ответ.

Возможные типы

CodeExecutionCallStep

Шаг вызова выполнения кода.

аргументы CodeExecutionCallStepArguments (обязательно)

Обязательный параметр. Аргументы, передаваемые для выполнения кода.

Поля

строка кода (необязательно)

Код, который необходимо выполнить.

языковой перечисление (строка) (необязательно)

Язык программирования кода.

Возможные значения:

python
Python >= 3.10, с доступными библиотеками numpy и simpy.

строковый идентификатор (обязательно)

Обязательно. Уникальный идентификатор для данного вызова инструмента.

строка подписи (необязательно)

Хэш подписи для проверки данных на стороне бэкэнда.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "code_execution_call" .

CodeExecutionResultStep

Шаг, определяющий результат выполнения кода.

call_id — строка (обязательно)

Обязательно. Идентификатор, соответствующий идентификатору из блока вызова функции.

is_error логическое значение (необязательно)

Выполнился ли код с ошибкой?

строка результата (обязательно)

Обязательно. Результат выполнения кода.

строка подписи (необязательно)

Хэш подписи для проверки данных на стороне бэкэнда.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "code_execution_result" .

FileSearchCallStep

Шаг вызова поиска файла.

строковый идентификатор (обязательно)

Обязательно. Уникальный идентификатор для данного вызова инструмента.

строка подписи (необязательно)

Хэш подписи для проверки данных на стороне бэкэнда.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "file_search_call" .

FileSearchResultStep

Шаг поиска файлов по результатам.

call_id — строка (обязательно)

Обязательно. Идентификатор, соответствующий идентификатору из блока вызова функции.

строка подписи (необязательно)

Хэш подписи для проверки данных на стороне бэкэнда.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "file_search_result" .

FunctionCallStep

Шаг вызова функции инструмента.

Объект аргументов (обязательный)

Обязательный параметр. Аргументы, передаваемые функции.

строковый идентификатор (обязательно)

Обязательно. Уникальный идентификатор для данного вызова инструмента.

имя строка (обязательно)

Обязательно. Название вызываемого инструмента.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "function_call" .

FunctionResultStep

Результат вызова функции инструмента.

call_id — строка (обязательно)

Обязательно. Идентификатор, соответствующий идентификатору из блока вызова функции.

is_error логическое значение (необязательно)

Вызвал ли вызов инструмента ошибку?

строковое имя (необязательно)

Название вызванного инструмента.

массив результатов (ImageContent или TextContent) или объект, или строка (обязательно)

Обязательно. Результат вызова инструмента.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "function_result" .

GoogleКартыCallStep

Шаг вызова Google Maps.

аргументы GoogleMapsCallStepArguments (необязательно)

Аргументы, передаваемые инструменту Google Maps.

Поля

массив запросов (строка) (необязательно)

Запросы, подлежащие выполнению.

строковый идентификатор (обязательно)

Обязательно. Уникальный идентификатор для данного вызова инструмента.

строка подписи (необязательно)

Хэш подписи для проверки данных на стороне бэкэнда.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "google_maps_call" .

GoogleMapsResultStep

Шаг поиска результатов в Google Maps.

call_id — строка (обязательно)

Обязательно. Идентификатор, соответствующий идентификатору из блока вызова функции.

массив результатов (GoogleMapsResultItem) (обязательно)

Описание отсутствует.

Поля

массив мест (GoogleMapsResultPlaces) (необязательно)

Описание отсутствует.

Поля

строковое имя (необязательно)

Описание отсутствует.

place_id строка (необязательно)

Описание отсутствует.

массив review_snippets (ReviewSnippet) (необязательно)

Описание отсутствует.

Поля

review_id строка (необязательно)

Идентификатор фрагмента отзыва.

заголовок (необязательно )

Заголовок рецензии.

строка URL (необязательно)

Ссылка, соответствующая отзыву пользователя на Google Maps.

строка URL (необязательно)

Описание отсутствует.

widget_context_token строка (необязательно)

Описание отсутствует.

строка подписи (необязательно)

Хэш подписи для проверки данных на стороне бэкэнда.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "google_maps_result" .

GoogleSearchCallStep

Шаг вызова поиска Google.

arguments GoogleSearchCallStepArguments (required)

Обязательный параметр. Аргументы, которые будут переданы в поиск Google.

Поля

массив запросов (строка) (необязательно)

Поисковые запросы в интернете для последующего поиска.

строковый идентификатор (обязательно)

Обязательно. Уникальный идентификатор для данного вызова инструмента.

search_type enum (string) (optional)

Тип включенной привязки поиска.

Возможные значения:

web_search
Включение этого поля активирует веб-поиск. Возвращаются только текстовые результаты.
image_search
Установив это поле, можно включить поиск изображений. Возвращаются байты изображения.
enterprise_web_search
Включение корпоративного веб-поиска.

строка подписи (необязательно)

Хэш подписи для проверки данных на стороне бэкэнда.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "google_search_call" .

GoogleSearchResultStep

Шаг поиска в Google.

call_id — строка (обязательно)

Обязательно. Идентификатор, соответствующий идентификатору из блока вызова функции.

is_error логическое значение (необязательно)

Вызвал ли поиск в Google ошибку.

массив результатов (GoogleSearchResultItem) (обязательно)

Обязательно. Результаты поиска Google.

Поля

строка search_suggestions (необязательно)

Фрагмент веб-контента, который можно встроить в веб-страницу или веб-представление приложения.

строка подписи (необязательно)

Хэш подписи для проверки данных на стороне бэкэнда.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "google_search_result" .

McpServerToolCallStep

Шаг вызова инструмента MCPServer.

Объект аргументов (обязательный)

Обязательный параметр. JSON-объект с аргументами для функции.

строковый идентификатор (обязательно)

Обязательно. Уникальный идентификатор для данного вызова инструмента.

имя строка (обязательно)

Обязательно. Название вызванного инструмента.

server_name — строка (обязательно)

Обязательно. Имя используемого MCP-сервера.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "mcp_server_tool_call" .

McpServerToolResultStep

Шаг получения результатов работы инструмента MCPServer.

call_id — строка (обязательно)

Обязательно. Идентификатор, соответствующий идентификатору из блока вызова функции.

строковое имя (необязательно)

Название инструмента, который вызывается для данного конкретного вызова инструмента.

массив результатов (ImageContent или TextContent) или объект, или строка (обязательно)

Обязательный параметр. Результат вызова сервера MCP. Может представлять собой простой текст или расширенное содержимое.

server_name строка (необязательно)

Название используемого MCP-сервера.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "mcp_server_tool_result" .

ModelOutputStep

Результаты, сгенерированные моделью.

Массив содержимого (Содержимое) (необязательно)

Описание отсутствует.

Возможные типы

Аудиоконтент

Блок аудиоконтента.

каналы целое число (необязательно)

Количество аудиоканалов.

строка данных (необязательно)

Аудиоконтент.

перечисление mime_type (строка) (необязательно)

MIME-тип аудиофайла.

Возможные значения:

audio/wav
аудиоформат WAV
audio/mp3
аудиоформат MP3
audio/aiff
аудиоформат AIFF
audio/aac
аудиоформат AAC
audio/ogg
Аудиоформат OGG
audio/flac
аудиоформат FLAC
audio/mpeg
аудиоформат MPEG
audio/m4a
аудиоформат M4A
audio/l16
аудиоформат L16
audio/opus
Аудиоформат OPUS
audio/alaw
Аудиоформат ALAW
audio/mulaw
Аудиоформат MULAW

sample_rate — целое число (необязательно)

Частота дискретизации аудиосигнала.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "audio" .

строка URI (необязательно)

URI аудиофайла.

Содержимое документа

Блок содержимого документа.

строка данных (необязательно)

Содержание документа.

перечисление mime_type (строка) (необязательно)

MIME-тип документа.

Возможные значения:

application/pdf
PDF-документ
text/csv
формат документа CSV

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "document" .

строка URI (необязательно)

URI документа.

ImageContent

Блок с графическим содержимым.

строка данных (необязательно)

Содержание изображения.

перечисление mime_type (строка) (необязательно)

MIME-тип изображения.

Возможные значения:

image/png
формат изображения PNG
image/jpeg
формат изображения JPEG
image/webp
формат изображений WebP
image/heic
формат изображения HEIC
image/heif
формат изображения HEIF
image/gif
формат изображения GIF
image/bmp
формат изображения BMP
image/tiff
формат изображения TIFF

разрешение MediaResolution (необязательно)

Разрешение средств массовой информации.

Возможные значения

low
Низкое разрешение.
medium
Среднее разрешение.
high
Высокое разрешение.
ultra_high
Сверхвысокое разрешение.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "image" .

строка URI (необязательно)

URI изображения.

Текстовое содержимое

Блок текстового содержимого.

массив аннотаций (Аннотация) (необязательно)

Информация об источниках для контента, сгенерированного моделью.

Возможные типы

FileCitation

Аннотация к файлу.

объект custom_metadata (необязательно)

Пользователь предоставил метаданные о полученном контексте.

document_uri строка (необязательно)

URI файла.

end_index целое число (необязательно)

Конец выделенного сегмента, без учета каких-либо ограничений.

file_name string (необязательно)

Название файла.

media_id строка (необязательно)

В случае цитирования изображений, пожалуйста, укажите идентификатор медиафайла (Media ID), если таковой имеется.

page_number целое число (необязательно)

Номер страницы цитируемого документа, если таковой имеется.

исходная строка (необязательно)

Источник указан для части текста.

start_index — целое число (необязательно)

Начало сегмента ответа, который относится к данному источнику. Индекс указывает начало сегмента, измеряемое в байтах.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "file_citation" .

PlaceCitation

Аннотация к географическому местоположению.

end_index целое число (необязательно)

Конец выделенного сегмента, без учета каких-либо ограничений.

строковое имя (необязательно)

Название места.

place_id строка (необязательно)

Идентификатор места в формате `places/{place_id}`.

массив review_snippets (ReviewSnippet) (необязательно)

Фрагменты отзывов, используемые для генерации ответов об особенностях того или иного места в Google Maps.

Поля

review_id строка (необязательно)

Идентификатор фрагмента отзыва.

заголовок (необязательно )

Заголовок рецензии.

строка URL (необязательно)

Ссылка, соответствующая отзыву пользователя на Google Maps.

start_index — целое число (необязательно)

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "place_citation" .

строка URL (необязательно)

URI-ссылка на это место.

URLCitation

Аннотация URL-адреса.

end_index целое число (необязательно)

Конец выделенного сегмента, без учета каких-либо ограничений.

start_index — целое число (необязательно)

заголовок (необязательно )

Заголовок URL-адреса.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "url_citation" .

строка URL (необязательно)

URL.

WordInfo

Аннотации автоматического распознавания речи на уровне слов для вывода транскрипции. Содержат текст слова, необязательное время и необязательное указание говорящего.

end_index целое число (необязательно)

Конец выделенного сегмента, без учета каких-либо ограничений.

end_offset string (необязательно)

Смещение в конце слова относительно начала аудиозаписи. Присутствует, если timestamp_granularities содержит "word".

Кабель для подключения динамика (опционально)

Необязательно. Метка говорящего для этого слова (например, "spk_1", "spk_2"). Присутствует, если в TranscriptionConfig установлен параметр diarization_mode.

start_index — целое число (необязательно)

строка начального смещения (необязательно)

Начальное смещение слова относительно начала аудиозаписи. Присутствует, если timestamp_granularities содержит "word".

текстовая строка (необязательно)

Записанное слово.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "word_info" .

текстовая строка (обязательно)

Обязательно. Текстовое содержимое.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "text" .

Видеоконтент

Блок видеоконтента.

строка данных (необязательно)

Видеоконтент.

перечисление mime_type (строка) (необязательно)

Тип MIME видео.

Возможные значения:

video/mp4
видеоформат MP4
video/mpeg
видеоформат MPEG
video/mpg
видеоформат MPG
video/mov
видеоформат MOV
video/avi
видеоформат AVI
video/x-flv
видеоформат FLV
video/webm
видеоформат WebM
video/wmv
видеоформат WMV
video/3gpp
видеоформат 3GPP

Обработка медиафайлов или перечисление (строка) (необязательно)

Как модель обрабатывает это видео для понимания.

разрешение MediaResolution (необязательно)

Разрешение средств массовой информации.

Возможные значения

low
Низкое разрешение.
medium
Среднее разрешение.
high
Высокое разрешение.
ultra_high
Сверхвысокое разрешение.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "video" .

строка URI (необязательно)

URI видео.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "model_output" .

ThoughtStep

Шаг для размышления.

строка подписи (необязательно)

Хэш подписи для проверки данных на стороне бэкэнда.

массив сводных данных (ThoughtSummaryContent) (необязательно)

Краткое изложение мысли.

Возможные типы

ImageContent

Блок с графическим содержимым.

строка данных (необязательно)

Содержание изображения.

перечисление mime_type (строка) (необязательно)

MIME-тип изображения.

Возможные значения:

image/png
формат изображения PNG
image/jpeg
формат изображения JPEG
image/webp
формат изображений WebP
image/heic
формат изображения HEIC
image/heif
формат изображения HEIF
image/gif
формат изображения GIF
image/bmp
формат изображения BMP
image/tiff
формат изображения TIFF

разрешение MediaResolution (необязательно)

Разрешение средств массовой информации.

Возможные значения

low
Низкое разрешение.
medium
Среднее разрешение.
high
Высокое разрешение.
ultra_high
Сверхвысокое разрешение.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "image" .

строка URI (необязательно)

URI изображения.

Текстовое содержимое

Блок текстового содержимого.

массив аннотаций (Аннотация) (необязательно)

Информация об источниках для контента, сгенерированного моделью.

Возможные типы

FileCitation

Аннотация к файлу.

объект custom_metadata (необязательно)

Пользователь предоставил метаданные о полученном контексте.

document_uri строка (необязательно)

URI файла.

end_index целое число (необязательно)

Конец выделенного сегмента, без учета каких-либо ограничений.

file_name string (необязательно)

Название файла.

media_id строка (необязательно)

В случае цитирования изображений, пожалуйста, укажите идентификатор медиафайла (Media ID), если таковой имеется.

page_number целое число (необязательно)

Номер страницы цитируемого документа, если таковой имеется.

исходная строка (необязательно)

Источник указан для части текста.

start_index — целое число (необязательно)

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "file_citation" .

PlaceCitation

Аннотация к географическому местоположению.

end_index целое число (необязательно)

Конец выделенного сегмента, без учета каких-либо ограничений.

строковое имя (необязательно)

Название места.

place_id строка (необязательно)

Идентификатор места в формате `places/{place_id}`.

массив review_snippets (ReviewSnippet) (необязательно)

Фрагменты отзывов, используемые для генерации ответов об особенностях того или иного места в Google Maps.

Поля

review_id строка (необязательно)

Идентификатор фрагмента отзыва.

заголовок (необязательно )

Заголовок рецензии.

строка URL (необязательно)

Ссылка, соответствующая отзыву пользователя на Google Maps.

start_index — целое число (необязательно)

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "place_citation" .

строка URL (необязательно)

URI-ссылка на это место.

URLCitation

Аннотация URL-адреса.

end_index целое число (необязательно)

Конец выделенного сегмента, без учета каких-либо ограничений.

start_index — целое число (необязательно)

заголовок (необязательно )

Заголовок URL-адреса.

тип объекта (обязательно)

Описание отсутствует.

Всегда устанавливайте значение "url_citation" .

строка URL (необязательно)

URL.

WordInfo

end_index целое число (необязательно)

Конец выделенного сегмента, без учета каких-либо ограничений.

end_offset string (необязательно)

Смещение в конце слова относительно начала аудиозаписи. Присутствует, если timestamp_granularities содержит "word".

Кабель для подключения динамика (опционально)

start_index — целое число (необязательно)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

start_offset string (optional)

Start offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

text string (optional)

The transcribed word.

type object (required)

Описание отсутствует.

Always set to "word_info" .

text string (required)

Required. The text content.

type object (required)

Описание отсутствует.

Always set to "text" .

type object (required)

Описание отсутствует.

Always set to "thought" .

UrlContextCallStep

URL context call step.

arguments UrlContextCallArguments (required)

Required. The arguments to pass to the URL context.

Поля

urls array (string) (optional)

The URLs to fetch.

id string (required)

Required. A unique ID for this specific tool call.

signature string (optional)

A signature hash for backend validation.

type object (required)

Описание отсутствует.

Always set to "url_context_call" .

UrlContextResultStep

URL context result step.

call_id string (required)

Required. ID to match the ID from the function call block.

is_error boolean (optional)

Whether the URL context resulted in an error.

result array (UrlContextResult) (required)

Required. The results of the URL context.

Поля

status enum (string) (optional)

The status of the URL retrieval.

Возможные значения:

success
Url retrieval is successful.
error
Url retrieval is failed due to error.
paywall
Url retrieval is failed because the content is behind paywall.
unsafe
Url retrieval is failed because the content is unsafe.

url string (optional)

The URL that was fetched.

signature string (optional)

A signature hash for backend validation.

type object (required)

Описание отсутствует.

Always set to "url_context_result" .

UserInputStep

Input provided by the user.

content array (Content) (optional)

Описание отсутствует.

Possible Types

AudioContent

An audio content block.

channels integer (optional)

Количество аудиоканалов.

data string (optional)

The audio content.

mime_type enum (string) (optional)

The mime type of the audio.

Возможные значения:

audio/wav
WAV audio format
audio/mp3
MP3 audio format
audio/aiff
AIFF audio format
audio/aac
AAC audio format
audio/ogg
OGG audio format
audio/flac
FLAC audio format
audio/mpeg
MPEG audio format
audio/m4a
M4A audio format
audio/l16
L16 audio format
audio/opus
OPUS audio format
audio/alaw
ALAW audio format
audio/mulaw
MULAW audio format

sample_rate integer (optional)

The sample rate of the audio.

type object (required)

Описание отсутствует.

Always set to "audio" .

uri string (optional)

The URI of the audio.

DocumentContent

A document content block.

data string (optional)

The document content.

mime_type enum (string) (optional)

The mime type of the document.

Возможные значения:

application/pdf
PDF document format
text/csv
CSV document format

type object (required)

Описание отсутствует.

Always set to "document" .

uri string (optional)

The URI of the document.

ImageContent

An image content block.

data string (optional)

The image content.

mime_type enum (string) (optional)

The mime type of the image.

Возможные значения:

image/png
PNG image format
image/jpeg
JPEG image format
image/webp
WebP image format
image/heic
HEIC image format
image/heif
формат изображения HEIF
image/gif
GIF image format
image/bmp
BMP image format
image/tiff
TIFF image format

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

Описание отсутствует.

Always set to "image" .

uri string (optional)

The URI of the image.

TextContent

A text content block.

annotations array (Annotation) (optional)

Информация об источниках для контента, сгенерированного моделью.

Possible Types

FileCitation

A file citation annotation.

custom_metadata object (optional)

User provided metadata about the retrieved context.

document_uri string (optional)

The URI of the file.

end_index integer (optional)

End of the attributed segment, exclusive.

file_name string (optional)

The name of the file.

media_id string (optional)

Media ID in-case of image citations, if applicable.

page_number integer (optional)

Page number of the cited document, if applicable.

source string (optional)

Source attributed for a portion of the text.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

Описание отсутствует.

Always set to "file_citation" .

PlaceCitation

A place citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

name string (optional)

Title of the place.

place_id string (optional)

The ID of the place, in `places/{place_id}` format.

review_snippets array (ReviewSnippet) (optional)

Snippets of reviews that are used to generate answers about the features of a given place in Google Maps.

Поля

review_id string (optional)

The ID of the review snippet.

title string (optional)

Title of the review.

url string (optional)

A link that corresponds to the user review on Google Maps.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

Описание отсутствует.

Always set to "place_citation" .

url string (optional)

URI reference of the place.

UrlCitation

A URL citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

title string (optional)

The title of the URL.

type object (required)

Описание отсутствует.

Always set to "url_citation" .

url string (optional)

The URL.

