# Gemini Webhooks API

> [!NOTE]
> **Beta** : This API is in Beta. Endpoints are under `/v1beta/`.

Webhooks allow the Gemini API to push real-time notifications to your server when asynchronous or Long-Running Operations (LROs) complete. This replaces the need to poll the API for status updates, reducing latency and overhead.
[View as markdown](https://ai.google.dev/static/api/webhooks.md.txt) [View the OpenAPI Spec](https://ai.google.dev/static/api/interactions.openapi.json)

## CreateWebhook

post https://generativelanguage.googleapis.com/v1beta/webhooks Creates a new Webhook.
- [Request body](https://ai.google.dev/api/webhooks#CreateWebhook.request_body)
- [Response](https://ai.google.dev/api/webhooks#CreateWebhook.response)

### Request body

The request body contains data with the following structure:
name string (optional) Optional. The user-provided name of the webhook.
uri string (required) Required. The URI to which webhook events will be sent.
subscribed_events array (enum (string)) (required) Required. The events that the webhook is subscribed to.
Available events:
- batch.succeeded
- batch.expired
- batch.failed
- interaction.requires_action
- interaction.completed
- interaction.failed
- video.generated

Possible
values:

- `batch.succeeded`

  Batch processing finished successfully.
- `batch.expired`

  Batch has not been processed within the 48h timeframe.
- `batch.failed`

  Batch job failed.
- `interaction.requires_action`

  Interaction requires action (e.g., function calling).
- `interaction.completed`

  Interaction completed successfully.
- `interaction.failed`

  Interaction failed.
- `video.generated`

  Video generation completed.

### Response

If successful, the response body contains data with the following structure:
name string (optional) Optional. The user-provided name of the webhook.
uri string (optional) Required. The URI to which webhook events will be sent.
subscribed_events array (enum (string)) (optional) Required. The events that the webhook is subscribed to.
Available events:
- batch.succeeded
- batch.expired
- batch.failed
- interaction.requires_action
- interaction.completed
- interaction.failed
- video.generated

Possible
values:

- `batch.succeeded`

  Batch processing finished successfully.
- `batch.expired`

  Batch has not been processed within the 48h timeframe.
- `batch.failed`

  Batch job failed.
- `interaction.requires_action`

  Interaction requires action (e.g., function calling).
- `interaction.completed`

  Interaction completed successfully.
- `interaction.failed`

  Interaction failed.
- `video.generated`

  Video generation completed.
create_time string (optional) Output only. The timestamp when the webhook was created.
update_time string (optional) Output only. The timestamp when the webhook was last updated.
signing_secrets SigningSecret (optional) Output only. The signing secrets associated with this webhook.
Represents a signing secret used to verify webhook payloads.

#### Fields

truncated_secret string (optional) Output only. The truncated version of the signing secret.
expire_time string (optional) Output only. The expiration date of the signing secret.
state enum (string) (optional) Output only. The state of the webhook.

Possible
values:

- `enabled`

  The webhook is enabled.
- `disabled`

  The webhook is disabled by the user.
- `disabled_due_to_failed_deliveries`

  The webhook is disabled due to failed deliveries.
new_signing_secret string (optional) Output only. The new signing secret for the webhook. Only populated on create.
id string (optional) Output only. The ID of the webhook.

### Example

#### Example Request

REST

```sh
curl -X POST 'https://generativelanguage.googleapis.com/v1beta/webhooks' 
-H 'Content-Type: application/json' 
-d '{
  "name": "string",
  "uri": "string",
  "subscribed_events": [
    "batch.succeeded"
  ],
  "create_time": "string",
  "update_time": "string",
  "signing_secrets": [
    {
      "truncated_secret": "string",
      "expire_time": "string"
    }
  ],
  "state": "enabled",
  "new_signing_secret": "string",
  "id": "string"
}'
```

#### Example Response

```json
{
  "name": "string",
  "uri": "string",
  "subscribed_events": [
    "batch.succeeded"
  ],
  "create_time": "string",
  "update_time": "string",
  "signing_secrets": [
    {
      "truncated_secret": "string",
      "expire_time": "string"
    }
  ],
  "state": "enabled",
  "new_signing_secret": "string",
  "id": "string"
}
```

## PingWebhook

post https://generativelanguage.googleapis.com/v1beta/webhooks/{id}:ping Sends a ping event to a Webhook.
- [Path / Query parameters](https://ai.google.dev/api/webhooks#PingWebhook.PATH_PARAMETERS)
- [Request body](https://ai.google.dev/api/webhooks#PingWebhook.request_body)
- [Response](https://ai.google.dev/api/webhooks#PingWebhook.response)

### Path / Query Parameters

id string (required) Required. The ID of the webhook to ping.
Format: \`{webhook_id}\`

### Request body

The request body contains data with the following structure:

### Response

If successful, the response is empty.

### Example

#### Example Request

REST

```sh
curl -X POST 'https://generativelanguage.googleapis.com/v1beta/webhooks/{id}:ping' 
-H 'Content-Type: application/json' 
```

## RotateSigningSecret

post https://generativelanguage.googleapis.com/v1beta/webhooks/{id}:rotateSigningSecret Generates a new signing secret for a Webhook.
- [Path / Query parameters](https://ai.google.dev/api/webhooks#RotateSigningSecret.PATH_PARAMETERS)
- [Request body](https://ai.google.dev/api/webhooks#RotateSigningSecret.request_body)
- [Response](https://ai.google.dev/api/webhooks#RotateSigningSecret.response)

### Path / Query Parameters

id string (required) Required. The ID of the webhook for which to generate a signing secret.
Format: \`{webhook_id}\`

### Request body

The request body contains data with the following structure:
revocation_behavior enum (string) (optional) Optional. The revocation behavior for previous signing secrets.

Possible
values:

- `revoke_previous_secrets_after_h24`

  Generate a new signing secret and revoke all previous secrets after 24
  hours. Default and safest option for migrations.
- `revoke_previous_secrets_immediately`

  Revoke all previous secrets immediately. Use with caution as this can
  interrupt ongoing notifications.

### Response

If successful, the response body contains data with the following structure:
secret string (optional) Output only. The newly generated signing secret.

### Example

#### Example Request

REST

```sh
curl -X POST 'https://generativelanguage.googleapis.com/v1beta/webhooks/{id}:rotateSigningSecret' 
-H 'Content-Type: application/json' 
-d '{
  "revocation_behavior": "revoke_previous_secrets_after_h24"
}'
```

#### Example Response

```json
{
  "secret": "string"
}
```

## ListWebhooks

get https://generativelanguage.googleapis.com/v1beta/webhooks Lists all Webhooks.
- [Path / Query parameters](https://ai.google.dev/api/webhooks#ListWebhooks.PATH_PARAMETERS)
- [Response](https://ai.google.dev/api/webhooks#ListWebhooks.response)

### Path / Query Parameters

page_size integer (optional) Optional. The maximum number of webhooks to return. The service may return fewer than
this value. If unspecified, at most 50 webhooks will be returned.
The maximum value is 1000.
page_token string (optional) Optional. A page token, received from a previous \`ListWebhooks\` call.
Provide this to retrieve the subsequent page.

### Response

If successful, the response body contains data with the following structure:
webhooks array ([Webhook](https://ai.google.dev/api/webhooks#Resource:Webhook)) (optional) The webhooks.
next_page_token string (optional) A token, which can be sent as \`page_token\` to retrieve the next page.
If this field is omitted, there are no subsequent pages.

### Example

#### Example Request

REST

```sh
curl -X GET 'https://generativelanguage.googleapis.com/v1beta/webhooks' 
-H 'Content-Type: application/json' 
```

#### Example Response

```json
{
  "webhooks": [
    {
      "name": "string",
      "uri": "string",
      "subscribed_events": [
        "batch.succeeded"
      ],
      "create_time": "string",
      "update_time": "string",
      "signing_secrets": [
        {
          "truncated_secret": "string",
          "expire_time": "string"
        }
      ],
      "state": "enabled",
      "new_signing_secret": "string",
      "id": "string"
    }
  ],
  "next_page_token": "string"
}
```

## GetWebhook

get https://generativelanguage.googleapis.com/v1beta/webhooks/{id} Gets a specific Webhook.
- [Path / Query parameters](https://ai.google.dev/api/webhooks#GetWebhook.PATH_PARAMETERS)
- [Response](https://ai.google.dev/api/webhooks#GetWebhook.response)

### Path / Query Parameters

id string (required) Required. The ID of the webhook to retrieve.

### Response

If successful, the response body contains data with the following structure:
name string (optional) Optional. The user-provided name of the webhook.
uri string (optional) Required. The URI to which webhook events will be sent.
subscribed_events array (enum (string)) (optional) Required. The events that the webhook is subscribed to.
Available events:
- batch.succeeded
- batch.expired
- batch.failed
- interaction.requires_action
- interaction.completed
- interaction.failed
- video.generated

Possible
values:

- `batch.succeeded`

  Batch processing finished successfully.
- `batch.expired`

  Batch has not been processed within the 48h timeframe.
- `batch.failed`

  Batch job failed.
- `interaction.requires_action`

  Interaction requires action (e.g., function calling).
- `interaction.completed`

  Interaction completed successfully.
- `interaction.failed`

  Interaction failed.
- `video.generated`

  Video generation completed.
create_time string (optional) Output only. The timestamp when the webhook was created.
update_time string (optional) Output only. The timestamp when the webhook was last updated.
signing_secrets SigningSecret (optional) Output only. The signing secrets associated with this webhook.
Represents a signing secret used to verify webhook payloads.

#### Fields

truncated_secret string (optional) Output only. The truncated version of the signing secret.
expire_time string (optional) Output only. The expiration date of the signing secret.
state enum (string) (optional) Output only. The state of the webhook.

Possible
values:

- `enabled`

  The webhook is enabled.
- `disabled`

  The webhook is disabled by the user.
- `disabled_due_to_failed_deliveries`

  The webhook is disabled due to failed deliveries.
new_signing_secret string (optional) Output only. The new signing secret for the webhook. Only populated on create.
id string (optional) Output only. The ID of the webhook.

### Example

#### Example Request

REST

```sh
curl -X GET 'https://generativelanguage.googleapis.com/v1beta/webhooks/{id}' 
-H 'Content-Type: application/json' 
```

#### Example Response

```json
{
  "name": "string",
  "uri": "string",
  "subscribed_events": [
    "batch.succeeded"
  ],
  "create_time": "string",
  "update_time": "string",
  "signing_secrets": [
    {
      "truncated_secret": "string",
      "expire_time": "string"
    }
  ],
  "state": "enabled",
  "new_signing_secret": "string",
  "id": "string"
}
```

## UpdateWebhook

patch https://generativelanguage.googleapis.com/v1beta/webhooks/{id} Updates an existing Webhook.
- [Path / Query parameters](https://ai.google.dev/api/webhooks#UpdateWebhook.PATH_PARAMETERS)
- [Request body](https://ai.google.dev/api/webhooks#UpdateWebhook.request_body)
- [Response](https://ai.google.dev/api/webhooks#UpdateWebhook.response)

### Path / Query Parameters

id string (required) Required. The ID of the webhook to update.
update_mask string (optional) Optional. The list of fields to update.

### Request body

The request body contains data with the following structure:
name string (optional) Optional. The user-provided name of the webhook.
uri string (optional) Optional. The URI to which webhook events will be sent.
subscribed_events array (enum (string)) (optional) Optional. The events that the webhook is subscribed to.
Available events:
- batch.succeeded
- batch.expired
- batch.failed
- interaction.requires_action
- interaction.completed
- interaction.failed
- video.generated

Possible
values:

- `batch.succeeded`

  Batch processing finished successfully.
- `batch.expired`

  Batch has not been processed within the 48h timeframe.
- `batch.failed`

  Batch job failed.
- `interaction.requires_action`

  Interaction requires action (e.g., function calling).
- `interaction.completed`

  Interaction completed successfully.
- `interaction.failed`

  Interaction failed.
- `video.generated`

  Video generation completed.
state enum (string) (optional) Optional. The state of the webhook.

Possible
values:

- `enabled`

  The webhook is enabled.
- `disabled`

  The webhook is disabled by the user.
- `disabled_due_to_failed_deliveries`

  The webhook is disabled due to failed deliveries.

### Response

If successful, the response body contains data with the following structure:
name string (optional) Optional. The user-provided name of the webhook.
uri string (optional) Required. The URI to which webhook events will be sent.
subscribed_events array (enum (string)) (optional) Required. The events that the webhook is subscribed to.
Available events:
- batch.succeeded
- batch.expired
- batch.failed
- interaction.requires_action
- interaction.completed
- interaction.failed
- video.generated

Possible
values:

- `batch.succeeded`

  Batch processing finished successfully.
- `batch.expired`

  Batch has not been processed within the 48h timeframe.
- `batch.failed`

  Batch job failed.
- `interaction.requires_action`

  Interaction requires action (e.g., function calling).
- `interaction.completed`

  Interaction completed successfully.
- `interaction.failed`

  Interaction failed.
- `video.generated`

  Video generation completed.
create_time string (optional) Output only. The timestamp when the webhook was created.
update_time string (optional) Output only. The timestamp when the webhook was last updated.
signing_secrets SigningSecret (optional) Output only. The signing secrets associated with this webhook.
Represents a signing secret used to verify webhook payloads.

#### Fields

truncated_secret string (optional) Output only. The truncated version of the signing secret.
expire_time string (optional) Output only. The expiration date of the signing secret.
state enum (string) (optional) Output only. The state of the webhook.

Possible
values:

- `enabled`

  The webhook is enabled.
- `disabled`

  The webhook is disabled by the user.
- `disabled_due_to_failed_deliveries`

  The webhook is disabled due to failed deliveries.
new_signing_secret string (optional) Output only. The new signing secret for the webhook. Only populated on create.
id string (optional) Output only. The ID of the webhook.

### Example

#### Example Request

REST

```sh
curl -X PATCH 'https://generativelanguage.googleapis.com/v1beta/webhooks/{id}' 
-H 'Content-Type: application/json' 
-d '{
  "name": "string",
  "uri": "string",
  "subscribed_events": [
    "batch.succeeded"
  ],
  "state": "enabled"
}'
```

#### Example Response

```json
{
  "name": "string",
  "uri": "string",
  "subscribed_events": [
    "batch.succeeded"
  ],
  "create_time": "string",
  "update_time": "string",
  "signing_secrets": [
    {
      "truncated_secret": "string",
      "expire_time": "string"
    }
  ],
  "state": "enabled",
  "new_signing_secret": "string",
  "id": "string"
}
```

## DeleteWebhook

delete https://generativelanguage.googleapis.com/v1beta/webhooks/{id} Deletes a Webhook.
- [Path / Query parameters](https://ai.google.dev/api/webhooks#DeleteWebhook.PATH_PARAMETERS)
- [Response](https://ai.google.dev/api/webhooks#DeleteWebhook.response)

### Path / Query Parameters

id string (required) Required. The ID of the webhook to delete.
Format: \`{webhook_id}\`

### Response

If successful, the response is empty.

### Example

#### Example Request

REST

```sh
curl -X DELETE 'https://generativelanguage.googleapis.com/v1beta/webhooks/{id}' 
-H 'Content-Type: application/json' 
```

## Resources

### Webhook

A Webhook resource.

#### Fields

name string (optional) Optional. The user-provided name of the webhook.
uri string (optional) Required. The URI to which webhook events will be sent.
subscribed_events array (enum (string)) (optional) Required. The events that the webhook is subscribed to.
Available events:
- batch.succeeded
- batch.expired
- batch.failed
- interaction.requires_action
- interaction.completed
- interaction.failed
- video.generated

Possible
values:

- `batch.succeeded`

  Batch processing finished successfully.
- `batch.expired`

  Batch has not been processed within the 48h timeframe.
- `batch.failed`

  Batch job failed.
- `interaction.requires_action`

  Interaction requires action (e.g., function calling).
- `interaction.completed`

  Interaction completed successfully.
- `interaction.failed`

  Interaction failed.
- `video.generated`

  Video generation completed.
create_time string (optional) Output only. The timestamp when the webhook was created.
update_time string (optional) Output only. The timestamp when the webhook was last updated.
signing_secrets SigningSecret (optional) Output only. The signing secrets associated with this webhook.
Represents a signing secret used to verify webhook payloads.