WordInfo

Word-level ASR annotation for transcription output. Carries the word text, optional timing, and optional speaker attribution.

end_index integer (optional)

End of the attributed segment, exclusive.

end_offset string (optional)

End offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

speaker string (optional)

Optional. Speaker label for this word (eg "spk_1", "spk_2"). Present when diarization_mode is set in TranscriptionConfig.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

start_offset string (optional)

Start offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

text string (optional)

The transcribed word.

type object (required)

Описание отсутствует.

Always set to "word_info" .

text string (required)

Required. The text content.

type object (required)

Описание отсутствует.

Always set to "text" .

VideoContent

A video content block.

data string (optional)

The video content.

mime_type enum (string) (optional)

The mime type of the video.

Возможные значения:

video/mp4
MP4 video format
video/mpeg
видеоформат MPEG
video/mpg
MPG video format
video/mov
MOV video format
video/avi
AVI video format
video/x-flv
FLV video format
video/webm
WebM video format
video/wmv
WMV video format
video/3gpp
3GPP video format

processing MediaProcessing or enum (string) (optional)

How the model processes this video for understanding.

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

Описание отсутствует.

Always set to "video" .

uri string (optional)

The URI of the video.

type object (required)

Описание отсутствует.

Always set to "user_input" .

system_instruction string (optional)

System instruction for the interaction.

tools array (Tool) (optional)

A list of tool declarations the model may call during interaction.

Possible Types

CodeExecution

A tool that can be used by the model to execute code.

type object (required)

Описание отсутствует.

Always set to "code_execution" .

ComputerUse

A tool that can be used by the model to interact with the computer.

disabled_safety_policies array (enum (string)) (optional)

Optional. Disabled safety policies for computer use.

Возможные значения:

financial_transactions
Safety policy for financial transactions.
sensitive_data_modification
Safety policy for sensitive data modification.
communication_tool
Safety policy for communication tools (eg Gmail, Chat, Meet).
account_creation
Safety policy for account creation.
data_modification
Safety policy for data modification.
user_consent_management
Safety policy for user consent management.
legal_terms_and_agreements
Safety policy for legal terms and agreements.

enable_prompt_injection_detection boolean (optional)

Whether enable the prompt injection detection check on computer-use request.

environment enum (string) (optional)

The environment being operated.

Возможные значения:

browser
Operates in a web browser.
mobile
Operates in a mobile environment.
desktop
Operates in a desktop environment.

excluded_predefined_functions array (string) (optional)

The list of predefined functions that are excluded from the model call.

type object (required)

Описание отсутствует.

Always set to "computer_use" .

Поиск файлов

A tool that can be used by the model to search files.

file_search_store_names array (string) (optional)

The file search store names to search.

metadata_filter string (optional)

Metadata filter to apply to the semantic retrieval documents and chunks.

top_k integer (optional)

The number of semantic retrieval chunks to retrieve.

type object (required)

Описание отсутствует.

Always set to "file_search" .

Функция

Инструмент, который может быть использован моделью.

description string (optional)

A description of the function.

name string (optional)

The name of the function.

parameters object (optional)

The JSON Schema for the function's parameters.

type object (required)

Описание отсутствует.

Always set to "function" .

Google Карты

A tool that can be used by the model to call Google Maps.

enable_widget boolean (optional)

Whether to return a widget context token in the tool call result of the response.

latitude number (optional)

The latitude of the user's location.

longitude number (optional)

The longitude of the user's location.

type object (required)

Описание отсутствует.

Always set to "google_maps" .

GoogleSearch

A tool that can be used by the model to search Google.

search_types array (enum (string)) (optional)

The types of search grounding to enable.

Возможные значения:

web_search
Setting this field enables web search. Only text results are returned.
image_search
Setting this field enables image search. Image bytes are returned.
enterprise_web_search
Setting this field enables enterprise web search.

type object (required)

Описание отсутствует.

Always set to "google_search" .

McpServer

A MCPServer is a server that can be called by the model to perform actions.

allowed_tools array (AllowedTools) (optional)

The allowed tools.

Поля

mode enum (string) (optional)

The mode of the tool choice.

Возможные значения:

auto
Auto tool choice.
any
Any tool choice.
none
No tool choice.
validated
Validated tool choice.

tools array (string) (optional)

The names of the allowed tools.

headers object (optional)

Optional: Fields for authentication headers, timeouts, etc., if needed.

name string (optional)

The name of the MCPServer.

type object (required)

Описание отсутствует.

Always set to "mcp_server" .

url string (optional)

The full URL for the MCPServer endpoint. Example: "https://api.example.com/mcp"

Извлечение

A tool that can be used by the model to retrieve files.

exa_ai_search_config ExaAISearchConfig (optional)

Used to specify configuration for ExaAISearch.

Поля

api_key string (optional)

Required. The API key for ExaAiSearch.

custom_config object (optional)

Optional. This field can be used to pass any parameter from the Exa.ai Search API.

parallel_ai_search_config ParallelAISearchConfig (optional)

Used to specify configuration for ParallelAISearch.

Поля

api_key string (optional)

Optional. The API key for ParallelAiSearch.

custom_config object (optional)

Optional. Custom configs for ParallelAiSearch.

rag_store_config RagStoreConfig (optional)

Used to specify configuration for RagStore.

Поля

rag_resources array (RagResource) (optional)

Optional. The representation of the rag source.

Поля

rag_corpus string (optional)

Optional. RagCorpora resource name.

rag_file_ids array (string) (optional)

Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field.

rag_retrieval_config RagRetrievalConfig (optional)

Optional. The retrieval config for the Rag query.

Поля

filter Filter (optional)

Optional. Config for filters.

Поля

metadata_filter string (optional)

Optional. String for metadata filtering.

vector_distance_threshold number (optional)

Optional. Only returns contexts with vector distance smaller than the threshold.

vector_similarity_threshold number (optional)

Optional. Only returns contexts with vector similarity larger than the threshold.

hybrid_search HybridSearch (optional)

Optional. Config for Hybrid Search.

Поля

alpha number (optional)

Optional. Alpha value controls the weight between dense and sparse vector search results.

ranking Ranking (optional)

Optional. Config for ranking and reranking.

top_k integer (optional)

Optional. The number of contexts to retrieve.

retrieval_types array (enum (string)) (optional)

The types of file retrieval to enable.

Возможные значения:

rag_store
exa_ai_search
parallel_ai_search

type object (required)

Описание отсутствует.

Always set to "retrieval" .

UrlContext

A tool that can be used by the model to fetch URL context.

type object (required)

Описание отсутствует.

Always set to "url_context" .

updated string (optional)

Output only. The time at which the response was last updated in ISO 8601 format (YYYY-MM-DDThh:mm:ssZ).

usage Usage (optional)

Output only. Statistics on the interaction request's token usage.

Поля

cached_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of cached token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

grounding_tool_count array (GroundingToolCount) (optional)

Grounding tool count.

Поля

count integer (optional)

Количество заземляющих инструментов подсчитывается.

type enum (string) (optional)

The grounding tool type associated with the count.

Возможные значения:

google_search
Grounding with Google Web Search and Image Search, & Web Grounding for Enterprise.
google_maps
Grounding with Google Maps.
retrieval
Grounding with customer's data, for example, VertexAISearch.

input_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of input token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

output_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of output token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

tool_use_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of tool-use token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

total_cached_tokens integer (optional)

Number of tokens in the cached part of the prompt (the cached content).

total_input_tokens integer (optional)

Number of tokens in the prompt (context).

total_output_tokens integer (optional)

Total number of tokens across all the generated responses.

total_thought_tokens integer (optional)

Number of tokens of thoughts for thinking models.

total_tokens integer (optional)

Total token count for the interaction request (prompt + responses + other internal tokens).

total_tool_use_tokens integer (optional)

Number of tokens present in tool-use prompt(s).

webhook_config WebhookConfig (optional)

Optional. Webhook configuration for receiving notifications when the interaction completes.

Поля

uris array (string) (optional)

Optional. If set, these webhook URIs will be used for webhook events instead of the registered webhooks.

user_metadata object (optional)

Optional. The user metadata that will be returned on each event emission to the webhooks.

last_pause_time string (optional)

Output only. The time when the trigger was last paused.

last_resume_time string (optional)

Output only. The time when the trigger was last resumed.

last_run_time string (optional)

Output only. The time when the trigger was last run.

max_consecutive_failures integer (optional)

Optional. The maximum number of consecutive failures allowed before the trigger is automatically paused (status becomes ERROR).

next_run_time string (optional)

Output only. The time when the trigger is scheduled to run next.

previous_interaction_id string (optional)

Output only. The ID of the last interaction created by this trigger.

schedule string (optional)

Required. The cron schedule on which the trigger should run. Standard cron format.

status enum (string) (optional)

Output only. The current status of the trigger.

Возможные значения:

active
The trigger is active and will fire on schedule.
paused
The trigger is paused and will not fire.
error
The trigger has entered an error state due to consecutive failures.

time_zone string (optional)

Required. Time zone in which the schedule should be interpreted.

update_time string (optional)

Output only. The time when the trigger was last updated.

Пример

Пример ответа

{
  "consecutive_failure_count": 0,
  "create_time": "string",
  "display_name": "string",
  "environment_id": "string",
  "execution_timeout_seconds": 0,
  "id": "string",
  "interaction": {
    "created": "2025-12-04T15:01:45Z",
    "id": "v1_ChdXS0l4YWZXTk9xbk0xZThQczhEcmlROBIXV0tJeGFmV05PcW5NMWU4UHM4RHJpUTg",
    "model": "gemini-3.6-flash",
    "object": "interaction",
    "status": "completed",
    "steps": [
      {
        "type": "model_output",
        "content": [
          {
            "type": "text",
            "text": "Hello! I'm doing well, functioning as expected. Thank you for asking! How are you doing today?"
          }
        ]
      }
    ],
    "updated": "2025-12-04T15:01:45Z",
    "usage": {
      "input_tokens_by_modality": [
        {
          "modality": "text",
          "tokens": 7
        }
      ],
      "total_cached_tokens": 0,
      "total_input_tokens": 7,
      "total_output_tokens": 23,
      "total_thought_tokens": 49,
      "total_tokens": 79,
      "total_tool_use_tokens": 0
    }
  },
  "last_pause_time": "string",
  "last_resume_time": "string",
  "last_run_time": "string",
  "max_consecutive_failures": 0,
  "next_run_time": "string",
  "previous_interaction_id": "string",
  "schedule": "string",
  "status": "active",
  "time_zone": "string",
  "update_time": "string"
}

RunTrigger

post https://generativelanguage.googleapis.com/v1beta/triggers/{trigger_id}/executions

Runs a trigger immediately.

Ответ

Ответ

If successful, the response body contains data with the following structure:

end_time string (optional)

Output only. The time when the execution finished.

environment_id string (optional)

Output only. The environment ID used for the execution.

error string (optional)

Output only. The error message if the execution failed.

id string (optional)

Required. Output only. Identifier. The ID of the trigger execution.

interaction_id string (optional)

Output only. The ID of the interaction created by this execution, if any.

scheduled_time string (optional)

Output only. The time when the execution was scheduled to run.

start_time string (optional)

Output only. The time when the execution started.

status enum (string) (optional)

Output only. The status of the execution.

Возможные значения:

in_progress
The execution is currently in progress.
completed
The execution completed successfully.
failed
Выполнение не удалось.
skipped
The execution was skipped (eg, previous execution still running).
timed_out
The execution timed out.

trigger_id string (optional)

Required. Output only. Identifier. The ID of the trigger that created this execution.

Пример

Пример ответа

{
  "end_time": "string",
  "environment_id": "string",
  "error": "string",
  "id": "string",
  "interaction_id": "string",
  "scheduled_time": "string",
  "start_time": "string",
  "status": "in_progress",
  "trigger_id": "string"
}

ListTriggers

get https://generativelanguage.googleapis.com/v1beta/triggers

Lists triggers for a project.

Path / Query parameters
Ответ

Path / Query Parameters

filter string (optional)

Optional. Filter expression (eg, by state).

page_size integer (optional)

Optional. The maximum number of triggers to return per page.

page_token string (optional)

Optional. A page token from a previous ListTriggers call.

Ответ

If successful, the response body contains data with the following structure:

next_page_token string (optional)

A page token, received from a previous `ListTriggers` call. Provide this to retrieve the subsequent page.

triggers array ( Trigger ) (optional)

The list of triggers.

Пример

Пример ответа

{
  "next_page_token": "string",
  "triggers": [
    {
      "consecutive_failure_count": 0,
      "create_time": "string",
      "display_name": "string",
      "environment_id": "string",
      "execution_timeout_seconds": 0,
      "id": "string",
      "interaction": {
        "created": "2025-12-04T15:01:45Z",
        "id": "v1_ChdXS0l4YWZXTk9xbk0xZThQczhEcmlROBIXV0tJeGFmV05PcW5NMWU4UHM4RHJpUTg",
        "model": "gemini-3.6-flash",
        "object": "interaction",
        "status": "completed",
        "steps": [
          {
            "type": "model_output",
            "content": [
              {
                "type": "text",
                "text": "Hello! I'm doing well, functioning as expected. Thank you for asking! How are you doing today?"
              }
            ]
          }
        ],
        "updated": "2025-12-04T15:01:45Z",
        "usage": {
          "input_tokens_by_modality": [
            {
              "modality": "text",
              "tokens": 7
            }
          ],
          "total_cached_tokens": 0,
          "total_input_tokens": 7,
          "total_output_tokens": 23,
          "total_thought_tokens": 49,
          "total_tokens": 79,
          "total_tool_use_tokens": 0
        }
      },
      "last_pause_time": "string",
      "last_resume_time": "string",
      "last_run_time": "string",
      "max_consecutive_failures": 0,
      "next_run_time": "string",
      "previous_interaction_id": "string",
      "schedule": "string",
      "status": "active",
      "time_zone": "string",
      "update_time": "string"
    }
  ]
}

GetTrigger

get https://generativelanguage.googleapis.com/v1beta/triggers/{id}

Gets details of a single trigger.

Ответ

Ответ

If successful, the response body contains data with the following structure:

consecutive_failure_count integer (optional)

Output only. The number of consecutive failures that have occurred since the last successful execution.

create_time string (optional)

Output only. The time when the trigger was created.

display_name string (optional)

Optional. The display name of the trigger.

environment_id string (optional)

Optional. The environment ID for the trigger execution.

execution_timeout_seconds integer (optional)

Optional. The execution timeout for the triggered interaction.

id string (optional)

Required. Output only. Identifier. The ID of the trigger.

interaction Interaction (optional)

Required. The interaction request template to be executed.

Поля

agent AgentOption (optional)

The name of the `Agent` used for generating the interaction.

Возможные значения

deep-research-pro-preview-12-2025
Gemini Deep Research Agent
deep-research-preview-04-2026
Gemini Deep Research Agent
deep-research-max-preview-04-2026
Gemini Deep Research Max Agent
antigravity-preview-05-2026
Use the Antigravity managed agent to perform multi-step tasks that require reasoning, file operations, and tool use.

agent_config object (optional)

Configuration parameters for the agent interaction.

Possible Types

Polymorphic discriminator: type

AntigravityAgentConfig

Configuration for the Antigravity agent runtime. Provides server-side control over the agent's execution environment and tool configuration.

max_total_tokens string (optional)

Max total tokens for the agent run.

model string (optional)

The model to use for agent reasoning.

type object (required)

Описание отсутствует.

Always set to "antigravity" .

CodeMenderAgentConfig

Configuration for the CodeMender agent.

find_request FindRequest (optional)

Parameters for finding vulnerabilities.

Поля

description string (optional)

Additional context or custom instructions provided by the user to guide the vulnerability analysis.

finding_id string (optional)

The identifier of a specific finding to verify. This is primarily used in VERIFY mode to focus the agent's execution-based validation on a single vulnerability.

mode enum (string) (optional)

The mode of the find session.

Возможные значения:

scan
Fast scan using only the initial classifier.
verify
Performs classification followed by detailed investigation.

source_files array (FileContent) (optional)

A list of source files to provide as context for the scan.

Поля

content string (optional)

The UTF-8 encoded text content of the file.

path string (optional)

The relative path of the file from the project root.

fix_request FixRequest (optional)

Parameters for fixing vulnerabilities.

Поля

description string (optional)

Additional context or custom instructions provided by the user to guide the patch generation process.

finding_id string (optional)

The identifier of the specific security finding to be remediated. This ID maps to a previously discovered vulnerability.

source_files array (FileContent) (optional)

A list of source files providing context for the remediation. These files are typically the ones containing the identified vulnerability.

Поля

content string (optional)

The UTF-8 encoded text content of the file.

path string (optional)

The relative path of the file from the project root.

model string (optional)

The name of the model to use for the CodeMender agent. One CodeMender session will only use one model.

session_config SessionConfig (optional)

Optional session-specific configurations to override default agent behavior.

Поля

max_rounds integer (optional)

The maximum number of interaction rounds the agent is allowed to perform before reaching a timeout.

session_id string (optional)

Parameter for grouping multiple interactions that belong to the same CodeMender session.

type object (required)

Описание отсутствует.

Always set to "code-mender" .

DeepResearchAgentConfig

Configuration for the Deep Research agent.

collaborative_planning boolean (optional)

Enables human-in-the-loop planning for the Deep Research agent. If set to true, the Deep Research agent will provide a research plan in its response. The agent will then proceed only if the user confirms the plan in the next turn.

enable_bigquery_tool boolean (optional)

Enables bigquery tool for the Deep Research agent.

thinking_summaries ThinkingSummaries (optional)

Whether to include thought summaries in the response.

Возможные значения

auto
Auto thinking summaries.
none
No thinking summaries.

type object (required)

Описание отсутствует.

Always set to "deep-research" .

visualization enum (string) (optional)

Whether to include visualizations in the response.

Возможные значения:

off
Do not include visualizations.
auto
Automatically include visualizations.

DynamicAgentConfig

Configuration for dynamic agents.

type object (required)

Описание отсутствует.

Always set to "dynamic" .

created string (optional)

Output only. The time at which the response was created in ISO 8601 format (YYYY-MM-DDThh:mm:ssZ).

environment EnvironmentConfig or string (optional)

The environment configuration for the interaction. Can be an object specifying remote environment sources or a string referencing an existing environment ID.

Поля

environment_id string (optional)

Optional. The environment ID for the interaction. If specified, the request will update the existing environment instead of creating a new one.

network EnvironmentNetworkEgressAllowlist or enum (string) (optional)

Network configuration for the environment.

Possible Types

объект

Outbound networking configuration for the sandbox. When specified, restricts which external domains the sandbox can reach. Omit entirely to allow all outbound traffic with no header injection.

allowlist array (AllowlistEntry) (optional)

List of allowed outbound domains. Only requests to listed domains are permitted. Use [{'domain': '*'}] to allow all domains while still injecting headers on specific ones.

Поля

domain string (optional)

Domain to allow outbound requests to. Supports wildcards (eg '*.googleapis.com'). Use '*' to allow all domains.

transform array (object) or object (optional)

Headers to inject on all outbound requests matching this domain. Accepts a single dict or a list of dicts. The egress proxy injects these automatically.

нить

Turns all network off.

Возможные значения

disabled
Turns all network off.

sources array (Source) (optional)

Описание отсутствует.

Поля

content string (optional)

The inline content if `type` is `INLINE`.

encoding string (optional)

Optional encoding for inline content (eg `base64`).

source string (optional)

The source of the environment. For Cloud Storage, this is the Cloud Storage path. For GitHub, this is the GitHub path.

target string (optional)

Where the source should appear in the environment.

type enum (string) (optional)

Описание отсутствует.

Возможные значения:

gcs
A Cloud Storage bucket.
inline
Inline content.
repository
A generic repository. The protocol prefix in the source URL identifies the provider (eg, github://, gcs://).
skill_registry
A skill resource from the Skill Registry Service. Skill: projects/{project}/locations/{location}/skills/{skill} SkillRevision: projects/{project}/locations/{location}/skills/{skill}/revisions/{revision} Support mounting all skills under a project: projects/{project}/locations/{location}/skills.

type object (optional)

Описание отсутствует.