#### Fields

truncated_secret string (optional) Output only. The truncated version of the signing secret.
expire_time string (optional) Output only. The expiration date of the signing secret.
state enum (string) (optional) Output only. The state of the webhook.

Possible
values:

- `enabled`

  The webhook is enabled.
- `disabled`

  The webhook is disabled by the user.
- `disabled_due_to_failed_deliveries`

  The webhook is disabled due to failed deliveries.
new_signing_secret string (optional) Output only. The new signing secret for the webhook. Only populated on create.
id string (optional) Output only. The ID of the webhook.

## Data Models

### InteractionSseEvent

<br />

### Possible Types

Polymorphic discriminator: `event_type`
InteractionCreatedEvent <br />

event_type object (required) No description provided.

Always set to `"interaction.created"`.
event_id string (optional) The event_id token to be used to resume the interaction stream, from
this event.
metadata StreamMetadata (optional) Optional metadata accompanying ANY streamed event.
<br />

#### Fields

total_usage Usage (optional) No description provided.
Statistics on the interaction request's token usage.

#### Fields

total_input_tokens integer (optional) Number of tokens in the prompt (context).
input_tokens_by_modality ModalityTokens (optional) A breakdown of input token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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).
cached_tokens_by_modality ModalityTokens (optional) A breakdown of cached token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_output_tokens integer (optional) Total number of tokens across all the generated responses.
output_tokens_by_modality ModalityTokens (optional) A breakdown of output token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_tool_use_tokens integer (optional) Number of tokens present in tool-use prompt(s).
tool_use_tokens_by_modality ModalityTokens (optional) A breakdown of tool-use token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_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).
grounding_tool_count GroundingToolCount (optional) Grounding tool count.
The number of grounding tool counts.

#### Fields

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.
count integer (optional) The number of grounding tool counts.
interaction InteractionSseEventInteraction (required) Partial interaction resource emitted when the stream is created.
Partial interaction resource emitted by interaction lifecycle SSE events.
Streaming lifecycle payloads may omit fields that are only available on
full non-streaming Interaction responses.

#### Fields

id string (optional) Required. Output only. A unique identifier for the interaction completion.
object string (optional) Output only. The resource type.
model string (optional) The model that will complete your prompt.
agent string (optional) The agent to interact with.
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 (e.g. hitting max_tokens).
created string (optional) Output only. The time at which the response was created in ISO 8601 format.
updated string (optional) Output only. The time at which the response was last updated in ISO 8601 format.
service_tier ServiceTier (optional) The service tier for the interaction.
<br />

#### Possible values

- `flex`

  Flex service tier.
- `standard`

  Standard service tier.
- `priority`

  Priority service tier.
usage Usage (optional) Output only. Statistics on the interaction request's token usage.
Statistics on the interaction request's token usage.

#### Fields

total_input_tokens integer (optional) Number of tokens in the prompt (context).
input_tokens_by_modality ModalityTokens (optional) A breakdown of input token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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).
cached_tokens_by_modality ModalityTokens (optional) A breakdown of cached token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_output_tokens integer (optional) Total number of tokens across all the generated responses.
output_tokens_by_modality ModalityTokens (optional) A breakdown of output token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_tool_use_tokens integer (optional) Number of tokens present in tool-use prompt(s).
tool_use_tokens_by_modality ModalityTokens (optional) A breakdown of tool-use token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_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).
grounding_tool_count GroundingToolCount (optional) Grounding tool count.
The number of grounding tool counts.

#### Fields

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.
count integer (optional) The number of grounding tool counts.
steps Step (optional) Output only. The steps that make up the interaction, if included in this event.
A step in the interaction.

#### Possible Types

Polymorphic discriminator: `type`
UserInputStep Input provided by the user.
content Content (optional) No description provided.
The content of the response.

#### Possible Types

Polymorphic discriminator: `type`
TextContent A text content block.
type object (required) No description provided.

Always set to `"text"`.
text string (required) Required. The text content.
annotations Annotation (optional) Citation information for model-generated content.
Citation information for model-generated content.

#### Possible Types

Polymorphic discriminator: `type`
UrlCitation A URL citation annotation.
type object (required) No description provided.

Always set to `"url_citation"`.
url string (optional) The URL.
title string (optional) The title of the URL.
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.
end_index integer (optional) End of the attributed segment, exclusive.
FileCitation A file citation annotation.
type object (required) No description provided.

Always set to `"file_citation"`.
document_uri string (optional) The URI of the file.
file_name string (optional) The name of the file.
source string (optional) Source attributed for a portion of the text.
custom_metadata object (optional) User provided metadata about the retrieved context.
page_number integer (optional) Page number of the cited document, if applicable.
media_id string (optional) Media ID in-case of image citations, if applicable.
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.
end_index integer (optional) End of the attributed segment, exclusive.
PlaceCitation A place citation annotation.
type object (required) No description provided.

Always set to `"place_citation"`.
place_id string (optional) The ID of the place, in \`places/{place_id}\` format.
name string (optional) Title of the place.
url string (optional) URI reference of the place.
review_snippets ReviewSnippet (optional) Snippets of reviews that are used to generate answers about the
features of a given place in Google Maps.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
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.
end_index integer (optional) End of the attributed segment, exclusive.
ImageContent An image content block.
type object (required) No description provided.

Always set to `"image"`.
data string (optional) The image content.
uri string (optional) The URI of the image.
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.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
AudioContent An audio content block.
type object (required) No description provided.

Always set to `"audio"`.
data string (optional) The audio content.
uri string (optional) The URI of the audio.
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
channels integer (optional) The number of audio channels.
sample_rate integer (optional) The sample rate of the audio.
DocumentContent A document content block.
type object (required) No description provided.

Always set to `"document"`.
data string (optional) The document content.
uri string (optional) The URI of the document.
mime_type enum (string) (optional) The mime type of the document.

Possible
values:

- `application/pdf`

  PDF document format
- `text/csv`

  CSV document format
VideoContent A video content block.
type object (required) No description provided.

Always set to `"video"`.
data string (optional) The video content.
uri string (optional) The URI of the video.
mime_type enum (string) (optional) The mime type of the video.

Possible
values:

- `video/mp4`

  MP4 video format
- `video/mpeg`

  MPEG video format
- `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
resolution MediaResolution (optional) The resolution of the media.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
type object (required) No description provided.

Always set to `"user_input"`.
ModelOutputStep Output generated by the model.
type object (required) No description provided.

Always set to `"model_output"`.
content Content (optional) No description provided.
The content of the response.

#### Possible Types

Polymorphic discriminator: `type`
TextContent A text content block.
type object (required) No description provided.

Always set to `"text"`.
text string (required) Required. The text content.
annotations Annotation (optional) Citation information for model-generated content.
Citation information for model-generated content.

#### Possible Types

Polymorphic discriminator: `type`
UrlCitation A URL citation annotation.
type object (required) No description provided.

Always set to `"url_citation"`.
url string (optional) The URL.
title string (optional) The title of the URL.
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.
end_index integer (optional) End of the attributed segment, exclusive.
FileCitation A file citation annotation.
type object (required) No description provided.

Always set to `"file_citation"`.
document_uri string (optional) The URI of the file.
file_name string (optional) The name of the file.
source string (optional) Source attributed for a portion of the text.
custom_metadata object (optional) User provided metadata about the retrieved context.
page_number integer (optional) Page number of the cited document, if applicable.
media_id string (optional) Media ID in-case of image citations, if applicable.
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.
end_index integer (optional) End of the attributed segment, exclusive.
PlaceCitation A place citation annotation.
type object (required) No description provided.

Always set to `"place_citation"`.
place_id string (optional) The ID of the place, in \`places/{place_id}\` format.
name string (optional) Title of the place.
url string (optional) URI reference of the place.
review_snippets ReviewSnippet (optional) Snippets of reviews that are used to generate answers about the
features of a given place in Google Maps.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
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.
end_index integer (optional) End of the attributed segment, exclusive.
ImageContent An image content block.
type object (required) No description provided.

Always set to `"image"`.
data string (optional) The image content.
uri string (optional) The URI of the image.
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.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
AudioContent An audio content block.
type object (required) No description provided.

Always set to `"audio"`.
data string (optional) The audio content.
uri string (optional) The URI of the audio.
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
channels integer (optional) The number of audio channels.
sample_rate integer (optional) The sample rate of the audio.
DocumentContent A document content block.
type object (required) No description provided.

Always set to `"document"`.
data string (optional) The document content.
uri string (optional) The URI of the document.
mime_type enum (string) (optional) The mime type of the document.

Possible
values:

- `application/pdf`

  PDF document format
- `text/csv`

  CSV document format
VideoContent A video content block.
type object (required) No description provided.

Always set to `"video"`.
data string (optional) The video content.
uri string (optional) The URI of the video.
mime_type enum (string) (optional) The mime type of the video.

Possible
values:

- `video/mp4`

  MP4 video format
- `video/mpeg`

  MPEG video format
- `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
resolution MediaResolution (optional) The resolution of the media.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
ThoughtStep A thought step.
type object (required) No description provided.

Always set to `"thought"`.
signature string (optional) A signature hash for backend validation.
summary ThoughtSummaryContent (optional) A summary of the thought.
<br />

#### Possible Types

Polymorphic discriminator: `type`
TextContent A text content block.
type object (required) No description provided.

Always set to `"text"`.
text string (required) Required. The text content.
annotations Annotation (optional) Citation information for model-generated content.
Citation information for model-generated content.

#### Possible Types

Polymorphic discriminator: `type`
UrlCitation A URL citation annotation.
type object (required) No description provided.

Always set to `"url_citation"`.
url string (optional) The URL.
title string (optional) The title of the URL.
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.
end_index integer (optional) End of the attributed segment, exclusive.
FileCitation A file citation annotation.
type object (required) No description provided.

Always set to `"file_citation"`.
document_uri string (optional) The URI of the file.
file_name string (optional) The name of the file.
source string (optional) Source attributed for a portion of the text.
custom_metadata object (optional) User provided metadata about the retrieved context.
page_number integer (optional) Page number of the cited document, if applicable.
media_id string (optional) Media ID in-case of image citations, if applicable.
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.
end_index integer (optional) End of the attributed segment, exclusive.
PlaceCitation A place citation annotation.
type object (required) No description provided.

Always set to `"place_citation"`.
place_id string (optional) The ID of the place, in \`places/{place_id}\` format.
name string (optional) Title of the place.
url string (optional) URI reference of the place.
review_snippets ReviewSnippet (optional) Snippets of reviews that are used to generate answers about the
features of a given place in Google Maps.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
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.
end_index integer (optional) End of the attributed segment, exclusive.
ImageContent An image content block.
type object (required) No description provided.

Always set to `"image"`.
data string (optional) The image content.
uri string (optional) The URI of the image.
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.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
FunctionCallStep A function tool call step.
type object (required) No description provided.

Always set to `"function_call"`.
name string (required) Required. The name of the tool to call.
arguments object (required) Required. The arguments to pass to the function.
id string (required) Required. A unique ID for this specific tool call.
CodeExecutionCallStep Code execution call step.
type object (required) No description provided.

Always set to `"code_execution_call"`.
arguments CodeExecutionCallStepArguments (required) Required. The arguments to pass to the code execution.
The arguments to pass to the code execution.

#### Fields

language enum (string) (optional) Programming language of the \`code\`.

Possible
values:

- `python`

  Python \>= 3.10, with numpy and simpy available.
code string (optional) The code to be executed.
id string (required) Required. A unique ID for this specific tool call.
signature string (optional) A signature hash for backend validation.
UrlContextCallStep URL context call step.
type object (required) No description provided.

Always set to `"url_context_call"`.
id string (required) Required. A unique ID for this specific tool call.
signature string (optional) A signature hash for backend validation.
arguments UrlContextCallArguments (required) The arguments to pass to the URL context.
The arguments to pass to the URL context.

#### Fields

urls array (string) (optional) The URLs to fetch.
McpServerToolCallStep MCPServer tool call step.
type object (required) No description provided.

Always set to `"mcp_server_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.
arguments object (required) Required. The JSON object of arguments for the function.
id string (required) Required. A unique ID for this specific tool call.
GoogleSearchCallStep Google Search call step.
type object (required) No description provided.

Always set to `"google_search_call"`.
arguments GoogleSearchCallStepArguments (required) Required. The arguments to pass to Google Search.
The arguments to pass to Google Search.

#### Fields

queries array (string) (optional) Web search queries for the following-up web search.
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.
id string (required) Required. A unique ID for this specific tool call.
signature string (optional) A signature hash for backend validation.
FileSearchCallStep File Search call step.
type object (required) No description provided.

Always set to `"file_search_call"`.
id string (required) Required. A unique ID for this specific tool call.
signature string (optional) A signature hash for backend validation.
GoogleMapsCallStep Google Maps call step.
type object (required) No description provided.

Always set to `"google_maps_call"`.
arguments GoogleMapsCallStepArguments (optional) The arguments to pass to the Google Maps tool.
The arguments to pass to the Google Maps tool.

#### Fields

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.
FunctionResultStep Result of a function tool call.
type object (required) No description provided.

Always set to `"function_result"`.
name string (optional) The name of the tool that was called.
is_error boolean (optional) Whether the tool call resulted in an error.
call_id string (required) Required. ID to match the ID from the function call block.
result array (ImageContent or TextContent) or object or string (required) The result of the tool call.
CodeExecutionResultStep Code execution result step.
type object (required) No description provided.

Always set to `"code_execution_result"`.
result string (required) Required. The output of the code execution.
is_error boolean (optional) Whether the code execution resulted in an error.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
UrlContextResultStep URL context result step.
type object (required) No description provided.

Always set to `"url_context_result"`.
result UrlContextResult (required) Required. The results of the URL context.
The result of the URL context.

#### Fields

url string (optional) The URL that was fetched.
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.
is_error boolean (optional) Whether the URL context resulted in an error.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
GoogleSearchResultStep Google Search result step.
type object (required) No description provided.

Always set to `"google_search_result"`.
result GoogleSearchResultItem (required) Required. The results of the Google Search.
The result of the Google Search.

#### Fields

search_suggestions string (optional) Web content snippet that can be embedded in a web page or an app webview.
is_error boolean (optional) Whether the Google Search resulted in an error.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
McpServerToolResultStep MCPServer tool result step.
type object (required) No description provided.

Always set to `"mcp_server_tool_result"`.
name string (optional) Name of the tool which is called for this specific tool call.
server_name string (optional) The name of the used MCP server.
call_id string (required) Required. ID to match the ID from the function call block.
result array (ImageContent or TextContent) or object or string (required) The output from the MCP server call. Can be simple text or rich content.
FileSearchResultStep File Search result step.
type object (required) No description provided.

Always set to `"file_search_result"`.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
GoogleMapsResultStep Google Maps result step.
type object (required) No description provided.

Always set to `"google_maps_result"`.
result GoogleMapsResultItem (required) No description provided.
The result of the Google Maps.

#### Fields

places GoogleMapsResultPlaces (optional) No description provided.
<br />

#### Fields

place_id string (optional) No description provided.
name string (optional) No description provided.
url string (optional) No description provided.
review_snippets ReviewSnippet (optional) No description provided.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
widget_context_token string (optional) No description provided.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
InteractionCompletedEvent <br />

event_type object (required) No description provided.

Always set to `"interaction.completed"`.
event_id string (optional) The event_id token to be used to resume the interaction stream, from
this event.
metadata StreamMetadata (optional) Optional metadata accompanying ANY streamed event.
<br />

#### Fields

total_usage Usage (optional) No description provided.
Statistics on the interaction request's token usage.