Always set to "remote" .

environment_id string (optional)

Output only. The environment ID for the interaction. Only populated if environment config is set in the request.

errors array (Error) (optional)

Output only. Diagnostic faults / platform errors recorded on the interaction.

Поля

code string (optional)

A URI that identifies the error type.

message string (optional)

A human-readable error message.

id string (optional)

Required. Output only. A unique identifier for the interaction completion.

Defaults to:

input Content or array (Content) or array (Step) or string (optional)

The input for the interaction.

labels object (optional)

The labels with user-defined metadata for the request.

model ModelOption (optional)

The name of the `Model` used for generating the interaction.

Возможные значения

gemini-2.5-flash
Наша первая гибридная модель рассуждений, поддерживающая контекстное окно в 1 миллион токенов и имеющая бюджеты мышления.
gemini-2.5-pro
Our state-of-the-art multipurpose model, which excels at coding and complex reasoning tasks.
gemma-4-26b-a4b-it
Джемма 4 26B A4B IT
gemma-4-31b-it
Джемма 4 31B IT
gemini-flash-latest
Latest release of Gemini Flash
gemini-flash-lite-latest
Latest release of Gemini Flash-Lite
gemini-pro-latest
Latest release of Gemini Pro
gemini-2.5-flash-lite
Наша самая компактная и экономичная модель, предназначенная для масштабного использования.
gemini-2.5-flash-image
Our native image generation model, optimized for speed, flexibility, and contextual understanding. Text input and output is priced the same as 2.5 Flash.
gemini-3-flash-preview
Наша самая интеллектуальная модель, созданная для скорости, сочетает в себе передовые методы разведки с превосходными возможностями поиска и посадки на землю.
gemini-3.1-pro-preview
Our latest SOTA reasoning model with unprecedented depth and nuance, and powerful multimodal understanding and coding capabilities.
gemini-3.1-pro-preview-customtools
Gemini 3.1 Pro Preview optimized for custom tool usage
gemini-3.1-flash-lite
Наша наиболее экономичная модель, оптимизированная для выполнения больших объемов агентских задач, перевода и простой обработки данных.
gemini-3-pro-image
Изображение Gemini 3 Pro
nano-banana-pro-preview
Gemini 3 Pro Image Preview
gemini-3.1-flash-image
Gemini 3.1 Flash Image.
gemini-3.5-flash
Our most intelligent model for sustained frontier performance in agentic and coding tasks.
gemini-3.6-flash
Our most intelligent model for sustained frontier performance in agentic and coding tasks.
gemini-3.7-flash
Our most intelligent model for sustained frontier performance in agentic and coding tasks.
lyria-3-clip-preview
Наша модель генерации музыки с низкой задержкой оптимизирована для высококачественных аудиоклипов и точного контроля ритма.
lyria-3-pro-preview
Наша передовая генеративная модель, способная обрабатывать целые композиции и обладающая глубоким пониманием композиции, оптимизирована для точного структурного контроля и сложных переходов между различными музыкальными стилями.
gemini-robotics-er-1.6-preview
Gemini Robotics-ER 1.6 Preview
gemini-robotics-er-2-preview
Gemini Robotics Embodied Reasoning 2 Preview

output_audio AudioContent (optional)

The last audio generated by the model in response to the current request. Note: this is added by the SDK.

Поля

channels integer (optional)

Количество аудиоканалов.

data string (optional)

The audio content.

mime_type enum (string) (optional)

The mime type of the audio.

Возможные значения:

audio/wav
WAV audio format
audio/mp3
MP3 audio format
audio/aiff
AIFF audio format
audio/aac
AAC audio format
audio/ogg
OGG audio format
audio/flac
FLAC audio format
audio/mpeg
MPEG audio format
audio/m4a
M4A audio format
audio/l16
L16 audio format
audio/opus
OPUS audio format
audio/alaw
ALAW audio format
audio/mulaw
MULAW audio format

sample_rate integer (optional)

The sample rate of the audio.

type object (optional)

Описание отсутствует.

Always set to "audio" .

uri string (optional)

The URI of the audio.

output_image ImageContent (optional)

The last image generated by the model in response to the current request. Note: this is added by the SDK.

Поля

data string (optional)

The image content.

mime_type enum (string) (optional)

The mime type of the image.

Возможные значения:

image/png
PNG image format
image/jpeg
JPEG image format
image/webp
WebP image format
image/heic
HEIC image format
image/heif
формат изображения HEIF
image/gif
GIF image format
image/bmp
BMP image format
image/tiff
TIFF image format

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (optional)

Описание отсутствует.

Always set to "image" .

uri string (optional)

The URI of the image.

output_text string (optional)

Concatenated text from the last model output in response to the current request. Note: this is added by the SDK.

output_video VideoContent (optional)

The last video generated by the model in response to the current request. Note: this is added by the SDK.

Поля

data string (optional)

The video content.

mime_type enum (string) (optional)

The mime type of the video.

Возможные значения:

video/mp4
MP4 video format
video/mpeg
видеоформат MPEG
video/mpg
MPG video format
video/mov
MOV video format
video/avi
AVI video format
video/x-flv
FLV video format
video/webm
WebM video format
video/wmv
WMV video format
video/3gpp
3GPP video format

processing MediaProcessing or enum (string) (optional)

How the model processes this video for understanding.

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (optional)

Описание отсутствует.

Always set to "video" .

uri string (optional)

The URI of the video.

previous_interaction_id string (optional)

The ID of the previous interaction, if any.

response_format ResponseFormat or array (ResponseFormat) (optional)

Enforces that the generated response is a JSON object that complies with the JSON schema specified in this field.

Possible Types

AudioResponseFormat

Configuration for audio output format.

bit_rate integer (optional)

Bit rate in bits per second (bps). Only applicable for compressed formats (MP3, Opus).

delivery enum (string) (optional)

The delivery mode for the audio output.

Возможные значения:

inline
Audio data is returned inline in the response.
uri
Audio data is returned as a URI.

mime_type enum (string) (optional)

The MIME type of the audio output.

Возможные значения:

audio/mp3
MP3 audio format.
audio/ogg_opus
OGG Opus audio format.
audio/l16
Raw PCM (L16) audio format.
audio/wav
WAV audio format.
audio/alaw
A-law audio format.
audio/mulaw
Mu-law audio format.

sample_rate integer (optional)

Sample rate in Hz.

type object (required)

Описание отсутствует.

Always set to "audio" .

ImageResponseFormat

Configuration for image output format.

aspect_ratio enum (string) (optional)

The aspect ratio for the image output.

Возможные значения:

1:1
Соотношение сторон 1:1.
2:3
2:3 aspect ratio.
3:2
3:2 aspect ratio.
3:4
Соотношение сторон 3:4.
4:3
4:3 aspect ratio.
4:5
4:5 aspect ratio.
5:4
5:4 aspect ratio.
9:16
9:16 aspect ratio.
16:9
Соотношение сторон 16:9.
21:9
21:9 aspect ratio.
1:8
1:8 aspect ratio.
8:1
8:1 aspect ratio.
1:4
1:4 aspect ratio.
4:1
4:1 aspect ratio.

delivery enum (string) (optional)

The delivery mode for the image output.

Возможные значения:

inline
Image data is returned inline in the response.
uri
Image data is returned as a URI.

image_size enum (string) (optional)

The size of the image output.

Возможные значения:

512
512px image size.
1K
1K image size.
2K
2K image size.
4K
4K image size.

mime_type enum (string) (optional)

The MIME type of the image output.

Возможные значения:

image/jpeg
JPEG image format.

type object (required)

Описание отсутствует.

Always set to "image" .

TextResponseFormat

Configuration for text output format.

mime_type enum (string) (optional)

The MIME type of the text output.

Возможные значения:

application/json
JSON output format.
text/plain
Plain text output format.

schema object (optional)

The JSON schema that the output should conform to. Only applicable when mime_type is application/json.

type object (required)

Описание отсутствует.

Always set to "text" .

VideoResponseFormat

Configuration for video output format.

aspect_ratio enum (string) (optional)

The aspect ratio for the video output.

Возможные значения:

16:9
Соотношение сторон 16:9.
9:16
9:16 aspect ratio.

delivery enum (string) (optional)

The delivery mode for the video output.

Возможные значения:

inline
Video data is returned inline in the response.
uri
Video data is returned as a URI.

duration string (optional)

The duration for the video output.

gcs_uri string (optional)

The Cloud Storage URI to store the video output. Required for Vertex if delivery mode is URI.

resolution enum (string) (optional)

The video output resolution. Defaults to 720p.

Возможные значения:

360p
360p resolution.
720p
720p resolution.
1080p
1080p resolution.
4k
Разрешение 4K.

type object (required)

Описание отсутствует.

Always set to "video" .

safety_settings array (SafetySetting) (optional)

Safety settings for the interaction.

Поля

method enum (string) (optional)

Optional. The method for blocking content. If not specified, the default behavior is to use the probability score.

Возможные значения:

severity
The harm block method uses both probability and severity scores.
probability
The harm block method uses the probability score.

threshold enum (string) (optional)

Required. The threshold for blocking content. If the harm probability exceeds this threshold, the content will be blocked.

Возможные значения:

block_low_and_above
Block content with a low harm probability or higher.
block_medium_and_above
Block content with a medium harm probability or higher.
block_only_high
Block content with a high harm probability.
block_none
Do not block any content, regardless of its harm probability.
off
Turn off the safety filter entirely.

type HarmCategory (optional)

Required. The type of harm category to be blocked.

Возможные значения

hate_speech
Content that promotes violence or incites hatred against individuals or groups based on certain attributes.
dangerous_content
Content that promotes, facilitates, or enables dangerous activities.
harassment
Abusive, threatening, or content intended to bully, torment, or ridicule.
sexually_explicit
Content that contains sexually explicit material.
civic_integrity
Deprecated: Election filter is not longer supported. The harm category is civic integrity.
image_hate
Images that contain hate speech.
image_dangerous_content
Images that contain dangerous content.
image_harassment
Images that contain harassment.
image_sexually_explicit
Images that contain sexually explicit content.
jailbreak
Prompts designed to bypass safety filters.

service_tier ServiceTier (optional)

The service tier for the interaction.

Возможные значения

flex
Flex service tier.
standard
Standard service tier.
priority
Priority service tier.
deferred
Deferred service tier.

status enum (string) (optional)

Required. Output only. The status of the interaction.

Возможные значения:

in_progress
The interaction is in progress.
requires_action
The interaction requires action/input from the user.
completed
The interaction is completed.
failed
The interaction failed.
cancelled
The interaction was cancelled.
incomplete
The interaction is completed, but contains incomplete results (eg hitting max_tokens).
budget_exceeded
The interaction was halted because the token budget was exceeded.
queued
The interaction is queued, waiting for processing.

steps array (Step) (optional)

Output only. The steps that make up the interaction, when included in the response.

Possible Types

CodeExecutionCallStep

Code execution call step.

arguments CodeExecutionCallStepArguments (required)

Required. The arguments to pass to the code execution.

Поля

code string (optional)

The code to be executed.

language enum (string) (optional)

Programming language of the `code`.

Возможные значения:

python
Python >= 3.10, with numpy and simpy available.

id string (required)

Required. A unique ID for this specific tool call.

signature string (optional)

A signature hash for backend validation.

type object (required)

Описание отсутствует.

Always set to "code_execution_call" .

CodeExecutionResultStep

Code execution result step.

call_id string (required)

Required. ID to match the ID from the function call block.

is_error boolean (optional)

Whether the code execution resulted in an error.

result string (required)

Required. The output of the code execution.

signature string (optional)

A signature hash for backend validation.

type object (required)

Описание отсутствует.

Always set to "code_execution_result" .

FileSearchCallStep

File Search call step.

id string (required)

Required. A unique ID for this specific tool call.

signature string (optional)

A signature hash for backend validation.

type object (required)

Описание отсутствует.

Always set to "file_search_call" .

FileSearchResultStep

File Search result step.

call_id string (required)

Required. ID to match the ID from the function call block.

signature string (optional)

A signature hash for backend validation.

type object (required)

Описание отсутствует.

Always set to "file_search_result" .

FunctionCallStep

A function tool call step.

arguments object (required)

Required. The arguments to pass to the function.

id string (required)

Required. A unique ID for this specific tool call.

name string (required)

Required. The name of the tool to call.

type object (required)

Описание отсутствует.

Always set to "function_call" .

FunctionResultStep

Result of a function tool call.

call_id string (required)

Required. ID to match the ID from the function call block.

is_error boolean (optional)

Whether the tool call resulted in an error.

name string (optional)

The name of the tool that was called.

result array (ImageContent or TextContent) or object or string (required)

Required. The result of the tool call.

type object (required)

Описание отсутствует.

Always set to "function_result" .

GoogleMapsCallStep

Google Maps call step.

arguments GoogleMapsCallStepArguments (optional)

Аргументы, передаваемые инструменту Google Maps.

Поля

queries array (string) (optional)

The queries to be executed.

id string (required)

Required. A unique ID for this specific tool call.

signature string (optional)

A signature hash for backend validation.

type object (required)

Описание отсутствует.

Always set to "google_maps_call" .

GoogleMapsResultStep

Google Maps result step.

call_id string (required)

Required. ID to match the ID from the function call block.

result array (GoogleMapsResultItem) (required)

Описание отсутствует.

Поля

places array (GoogleMapsResultPlaces) (optional)

Описание отсутствует.

Поля

name string (optional)

Описание отсутствует.

place_id string (optional)

Описание отсутствует.

review_snippets array (ReviewSnippet) (optional)

Описание отсутствует.

Поля

review_id string (optional)

The ID of the review snippet.

title string (optional)

Title of the review.

url string (optional)

A link that corresponds to the user review on Google Maps.

url string (optional)

Описание отсутствует.

widget_context_token string (optional)

Описание отсутствует.

signature string (optional)

A signature hash for backend validation.

type object (required)

Описание отсутствует.

Always set to "google_maps_result" .

GoogleSearchCallStep

Google Search call step.

arguments GoogleSearchCallStepArguments (required)

Required. The arguments to pass to Google Search.

Поля

queries array (string) (optional)

Web search queries for the following-up web search.

id string (required)

Required. A unique ID for this specific tool call.

search_type enum (string) (optional)

The type of search grounding enabled.

Возможные значения:

web_search
Setting this field enables web search. Only text results are returned.
image_search
Setting this field enables image search. Image bytes are returned.
enterprise_web_search
Setting this field enables enterprise web search.

signature string (optional)

A signature hash for backend validation.

type object (required)

Описание отсутствует.

Always set to "google_search_call" .

GoogleSearchResultStep

Google Search result step.

call_id string (required)

Required. ID to match the ID from the function call block.

is_error boolean (optional)

Whether the Google Search resulted in an error.

result array (GoogleSearchResultItem) (required)

Required. The results of the Google Search.

Поля

search_suggestions string (optional)

Web content snippet that can be embedded in a web page or an app webview.

signature string (optional)

A signature hash for backend validation.

type object (required)

Описание отсутствует.

Always set to "google_search_result" .

McpServerToolCallStep

MCPServer tool call step.

arguments object (required)

Required. The JSON object of arguments for the function.

id string (required)

Required. A unique ID for this specific tool call.

name string (required)

Required. The name of the tool which was called.

server_name string (required)

Required. The name of the used MCP server.

type object (required)

Описание отсутствует.

Always set to "mcp_server_tool_call" .

McpServerToolResultStep

MCPServer tool result step.

call_id string (required)

Required. ID to match the ID from the function call block.

name string (optional)

Name of the tool which is called for this specific tool call.

result array (ImageContent or TextContent) or object or string (required)

Required. The output from the MCP server call. Can be simple text or rich content.

server_name string (optional)

The name of the used MCP server.

type object (required)

Описание отсутствует.

Always set to "mcp_server_tool_result" .

ModelOutputStep

Output generated by the model.

content array (Content) (optional)

Описание отсутствует.

Possible Types

AudioContent

An audio content block.

channels integer (optional)

Количество аудиоканалов.

data string (optional)

The audio content.

mime_type enum (string) (optional)

The mime type of the audio.

Возможные значения:

audio/wav
WAV audio format
audio/mp3
MP3 audio format
audio/aiff
AIFF audio format
audio/aac
AAC audio format
audio/ogg
OGG audio format
audio/flac
FLAC audio format
audio/mpeg
MPEG audio format
audio/m4a
M4A audio format
audio/l16
L16 audio format
audio/opus
OPUS audio format
audio/alaw
ALAW audio format
audio/mulaw
MULAW audio format

sample_rate integer (optional)

The sample rate of the audio.

type object (required)

Описание отсутствует.

Always set to "audio" .

uri string (optional)

The URI of the audio.

DocumentContent

A document content block.

data string (optional)

The document content.

mime_type enum (string) (optional)

The mime type of the document.

Возможные значения:

application/pdf
PDF document format
text/csv
CSV document format

type object (required)

Описание отсутствует.

Always set to "document" .

uri string (optional)

The URI of the document.

ImageContent

An image content block.

data string (optional)

The image content.

mime_type enum (string) (optional)

The mime type of the image.

Возможные значения:

image/png
PNG image format
image/jpeg
JPEG image format
image/webp
WebP image format
image/heic
HEIC image format
image/heif
формат изображения HEIF
image/gif
GIF image format
image/bmp
BMP image format
image/tiff
TIFF image format

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

Описание отсутствует.

Always set to "image" .

uri string (optional)

The URI of the image.

TextContent

A text content block.

annotations array (Annotation) (optional)

Информация об источниках для контента, сгенерированного моделью.

Possible Types

FileCitation

A file citation annotation.

custom_metadata object (optional)

User provided metadata about the retrieved context.

document_uri string (optional)

The URI of the file.

end_index integer (optional)

End of the attributed segment, exclusive.

file_name string (optional)

The name of the file.

media_id string (optional)

Media ID in-case of image citations, if applicable.

page_number integer (optional)

Page number of the cited document, if applicable.

source string (optional)

Source attributed for a portion of the text.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

Описание отсутствует.

Always set to "file_citation" .

PlaceCitation

A place citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

name string (optional)

Title of the place.

place_id string (optional)

The ID of the place, in `places/{place_id}` format.

review_snippets array (ReviewSnippet) (optional)

Snippets of reviews that are used to generate answers about the features of a given place in Google Maps.

Поля

review_id string (optional)

The ID of the review snippet.

title string (optional)

Title of the review.

url string (optional)

A link that corresponds to the user review on Google Maps.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

Описание отсутствует.

Always set to "place_citation" .

url string (optional)

URI reference of the place.

UrlCitation

A URL citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

title string (optional)

The title of the URL.

type object (required)

Описание отсутствует.

Always set to "url_citation" .

url string (optional)

The URL.

WordInfo

Word-level ASR annotation for transcription output. Carries the word text, optional timing, and optional speaker attribution.

end_index integer (optional)

End of the attributed segment, exclusive.

end_offset string (optional)

End offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

speaker string (optional)

Optional. Speaker label for this word (eg "spk_1", "spk_2"). Present when diarization_mode is set in TranscriptionConfig.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

start_offset string (optional)

Start offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

text string (optional)

The transcribed word.

type object (required)

Описание отсутствует.

Always set to "word_info" .

text string (required)

Required. The text content.

type object (required)

Описание отсутствует.

Always set to "text" .

VideoContent

A video content block.

data string (optional)

The video content.

mime_type enum (string) (optional)

The mime type of the video.

Возможные значения:

video/mp4
MP4 video format
video/mpeg
видеоформат MPEG
video/mpg
MPG video format
video/mov
MOV video format
video/avi
AVI video format
video/x-flv
FLV video format
video/webm
WebM video format
video/wmv
WMV video format
video/3gpp
3GPP video format

processing MediaProcessing or enum (string) (optional)

How the model processes this video for understanding.

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

Описание отсутствует.

Always set to "video" .

uri string (optional)

The URI of the video.

type object (required)

Описание отсутствует.

Always set to "model_output" .