#### Fields

total_input_tokens integer (optional) Number of tokens in the prompt (context).
input_tokens_by_modality ModalityTokens (optional) A breakdown of input token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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).
cached_tokens_by_modality ModalityTokens (optional) A breakdown of cached token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_output_tokens integer (optional) Total number of tokens across all the generated responses.
output_tokens_by_modality ModalityTokens (optional) A breakdown of output token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_tool_use_tokens integer (optional) Number of tokens present in tool-use prompt(s).
tool_use_tokens_by_modality ModalityTokens (optional) A breakdown of tool-use token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_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).
grounding_tool_count GroundingToolCount (optional) Grounding tool count.
The number of grounding tool counts.

#### Fields

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.
count integer (optional) The number of grounding tool counts.
interaction InteractionSseEventInteraction (required) Partial completed interaction resource emitted at the end of the stream.
Partial interaction resource emitted by interaction lifecycle SSE events.
Streaming lifecycle payloads may omit fields that are only available on
full non-streaming Interaction responses.

#### Fields

id string (optional) Required. Output only. A unique identifier for the interaction completion.
object string (optional) Output only. The resource type.
model string (optional) The model that will complete your prompt.
agent string (optional) The agent to interact with.
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 (e.g. hitting max_tokens).
created string (optional) Output only. The time at which the response was created in ISO 8601 format.
updated string (optional) Output only. The time at which the response was last updated in ISO 8601 format.
service_tier ServiceTier (optional) The service tier for the interaction.
<br />

#### Possible values

- `flex`

  Flex service tier.
- `standard`

  Standard service tier.
- `priority`

  Priority service tier.
usage Usage (optional) Output only. Statistics on the interaction request's token usage.
Statistics on the interaction request's token usage.

#### Fields

total_input_tokens integer (optional) Number of tokens in the prompt (context).
input_tokens_by_modality ModalityTokens (optional) A breakdown of input token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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).
cached_tokens_by_modality ModalityTokens (optional) A breakdown of cached token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_output_tokens integer (optional) Total number of tokens across all the generated responses.
output_tokens_by_modality ModalityTokens (optional) A breakdown of output token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_tool_use_tokens integer (optional) Number of tokens present in tool-use prompt(s).
tool_use_tokens_by_modality ModalityTokens (optional) A breakdown of tool-use token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_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).
grounding_tool_count GroundingToolCount (optional) Grounding tool count.
The number of grounding tool counts.

#### Fields

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.
count integer (optional) The number of grounding tool counts.
steps Step (optional) Output only. The steps that make up the interaction, if included in this event.
A step in the interaction.

#### Possible Types

Polymorphic discriminator: `type`
UserInputStep Input provided by the user.
content Content (optional) No description provided.
The content of the response.

#### Possible Types

Polymorphic discriminator: `type`
TextContent A text content block.
type object (required) No description provided.

Always set to `"text"`.
text string (required) Required. The text content.
annotations Annotation (optional) Citation information for model-generated content.
Citation information for model-generated content.

#### Possible Types

Polymorphic discriminator: `type`
UrlCitation A URL citation annotation.
type object (required) No description provided.

Always set to `"url_citation"`.
url string (optional) The URL.
title string (optional) The title of the URL.
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.
end_index integer (optional) End of the attributed segment, exclusive.
FileCitation A file citation annotation.
type object (required) No description provided.

Always set to `"file_citation"`.
document_uri string (optional) The URI of the file.
file_name string (optional) The name of the file.
source string (optional) Source attributed for a portion of the text.
custom_metadata object (optional) User provided metadata about the retrieved context.
page_number integer (optional) Page number of the cited document, if applicable.
media_id string (optional) Media ID in-case of image citations, if applicable.
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.
end_index integer (optional) End of the attributed segment, exclusive.
PlaceCitation A place citation annotation.
type object (required) No description provided.

Always set to `"place_citation"`.
place_id string (optional) The ID of the place, in \`places/{place_id}\` format.
name string (optional) Title of the place.
url string (optional) URI reference of the place.
review_snippets ReviewSnippet (optional) Snippets of reviews that are used to generate answers about the
features of a given place in Google Maps.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
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.
end_index integer (optional) End of the attributed segment, exclusive.
ImageContent An image content block.
type object (required) No description provided.

Always set to `"image"`.
data string (optional) The image content.
uri string (optional) The URI of the image.
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.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
AudioContent An audio content block.
type object (required) No description provided.

Always set to `"audio"`.
data string (optional) The audio content.
uri string (optional) The URI of the audio.
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
channels integer (optional) The number of audio channels.
sample_rate integer (optional) The sample rate of the audio.
DocumentContent A document content block.
type object (required) No description provided.

Always set to `"document"`.
data string (optional) The document content.
uri string (optional) The URI of the document.
mime_type enum (string) (optional) The mime type of the document.

Possible
values:

- `application/pdf`

  PDF document format
- `text/csv`

  CSV document format
VideoContent A video content block.
type object (required) No description provided.

Always set to `"video"`.
data string (optional) The video content.
uri string (optional) The URI of the video.
mime_type enum (string) (optional) The mime type of the video.

Possible
values:

- `video/mp4`

  MP4 video format
- `video/mpeg`

  MPEG video format
- `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
resolution MediaResolution (optional) The resolution of the media.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
type object (required) No description provided.

Always set to `"user_input"`.
ModelOutputStep Output generated by the model.
type object (required) No description provided.

Always set to `"model_output"`.
content Content (optional) No description provided.
The content of the response.

#### Possible Types

Polymorphic discriminator: `type`
TextContent A text content block.
type object (required) No description provided.

Always set to `"text"`.
text string (required) Required. The text content.
annotations Annotation (optional) Citation information for model-generated content.
Citation information for model-generated content.

#### Possible Types

Polymorphic discriminator: `type`
UrlCitation A URL citation annotation.
type object (required) No description provided.

Always set to `"url_citation"`.
url string (optional) The URL.
title string (optional) The title of the URL.
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.
end_index integer (optional) End of the attributed segment, exclusive.
FileCitation A file citation annotation.
type object (required) No description provided.

Always set to `"file_citation"`.
document_uri string (optional) The URI of the file.
file_name string (optional) The name of the file.
source string (optional) Source attributed for a portion of the text.
custom_metadata object (optional) User provided metadata about the retrieved context.
page_number integer (optional) Page number of the cited document, if applicable.
media_id string (optional) Media ID in-case of image citations, if applicable.
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.
end_index integer (optional) End of the attributed segment, exclusive.
PlaceCitation A place citation annotation.
type object (required) No description provided.

Always set to `"place_citation"`.
place_id string (optional) The ID of the place, in \`places/{place_id}\` format.
name string (optional) Title of the place.
url string (optional) URI reference of the place.
review_snippets ReviewSnippet (optional) Snippets of reviews that are used to generate answers about the
features of a given place in Google Maps.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
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.
end_index integer (optional) End of the attributed segment, exclusive.
ImageContent An image content block.
type object (required) No description provided.

Always set to `"image"`.
data string (optional) The image content.
uri string (optional) The URI of the image.
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.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
AudioContent An audio content block.
type object (required) No description provided.

Always set to `"audio"`.
data string (optional) The audio content.
uri string (optional) The URI of the audio.
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
channels integer (optional) The number of audio channels.
sample_rate integer (optional) The sample rate of the audio.
DocumentContent A document content block.
type object (required) No description provided.

Always set to `"document"`.
data string (optional) The document content.
uri string (optional) The URI of the document.
mime_type enum (string) (optional) The mime type of the document.

Possible
values:

- `application/pdf`

  PDF document format
- `text/csv`

  CSV document format
VideoContent A video content block.
type object (required) No description provided.

Always set to `"video"`.
data string (optional) The video content.
uri string (optional) The URI of the video.
mime_type enum (string) (optional) The mime type of the video.

Possible
values:

- `video/mp4`

  MP4 video format
- `video/mpeg`

  MPEG video format
- `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
resolution MediaResolution (optional) The resolution of the media.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
ThoughtStep A thought step.
type object (required) No description provided.