ThoughtStep

A thought step.

signature string (optional)

A signature hash for backend validation.

summary array (ThoughtSummaryContent) (optional)

A summary of the thought.

Possible Types

ImageContent

An image content block.

data string (optional)

The image content.

mime_type enum (string) (optional)

The mime type of the image.

Возможные значения:

image/png
PNG image format
image/jpeg
JPEG image format
image/webp
WebP image format
image/heic
HEIC image format
image/heif
формат изображения HEIF
image/gif
GIF image format
image/bmp
BMP image format
image/tiff
TIFF image format

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

Описание отсутствует.

Always set to "image" .

uri string (optional)

The URI of the image.

TextContent

A text content block.

annotations array (Annotation) (optional)

Информация об источниках для контента, сгенерированного моделью.

Possible Types

FileCitation

A file citation annotation.

custom_metadata object (optional)

User provided metadata about the retrieved context.

document_uri string (optional)

The URI of the file.

end_index integer (optional)

End of the attributed segment, exclusive.

file_name string (optional)

The name of the file.

media_id string (optional)

Media ID in-case of image citations, if applicable.

page_number integer (optional)

Page number of the cited document, if applicable.

source string (optional)

Source attributed for a portion of the text.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

Описание отсутствует.

Always set to "file_citation" .

PlaceCitation

A place citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

name string (optional)

Title of the place.

place_id string (optional)

The ID of the place, in `places/{place_id}` format.

review_snippets array (ReviewSnippet) (optional)

Snippets of reviews that are used to generate answers about the features of a given place in Google Maps.

Поля

review_id string (optional)

The ID of the review snippet.

title string (optional)

Title of the review.

url string (optional)

A link that corresponds to the user review on Google Maps.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

Описание отсутствует.

Always set to "place_citation" .

url string (optional)

URI reference of the place.

UrlCitation

A URL citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

title string (optional)

The title of the URL.

type object (required)

No description provided.

Always set to "url_citation" .

url string (optional)

The URL.

WordInfo

Word-level ASR annotation for transcription output. Carries the word text, optional timing, and optional speaker attribution.

end_index integer (optional)

End of the attributed segment, exclusive.

end_offset string (optional)

End offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

speaker string (optional)

Optional. Speaker label for this word (eg "spk_1", "spk_2"). Present when diarization_mode is set in TranscriptionConfig.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

start_offset string (optional)

Start offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

text string (optional)

The transcribed word.

type object (required)

No description provided.

Always set to "word_info" .

text string (required)

Required. The text content.

type object (required)

No description provided.

Always set to "text" .

type object (required)

No description provided.

Always set to "thought" .

UrlContextCallStep

URL context call step.

arguments UrlContextCallArguments (required)

Required. The arguments to pass to the URL context.

Поля

urls array (string) (optional)

The URLs to fetch.

id string (required)

Required. A unique ID for this specific tool call.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "url_context_call" .

UrlContextResultStep

URL context result step.

call_id string (required)

Required. ID to match the ID from the function call block.

is_error boolean (optional)

Whether the URL context resulted in an error.

result array (UrlContextResult) (required)

Required. The results of the URL context.

Поля

status enum (string) (optional)

The status of the URL retrieval.

Возможные значения:

success
Url retrieval is successful.
error
Url retrieval is failed due to error.
paywall
Url retrieval is failed because the content is behind paywall.
unsafe
Url retrieval is failed because the content is unsafe.

url string (optional)

The URL that was fetched.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "url_context_result" .

UserInputStep

Input provided by the user.

content array (Content) (optional)

No description provided.

Possible Types

AudioContent

An audio content block.

channels integer (optional)

The number of audio channels.

data string (optional)

The audio content.

mime_type enum (string) (optional)

The mime type of the audio.

Возможные значения:

audio/wav
WAV audio format
audio/mp3
MP3 audio format
audio/aiff
AIFF audio format
audio/aac
AAC audio format
audio/ogg
OGG audio format
audio/flac
FLAC audio format
audio/mpeg
MPEG audio format
audio/m4a
M4A audio format
audio/l16
L16 audio format
audio/opus
OPUS audio format
audio/alaw
ALAW audio format
audio/mulaw
MULAW audio format

sample_rate integer (optional)

The sample rate of the audio.

type object (required)

No description provided.

Always set to "audio" .

uri string (optional)

The URI of the audio.

DocumentContent

A document content block.

data string (optional)

The document content.

mime_type enum (string) (optional)

The mime type of the document.

Возможные значения:

application/pdf
PDF document format
text/csv
CSV document format

type object (required)

No description provided.

Always set to "document" .

uri string (optional)

The URI of the document.

ImageContent

An image content block.

data string (optional)

The image content.

mime_type enum (string) (optional)

The mime type of the image.

Возможные значения:

image/png
PNG image format
image/jpeg
JPEG image format
image/webp
WebP image format
image/heic
HEIC image format
image/heif
формат изображения HEIF
image/gif
GIF image format
image/bmp
BMP image format
image/tiff
TIFF image format

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

No description provided.

Always set to "image" .

uri string (optional)

The URI of the image.

TextContent

A text content block.

annotations array (Annotation) (optional)

Информация об источниках для контента, сгенерированного моделью.

Possible Types

FileCitation

A file citation annotation.

custom_metadata object (optional)

User provided metadata about the retrieved context.

document_uri string (optional)

The URI of the file.

end_index integer (optional)

End of the attributed segment, exclusive.

file_name string (optional)

The name of the file.

media_id string (optional)

Media ID in-case of image citations, if applicable.

page_number integer (optional)

Page number of the cited document, if applicable.

source string (optional)

Source attributed for a portion of the text.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "file_citation" .

PlaceCitation

A place citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

name string (optional)

Title of the place.

place_id string (optional)

The ID of the place, in `places/{place_id}` format.

review_snippets array (ReviewSnippet) (optional)

Snippets of reviews that are used to generate answers about the features of a given place in Google Maps.

Поля

review_id string (optional)

The ID of the review snippet.

title string (optional)

Title of the review.

url string (optional)

A link that corresponds to the user review on Google Maps.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "place_citation" .

url string (optional)

URI reference of the place.

UrlCitation

A URL citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

title string (optional)

The title of the URL.

type object (required)

No description provided.

Always set to "url_citation" .

url string (optional)

The URL.

WordInfo

Word-level ASR annotation for transcription output. Carries the word text, optional timing, and optional speaker attribution.

end_index integer (optional)

End of the attributed segment, exclusive.

end_offset string (optional)

End offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

speaker string (optional)

Optional. Speaker label for this word (eg "spk_1", "spk_2"). Present when diarization_mode is set in TranscriptionConfig.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

start_offset string (optional)

Start offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

text string (optional)

The transcribed word.

type object (required)

No description provided.

Always set to "word_info" .

text string (required)

Required. The text content.

type object (required)

No description provided.

Always set to "text" .

VideoContent

A video content block.

data string (optional)

The video content.

mime_type enum (string) (optional)

The mime type of the video.

Возможные значения:

video/mp4
MP4 video format
video/mpeg
видеоформат MPEG
video/mpg
MPG video format
video/mov
MOV video format
video/avi
AVI video format
video/x-flv
FLV video format
video/webm
WebM video format
video/wmv
WMV video format
video/3gpp
3GPP video format

processing MediaProcessing or enum (string) (optional)

How the model processes this video for understanding.

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

No description provided.

Always set to "video" .

uri string (optional)

The URI of the video.

type object (required)

No description provided.

Always set to "user_input" .

system_instruction string (optional)

System instruction for the interaction.

tools array (Tool) (optional)

A list of tool declarations the model may call during interaction.

Possible Types

CodeExecution

A tool that can be used by the model to execute code.

type object (required)

No description provided.

Always set to "code_execution" .

ComputerUse

A tool that can be used by the model to interact with the computer.

disabled_safety_policies array (enum (string)) (optional)

Optional. Disabled safety policies for computer use.

Возможные значения:

financial_transactions
Safety policy for financial transactions.
sensitive_data_modification
Safety policy for sensitive data modification.
communication_tool
Safety policy for communication tools (eg Gmail, Chat, Meet).
account_creation
Safety policy for account creation.
data_modification
Safety policy for data modification.
user_consent_management
Safety policy for user consent management.
legal_terms_and_agreements
Safety policy for legal terms and agreements.

enable_prompt_injection_detection boolean (optional)

Whether enable the prompt injection detection check on computer-use request.

environment enum (string) (optional)

The environment being operated.

Возможные значения:

browser
Operates in a web browser.
mobile
Operates in a mobile environment.
desktop
Operates in a desktop environment.

excluded_predefined_functions array (string) (optional)

The list of predefined functions that are excluded from the model call.

type object (required)

No description provided.

Always set to "computer_use" .

Поиск файлов

A tool that can be used by the model to search files.

file_search_store_names array (string) (optional)

The file search store names to search.

metadata_filter string (optional)

Metadata filter to apply to the semantic retrieval documents and chunks.

top_k integer (optional)

The number of semantic retrieval chunks to retrieve.

type object (required)

No description provided.

Always set to "file_search" .

Функция

Инструмент, который может быть использован моделью.

description string (optional)

A description of the function.

name string (optional)

The name of the function.

parameters object (optional)

The JSON Schema for the function's parameters.

type object (required)

No description provided.

Always set to "function" .

Google Карты

A tool that can be used by the model to call Google Maps.

enable_widget boolean (optional)

Whether to return a widget context token in the tool call result of the response.

latitude number (optional)

The latitude of the user's location.

longitude number (optional)

The longitude of the user's location.

type object (required)

No description provided.

Always set to "google_maps" .

GoogleSearch

A tool that can be used by the model to search Google.

search_types array (enum (string)) (optional)

The types of search grounding to enable.

Возможные значения:

web_search
Setting this field enables web search. Only text results are returned.
image_search
Setting this field enables image search. Image bytes are returned.
enterprise_web_search
Setting this field enables enterprise web search.

type object (required)

No description provided.

Always set to "google_search" .

McpServer

A MCPServer is a server that can be called by the model to perform actions.

allowed_tools array (AllowedTools) (optional)

The allowed tools.

Поля

mode enum (string) (optional)

The mode of the tool choice.

Возможные значения:

auto
Auto tool choice.
any
Any tool choice.
none
No tool choice.
validated
Validated tool choice.

tools array (string) (optional)

The names of the allowed tools.

headers object (optional)

Optional: Fields for authentication headers, timeouts, etc., if needed.

name string (optional)

The name of the MCPServer.

type object (required)

No description provided.

Always set to "mcp_server" .

url string (optional)

The full URL for the MCPServer endpoint. Example: "https://api.example.com/mcp"

Извлечение

A tool that can be used by the model to retrieve files.

exa_ai_search_config ExaAISearchConfig (optional)

Used to specify configuration for ExaAISearch.

Поля

api_key string (optional)

Required. The API key for ExaAiSearch.

custom_config object (optional)

Optional. This field can be used to pass any parameter from the Exa.ai Search API.

parallel_ai_search_config ParallelAISearchConfig (optional)

Used to specify configuration for ParallelAISearch.

Поля

api_key string (optional)

Optional. The API key for ParallelAiSearch.

custom_config object (optional)

Optional. Custom configs for ParallelAiSearch.

rag_store_config RagStoreConfig (optional)

Used to specify configuration for RagStore.

Поля

rag_resources array (RagResource) (optional)

Optional. The representation of the rag source.

Поля

rag_corpus string (optional)

Optional. RagCorpora resource name.

rag_file_ids array (string) (optional)

Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field.

rag_retrieval_config RagRetrievalConfig (optional)

Optional. The retrieval config for the Rag query.

Поля

filter Filter (optional)

Optional. Config for filters.

Поля

metadata_filter string (optional)

Optional. String for metadata filtering.

vector_distance_threshold number (optional)

Optional. Only returns contexts with vector distance smaller than the threshold.

vector_similarity_threshold number (optional)

Optional. Only returns contexts with vector similarity larger than the threshold.

hybrid_search HybridSearch (optional)

Optional. Config for Hybrid Search.

Поля

alpha number (optional)

Optional. Alpha value controls the weight between dense and sparse vector search results.

ranking Ranking (optional)

Optional. Config for ranking and reranking.

top_k integer (optional)

Optional. The number of contexts to retrieve.

retrieval_types array (enum (string)) (optional)

The types of file retrieval to enable.

Возможные значения:

rag_store
exa_ai_search
parallel_ai_search

type object (required)

No description provided.

Always set to "retrieval" .

UrlContext

A tool that can be used by the model to fetch URL context.

type object (required)

No description provided.

Always set to "url_context" .

updated string (optional)

Output only. The time at which the response was last updated in ISO 8601 format (YYYY-MM-DDThh:mm:ssZ).

usage Usage (optional)

Output only. Statistics on the interaction request's token usage.

Поля

cached_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of cached token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

grounding_tool_count array (GroundingToolCount) (optional)

Grounding tool count.

Поля

count integer (optional)

Количество заземляющих инструментов подсчитывается.

type enum (string) (optional)

The grounding tool type associated with the count.

Возможные значения:

google_search
Grounding with Google Web Search and Image Search, & Web Grounding for Enterprise.
google_maps
Grounding with Google Maps.
retrieval
Grounding with customer's data, for example, VertexAISearch.

input_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of input token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

output_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of output token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

tool_use_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of tool-use token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

total_cached_tokens integer (optional)

Number of tokens in the cached part of the prompt (the cached content).

total_input_tokens integer (optional)

Number of tokens in the prompt (context).

total_output_tokens integer (optional)

Total number of tokens across all the generated responses.

total_thought_tokens integer (optional)

Number of tokens of thoughts for thinking models.

total_tokens integer (optional)

Total token count for the interaction request (prompt + responses + other internal tokens).

total_tool_use_tokens integer (optional)

Number of tokens present in tool-use prompt(s).

webhook_config WebhookConfig (optional)

Optional. Webhook configuration for receiving notifications when the interaction completes.

Поля

uris array (string) (optional)

Optional. If set, these webhook URIs will be used for webhook events instead of the registered webhooks.

user_metadata object (optional)

Optional. The user metadata that will be returned on each event emission to the webhooks.

last_pause_time string (optional)

Output only. The time when the trigger was last paused.

last_resume_time string (optional)

Output only. The time when the trigger was last resumed.

last_run_time string (optional)

Output only. The time when the trigger was last run.

max_consecutive_failures integer (optional)

Optional. The maximum number of consecutive failures allowed before the trigger is automatically paused (status becomes ERROR).

next_run_time string (optional)

Output only. The time when the trigger is scheduled to run next.

previous_interaction_id string (optional)

Output only. The ID of the last interaction created by this trigger.

schedule string (optional)

Required. The cron schedule on which the trigger should run. Standard cron format.

status enum (string) (optional)

Output only. The current status of the trigger.

Возможные значения:

active
The trigger is active and will fire on schedule.
paused
The trigger is paused and will not fire.
error
The trigger has entered an error state due to consecutive failures.

time_zone string (optional)

Required. Time zone in which the schedule should be interpreted.

update_time string (optional)

Output only. The time when the trigger was last updated.

Пример

Пример ответа

{
  "consecutive_failure_count": 0,
  "create_time": "string",
  "display_name": "string",
  "environment_id": "string",
  "execution_timeout_seconds": 0,
  "id": "string",
  "interaction": {
    "created": "2025-12-04T15:01:45Z",
    "id": "v1_ChdXS0l4YWZXTk9xbk0xZThQczhEcmlROBIXV0tJeGFmV05PcW5NMWU4UHM4RHJpUTg",
    "model": "gemini-3.6-flash",
    "object": "interaction",
    "status": "completed",
    "steps": [
      {
        "type": "model_output",
        "content": [
          {
            "type": "text",
            "text": "Hello! I'm doing well, functioning as expected. Thank you for asking! How are you doing today?"
          }
        ]
      }
    ],
    "updated": "2025-12-04T15:01:45Z",
    "usage": {
      "input_tokens_by_modality": [
        {
          "modality": "text",
          "tokens": 7
        }
      ],
      "total_cached_tokens": 0,
      "total_input_tokens": 7,
      "total_output_tokens": 23,
      "total_thought_tokens": 49,
      "total_tokens": 79,
      "total_tool_use_tokens": 0
    }
  },
  "last_pause_time": "string",
  "last_resume_time": "string",
  "last_run_time": "string",
  "max_consecutive_failures": 0,
  "next_run_time": "string",
  "previous_interaction_id": "string",
  "schedule": "string",
  "status": "active",
  "time_zone": "string",
  "update_time": "string"
}

ListTriggerExecutions

get https://generativelanguage.googleapis.com/v1beta/triggers/{trigger_id}/executions

Lists executions for a trigger.

Path / Query parameters
Ответ

Path / Query Parameters

page_size integer (optional)

Optional. The maximum number of executions to return per page.

page_token string (optional)

Optional. A page token from a previous ListTriggerExecutions call.

Ответ

If successful, the response body contains data with the following structure:

next_page_token string (optional)

A page token, received from a previous `ListTriggerExecutions` call. Provide this to retrieve the subsequent page.

trigger_executions array (TriggerExecution) (optional)

The list of trigger executions.

Поля

end_time string (optional)

Output only. The time when the execution finished.

environment_id string (optional)

Output only. The environment ID used for the execution.

error string (optional)

Output only. The error message if the execution failed.

id string (optional)

Required. Output only. Identifier. The ID of the trigger execution.

interaction_id string (optional)

Output only. The ID of the interaction created by this execution, if any.

scheduled_time string (optional)

Output only. The time when the execution was scheduled to run.

start_time string (optional)

Output only. The time when the execution started.

status enum (string) (optional)

Output only. The status of the execution.

Возможные значения:

in_progress
The execution is currently in progress.
completed
The execution completed successfully.
failed
Выполнение не удалось.
skipped
The execution was skipped (eg, previous execution still running).
timed_out
The execution timed out.

trigger_id string (optional)

Required. Output only. Identifier. The ID of the trigger that created this execution.

Пример

Пример ответа

{
  "next_page_token": "string",
  "trigger_executions": [
    {
      "end_time": "string",
      "environment_id": "string",
      "error": "string",
      "id": "string",
      "interaction_id": "string",
      "scheduled_time": "string",
      "start_time": "string",
      "status": "in_progress",
      "trigger_id": "string"
    }
  ]
}

UpdateTrigger

patch https://generativelanguage.googleapis.com/v1beta/triggers/{id}

Updates a trigger.

Текст запроса
Ответ

Текст запроса

The request body contains data with the following structure:

display_name string (optional)

Optional. The display name of the trigger.

status enum (string) (optional)

Optional. The status of the trigger.

Возможные значения:

active
The trigger is active and will fire on schedule.
paused
The trigger is paused and will not fire.
error
The trigger has entered an error state due to consecutive failures.

Ответ

If successful, the response body contains data with the following structure:

consecutive_failure_count integer (optional)

Output only. The number of consecutive failures that have occurred since the last successful execution.

create_time string (optional)

Output only. The time when the trigger was created.

display_name string (optional)

Optional. The display name of the trigger.

environment_id string (optional)

Optional. The environment ID for the trigger execution.

execution_timeout_seconds integer (optional)

Optional. The execution timeout for the triggered interaction.

id string (optional)

Required. Output only. Identifier. The ID of the trigger.

interaction Interaction (optional)

Required. The interaction request template to be executed.

Поля

agent AgentOption (optional)

The name of the `Agent` used for generating the interaction.

Возможные значения

deep-research-pro-preview-12-2025
Gemini Deep Research Agent
deep-research-preview-04-2026
Gemini Deep Research Agent
deep-research-max-preview-04-2026
Gemini Deep Research Max Agent
antigravity-preview-05-2026
Use the Antigravity managed agent to perform multi-step tasks that require reasoning, file operations, and tool use.

agent_config object (optional)

Configuration parameters for the agent interaction.

Possible Types

Polymorphic discriminator: type

AntigravityAgentConfig

Configuration for the Antigravity agent runtime. Provides server-side control over the agent's execution environment and tool configuration.

max_total_tokens string (optional)

Max total tokens for the agent run.

model string (optional)

The model to use for agent reasoning.

type object (required)

No description provided.