Always set to `"thought"`.
signature string (optional) A signature hash for backend validation.
summary ThoughtSummaryContent (optional) A summary of the thought.
<br />

#### Possible Types

Polymorphic discriminator: `type`
TextContent A text content block.
type object (required) No description provided.

Always set to `"text"`.
text string (required) Required. The text content.
annotations Annotation (optional) Citation information for model-generated content.
Citation information for model-generated content.

#### Possible Types

Polymorphic discriminator: `type`
UrlCitation A URL citation annotation.
type object (required) No description provided.

Always set to `"url_citation"`.
url string (optional) The URL.
title string (optional) The title of the URL.
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.
end_index integer (optional) End of the attributed segment, exclusive.
FileCitation A file citation annotation.
type object (required) No description provided.

Always set to `"file_citation"`.
document_uri string (optional) The URI of the file.
file_name string (optional) The name of the file.
source string (optional) Source attributed for a portion of the text.
custom_metadata object (optional) User provided metadata about the retrieved context.
page_number integer (optional) Page number of the cited document, if applicable.
media_id string (optional) Media ID in-case of image citations, if applicable.
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.
end_index integer (optional) End of the attributed segment, exclusive.
PlaceCitation A place citation annotation.
type object (required) No description provided.

Always set to `"place_citation"`.
place_id string (optional) The ID of the place, in \`places/{place_id}\` format.
name string (optional) Title of the place.
url string (optional) URI reference of the place.
review_snippets ReviewSnippet (optional) Snippets of reviews that are used to generate answers about the
features of a given place in Google Maps.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
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.
end_index integer (optional) End of the attributed segment, exclusive.
ImageContent An image content block.
type object (required) No description provided.

Always set to `"image"`.
data string (optional) The image content.
uri string (optional) The URI of the image.
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.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
FunctionCallStep A function tool call step.
type object (required) No description provided.

Always set to `"function_call"`.
name string (required) Required. The name of the tool to call.
arguments object (required) Required. The arguments to pass to the function.
id string (required) Required. A unique ID for this specific tool call.
CodeExecutionCallStep Code execution call step.
type object (required) No description provided.

Always set to `"code_execution_call"`.
arguments CodeExecutionCallStepArguments (required) Required. The arguments to pass to the code execution.
The arguments to pass to the code execution.

#### Fields

language enum (string) (optional) Programming language of the \`code\`.

Possible
values:

- `python`

  Python \>= 3.10, with numpy and simpy available.
code string (optional) The code to be executed.
id string (required) Required. A unique ID for this specific tool call.
signature string (optional) A signature hash for backend validation.
UrlContextCallStep URL context call step.
type object (required) No description provided.

Always set to `"url_context_call"`.
id string (required) Required. A unique ID for this specific tool call.
signature string (optional) A signature hash for backend validation.
arguments UrlContextCallArguments (required) The arguments to pass to the URL context.
The arguments to pass to the URL context.

#### Fields

urls array (string) (optional) The URLs to fetch.
McpServerToolCallStep MCPServer tool call step.
type object (required) No description provided.

Always set to `"mcp_server_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.
arguments object (required) Required. The JSON object of arguments for the function.
id string (required) Required. A unique ID for this specific tool call.
GoogleSearchCallStep Google Search call step.
type object (required) No description provided.

Always set to `"google_search_call"`.
arguments GoogleSearchCallStepArguments (required) Required. The arguments to pass to Google Search.
The arguments to pass to Google Search.

#### Fields

queries array (string) (optional) Web search queries for the following-up web search.
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.
id string (required) Required. A unique ID for this specific tool call.
signature string (optional) A signature hash for backend validation.
FileSearchCallStep File Search call step.
type object (required) No description provided.

Always set to `"file_search_call"`.
id string (required) Required. A unique ID for this specific tool call.
signature string (optional) A signature hash for backend validation.
GoogleMapsCallStep Google Maps call step.
type object (required) No description provided.

Always set to `"google_maps_call"`.
arguments GoogleMapsCallStepArguments (optional) The arguments to pass to the Google Maps tool.
The arguments to pass to the Google Maps tool.

#### Fields

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.
FunctionResultStep Result of a function tool call.
type object (required) No description provided.

Always set to `"function_result"`.
name string (optional) The name of the tool that was called.
is_error boolean (optional) Whether the tool call resulted in an error.
call_id string (required) Required. ID to match the ID from the function call block.
result array (ImageContent or TextContent) or object or string (required) The result of the tool call.
CodeExecutionResultStep Code execution result step.
type object (required) No description provided.

Always set to `"code_execution_result"`.
result string (required) Required. The output of the code execution.
is_error boolean (optional) Whether the code execution resulted in an error.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
UrlContextResultStep URL context result step.
type object (required) No description provided.

Always set to `"url_context_result"`.
result UrlContextResult (required) Required. The results of the URL context.
The result of the URL context.

#### Fields

url string (optional) The URL that was fetched.
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.
is_error boolean (optional) Whether the URL context resulted in an error.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
GoogleSearchResultStep Google Search result step.
type object (required) No description provided.

Always set to `"google_search_result"`.
result GoogleSearchResultItem (required) Required. The results of the Google Search.
The result of the Google Search.

#### Fields

search_suggestions string (optional) Web content snippet that can be embedded in a web page or an app webview.
is_error boolean (optional) Whether the Google Search resulted in an error.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
McpServerToolResultStep MCPServer tool result step.
type object (required) No description provided.

Always set to `"mcp_server_tool_result"`.
name string (optional) Name of the tool which is called for this specific tool call.
server_name string (optional) The name of the used MCP server.
call_id string (required) Required. ID to match the ID from the function call block.
result array (ImageContent or TextContent) or object or string (required) The output from the MCP server call. Can be simple text or rich content.
FileSearchResultStep File Search result step.
type object (required) No description provided.

Always set to `"file_search_result"`.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
GoogleMapsResultStep Google Maps result step.
type object (required) No description provided.

Always set to `"google_maps_result"`.
result GoogleMapsResultItem (required) No description provided.
The result of the Google Maps.

#### Fields

places GoogleMapsResultPlaces (optional) No description provided.
<br />

#### Fields

place_id string (optional) No description provided.
name string (optional) No description provided.
url string (optional) No description provided.
review_snippets ReviewSnippet (optional) No description provided.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
widget_context_token string (optional) No description provided.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
InteractionStatusUpdate <br />

event_type object (required) No description provided.

Always set to `"interaction.status_update"`.
interaction_id string (required) No description provided.
status enum (string) (required) No description provided.

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 (e.g.
  hitting max_tokens).
- `budget_exceeded`

  The interaction was halted because the token budget was exceeded.
event_id string (optional) The event_id token to be used to resume the interaction stream, from
this event.
metadata StreamMetadata (optional) Optional metadata accompanying ANY streamed event.
<br />

#### Fields

total_usage Usage (optional) No description provided.
Statistics on the interaction request's token usage.

#### Fields

total_input_tokens integer (optional) Number of tokens in the prompt (context).
input_tokens_by_modality ModalityTokens (optional) A breakdown of input token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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).
cached_tokens_by_modality ModalityTokens (optional) A breakdown of cached token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_output_tokens integer (optional) Total number of tokens across all the generated responses.
output_tokens_by_modality ModalityTokens (optional) A breakdown of output token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_tool_use_tokens integer (optional) Number of tokens present in tool-use prompt(s).
tool_use_tokens_by_modality ModalityTokens (optional) A breakdown of tool-use token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_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).
grounding_tool_count GroundingToolCount (optional) Grounding tool count.
The number of grounding tool counts.

#### Fields

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.
count integer (optional) The number of grounding tool counts.
ErrorEvent <br />

event_type object (required) No description provided.

Always set to `"error"`.
error Error (optional) No description provided.
Error message from an interaction.

#### Fields

code string (optional) A URI that identifies the error type.
message string (optional) A human-readable error message.
event_id string (optional) The event_id token to be used to resume the interaction stream, from
this event.
metadata StreamMetadata (optional) Optional metadata accompanying ANY streamed event.
<br />

#### Fields

total_usage Usage (optional) No description provided.
Statistics on the interaction request's token usage.

#### Fields

total_input_tokens integer (optional) Number of tokens in the prompt (context).
input_tokens_by_modality ModalityTokens (optional) A breakdown of input token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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).
cached_tokens_by_modality ModalityTokens (optional) A breakdown of cached token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_output_tokens integer (optional) Total number of tokens across all the generated responses.
output_tokens_by_modality ModalityTokens (optional) A breakdown of output token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_tool_use_tokens integer (optional) Number of tokens present in tool-use prompt(s).
tool_use_tokens_by_modality ModalityTokens (optional) A breakdown of tool-use token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_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).
grounding_tool_count GroundingToolCount (optional) Grounding tool count.
The number of grounding tool counts.

#### Fields

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.
count integer (optional) The number of grounding tool counts.
StepStart <br />

event_type object (required) No description provided.

Always set to `"step.start"`.
index integer (required) No description provided.
step Step (required) No description provided.
A step in the interaction.

#### Possible Types

Polymorphic discriminator: `type`
UserInputStep Input provided by the user.
content Content (optional) No description provided.
The content of the response.

#### Possible Types

Polymorphic discriminator: `type`
TextContent A text content block.
type object (required) No description provided.

Always set to `"text"`.
text string (required) Required. The text content.
annotations Annotation (optional) Citation information for model-generated content.
Citation information for model-generated content.

#### Possible Types

Polymorphic discriminator: `type`
UrlCitation A URL citation annotation.
type object (required) No description provided.

Always set to `"url_citation"`.
url string (optional) The URL.
title string (optional) The title of the URL.
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.
end_index integer (optional) End of the attributed segment, exclusive.
FileCitation A file citation annotation.
type object (required) No description provided.

Always set to `"file_citation"`.
document_uri string (optional) The URI of the file.
file_name string (optional) The name of the file.
source string (optional) Source attributed for a portion of the text.
custom_metadata object (optional) User provided metadata about the retrieved context.
page_number integer (optional) Page number of the cited document, if applicable.
media_id string (optional) Media ID in-case of image citations, if applicable.
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.
end_index integer (optional) End of the attributed segment, exclusive.
PlaceCitation A place citation annotation.
type object (required) No description provided.

Always set to `"place_citation"`.
place_id string (optional) The ID of the place, in \`places/{place_id}\` format.
name string (optional) Title of the place.
url string (optional) URI reference of the place.
review_snippets ReviewSnippet (optional) Snippets of reviews that are used to generate answers about the
features of a given place in Google Maps.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
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.
end_index integer (optional) End of the attributed segment, exclusive.
ImageContent An image content block.
type object (required) No description provided.

Always set to `"image"`.
data string (optional) The image content.
uri string (optional) The URI of the image.
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.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
AudioContent An audio content block.
type object (required) No description provided.

Always set to `"audio"`.
data string (optional) The audio content.
uri string (optional) The URI of the audio.
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
channels integer (optional) The number of audio channels.
sample_rate integer (optional) The sample rate of the audio.
DocumentContent A document content block.
type object (required) No description provided.

Always set to `"document"`.
data string (optional) The document content.
uri string (optional) The URI of the document.
mime_type enum (string) (optional) The mime type of the document.

Possible
values:

- `application/pdf`

  PDF document format
- `text/csv`

  CSV document format
VideoContent A video content block.
type object (required) No description provided.

Always set to `"video"`.
data string (optional) The video content.
uri string (optional) The URI of the video.
mime_type enum (string) (optional) The mime type of the video.

Possible
values:

- `video/mp4`

  MP4 video format
- `video/mpeg`

  MPEG video format
- `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
resolution MediaResolution (optional) The resolution of the media.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
type object (required) No description provided.

Always set to `"user_input"`.
ModelOutputStep Output generated by the model.
type object (required) No description provided.

Always set to `"model_output"`.
content Content (optional) No description provided.
The content of the response.

#### Possible Types

Polymorphic discriminator: `type`
TextContent A text content block.
type object (required) No description provided.

Always set to `"text"`.
text string (required) Required. The text content.
annotations Annotation (optional) Citation information for model-generated content.
Citation information for model-generated content.

#### Possible Types

Polymorphic discriminator: `type`
UrlCitation A URL citation annotation.
type object (required) No description provided.

Always set to `"url_citation"`.
url string (optional) The URL.
title string (optional) The title of the URL.
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.
end_index integer (optional) End of the attributed segment, exclusive.
FileCitation A file citation annotation.
type object (required) No description provided.

Always set to `"file_citation"`.
document_uri string (optional) The URI of the file.
file_name string (optional) The name of the file.
source string (optional) Source attributed for a portion of the text.
custom_metadata object (optional) User provided metadata about the retrieved context.
page_number integer (optional) Page number of the cited document, if applicable.
media_id string (optional) Media ID in-case of image citations, if applicable.
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.
end_index integer (optional) End of the attributed segment, exclusive.
PlaceCitation A place citation annotation.
type object (required) No description provided.

Always set to `"place_citation"`.
place_id string (optional) The ID of the place, in \`places/{place_id}\` format.
name string (optional) Title of the place.
url string (optional) URI reference of the place.
review_snippets ReviewSnippet (optional) Snippets of reviews that are used to generate answers about the
features of a given place in Google Maps.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
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.
end_index integer (optional) End of the attributed segment, exclusive.
ImageContent An image content block.
type object (required) No description provided.

Always set to `"image"`.
data string (optional) The image content.
uri string (optional) The URI of the image.
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.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
AudioContent An audio content block.
type object (required) No description provided.

Always set to `"audio"`.
data string (optional) The audio content.
uri string (optional) The URI of the audio.
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
channels integer (optional) The number of audio channels.
sample_rate integer (optional) The sample rate of the audio.
DocumentContent A document content block.
type object (required) No description provided.

Always set to `"document"`.
data string (optional) The document content.
uri string (optional) The URI of the document.
mime_type enum (string) (optional) The mime type of the document.

Possible
values:

- `application/pdf`

  PDF document format
- `text/csv`

  CSV document format
VideoContent A video content block.
type object (required) No description provided.

Always set to `"video"`.
data string (optional) The video content.
uri string (optional) The URI of the video.
mime_type enum (string) (optional) The mime type of the video.

Possible
values:

- `video/mp4`

  MP4 video format
- `video/mpeg`

  MPEG video format
- `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
resolution MediaResolution (optional) The resolution of the media.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
ThoughtStep A thought step.
type object (required) No description provided.

Always set to `"thought"`.
signature string (optional) A signature hash for backend validation.
summary ThoughtSummaryContent (optional) A summary of the thought.
<br />

#### Possible Types

Polymorphic discriminator: `type`
TextContent A text content block.
type object (required) No description provided.

Always set to `"text"`.
text string (required) Required. The text content.
annotations Annotation (optional) Citation information for model-generated content.
Citation information for model-generated content.

#### Possible Types

Polymorphic discriminator: `type`
UrlCitation A URL citation annotation.
type object (required) No description provided.

Always set to `"url_citation"`.
url string (optional) The URL.
title string (optional) The title of the URL.
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.
end_index integer (optional) End of the attributed segment, exclusive.
FileCitation A file citation annotation.
type object (required) No description provided.

Always set to `"file_citation"`.
document_uri string (optional) The URI of the file.
file_name string (optional) The name of the file.
source string (optional) Source attributed for a portion of the text.
custom_metadata object (optional) User provided metadata about the retrieved context.
page_number integer (optional) Page number of the cited document, if applicable.
media_id string (optional) Media ID in-case of image citations, if applicable.
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.
end_index integer (optional) End of the attributed segment, exclusive.
PlaceCitation A place citation annotation.
type object (required) No description provided.

Always set to `"place_citation"`.
place_id string (optional) The ID of the place, in \`places/{place_id}\` format.
name string (optional) Title of the place.
url string (optional) URI reference of the place.
review_snippets ReviewSnippet (optional) Snippets of reviews that are used to generate answers about the
features of a given place in Google Maps.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
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.
end_index integer (optional) End of the attributed segment, exclusive.
ImageContent An image content block.
type object (required) No description provided.