Always set to "antigravity" .

CodeMenderAgentConfig

Configuration for the CodeMender agent.

find_request FindRequest (optional)

Parameters for finding vulnerabilities.

Поля

description string (optional)

Additional context or custom instructions provided by the user to guide the vulnerability analysis.

finding_id string (optional)

The identifier of a specific finding to verify. This is primarily used in VERIFY mode to focus the agent's execution-based validation on a single vulnerability.

mode enum (string) (optional)

The mode of the find session.

Возможные значения:

scan
Fast scan using only the initial classifier.
verify
Performs classification followed by detailed investigation.

source_files array (FileContent) (optional)

A list of source files to provide as context for the scan.

Поля

content string (optional)

The UTF-8 encoded text content of the file.

path string (optional)

The relative path of the file from the project root.

fix_request FixRequest (optional)

Parameters for fixing vulnerabilities.

Поля

description string (optional)

Additional context or custom instructions provided by the user to guide the patch generation process.

finding_id string (optional)

The identifier of the specific security finding to be remediated. This ID maps to a previously discovered vulnerability.

source_files array (FileContent) (optional)

A list of source files providing context for the remediation. These files are typically the ones containing the identified vulnerability.

Поля

content string (optional)

The UTF-8 encoded text content of the file.

path string (optional)

The relative path of the file from the project root.

model string (optional)

The name of the model to use for the CodeMender agent. One CodeMender session will only use one model.

session_config SessionConfig (optional)

Optional session-specific configurations to override default agent behavior.

Поля

max_rounds integer (optional)

The maximum number of interaction rounds the agent is allowed to perform before reaching a timeout.

session_id string (optional)

Parameter for grouping multiple interactions that belong to the same CodeMender session.

type object (required)

No description provided.

Always set to "code-mender" .

DeepResearchAgentConfig

Configuration for the Deep Research agent.

collaborative_planning boolean (optional)

enable_bigquery_tool boolean (optional)

Enables bigquery tool for the Deep Research agent.

thinking_summaries ThinkingSummaries (optional)

Whether to include thought summaries in the response.

Возможные значения

auto
Auto thinking summaries.
none
No thinking summaries.

type object (required)

No description provided.

Always set to "deep-research" .

visualization enum (string) (optional)

Whether to include visualizations in the response.

Возможные значения:

off
Do not include visualizations.
auto
Automatically include visualizations.

DynamicAgentConfig

Configuration for dynamic agents.

type object (required)

No description provided.

Always set to "dynamic" .

created string (optional)

Output only. The time at which the response was created in ISO 8601 format (YYYY-MM-DDThh:mm:ssZ).

environment EnvironmentConfig or string (optional)

The environment configuration for the interaction. Can be an object specifying remote environment sources or a string referencing an existing environment ID.

Поля

environment_id string (optional)

Optional. The environment ID for the interaction. If specified, the request will update the existing environment instead of creating a new one.

network EnvironmentNetworkEgressAllowlist or enum (string) (optional)

Network configuration for the environment.

Possible Types

объект

Outbound networking configuration for the sandbox. When specified, restricts which external domains the sandbox can reach. Omit entirely to allow all outbound traffic with no header injection.

allowlist array (AllowlistEntry) (optional)

List of allowed outbound domains. Only requests to listed domains are permitted. Use [{'domain': '*'}] to allow all domains while still injecting headers on specific ones.

Поля

domain string (optional)

Domain to allow outbound requests to. Supports wildcards (eg '*.googleapis.com'). Use '*' to allow all domains.

transform array (object) or object (optional)

Headers to inject on all outbound requests matching this domain. Accepts a single dict or a list of dicts. The egress proxy injects these automatically.

нить

Turns all network off.

Возможные значения

disabled
Turns all network off.

sources array (Source) (optional)

No description provided.

Поля

content string (optional)

The inline content if `type` is `INLINE`.

encoding string (optional)

Optional encoding for inline content (eg `base64`).

source string (optional)

The source of the environment. For Cloud Storage, this is the Cloud Storage path. For GitHub, this is the GitHub path.

target string (optional)

Where the source should appear in the environment.

type enum (string) (optional)

No description provided.

Возможные значения:

gcs
A Cloud Storage bucket.
inline
Inline content.
repository
A generic repository. The protocol prefix in the source URL identifies the provider (eg, github://, gcs://).
skill_registry
A skill resource from the Skill Registry Service. Skill: projects/{project}/locations/{location}/skills/{skill} SkillRevision: projects/{project}/locations/{location}/skills/{skill}/revisions/{revision} Support mounting all skills under a project: projects/{project}/locations/{location}/skills.

type object (optional)

No description provided.

Always set to "remote" .

environment_id string (optional)

Output only. The environment ID for the interaction. Only populated if environment config is set in the request.

errors array (Error) (optional)

Output only. Diagnostic faults / platform errors recorded on the interaction.

Поля

code string (optional)

A URI that identifies the error type.

message string (optional)

A human-readable error message.

id string (optional)

Required. Output only. A unique identifier for the interaction completion.

Defaults to:

input Content or array (Content) or array (Step) or string (optional)

The input for the interaction.

labels object (optional)

The labels with user-defined metadata for the request.

model ModelOption (optional)

The name of the `Model` used for generating the interaction.

Возможные значения

gemini-2.5-flash
Наша первая гибридная модель рассуждений, поддерживающая контекстное окно в 1 миллион токенов и имеющая бюджеты мышления.
gemini-2.5-pro
Our state-of-the-art multipurpose model, which excels at coding and complex reasoning tasks.
gemma-4-26b-a4b-it
Джемма 4 26B A4B IT
gemma-4-31b-it
Gemma 4 31B IT
gemini-flash-latest
Latest release of Gemini Flash
gemini-flash-lite-latest
Latest release of Gemini Flash-Lite
gemini-pro-latest
Latest release of Gemini Pro
gemini-2.5-flash-lite
Наша самая компактная и экономичная модель, предназначенная для масштабного использования.
gemini-2.5-flash-image
Our native image generation model, optimized for speed, flexibility, and contextual understanding. Text input and output is priced the same as 2.5 Flash.
gemini-3-flash-preview
Наша самая интеллектуальная модель, созданная для скорости, сочетает в себе передовые методы разведки с превосходными возможностями поиска и посадки на землю.
gemini-3.1-pro-preview
Our latest SOTA reasoning model with unprecedented depth and nuance, and powerful multimodal understanding and coding capabilities.
gemini-3.1-pro-preview-customtools
Gemini 3.1 Pro Preview optimized for custom tool usage
gemini-3.1-flash-lite
Наша наиболее экономичная модель, оптимизированная для выполнения больших объемов агентских задач, перевода и простой обработки данных.
gemini-3-pro-image
Изображение Gemini 3 Pro
nano-banana-pro-preview
Gemini 3 Pro Image Preview
gemini-3.1-flash-image
Gemini 3.1 Flash Image.
gemini-3.5-flash
Our most intelligent model for sustained frontier performance in agentic and coding tasks.
gemini-3.6-flash
Our most intelligent model for sustained frontier performance in agentic and coding tasks.
gemini-3.7-flash
Our most intelligent model for sustained frontier performance in agentic and coding tasks.
lyria-3-clip-preview
Наша модель генерации музыки с низкой задержкой оптимизирована для высококачественных аудиоклипов и точного контроля ритма.
lyria-3-pro-preview
Our advanced, full-song generative model with deep compositional understanding, optimized for precise structural control and complex transitions across diverse musical styles.
gemini-robotics-er-1.6-preview
Gemini Robotics-ER 1.6 Preview
gemini-robotics-er-2-preview
Gemini Robotics Embodied Reasoning 2 Preview

output_audio AudioContent (optional)

The last audio generated by the model in response to the current request. Note: this is added by the SDK.

Поля

channels integer (optional)

The number of audio channels.

data string (optional)

The audio content.

mime_type enum (string) (optional)

The mime type of the audio.

Возможные значения:

audio/wav
WAV audio format
audio/mp3
MP3 audio format
audio/aiff
AIFF audio format
audio/aac
AAC audio format
audio/ogg
OGG audio format
audio/flac
FLAC audio format
audio/mpeg
MPEG audio format
audio/m4a
M4A audio format
audio/l16
L16 audio format
audio/opus
OPUS audio format
audio/alaw
ALAW audio format
audio/mulaw
MULAW audio format

sample_rate integer (optional)

The sample rate of the audio.

type object (optional)

No description provided.

Always set to "audio" .

uri string (optional)

The URI of the audio.

output_image ImageContent (optional)

The last image generated by the model in response to the current request. Note: this is added by the SDK.

Поля

data string (optional)

The image content.

mime_type enum (string) (optional)

The mime type of the image.

Возможные значения:

image/png
PNG image format
image/jpeg
JPEG image format
image/webp
WebP image format
image/heic
HEIC image format
image/heif
формат изображения HEIF
image/gif
GIF image format
image/bmp
BMP image format
image/tiff
TIFF image format

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (optional)

No description provided.

Always set to "image" .

uri string (optional)

The URI of the image.

output_text string (optional)

Concatenated text from the last model output in response to the current request. Note: this is added by the SDK.

output_video VideoContent (optional)

The last video generated by the model in response to the current request. Note: this is added by the SDK.

Поля

data string (optional)

The video content.

mime_type enum (string) (optional)

The mime type of the video.

Возможные значения:

video/mp4
MP4 video format
video/mpeg
видеоформат MPEG
video/mpg
MPG video format
video/mov
MOV video format
video/avi
AVI video format
video/x-flv
FLV video format
video/webm
WebM video format
video/wmv
WMV video format
video/3gpp
3GPP video format

processing MediaProcessing or enum (string) (optional)

How the model processes this video for understanding.

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (optional)

No description provided.

Always set to "video" .

uri string (optional)

The URI of the video.

previous_interaction_id string (optional)

The ID of the previous interaction, if any.

response_format ResponseFormat or array (ResponseFormat) (optional)

Enforces that the generated response is a JSON object that complies with the JSON schema specified in this field.

Possible Types

AudioResponseFormat

Configuration for audio output format.

bit_rate integer (optional)

Bit rate in bits per second (bps). Only applicable for compressed formats (MP3, Opus).

delivery enum (string) (optional)

The delivery mode for the audio output.

Возможные значения:

inline
Audio data is returned inline in the response.
uri
Audio data is returned as a URI.

mime_type enum (string) (optional)

The MIME type of the audio output.

Возможные значения:

audio/mp3
MP3 audio format.
audio/ogg_opus
OGG Opus audio format.
audio/l16
Raw PCM (L16) audio format.
audio/wav
WAV audio format.
audio/alaw
A-law audio format.
audio/mulaw
Mu-law audio format.

sample_rate integer (optional)

Sample rate in Hz.

type object (required)

No description provided.

Always set to "audio" .

ImageResponseFormat

Configuration for image output format.

aspect_ratio enum (string) (optional)

The aspect ratio for the image output.

Возможные значения:

1:1
Соотношение сторон 1:1.
2:3
2:3 aspect ratio.
3:2
3:2 aspect ratio.
3:4
Соотношение сторон 3:4.
4:3
4:3 aspect ratio.
4:5
4:5 aspect ratio.
5:4
5:4 aspect ratio.
9:16
9:16 aspect ratio.
16:9
Соотношение сторон 16:9.
21:9
21:9 aspect ratio.
1:8
1:8 aspect ratio.
8:1
8:1 aspect ratio.
1:4
1:4 aspect ratio.
4:1
4:1 aspect ratio.

delivery enum (string) (optional)

The delivery mode for the image output.

Возможные значения:

inline
Image data is returned inline in the response.
uri
Image data is returned as a URI.

image_size enum (string) (optional)

The size of the image output.

Возможные значения:

512
512px image size.
1K
1K image size.
2K
2K image size.
4K
4K image size.

mime_type enum (string) (optional)

The MIME type of the image output.

Возможные значения:

image/jpeg
JPEG image format.

type object (required)

No description provided.

Always set to "image" .

TextResponseFormat

Configuration for text output format.

mime_type enum (string) (optional)

The MIME type of the text output.

Возможные значения:

application/json
JSON output format.
text/plain
Plain text output format.

schema object (optional)

The JSON schema that the output should conform to. Only applicable when mime_type is application/json.

type object (required)

No description provided.

Always set to "text" .

VideoResponseFormat

Configuration for video output format.

aspect_ratio enum (string) (optional)

The aspect ratio for the video output.

Возможные значения:

16:9
Соотношение сторон 16:9.
9:16
9:16 aspect ratio.

delivery enum (string) (optional)

The delivery mode for the video output.

Возможные значения:

inline
Video data is returned inline in the response.
uri
Video data is returned as a URI.

duration string (optional)

The duration for the video output.

gcs_uri string (optional)

The Cloud Storage URI to store the video output. Required for Vertex if delivery mode is URI.

resolution enum (string) (optional)

The video output resolution. Defaults to 720p.

Возможные значения:

360p
360p resolution.
720p
720p resolution.
1080p
1080p resolution.
4k
Разрешение 4K.

type object (required)

No description provided.

Always set to "video" .

safety_settings array (SafetySetting) (optional)

Safety settings for the interaction.

Поля

method enum (string) (optional)

Optional. The method for blocking content. If not specified, the default behavior is to use the probability score.

Возможные значения:

severity
The harm block method uses both probability and severity scores.
probability
The harm block method uses the probability score.

threshold enum (string) (optional)

Required. The threshold for blocking content. If the harm probability exceeds this threshold, the content will be blocked.

Возможные значения:

block_low_and_above
Block content with a low harm probability or higher.
block_medium_and_above
Block content with a medium harm probability or higher.
block_only_high
Block content with a high harm probability.
block_none
Do not block any content, regardless of its harm probability.
off
Turn off the safety filter entirely.

type HarmCategory (optional)

Required. The type of harm category to be blocked.

Возможные значения

hate_speech
Content that promotes violence or incites hatred against individuals or groups based on certain attributes.
dangerous_content
Content that promotes, facilitates, or enables dangerous activities.
harassment
Abusive, threatening, or content intended to bully, torment, or ridicule.
sexually_explicit
Content that contains sexually explicit material.
civic_integrity
Deprecated: Election filter is not longer supported. The harm category is civic integrity.
image_hate
Images that contain hate speech.
image_dangerous_content
Images that contain dangerous content.
image_harassment
Images that contain harassment.
image_sexually_explicit
Images that contain sexually explicit content.
jailbreak
Prompts designed to bypass safety filters.

service_tier ServiceTier (optional)

The service tier for the interaction.

Возможные значения

flex
Flex service tier.
standard
Standard service tier.
priority
Priority service tier.
deferred
Deferred service tier.

status enum (string) (optional)

Required. Output only. The status of the interaction.

Возможные значения:

in_progress
The interaction is in progress.
requires_action
The interaction requires action/input from the user.
completed
The interaction is completed.
failed
The interaction failed.
cancelled
The interaction was cancelled.
incomplete
The interaction is completed, but contains incomplete results (eg hitting max_tokens).
budget_exceeded
The interaction was halted because the token budget was exceeded.
queued
The interaction is queued, waiting for processing.

steps array (Step) (optional)

Output only. The steps that make up the interaction, when included in the response.

Possible Types

CodeExecutionCallStep

Code execution call step.

arguments CodeExecutionCallStepArguments (required)

Required. The arguments to pass to the code execution.

Поля

code string (optional)

The code to be executed.

language enum (string) (optional)

Programming language of the `code`.

Возможные значения:

python
Python >= 3.10, with numpy and simpy available.

id string (required)

Required. A unique ID for this specific tool call.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "code_execution_call" .

CodeExecutionResultStep

Code execution result step.

call_id string (required)

Required. ID to match the ID from the function call block.

is_error boolean (optional)

Whether the code execution resulted in an error.

result string (required)

Required. The output of the code execution.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "code_execution_result" .

FileSearchCallStep

File Search call step.

id string (required)

Required. A unique ID for this specific tool call.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "file_search_call" .

FileSearchResultStep

File Search result step.

call_id string (required)

Required. ID to match the ID from the function call block.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "file_search_result" .

FunctionCallStep

A function tool call step.

arguments object (required)

Required. The arguments to pass to the function.

id string (required)

Required. A unique ID for this specific tool call.

name string (required)

Required. The name of the tool to call.

type object (required)

No description provided.

Always set to "function_call" .

FunctionResultStep

Result of a function tool call.

call_id string (required)

Required. ID to match the ID from the function call block.

is_error boolean (optional)

Whether the tool call resulted in an error.

name string (optional)

The name of the tool that was called.

result array (ImageContent or TextContent) or object or string (required)

Required. The result of the tool call.

type object (required)

No description provided.

Always set to "function_result" .

GoogleMapsCallStep

Google Maps call step.

arguments GoogleMapsCallStepArguments (optional)

Аргументы, передаваемые инструменту Google Maps.

Поля

queries array (string) (optional)

The queries to be executed.

id string (required)

Required. A unique ID for this specific tool call.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "google_maps_call" .

GoogleMapsResultStep

Google Maps result step.

call_id string (required)

Required. ID to match the ID from the function call block.

result array (GoogleMapsResultItem) (required)

No description provided.

Поля

places array (GoogleMapsResultPlaces) (optional)

No description provided.

Поля

name string (optional)

No description provided.

place_id string (optional)

No description provided.

review_snippets array (ReviewSnippet) (optional)

No description provided.

Поля

review_id string (optional)

The ID of the review snippet.

title string (optional)

Title of the review.

url string (optional)

A link that corresponds to the user review on Google Maps.

url string (optional)

No description provided.

widget_context_token string (optional)

No description provided.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "google_maps_result" .

GoogleSearchCallStep

Google Search call step.

arguments GoogleSearchCallStepArguments (required)

Required. The arguments to pass to Google Search.

Поля

queries array (string) (optional)

Web search queries for the following-up web search.

id string (required)

Required. A unique ID for this specific tool call.

search_type enum (string) (optional)

The type of search grounding enabled.

Возможные значения:

web_search
Setting this field enables web search. Only text results are returned.
image_search
Setting this field enables image search. Image bytes are returned.
enterprise_web_search
Setting this field enables enterprise web search.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "google_search_call" .

GoogleSearchResultStep

Google Search result step.

call_id string (required)

Required. ID to match the ID from the function call block.

is_error boolean (optional)

Whether the Google Search resulted in an error.

result array (GoogleSearchResultItem) (required)

Required. The results of the Google Search.

Поля

search_suggestions string (optional)

Web content snippet that can be embedded in a web page or an app webview.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "google_search_result" .

McpServerToolCallStep

MCPServer tool call step.

arguments object (required)

Required. The JSON object of arguments for the function.

id string (required)

Required. A unique ID for this specific tool call.

name string (required)

Required. The name of the tool which was called.

server_name string (required)

Required. The name of the used MCP server.

type object (required)

No description provided.

Always set to "mcp_server_tool_call" .

McpServerToolResultStep

MCPServer tool result step.

call_id string (required)

Required. ID to match the ID from the function call block.

name string (optional)

Name of the tool which is called for this specific tool call.

result array (ImageContent or TextContent) or object or string (required)

Required. The output from the MCP server call. Can be simple text or rich content.

server_name string (optional)

The name of the used MCP server.

type object (required)

No description provided.

Always set to "mcp_server_tool_result" .

ModelOutputStep

Output generated by the model.

content array (Content) (optional)

No description provided.

Possible Types

AudioContent

An audio content block.

channels integer (optional)

The number of audio channels.

data string (optional)

The audio content.

mime_type enum (string) (optional)

The mime type of the audio.

Возможные значения:

audio/wav
WAV audio format
audio/mp3
MP3 audio format
audio/aiff
AIFF audio format
audio/aac
AAC audio format
audio/ogg
OGG audio format
audio/flac
FLAC audio format
audio/mpeg
MPEG audio format
audio/m4a
M4A audio format
audio/l16
L16 audio format
audio/opus
OPUS audio format
audio/alaw
ALAW audio format
audio/mulaw
MULAW audio format

sample_rate integer (optional)

The sample rate of the audio.

type object (required)

No description provided.

Always set to "audio" .

uri string (optional)

The URI of the audio.

DocumentContent

A document content block.

data string (optional)

The document content.

mime_type enum (string) (optional)

The mime type of the document.

Возможные значения:

application/pdf
PDF document format
text/csv
CSV document format

type object (required)

No description provided.

Always set to "document" .

uri string (optional)

The URI of the document.

ImageContent

An image content block.

data string (optional)

The image content.

mime_type enum (string) (optional)

The mime type of the image.

Возможные значения:

image/png
PNG image format
image/jpeg
JPEG image format
image/webp
WebP image format
image/heic
HEIC image format
image/heif
формат изображения HEIF
image/gif
GIF image format
image/bmp
BMP image format
image/tiff
TIFF image format

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

No description provided.

Always set to "image" .

uri string (optional)

The URI of the image.

TextContent

A text content block.

annotations array (Annotation) (optional)

Информация об источниках для контента, сгенерированного моделью.

Possible Types

FileCitation

A file citation annotation.

custom_metadata object (optional)

User provided metadata about the retrieved context.

document_uri string (optional)

The URI of the file.

end_index integer (optional)

End of the attributed segment, exclusive.

file_name string (optional)

The name of the file.

media_id string (optional)

Media ID in-case of image citations, if applicable.

page_number integer (optional)

Page number of the cited document, if applicable.

source string (optional)

Source attributed for a portion of the text.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "file_citation" .

PlaceCitation

A place citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

name string (optional)

Title of the place.

place_id string (optional)

The ID of the place, in `places/{place_id}` format.

review_snippets array (ReviewSnippet) (optional)

Snippets of reviews that are used to generate answers about the features of a given place in Google Maps.

Поля

review_id string (optional)

The ID of the review snippet.

title string (optional)

Title of the review.

url string (optional)

A link that corresponds to the user review on Google Maps.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "place_citation" .

url string (optional)

URI reference of the place.

UrlCitation

A URL citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

title string (optional)

The title of the URL.

type object (required)

No description provided.

Always set to "url_citation" .

url string (optional)

The URL.

WordInfo

Word-level ASR annotation for transcription output. Carries the word text, optional timing, and optional speaker attribution.

end_index integer (optional)

End of the attributed segment, exclusive.

end_offset string (optional)

End offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

speaker string (optional)

Optional. Speaker label for this word (eg "spk_1", "spk_2"). Present when diarization_mode is set in TranscriptionConfig.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

start_offset string (optional)

Start offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

text string (optional)

The transcribed word.

type object (required)

No description provided.

Always set to "word_info" .

text string (required)

Required. The text content.

type object (required)

No description provided.

Always set to "text" .

VideoContent

A video content block.

data string (optional)

The video content.

mime_type enum (string) (optional)

The mime type of the video.

Возможные значения:

video/mp4
MP4 video format
video/mpeg
видеоформат MPEG
video/mpg
MPG video format
video/mov
MOV video format
video/avi
AVI video format
video/x-flv
FLV video format
video/webm
WebM video format
video/wmv
WMV video format
video/3gpp
3GPP video format

processing MediaProcessing or enum (string) (optional)

How the model processes this video for understanding.

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

No description provided.

Always set to "video" .

uri string (optional)

The URI of the video.

type object (required)

No description provided.

Always set to "model_output" .

ThoughtStep

A thought step.

signature string (optional)

A signature hash for backend validation.

summary array (ThoughtSummaryContent) (optional)

A summary of the thought.

Possible Types

ImageContent

An image content block.

data string (optional)

The image content.

mime_type enum (string) (optional)

The mime type of the image.

Возможные значения:

image/png
PNG image format
image/jpeg
JPEG image format
image/webp
WebP image format
image/heic
HEIC image format
image/heif
формат изображения HEIF
image/gif
GIF image format
image/bmp
BMP image format
image/tiff
TIFF image format

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

No description provided.

Always set to "image" .

uri string (optional)

The URI of the image.

TextContent

A text content block.

annotations array (Annotation) (optional)

Информация об источниках для контента, сгенерированного моделью.

Possible Types

FileCitation

A file citation annotation.

custom_metadata object (optional)

User provided metadata about the retrieved context.

document_uri string (optional)

The URI of the file.

end_index integer (optional)

End of the attributed segment, exclusive.

file_name string (optional)

The name of the file.

media_id string (optional)

Media ID in-case of image citations, if applicable.

page_number integer (optional)

Page number of the cited document, if applicable.

source string (optional)

Source attributed for a portion of the text.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "file_citation" .

PlaceCitation

A place citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

name string (optional)

Title of the place.

place_id string (optional)

The ID of the place, in `places/{place_id}` format.

review_snippets array (ReviewSnippet) (optional)

Snippets of reviews that are used to generate answers about the features of a given place in Google Maps.

Поля

review_id string (optional)

The ID of the review snippet.

title string (optional)

Title of the review.

url string (optional)

A link that corresponds to the user review on Google Maps.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "place_citation" .

url string (optional)

URI reference of the place.

UrlCitation

A URL citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

title string (optional)

The title of the URL.

type object (required)

No description provided.

Always set to "url_citation" .

url string (optional)

The URL.

WordInfo

Word-level ASR annotation for transcription output. Carries the word text, optional timing, and optional speaker attribution.

end_index integer (optional)

End of the attributed segment, exclusive.

end_offset string (optional)

End offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

speaker string (optional)

Optional. Speaker label for this word (eg "spk_1", "spk_2"). Present when diarization_mode is set in TranscriptionConfig.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

start_offset string (optional)

Start offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

text string (optional)

The transcribed word.

type object (required)

No description provided.

Always set to "word_info" .

text string (required)

Required. The text content.

type object (required)

No description provided.

Always set to "text" .

type object (required)

No description provided.

Always set to "thought" .

UrlContextCallStep

URL context call step.

arguments UrlContextCallArguments (required)

Required. The arguments to pass to the URL context.

Поля

urls array (string) (optional)

The URLs to fetch.

id string (required)

Required. A unique ID for this specific tool call.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "url_context_call" .

UrlContextResultStep

URL context result step.

call_id string (required)

Required. ID to match the ID from the function call block.

is_error boolean (optional)

Whether the URL context resulted in an error.

result array (UrlContextResult) (required)

Required. The results of the URL context.

Поля

status enum (string) (optional)

The status of the URL retrieval.

Возможные значения:

success
Url retrieval is successful.
error
Url retrieval is failed due to error.
paywall
Url retrieval is failed because the content is behind paywall.
unsafe
Url retrieval is failed because the content is unsafe.

url string (optional)

The URL that was fetched.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "url_context_result" .

UserInputStep

Input provided by the user.

content array (Content) (optional)

No description provided.

Possible Types

AudioContent

An audio content block.

channels integer (optional)

The number of audio channels.

data string (optional)

The audio content.

mime_type enum (string) (optional)

The mime type of the audio.

Возможные значения:

audio/wav
WAV audio format
audio/mp3
MP3 audio format
audio/aiff
AIFF audio format
audio/aac
AAC audio format
audio/ogg
OGG audio format
audio/flac
FLAC audio format
audio/mpeg
MPEG audio format
audio/m4a
M4A audio format
audio/l16
L16 audio format
audio/opus
OPUS audio format
audio/alaw
ALAW audio format
audio/mulaw
MULAW audio format

sample_rate integer (optional)

The sample rate of the audio.

type object (required)

No description provided.

Always set to "audio" .

uri string (optional)

The URI of the audio.

DocumentContent

A document content block.

data string (optional)

The document content.

mime_type enum (string) (optional)

The mime type of the document.

Возможные значения:

application/pdf
PDF document format
text/csv
CSV document format

type object (required)

No description provided.

Always set to "document" .

uri string (optional)

The URI of the document.

ImageContent

An image content block.

data string (optional)

The image content.

mime_type enum (string) (optional)

The mime type of the image.

Возможные значения:

image/png
PNG image format
image/jpeg
JPEG image format
image/webp
WebP image format
image/heic
HEIC image format
image/heif
формат изображения HEIF
image/gif
GIF image format
image/bmp
BMP image format
image/tiff
TIFF image format

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

No description provided.

Always set to "image" .

uri string (optional)

The URI of the image.

TextContent

A text content block.

annotations array (Annotation) (optional)

Информация об источниках для контента, сгенерированного моделью.

Possible Types

FileCitation

A file citation annotation.

custom_metadata object (optional)

User provided metadata about the retrieved context.

document_uri string (optional)

The URI of the file.

end_index integer (optional)

End of the attributed segment, exclusive.

file_name string (optional)

The name of the file.

media_id string (optional)

Media ID in-case of image citations, if applicable.

page_number integer (optional)

Page number of the cited document, if applicable.

source string (optional)

Source attributed for a portion of the text.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "file_citation" .

PlaceCitation

A place citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

name string (optional)

Title of the place.

place_id string (optional)

The ID of the place, in `places/{place_id}` format.

review_snippets array (ReviewSnippet) (optional)

Snippets of reviews that are used to generate answers about the features of a given place in Google Maps.

Поля

review_id string (optional)

The ID of the review snippet.

title string (optional)

Title of the review.

url string (optional)

A link that corresponds to the user review on Google Maps.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "place_citation" .

url string (optional)

URI reference of the place.

UrlCitation

A URL citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

title string (optional)

The title of the URL.

type object (required)

No description provided.

Always set to "url_citation" .

url string (optional)

The URL.

WordInfo

Word-level ASR annotation for transcription output. Carries the word text, optional timing, and optional speaker attribution.

end_index integer (optional)

End of the attributed segment, exclusive.

end_offset string (optional)

End offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

speaker string (optional)

Optional. Speaker label for this word (eg "spk_1", "spk_2"). Present when diarization_mode is set in TranscriptionConfig.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

start_offset string (optional)

Start offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

text string (optional)

The transcribed word.

type object (required)

No description provided.

Always set to "word_info" .

text string (required)

Required. The text content.

type object (required)

No description provided.

Always set to "text" .

VideoContent

A video content block.

data string (optional)

The video content.

mime_type enum (string) (optional)

The mime type of the video.

Возможные значения:

video/mp4
MP4 video format
video/mpeg
видеоформат MPEG
video/mpg
MPG video format
video/mov
MOV video format
video/avi
AVI video format
video/x-flv
FLV video format
video/webm
WebM video format
video/wmv
WMV video format
video/3gpp
3GPP video format

processing MediaProcessing or enum (string) (optional)

How the model processes this video for understanding.

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

No description provided.

Always set to "video" .

uri string (optional)

The URI of the video.

type object (required)

No description provided.

Always set to "user_input" .

system_instruction string (optional)

System instruction for the interaction.

tools array (Tool) (optional)

A list of tool declarations the model may call during interaction.

Possible Types

CodeExecution

A tool that can be used by the model to execute code.

type object (required)

No description provided.

Always set to "code_execution" .

ComputerUse

A tool that can be used by the model to interact with the computer.

disabled_safety_policies array (enum (string)) (optional)

Optional. Disabled safety policies for computer use.

Возможные значения:

financial_transactions
Safety policy for financial transactions.
sensitive_data_modification
Safety policy for sensitive data modification.
communication_tool
Safety policy for communication tools (eg Gmail, Chat, Meet).
account_creation
Safety policy for account creation.
data_modification
Safety policy for data modification.
user_consent_management
Safety policy for user consent management.
legal_terms_and_agreements
Safety policy for legal terms and agreements.

enable_prompt_injection_detection boolean (optional)

Whether enable the prompt injection detection check on computer-use request.

environment enum (string) (optional)

The environment being operated.

Возможные значения:

browser
Operates in a web browser.
mobile
Operates in a mobile environment.
desktop
Operates in a desktop environment.

excluded_predefined_functions array (string) (optional)

The list of predefined functions that are excluded from the model call.

type object (required)

No description provided.

Always set to "computer_use" .

Поиск файлов

A tool that can be used by the model to search files.

file_search_store_names array (string) (optional)

The file search store names to search.

metadata_filter string (optional)

Metadata filter to apply to the semantic retrieval documents and chunks.

top_k integer (optional)

The number of semantic retrieval chunks to retrieve.

type object (required)

No description provided.

Always set to "file_search" .

Функция

Инструмент, который может быть использован моделью.

description string (optional)

A description of the function.

name string (optional)

The name of the function.

parameters object (optional)

The JSON Schema for the function's parameters.

type object (required)

No description provided.

Always set to "function" .

Google Карты

A tool that can be used by the model to call Google Maps.

enable_widget boolean (optional)

Whether to return a widget context token in the tool call result of the response.

latitude number (optional)

The latitude of the user's location.

longitude number (optional)

The longitude of the user's location.

type object (required)

No description provided.

Always set to "google_maps" .

GoogleSearch

A tool that can be used by the model to search Google.

search_types array (enum (string)) (optional)

The types of search grounding to enable.

Возможные значения:

web_search
Setting this field enables web search. Only text results are returned.
image_search
Setting this field enables image search. Image bytes are returned.
enterprise_web_search
Setting this field enables enterprise web search.

type object (required)

No description provided.

Always set to "google_search" .

McpServer

A MCPServer is a server that can be called by the model to perform actions.

allowed_tools array (AllowedTools) (optional)

The allowed tools.

Поля

mode enum (string) (optional)

The mode of the tool choice.

Возможные значения:

auto
Auto tool choice.
any
Any tool choice.
none
No tool choice.
validated
Validated tool choice.

tools array (string) (optional)

The names of the allowed tools.

headers object (optional)

Optional: Fields for authentication headers, timeouts, etc., if needed.

name string (optional)

The name of the MCPServer.

type object (required)

No description provided.

Always set to "mcp_server" .

url string (optional)

The full URL for the MCPServer endpoint. Example: "https://api.example.com/mcp"

Извлечение

A tool that can be used by the model to retrieve files.

exa_ai_search_config ExaAISearchConfig (optional)

Used to specify configuration for ExaAISearch.

Поля

api_key string (optional)

Required. The API key for ExaAiSearch.

custom_config object (optional)

Optional. This field can be used to pass any parameter from the Exa.ai Search API.

parallel_ai_search_config ParallelAISearchConfig (optional)

Used to specify configuration for ParallelAISearch.

Поля

api_key string (optional)

Optional. The API key for ParallelAiSearch.

custom_config object (optional)

Optional. Custom configs for ParallelAiSearch.

rag_store_config RagStoreConfig (optional)

Used to specify configuration for RagStore.

Поля

rag_resources array (RagResource) (optional)

Optional. The representation of the rag source.

Поля

rag_corpus string (optional)

Optional. RagCorpora resource name.

rag_file_ids array (string) (optional)

Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field.

rag_retrieval_config RagRetrievalConfig (optional)

Optional. The retrieval config for the Rag query.

Поля

filter Filter (optional)

Optional. Config for filters.

Поля

metadata_filter string (optional)

Optional. String for metadata filtering.

vector_distance_threshold number (optional)

Optional. Only returns contexts with vector distance smaller than the threshold.

vector_similarity_threshold number (optional)

Optional. Only returns contexts with vector similarity larger than the threshold.

hybrid_search HybridSearch (optional)

Optional. Config for Hybrid Search.

Поля

alpha number (optional)

Optional. Alpha value controls the weight between dense and sparse vector search results.

ranking Ranking (optional)

Optional. Config for ranking and reranking.

top_k integer (optional)

Optional. The number of contexts to retrieve.

retrieval_types array (enum (string)) (optional)

The types of file retrieval to enable.

Возможные значения:

rag_store
exa_ai_search
parallel_ai_search

type object (required)

No description provided.

Always set to "retrieval" .

UrlContext

A tool that can be used by the model to fetch URL context.

type object (required)

No description provided.

Always set to "url_context" .

updated string (optional)

Output only. The time at which the response was last updated in ISO 8601 format (YYYY-MM-DDThh:mm:ssZ).

usage Usage (optional)

Output only. Statistics on the interaction request's token usage.

Поля

cached_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of cached token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

grounding_tool_count array (GroundingToolCount) (optional)

Grounding tool count.

Поля

count integer (optional)

Количество заземляющих инструментов подсчитывается.

type enum (string) (optional)

The grounding tool type associated with the count.

Возможные значения:

google_search
Grounding with Google Web Search and Image Search, & Web Grounding for Enterprise.
google_maps
Grounding with Google Maps.
retrieval
Grounding with customer's data, for example, VertexAISearch.

input_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of input token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

output_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of output token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

tool_use_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of tool-use token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

total_cached_tokens integer (optional)

Number of tokens in the cached part of the prompt (the cached content).

total_input_tokens integer (optional)

Number of tokens in the prompt (context).

total_output_tokens integer (optional)

Total number of tokens across all the generated responses.

total_thought_tokens integer (optional)

Number of tokens of thoughts for thinking models.

total_tokens integer (optional)

Total token count for the interaction request (prompt + responses + other internal tokens).

total_tool_use_tokens integer (optional)

Number of tokens present in tool-use prompt(s).

webhook_config WebhookConfig (optional)

Optional. Webhook configuration for receiving notifications when the interaction completes.

Поля

uris array (string) (optional)

Optional. If set, these webhook URIs will be used for webhook events instead of the registered webhooks.

user_metadata object (optional)

Optional. The user metadata that will be returned on each event emission to the webhooks.

last_pause_time string (optional)

Output only. The time when the trigger was last paused.

last_resume_time string (optional)

Output only. The time when the trigger was last resumed.

last_run_time string (optional)

Output only. The time when the trigger was last run.

max_consecutive_failures integer (optional)

Optional. The maximum number of consecutive failures allowed before the trigger is automatically paused (status becomes ERROR).

next_run_time string (optional)

Output only. The time when the trigger is scheduled to run next.

previous_interaction_id string (optional)

Output only. The ID of the last interaction created by this trigger.

schedule string (optional)

Required. The cron schedule on which the trigger should run. Standard cron format.

status enum (string) (optional)

Output only. The current status of the trigger.

Possible values:

active
The trigger is active and will fire on schedule.
paused
The trigger is paused and will not fire.
error
The trigger has entered an error state due to consecutive failures.

time_zone string (optional)

Required. Time zone in which the schedule should be interpreted.

update_time string (optional)

Output only. The time when the trigger was last updated.

Пример

Пример ответа

{
  "consecutive_failure_count": 0,
  "create_time": "string",
  "display_name": "string",
  "environment_id": "string",
  "execution_timeout_seconds": 0,
  "id": "string",
  "interaction": {
    "created": "2025-12-04T15:01:45Z",
    "id": "v1_ChdXS0l4YWZXTk9xbk0xZThQczhEcmlROBIXV0tJeGFmV05PcW5NMWU4UHM4RHJpUTg",
    "model": "gemini-3.6-flash",
    "object": "interaction",
    "status": "completed",
    "steps": [
      {
        "type": "model_output",
        "content": [
          {
            "type": "text",
            "text": "Hello! I'm doing well, functioning as expected. Thank you for asking! How are you doing today?"
          }
        ]
      }
    ],
    "updated": "2025-12-04T15:01:45Z",
    "usage": {
      "input_tokens_by_modality": [
        {
          "modality": "text",
          "tokens": 7
        }
      ],
      "total_cached_tokens": 0,
      "total_input_tokens": 7,
      "total_output_tokens": 23,
      "total_thought_tokens": 49,
      "total_tokens": 79,
      "total_tool_use_tokens": 0
    }
  },
  "last_pause_time": "string",
  "last_resume_time": "string",
  "last_run_time": "string",
  "max_consecutive_failures": 0,
  "next_run_time": "string",
  "previous_interaction_id": "string",
  "schedule": "string",
  "status": "active",
  "time_zone": "string",
  "update_time": "string"
}

DeleteTrigger

delete https://generativelanguage.googleapis.com/v1beta/triggers/{id}

Deletes a trigger.

Ответ

Ответ

If successful, the response is empty.

Пример

Ресурсы

Курок

A trigger configuration that is scheduled to run an agent.

Поля

consecutive_failure_count integer (optional)

Output only. The number of consecutive failures that have occurred since the last successful execution.

create_time string (optional)

Output only. The time when the trigger was created.

display_name string (optional)

Optional. The display name of the trigger.

environment_id string (optional)

Optional. The environment ID for the trigger execution.

execution_timeout_seconds integer (optional)

Optional. The execution timeout for the triggered interaction.

id string (optional)

Required. Output only. Identifier. The ID of the trigger.

interaction Interaction (optional)

Required. The interaction request template to be executed.

Поля

agent AgentOption (optional)

The name of the `Agent` used for generating the interaction.

Возможные значения

deep-research-pro-preview-12-2025
Gemini Deep Research Agent
deep-research-preview-04-2026
Gemini Deep Research Agent
deep-research-max-preview-04-2026
Gemini Deep Research Max Agent
antigravity-preview-05-2026
Use the Antigravity managed agent to perform multi-step tasks that require reasoning, file operations, and tool use.

agent_config object (optional)

Configuration parameters for the agent interaction.

Possible Types

Polymorphic discriminator: type

AntigravityAgentConfig

Configuration for the Antigravity agent runtime. Provides server-side control over the agent's execution environment and tool configuration.

max_total_tokens string (optional)

Max total tokens for the agent run.

model string (optional)

The model to use for agent reasoning.

type object (required)

No description provided.

Always set to "antigravity" .

CodeMenderAgentConfig

Configuration for the CodeMender agent.

find_request FindRequest (optional)

Parameters for finding vulnerabilities.

Поля

description string (optional)

Additional context or custom instructions provided by the user to guide the vulnerability analysis.

finding_id string (optional)

The identifier of a specific finding to verify. This is primarily used in VERIFY mode to focus the agent's execution-based validation on a single vulnerability.

mode enum (string) (optional)

The mode of the find session.

Possible values:

scan
Fast scan using only the initial classifier.
verify
Performs classification followed by detailed investigation.

source_files array (FileContent) (optional)

A list of source files to provide as context for the scan.

Поля

content string (optional)

The UTF-8 encoded text content of the file.

path string (optional)

The relative path of the file from the project root.

fix_request FixRequest (optional)

Parameters for fixing vulnerabilities.

Поля

description string (optional)

Additional context or custom instructions provided by the user to guide the patch generation process.

finding_id string (optional)

The identifier of the specific security finding to be remediated. This ID maps to a previously discovered vulnerability.

source_files array (FileContent) (optional)

A list of source files providing context for the remediation. These files are typically the ones containing the identified vulnerability.

Поля

content string (optional)

The UTF-8 encoded text content of the file.

path string (optional)

The relative path of the file from the project root.

model string (optional)

The name of the model to use for the CodeMender agent. One CodeMender session will only use one model.

session_config SessionConfig (optional)

Optional session-specific configurations to override default agent behavior.

Поля

max_rounds integer (optional)

The maximum number of interaction rounds the agent is allowed to perform before reaching a timeout.

session_id string (optional)

Parameter for grouping multiple interactions that belong to the same CodeMender session.

type object (required)

No description provided.

Always set to "code-mender" .

DeepResearchAgentConfig

Configuration for the Deep Research agent.

collaborative_planning boolean (optional)

enable_bigquery_tool boolean (optional)

Enables bigquery tool for the Deep Research agent.

thinking_summaries ThinkingSummaries (optional)

Whether to include thought summaries in the response.

Возможные значения

auto
Auto thinking summaries.
none
No thinking summaries.

type object (required)

No description provided.

Always set to "deep-research" .

visualization enum (string) (optional)

Whether to include visualizations in the response.

Возможные значения:

off
Do not include visualizations.
auto
Automatically include visualizations.

DynamicAgentConfig

Configuration for dynamic agents.

type object (required)

No description provided.

Always set to "dynamic" .

created string (optional)

Output only. The time at which the response was created in ISO 8601 format (YYYY-MM-DDThh:mm:ssZ).

environment EnvironmentConfig or string (optional)

The environment configuration for the interaction. Can be an object specifying remote environment sources or a string referencing an existing environment ID.

Поля

environment_id string (optional)

Optional. The environment ID for the interaction. If specified, the request will update the existing environment instead of creating a new one.

network EnvironmentNetworkEgressAllowlist or enum (string) (optional)

Network configuration for the environment.

Possible Types

объект

Outbound networking configuration for the sandbox. When specified, restricts which external domains the sandbox can reach. Omit entirely to allow all outbound traffic with no header injection.

allowlist array (AllowlistEntry) (optional)

List of allowed outbound domains. Only requests to listed domains are permitted. Use [{'domain': '*'}] to allow all domains while still injecting headers on specific ones.

Поля

domain string (optional)

Domain to allow outbound requests to. Supports wildcards (eg '*.googleapis.com'). Use '*' to allow all domains.

transform array (object) or object (optional)

Headers to inject on all outbound requests matching this domain. Accepts a single dict or a list of dicts. The egress proxy injects these automatically.

нить

Turns all network off.

Возможные значения

disabled
Turns all network off.

sources array (Source) (optional)

No description provided.

Поля

content string (optional)

The inline content if `type` is `INLINE`.

encoding string (optional)

Optional encoding for inline content (eg `base64`).

source string (optional)

The source of the environment. For Cloud Storage, this is the Cloud Storage path. For GitHub, this is the GitHub path.

target string (optional)

Where the source should appear in the environment.

type enum (string) (optional)

No description provided.

Possible values:

gcs
A Cloud Storage bucket.
inline
Inline content.
repository
A generic repository. The protocol prefix in the source URL identifies the provider (eg, github://, gcs://).
skill_registry
A skill resource from the Skill Registry Service. Skill: projects/{project}/locations/{location}/skills/{skill} SkillRevision: projects/{project}/locations/{location}/skills/{skill}/revisions/{revision} Support mounting all skills under a project: projects/{project}/locations/{location}/skills.

type object (optional)

No description provided.

Always set to "remote" .

environment_id string (optional)

Output only. The environment ID for the interaction. Only populated if environment config is set in the request.

errors array (Error) (optional)

Output only. Diagnostic faults / platform errors recorded on the interaction.

Поля

code string (optional)

A URI that identifies the error type.

message string (optional)

A human-readable error message.

id string (optional)

Required. Output only. A unique identifier for the interaction completion.

Defaults to:

input Content or array (Content) or array (Step) or string (optional)

The input for the interaction.

labels object (optional)

The labels with user-defined metadata for the request.

model ModelOption (optional)

The name of the `Model` used for generating the interaction.

Возможные значения

gemini-2.5-flash
Наша первая гибридная модель рассуждений, поддерживающая контекстное окно в 1 миллион токенов и имеющая бюджеты мышления.
gemini-2.5-pro
Our state-of-the-art multipurpose model, which excels at coding and complex reasoning tasks.
gemma-4-26b-a4b-it
Джемма 4 26B A4B IT
gemma-4-31b-it
Gemma 4 31B IT
gemini-flash-latest
Latest release of Gemini Flash
gemini-flash-lite-latest
Latest release of Gemini Flash-Lite
gemini-pro-latest
Latest release of Gemini Pro
gemini-2.5-flash-lite
Наша самая компактная и экономичная модель, предназначенная для масштабного использования.
gemini-2.5-flash-image
Our native image generation model, optimized for speed, flexibility, and contextual understanding. Text input and output is priced the same as 2.5 Flash.
gemini-3-flash-preview
Наша самая интеллектуальная модель, созданная для скорости, сочетает в себе передовые методы разведки с превосходными возможностями поиска и посадки на землю.
gemini-3.1-pro-preview
Our latest SOTA reasoning model with unprecedented depth and nuance, and powerful multimodal understanding and coding capabilities.
gemini-3.1-pro-preview-customtools
Gemini 3.1 Pro Preview optimized for custom tool usage
gemini-3.1-flash-lite
Наша наиболее экономичная модель, оптимизированная для выполнения больших объемов агентских задач, перевода и простой обработки данных.
gemini-3-pro-image
Изображение Gemini 3 Pro
nano-banana-pro-preview
Gemini 3 Pro Image Preview
gemini-3.1-flash-image
Gemini 3.1 Flash Image.
gemini-3.5-flash
Our most intelligent model for sustained frontier performance in agentic and coding tasks.
gemini-3.6-flash
Our most intelligent model for sustained frontier performance in agentic and coding tasks.
gemini-3.7-flash
Our most intelligent model for sustained frontier performance in agentic and coding tasks.
lyria-3-clip-preview
Наша модель генерации музыки с низкой задержкой оптимизирована для высококачественных аудиоклипов и точного контроля ритма.
lyria-3-pro-preview
Our advanced, full-song generative model with deep compositional understanding, optimized for precise structural control and complex transitions across diverse musical styles.
gemini-robotics-er-1.6-preview
Gemini Robotics-ER 1.6 Preview
gemini-robotics-er-2-preview
Gemini Robotics Embodied Reasoning 2 Preview

output_audio AudioContent (optional)

The last audio generated by the model in response to the current request. Note: this is added by the SDK.

Поля

channels integer (optional)

The number of audio channels.

data string (optional)

The audio content.

mime_type enum (string) (optional)

The mime type of the audio.

Possible values:

audio/wav
WAV audio format
audio/mp3
MP3 audio format
audio/aiff
AIFF audio format
audio/aac
AAC audio format
audio/ogg
OGG audio format
audio/flac
FLAC audio format
audio/mpeg
MPEG audio format
audio/m4a
M4A audio format
audio/l16
L16 audio format
audio/opus
OPUS audio format
audio/alaw
ALAW audio format
audio/mulaw
MULAW audio format

sample_rate integer (optional)

The sample rate of the audio.

type object (optional)

No description provided.

Always set to "audio" .

uri string (optional)

The URI of the audio.

output_image ImageContent (optional)

The last image generated by the model in response to the current request. Note: this is added by the SDK.

Поля

data string (optional)

The image content.

mime_type enum (string) (optional)

The mime type of the image.

Possible values:

image/png
PNG image format
image/jpeg
JPEG image format
image/webp
WebP image format
image/heic
HEIC image format
image/heif
HEIF image format
image/gif
GIF image format
image/bmp
BMP image format
image/tiff
TIFF image format

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (optional)

No description provided.

Always set to "image" .

uri string (optional)

The URI of the image.

output_text string (optional)

Concatenated text from the last model output in response to the current request. Note: this is added by the SDK.

output_video VideoContent (optional)

The last video generated by the model in response to the current request. Note: this is added by the SDK.

Поля

data string (optional)

The video content.

mime_type enum (string) (optional)

The mime type of the video.

Possible values:

video/mp4
MP4 video format
video/mpeg
видеоформат MPEG
video/mpg
MPG video format
video/mov
MOV video format
video/avi
AVI video format
video/x-flv
FLV video format
video/webm
WebM video format
video/wmv
WMV video format
video/3gpp
3GPP video format

processing MediaProcessing or enum (string) (optional)

How the model processes this video for understanding.

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (optional)

No description provided.

Always set to "video" .

uri string (optional)

The URI of the video.

previous_interaction_id string (optional)

The ID of the previous interaction, if any.

response_format ResponseFormat or array (ResponseFormat) (optional)

Enforces that the generated response is a JSON object that complies with the JSON schema specified in this field.

Possible Types

AudioResponseFormat

Configuration for audio output format.

bit_rate integer (optional)

Bit rate in bits per second (bps). Only applicable for compressed formats (MP3, Opus).

delivery enum (string) (optional)

The delivery mode for the audio output.

Possible values:

inline
Audio data is returned inline in the response.
uri
Audio data is returned as a URI.

mime_type enum (string) (optional)

The MIME type of the audio output.

Possible values:

audio/mp3
MP3 audio format.
audio/ogg_opus
OGG Opus audio format.
audio/l16
Raw PCM (L16) audio format.
audio/wav
WAV audio format.
audio/alaw
A-law audio format.
audio/mulaw
Mu-law audio format.

sample_rate integer (optional)

Sample rate in Hz.

type object (required)

No description provided.

Always set to "audio" .

ImageResponseFormat

Configuration for image output format.

aspect_ratio enum (string) (optional)

The aspect ratio for the image output.

Possible values:

1:1
Соотношение сторон 1:1.
2:3
2:3 aspect ratio.
3:2
3:2 aspect ratio.
3:4
Соотношение сторон 3:4.
4:3
4:3 aspect ratio.
4:5
4:5 aspect ratio.
5:4
5:4 aspect ratio.
9:16
9:16 aspect ratio.
16:9
Соотношение сторон 16:9.
21:9
21:9 aspect ratio.
1:8
1:8 aspect ratio.
8:1
8:1 aspect ratio.
1:4
1:4 aspect ratio.
4:1
4:1 aspect ratio.

delivery enum (string) (optional)

The delivery mode for the image output.

Possible values:

inline
Image data is returned inline in the response.
uri
Image data is returned as a URI.

image_size enum (string) (optional)

The size of the image output.

Possible values:

512
512px image size.
1K
1K image size.
2K
2K image size.
4K
4K image size.

mime_type enum (string) (optional)

The MIME type of the image output.

Possible values:

image/jpeg
JPEG image format.

type object (required)

No description provided.

Always set to "image" .

TextResponseFormat

Configuration for text output format.

mime_type enum (string) (optional)

The MIME type of the text output.

Possible values:

application/json
JSON output format.
text/plain
Plain text output format.

schema object (optional)

The JSON schema that the output should conform to. Only applicable when mime_type is application/json.

type object (required)

No description provided.

Always set to "text" .

VideoResponseFormat

Configuration for video output format.

aspect_ratio enum (string) (optional)

The aspect ratio for the video output.

Possible values:

16:9
Соотношение сторон 16:9.
9:16
9:16 aspect ratio.

delivery enum (string) (optional)

The delivery mode for the video output.

Possible values:

inline
Video data is returned inline in the response.
uri
Video data is returned as a URI.

duration string (optional)

The duration for the video output.

gcs_uri string (optional)

The Cloud Storage URI to store the video output. Required for Vertex if delivery mode is URI.

resolution enum (string) (optional)

The video output resolution. Defaults to 720p.

Possible values:

360p
360p resolution.
720p
720p resolution.
1080p
1080p resolution.
4k
Разрешение 4K.

type object (required)

No description provided.

Always set to "video" .

safety_settings array (SafetySetting) (optional)

Safety settings for the interaction.

Поля

method enum (string) (optional)

Optional. The method for blocking content. If not specified, the default behavior is to use the probability score.

Possible values:

severity
The harm block method uses both probability and severity scores.
probability
The harm block method uses the probability score.

threshold enum (string) (optional)

Required. The threshold for blocking content. If the harm probability exceeds this threshold, the content will be blocked.

Possible values:

block_low_and_above
Block content with a low harm probability or higher.
block_medium_and_above
Block content with a medium harm probability or higher.
block_only_high
Block content with a high harm probability.
block_none
Do not block any content, regardless of its harm probability.
off
Turn off the safety filter entirely.

type HarmCategory (optional)

Required. The type of harm category to be blocked.

Возможные значения

hate_speech
Content that promotes violence or incites hatred against individuals or groups based on certain attributes.
dangerous_content
Content that promotes, facilitates, or enables dangerous activities.
harassment
Abusive, threatening, or content intended to bully, torment, or ridicule.
sexually_explicit
Content that contains sexually explicit material.
civic_integrity
Deprecated: Election filter is not longer supported. The harm category is civic integrity.
image_hate
Images that contain hate speech.
image_dangerous_content
Images that contain dangerous content.
image_harassment
Images that contain harassment.
image_sexually_explicit
Images that contain sexually explicit content.
jailbreak
Prompts designed to bypass safety filters.

service_tier ServiceTier (optional)

The service tier for the interaction.

Возможные значения

flex
Flex service tier.
standard
Standard service tier.
priority
Priority service tier.
deferred
Deferred service tier.

status enum (string) (optional)

Required. Output only. The status of the interaction.

Possible values:

in_progress
The interaction is in progress.
requires_action
The interaction requires action/input from the user.
completed
The interaction is completed.
failed
The interaction failed.
cancelled
The interaction was cancelled.
incomplete
The interaction is completed, but contains incomplete results (eg hitting max_tokens).
budget_exceeded
The interaction was halted because the token budget was exceeded.
queued
The interaction is queued, waiting for processing.

steps array (Step) (optional)

Output only. The steps that make up the interaction, when included in the response.

Possible Types

CodeExecutionCallStep

Code execution call step.

arguments CodeExecutionCallStepArguments (required)

Required. The arguments to pass to the code execution.

Поля

code string (optional)

The code to be executed.

language enum (string) (optional)

Programming language of the `code`.

Possible values:

python
Python >= 3.10, with numpy and simpy available.

id string (required)

Required. A unique ID for this specific tool call.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "code_execution_call" .

CodeExecutionResultStep

Code execution result step.

call_id string (required)

Required. ID to match the ID from the function call block.

is_error boolean (optional)

Whether the code execution resulted in an error.

result string (required)

Required. The output of the code execution.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "code_execution_result" .

FileSearchCallStep

File Search call step.

id string (required)

Required. A unique ID for this specific tool call.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "file_search_call" .

FileSearchResultStep

File Search result step.

call_id string (required)

Required. ID to match the ID from the function call block.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "file_search_result" .

FunctionCallStep

A function tool call step.

arguments object (required)

Required. The arguments to pass to the function.

id string (required)

Required. A unique ID for this specific tool call.

name string (required)

Required. The name of the tool to call.

type object (required)

No description provided.

Always set to "function_call" .

FunctionResultStep

Result of a function tool call.

call_id string (required)

Required. ID to match the ID from the function call block.

is_error boolean (optional)

Whether the tool call resulted in an error.

name string (optional)

The name of the tool that was called.

result array (ImageContent or TextContent) or object or string (required)

Required. The result of the tool call.

type object (required)

No description provided.

Always set to "function_result" .

GoogleMapsCallStep

Google Maps call step.

arguments GoogleMapsCallStepArguments (optional)

Аргументы, передаваемые инструменту Google Maps.

Поля

queries array (string) (optional)

The queries to be executed.

id string (required)

Required. A unique ID for this specific tool call.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "google_maps_call" .

GoogleMapsResultStep

Google Maps result step.

call_id string (required)

Required. ID to match the ID from the function call block.

result array (GoogleMapsResultItem) (required)

No description provided.

Поля

places array (GoogleMapsResultPlaces) (optional)

No description provided.

Поля

name string (optional)

No description provided.

place_id string (optional)

No description provided.

review_snippets array (ReviewSnippet) (optional)

No description provided.

Поля

review_id string (optional)

The ID of the review snippet.

title string (optional)

Title of the review.

url string (optional)

A link that corresponds to the user review on Google Maps.

url string (optional)

No description provided.

widget_context_token string (optional)

No description provided.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "google_maps_result" .

GoogleSearchCallStep

Google Search call step.

arguments GoogleSearchCallStepArguments (required)

Required. The arguments to pass to Google Search.

Поля

queries array (string) (optional)

Web search queries for the following-up web search.

id string (required)

Required. A unique ID for this specific tool call.

search_type enum (string) (optional)

The type of search grounding enabled.

Possible values:

web_search
Setting this field enables web search. Only text results are returned.
image_search
Setting this field enables image search. Image bytes are returned.
enterprise_web_search
Setting this field enables enterprise web search.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "google_search_call" .

GoogleSearchResultStep

Google Search result step.

call_id string (required)

Required. ID to match the ID from the function call block.

is_error boolean (optional)

Whether the Google Search resulted in an error.

result array (GoogleSearchResultItem) (required)

Required. The results of the Google Search.

Поля

search_suggestions string (optional)

Web content snippet that can be embedded in a web page or an app webview.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "google_search_result" .

McpServerToolCallStep

MCPServer tool call step.

arguments object (required)

Required. The JSON object of arguments for the function.

id string (required)

Required. A unique ID for this specific tool call.

name string (required)

Required. The name of the tool which was called.

server_name string (required)

Required. The name of the used MCP server.

type object (required)

No description provided.

Always set to "mcp_server_tool_call" .

McpServerToolResultStep

MCPServer tool result step.

call_id string (required)

Required. ID to match the ID from the function call block.

name string (optional)

Name of the tool which is called for this specific tool call.

result array (ImageContent or TextContent) or object or string (required)

Required. The output from the MCP server call. Can be simple text or rich content.

server_name string (optional)

The name of the used MCP server.

type object (required)

No description provided.

Always set to "mcp_server_tool_result" .

ModelOutputStep

Output generated by the model.

content array (Content) (optional)

No description provided.

Possible Types

AudioContent

An audio content block.

channels integer (optional)

The number of audio channels.

data string (optional)

The audio content.

mime_type enum (string) (optional)

The mime type of the audio.

Возможные значения:

audio/wav
WAV audio format
audio/mp3
MP3 audio format
audio/aiff
AIFF audio format
audio/aac
AAC audio format
audio/ogg
OGG audio format
audio/flac
FLAC audio format
audio/mpeg
MPEG audio format
audio/m4a
M4A audio format
audio/l16
L16 audio format
audio/opus
OPUS audio format
audio/alaw
ALAW audio format
audio/mulaw
MULAW audio format

sample_rate integer (optional)

The sample rate of the audio.

type object (required)

No description provided.

Always set to "audio" .

uri string (optional)

The URI of the audio.

DocumentContent

A document content block.

data string (optional)

The document content.

mime_type enum (string) (optional)

The mime type of the document.

Possible values:

application/pdf
PDF document format
text/csv
CSV document format

type object (required)

No description provided.

Always set to "document" .

uri string (optional)

The URI of the document.

ImageContent

An image content block.

data string (optional)

The image content.

mime_type enum (string) (optional)

The mime type of the image.

Possible values:

image/png
PNG image format
image/jpeg
JPEG image format
image/webp
WebP image format
image/heic
HEIC image format
image/heif
HEIF image format
image/gif
GIF image format
image/bmp
BMP image format
image/tiff
TIFF image format

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

No description provided.

Always set to "image" .

uri string (optional)

The URI of the image.

TextContent

A text content block.

annotations array (Annotation) (optional)

Информация об источниках для контента, сгенерированного моделью.

Possible Types

FileCitation

A file citation annotation.

custom_metadata object (optional)

User provided metadata about the retrieved context.

document_uri string (optional)

The URI of the file.

end_index integer (optional)

End of the attributed segment, exclusive.

file_name string (optional)

The name of the file.

media_id string (optional)

Media ID in-case of image citations, if applicable.

page_number integer (optional)

Page number of the cited document, if applicable.

source string (optional)

Source attributed for a portion of the text.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "file_citation" .

PlaceCitation

A place citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

name string (optional)

Title of the place.

place_id string (optional)

The ID of the place, in `places/{place_id}` format.

review_snippets array (ReviewSnippet) (optional)

Snippets of reviews that are used to generate answers about the features of a given place in Google Maps.

Поля

review_id string (optional)

The ID of the review snippet.

title string (optional)

Title of the review.

url string (optional)

A link that corresponds to the user review on Google Maps.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "place_citation" .

url string (optional)

URI reference of the place.

UrlCitation

A URL citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

title string (optional)

The title of the URL.

type object (required)

No description provided.

Always set to "url_citation" .

url string (optional)

The URL.

WordInfo

Word-level ASR annotation for transcription output. Carries the word text, optional timing, and optional speaker attribution.

end_index integer (optional)

End of the attributed segment, exclusive.

end_offset string (optional)

End offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

speaker string (optional)

Optional. Speaker label for this word (eg "spk_1", "spk_2"). Present when diarization_mode is set in TranscriptionConfig.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

start_offset string (optional)

Start offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

text string (optional)

The transcribed word.

type object (required)

No description provided.

Always set to "word_info" .

text string (required)

Required. The text content.

type object (required)

No description provided.

Always set to "text" .

VideoContent

A video content block.

data string (optional)

The video content.

mime_type enum (string) (optional)

The mime type of the video.

Possible values:

video/mp4
MP4 video format
video/mpeg
видеоформат MPEG
video/mpg
MPG video format
video/mov
MOV video format
video/avi
AVI video format
video/x-flv
FLV video format
video/webm
WebM video format
video/wmv
WMV video format
video/3gpp
3GPP video format

processing MediaProcessing or enum (string) (optional)

How the model processes this video for understanding.

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

No description provided.

Always set to "video" .

uri string (optional)

The URI of the video.

type object (required)

No description provided.

Always set to "model_output" .

ThoughtStep

A thought step.

signature string (optional)

A signature hash for backend validation.

summary array (ThoughtSummaryContent) (optional)

A summary of the thought.

Possible Types

ImageContent

An image content block.

data string (optional)

The image content.

mime_type enum (string) (optional)

The mime type of the image.

Possible values:

image/png
PNG image format
image/jpeg
JPEG image format
image/webp
WebP image format
image/heic
HEIC image format
image/heif
HEIF image format
image/gif
GIF image format
image/bmp
BMP image format
image/tiff
TIFF image format

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

No description provided.

Always set to "image" .

uri string (optional)

The URI of the image.

TextContent

A text content block.

annotations array (Annotation) (optional)

Информация об источниках для контента, сгенерированного моделью.

Possible Types

FileCitation

A file citation annotation.

custom_metadata object (optional)

User provided metadata about the retrieved context.

document_uri string (optional)

The URI of the file.

end_index integer (optional)

End of the attributed segment, exclusive.

file_name string (optional)

The name of the file.

media_id string (optional)

Media ID in-case of image citations, if applicable.

page_number integer (optional)

Page number of the cited document, if applicable.

source string (optional)

Source attributed for a portion of the text.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "file_citation" .

PlaceCitation

A place citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

name string (optional)

Title of the place.

place_id string (optional)

The ID of the place, in `places/{place_id}` format.

review_snippets array (ReviewSnippet) (optional)

Snippets of reviews that are used to generate answers about the features of a given place in Google Maps.

Поля

review_id string (optional)

The ID of the review snippet.

title string (optional)

Title of the review.

url string (optional)

A link that corresponds to the user review on Google Maps.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "place_citation" .

url string (optional)

URI reference of the place.

UrlCitation

A URL citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

title string (optional)

The title of the URL.

type object (required)

No description provided.

Always set to "url_citation" .

url string (optional)

The URL.

WordInfo

Word-level ASR annotation for transcription output. Carries the word text, optional timing, and optional speaker attribution.

end_index integer (optional)

End of the attributed segment, exclusive.

end_offset string (optional)

End offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

speaker string (optional)

Optional. Speaker label for this word (eg "spk_1", "spk_2"). Present when diarization_mode is set in TranscriptionConfig.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

start_offset string (optional)

Start offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

text string (optional)

The transcribed word.

type object (required)

No description provided.

Always set to "word_info" .

text string (required)

Required. The text content.

type object (required)

No description provided.

Always set to "text" .

type object (required)

No description provided.

Always set to "thought" .

UrlContextCallStep

URL context call step.

arguments UrlContextCallArguments (required)

Required. The arguments to pass to the URL context.

Поля

urls array (string) (optional)

The URLs to fetch.

id string (required)

Required. A unique ID for this specific tool call.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "url_context_call" .

UrlContextResultStep

URL context result step.

call_id string (required)

Required. ID to match the ID from the function call block.

is_error boolean (optional)

Whether the URL context resulted in an error.

result array (UrlContextResult) (required)

Required. The results of the URL context.

Поля

status enum (string) (optional)

The status of the URL retrieval.

Possible values:

success
Url retrieval is successful.
error
Url retrieval is failed due to error.
paywall
Url retrieval is failed because the content is behind paywall.
unsafe
Url retrieval is failed because the content is unsafe.

url string (optional)

The URL that was fetched.

signature string (optional)

A signature hash for backend validation.

type object (required)

No description provided.

Always set to "url_context_result" .

UserInputStep

Input provided by the user.

content array (Content) (optional)

No description provided.

Possible Types

AudioContent

An audio content block.

channels integer (optional)

The number of audio channels.

data string (optional)

The audio content.

mime_type enum (string) (optional)

The mime type of the audio.

Possible values:

audio/wav
WAV audio format
audio/mp3
MP3 audio format
audio/aiff
AIFF audio format
audio/aac
AAC audio format
audio/ogg
OGG audio format
audio/flac
FLAC audio format
audio/mpeg
MPEG audio format
audio/m4a
M4A audio format
audio/l16
L16 audio format
audio/opus
OPUS audio format
audio/alaw
ALAW audio format
audio/mulaw
MULAW audio format

sample_rate integer (optional)

The sample rate of the audio.

type object (required)

No description provided.

Always set to "audio" .

uri string (optional)

The URI of the audio.

DocumentContent

A document content block.

data string (optional)

The document content.

mime_type enum (string) (optional)

The mime type of the document.

Possible values:

application/pdf
PDF document format
text/csv
CSV document format

type object (required)

No description provided.

Always set to "document" .

uri string (optional)

The URI of the document.

ImageContent

An image content block.

data string (optional)

The image content.

mime_type enum (string) (optional)

The mime type of the image.

Possible values:

image/png
PNG image format
image/jpeg
JPEG image format
image/webp
WebP image format
image/heic
HEIC image format
image/heif
HEIF image format
image/gif
GIF image format
image/bmp
BMP image format
image/tiff
TIFF image format

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

No description provided.

Always set to "image" .

uri string (optional)

The URI of the image.

TextContent

A text content block.

annotations array (Annotation) (optional)

Информация об источниках для контента, сгенерированного моделью.

Possible Types

FileCitation

A file citation annotation.

custom_metadata object (optional)

User provided metadata about the retrieved context.

document_uri string (optional)

The URI of the file.

end_index integer (optional)

End of the attributed segment, exclusive.

file_name string (optional)

The name of the file.

media_id string (optional)

Media ID in-case of image citations, if applicable.

page_number integer (optional)

Page number of the cited document, if applicable.

source string (optional)

Source attributed for a portion of the text.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "file_citation" .

PlaceCitation

A place citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

name string (optional)

Title of the place.

place_id string (optional)

The ID of the place, in `places/{place_id}` format.

review_snippets array (ReviewSnippet) (optional)

Snippets of reviews that are used to generate answers about the features of a given place in Google Maps.

Поля

review_id string (optional)

The ID of the review snippet.

title string (optional)

Title of the review.

url string (optional)

A link that corresponds to the user review on Google Maps.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

type object (required)

No description provided.

Always set to "place_citation" .

url string (optional)

URI reference of the place.

UrlCitation

A URL citation annotation.

end_index integer (optional)

End of the attributed segment, exclusive.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

title string (optional)

The title of the URL.

type object (required)

No description provided.

Always set to "url_citation" .

url string (optional)

The URL.

WordInfo

Word-level ASR annotation for transcription output. Carries the word text, optional timing, and optional speaker attribution.

end_index integer (optional)

End of the attributed segment, exclusive.

end_offset string (optional)

End offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

speaker string (optional)

Optional. Speaker label for this word (eg "spk_1", "spk_2"). Present when diarization_mode is set in TranscriptionConfig.

start_index integer (optional)

Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes.

start_offset string (optional)

Start offset in time of the word relative to the start of the audio. Present when timestamp_granularities contains "word".

text string (optional)

The transcribed word.

type object (required)

No description provided.

Always set to "word_info" .

text string (required)

Required. The text content.

type object (required)

No description provided.

Always set to "text" .

VideoContent

A video content block.

data string (optional)

The video content.

mime_type enum (string) (optional)

The mime type of the video.

Possible values:

video/mp4
MP4 video format
video/mpeg
видеоформат MPEG
video/mpg
MPG video format
video/mov
MOV video format
video/avi
AVI video format
video/x-flv
FLV video format
video/webm
WebM video format
video/wmv
WMV video format
video/3gpp
3GPP video format

processing MediaProcessing or enum (string) (optional)

How the model processes this video for understanding.

resolution MediaResolution (optional)

The resolution of the media.

Возможные значения

low
Low resolution.
medium
Medium resolution.
high
High resolution.
ultra_high
Ultra high resolution.

type object (required)

No description provided.

Always set to "video" .

uri string (optional)

The URI of the video.

type object (required)

No description provided.

Always set to "user_input" .

system_instruction string (optional)

System instruction for the interaction.

tools array (Tool) (optional)

A list of tool declarations the model may call during interaction.

Possible Types

CodeExecution

A tool that can be used by the model to execute code.

type object (required)

No description provided.

Always set to "code_execution" .

ComputerUse

A tool that can be used by the model to interact with the computer.

disabled_safety_policies array (enum (string)) (optional)

Optional. Disabled safety policies for computer use.

Possible values:

financial_transactions
Safety policy for financial transactions.
sensitive_data_modification
Safety policy for sensitive data modification.
communication_tool
Safety policy for communication tools (eg Gmail, Chat, Meet).
account_creation
Safety policy for account creation.
data_modification
Safety policy for data modification.
user_consent_management
Safety policy for user consent management.
legal_terms_and_agreements
Safety policy for legal terms and agreements.

enable_prompt_injection_detection boolean (optional)

Whether enable the prompt injection detection check on computer-use request.

environment enum (string) (optional)

The environment being operated.

Possible values:

browser
Operates in a web browser.
mobile
Operates in a mobile environment.
desktop
Operates in a desktop environment.

excluded_predefined_functions array (string) (optional)

The list of predefined functions that are excluded from the model call.

type object (required)

No description provided.

Always set to "computer_use" .

Поиск файлов

A tool that can be used by the model to search files.

file_search_store_names array (string) (optional)

The file search store names to search.

metadata_filter string (optional)

Metadata filter to apply to the semantic retrieval documents and chunks.

top_k integer (optional)

The number of semantic retrieval chunks to retrieve.

type object (required)

No description provided.

Always set to "file_search" .

Функция

Инструмент, который может быть использован моделью.

description string (optional)

A description of the function.

name string (optional)

The name of the function.

parameters object (optional)

The JSON Schema for the function's parameters.

type object (required)

No description provided.

Always set to "function" .

Google Карты

A tool that can be used by the model to call Google Maps.

enable_widget boolean (optional)

Whether to return a widget context token in the tool call result of the response.

latitude number (optional)

The latitude of the user's location.

longitude number (optional)

The longitude of the user's location.

type object (required)

No description provided.

Always set to "google_maps" .

GoogleSearch

A tool that can be used by the model to search Google.

search_types array (enum (string)) (optional)

The types of search grounding to enable.

Possible values:

web_search
Setting this field enables web search. Only text results are returned.
image_search
Setting this field enables image search. Image bytes are returned.
enterprise_web_search
Setting this field enables enterprise web search.

type object (required)

No description provided.

Always set to "google_search" .

McpServer

A MCPServer is a server that can be called by the model to perform actions.

allowed_tools array (AllowedTools) (optional)

The allowed tools.

Поля

mode enum (string) (optional)

The mode of the tool choice.

Possible values:

auto
Auto tool choice.
any
Any tool choice.
none
No tool choice.
validated
Validated tool choice.

tools array (string) (optional)

The names of the allowed tools.

headers object (optional)

Optional: Fields for authentication headers, timeouts, etc., if needed.

name string (optional)

The name of the MCPServer.

type object (required)

No description provided.

Always set to "mcp_server" .

url string (optional)

The full URL for the MCPServer endpoint. Example: "https://api.example.com/mcp"

Извлечение

A tool that can be used by the model to retrieve files.

exa_ai_search_config ExaAISearchConfig (optional)

Used to specify configuration for ExaAISearch.

Поля

api_key string (optional)

Required. The API key for ExaAiSearch.

custom_config object (optional)

Optional. This field can be used to pass any parameter from the Exa.ai Search API.

parallel_ai_search_config ParallelAISearchConfig (optional)

Used to specify configuration for ParallelAISearch.

Поля

api_key string (optional)

Optional. The API key for ParallelAiSearch.

custom_config object (optional)

Optional. Custom configs for ParallelAiSearch.

rag_store_config RagStoreConfig (optional)

Used to specify configuration for RagStore.

Поля

rag_resources array (RagResource) (optional)

Optional. The representation of the rag source.

Поля

rag_corpus string (optional)

Optional. RagCorpora resource name.

rag_file_ids array (string) (optional)

Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field.

rag_retrieval_config RagRetrievalConfig (optional)

Optional. The retrieval config for the Rag query.

Поля

filter Filter (optional)

Optional. Config for filters.

Поля

metadata_filter string (optional)

Optional. String for metadata filtering.

vector_distance_threshold number (optional)

Optional. Only returns contexts with vector distance smaller than the threshold.

vector_similarity_threshold number (optional)

Optional. Only returns contexts with vector similarity larger than the threshold.

hybrid_search HybridSearch (optional)

Optional. Config for Hybrid Search.

Поля

alpha number (optional)

Optional. Alpha value controls the weight between dense and sparse vector search results.

ranking Ranking (optional)

Optional. Config for ranking and reranking.

top_k integer (optional)

Optional. The number of contexts to retrieve.

retrieval_types array (enum (string)) (optional)

The types of file retrieval to enable.

Possible values:

rag_store
exa_ai_search
parallel_ai_search

type object (required)

No description provided.

Always set to "retrieval" .

UrlContext

A tool that can be used by the model to fetch URL context.

type object (required)

No description provided.

Always set to "url_context" .

updated string (optional)

Output only. The time at which the response was last updated in ISO 8601 format (YYYY-MM-DDThh:mm:ssZ).

usage Usage (optional)

Output only. Statistics on the interaction request's token usage.

Поля

cached_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of cached token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

grounding_tool_count array (GroundingToolCount) (optional)

Grounding tool count.

Поля

count integer (optional)

Количество заземляющих инструментов подсчитывается.

type enum (string) (optional)

The grounding tool type associated with the count.

Possible values:

google_search
Grounding with Google Web Search and Image Search, & Web Grounding for Enterprise.
google_maps
Grounding with Google Maps.
retrieval
Grounding with customer's data, for example, VertexAISearch.

input_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of input token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

output_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of output token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

tool_use_tokens_by_modality array (ModalityTokens) (optional)

A breakdown of tool-use token usage by modality.

Поля

modality ResponseModality (optional)

The modality associated with the token count.

Возможные значения

text
Indicates the model should return text.
image
Indicates the model should return images.
audio
Indicates the model should return audio.
video
Indicates the model should return video.
document
Indicates the model should return documents.

tokens integer (optional)

Number of tokens for the modality.

total_cached_tokens integer (optional)

Number of tokens in the cached part of the prompt (the cached content).

total_input_tokens integer (optional)

Number of tokens in the prompt (context).

total_output_tokens integer (optional)

Total number of tokens across all the generated responses.

total_thought_tokens integer (optional)

Number of tokens of thoughts for thinking models.

total_tokens integer (optional)

Total token count for the interaction request (prompt + responses + other internal tokens).

total_tool_use_tokens integer (optional)

Number of tokens present in tool-use prompt(s).

webhook_config WebhookConfig (optional)

Optional. Webhook configuration for receiving notifications when the interaction completes.

Поля

uris array (string) (optional)

Optional. If set, these webhook URIs will be used for webhook events instead of the registered webhooks.

user_metadata object (optional)

Optional. The user metadata that will be returned on each event emission to the webhooks.

last_pause_time string (optional)

Output only. The time when the trigger was last paused.

last_resume_time string (optional)

Output only. The time when the trigger was last resumed.

last_run_time string (optional)

Output only. The time when the trigger was last run.

max_consecutive_failures integer (optional)

Optional. The maximum number of consecutive failures allowed before the trigger is automatically paused (status becomes ERROR).

next_run_time string (optional)

Output only. The time when the trigger is scheduled to run next.

previous_interaction_id string (optional)

Output only. The ID of the last interaction created by this trigger.

schedule string (optional)

Required. The cron schedule on which the trigger should run. Standard cron format.

status enum (string) (optional)

Output only. The current status of the trigger.

Possible values:

active
The trigger is active and will fire on schedule.
paused
The trigger is paused and will not fire.
error
The trigger has entered an error state due to consecutive failures.

time_zone string (optional)

Required. Time zone in which the schedule should be interpreted.

update_time string (optional)

Output only. The time when the trigger was last updated.