Always set to `"image"`.
data string (optional) The image content.
uri string (optional) The URI of the image.
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.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
FunctionCallStep A function tool call step.
type object (required) No description provided.

Always set to `"function_call"`.
name string (required) Required. The name of the tool to call.
arguments object (required) Required. The arguments to pass to the function.
id string (required) Required. A unique ID for this specific tool call.
CodeExecutionCallStep Code execution call step.
type object (required) No description provided.

Always set to `"code_execution_call"`.
arguments CodeExecutionCallStepArguments (required) Required. The arguments to pass to the code execution.
The arguments to pass to the code execution.

#### Fields

language enum (string) (optional) Programming language of the \`code\`.

Possible
values:

- `python`

  Python \>= 3.10, with numpy and simpy available.
code string (optional) The code to be executed.
id string (required) Required. A unique ID for this specific tool call.
signature string (optional) A signature hash for backend validation.
UrlContextCallStep URL context call step.
type object (required) No description provided.

Always set to `"url_context_call"`.
id string (required) Required. A unique ID for this specific tool call.
signature string (optional) A signature hash for backend validation.
arguments UrlContextCallArguments (required) The arguments to pass to the URL context.
The arguments to pass to the URL context.

#### Fields

urls array (string) (optional) The URLs to fetch.
McpServerToolCallStep MCPServer tool call step.
type object (required) No description provided.

Always set to `"mcp_server_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.
arguments object (required) Required. The JSON object of arguments for the function.
id string (required) Required. A unique ID for this specific tool call.
GoogleSearchCallStep Google Search call step.
type object (required) No description provided.

Always set to `"google_search_call"`.
arguments GoogleSearchCallStepArguments (required) Required. The arguments to pass to Google Search.
The arguments to pass to Google Search.

#### Fields

queries array (string) (optional) Web search queries for the following-up web search.
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.
id string (required) Required. A unique ID for this specific tool call.
signature string (optional) A signature hash for backend validation.
FileSearchCallStep File Search call step.
type object (required) No description provided.

Always set to `"file_search_call"`.
id string (required) Required. A unique ID for this specific tool call.
signature string (optional) A signature hash for backend validation.
GoogleMapsCallStep Google Maps call step.
type object (required) No description provided.

Always set to `"google_maps_call"`.
arguments GoogleMapsCallStepArguments (optional) The arguments to pass to the Google Maps tool.
The arguments to pass to the Google Maps tool.

#### Fields

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.
FunctionResultStep Result of a function tool call.
type object (required) No description provided.

Always set to `"function_result"`.
name string (optional) The name of the tool that was called.
is_error boolean (optional) Whether the tool call resulted in an error.
call_id string (required) Required. ID to match the ID from the function call block.
result array (ImageContent or TextContent) or object or string (required) The result of the tool call.
CodeExecutionResultStep Code execution result step.
type object (required) No description provided.

Always set to `"code_execution_result"`.
result string (required) Required. The output of the code execution.
is_error boolean (optional) Whether the code execution resulted in an error.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
UrlContextResultStep URL context result step.
type object (required) No description provided.

Always set to `"url_context_result"`.
result UrlContextResult (required) Required. The results of the URL context.
The result of the URL context.

#### Fields

url string (optional) The URL that was fetched.
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.
is_error boolean (optional) Whether the URL context resulted in an error.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
GoogleSearchResultStep Google Search result step.
type object (required) No description provided.

Always set to `"google_search_result"`.
result GoogleSearchResultItem (required) Required. The results of the Google Search.
The result of the Google Search.

#### Fields

search_suggestions string (optional) Web content snippet that can be embedded in a web page or an app webview.
is_error boolean (optional) Whether the Google Search resulted in an error.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
McpServerToolResultStep MCPServer tool result step.
type object (required) No description provided.

Always set to `"mcp_server_tool_result"`.
name string (optional) Name of the tool which is called for this specific tool call.
server_name string (optional) The name of the used MCP server.
call_id string (required) Required. ID to match the ID from the function call block.
result array (ImageContent or TextContent) or object or string (required) The output from the MCP server call. Can be simple text or rich content.
FileSearchResultStep File Search result step.
type object (required) No description provided.

Always set to `"file_search_result"`.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
GoogleMapsResultStep Google Maps result step.
type object (required) No description provided.

Always set to `"google_maps_result"`.
result GoogleMapsResultItem (required) No description provided.
The result of the Google Maps.

#### Fields

places GoogleMapsResultPlaces (optional) No description provided.
<br />

#### Fields

place_id string (optional) No description provided.
name string (optional) No description provided.
url string (optional) No description provided.
review_snippets ReviewSnippet (optional) No description provided.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
widget_context_token string (optional) No description provided.
call_id string (required) Required. ID to match the ID from the function call block.
signature string (optional) A signature hash for backend validation.
event_id string (optional) The event_id token to be used to resume the interaction stream, from
this event.
metadata StreamMetadata (optional) Optional metadata accompanying ANY streamed event.
<br />

#### Fields

total_usage Usage (optional) No description provided.
Statistics on the interaction request's token usage.

#### Fields

total_input_tokens integer (optional) Number of tokens in the prompt (context).
input_tokens_by_modality ModalityTokens (optional) A breakdown of input token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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).
cached_tokens_by_modality ModalityTokens (optional) A breakdown of cached token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_output_tokens integer (optional) Total number of tokens across all the generated responses.
output_tokens_by_modality ModalityTokens (optional) A breakdown of output token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_tool_use_tokens integer (optional) Number of tokens present in tool-use prompt(s).
tool_use_tokens_by_modality ModalityTokens (optional) A breakdown of tool-use token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_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).
grounding_tool_count GroundingToolCount (optional) Grounding tool count.
The number of grounding tool counts.

#### Fields

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.
count integer (optional) The number of grounding tool counts.
StepDelta <br />

event_type object (required) No description provided.

Always set to `"step.delta"`.
index integer (required) No description provided.
delta StepDeltaData (required) No description provided.
<br />

#### Possible Types

Polymorphic discriminator: `type`
TextDelta <br />

type object (required) No description provided.

Always set to `"text"`.
text string (required) No description provided.
ImageDelta <br />

type object (required) No description provided.

Always set to `"image"`.
data string (optional) No description provided.
uri string (optional) No description provided.
mime_type enum (string) (optional) No description provided.

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.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
AudioDelta <br />

type object (required) No description provided.

Always set to `"audio"`.
data string (optional) No description provided.
uri string (optional) No description provided.
mime_type enum (string) (optional) No description provided.

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.
channels integer (optional) The number of audio channels.
DocumentDelta <br />

type object (required) No description provided.

Always set to `"document"`.
data string (optional) No description provided.
uri string (optional) No description provided.
mime_type enum (string) (optional) No description provided.

Possible
values:

- `application/pdf`

  PDF document format
- `text/csv`

  CSV document format
VideoDelta <br />

type object (required) No description provided.

Always set to `"video"`.
data string (optional) No description provided.
uri string (optional) No description provided.
mime_type enum (string) (optional) No description provided.

Possible
values:

- `video/mp4`

  MP4 video format
- `video/mpeg`

  MPEG video format
- `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
resolution MediaResolution (optional) The resolution of the media.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
ThoughtSummaryDelta <br />

type object (required) No description provided.

Always set to `"thought_summary"`.
content Content (optional) A new summary item to be added to the thought.
The content of the response.

#### Possible Types

Polymorphic discriminator: `type`
TextContent A text content block.
type object (required) No description provided.

Always set to `"text"`.
text string (required) Required. The text content.
annotations Annotation (optional) Citation information for model-generated content.
Citation information for model-generated content.

#### Possible Types

Polymorphic discriminator: `type`
UrlCitation A URL citation annotation.
type object (required) No description provided.

Always set to `"url_citation"`.
url string (optional) The URL.
title string (optional) The title of the URL.
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.
end_index integer (optional) End of the attributed segment, exclusive.
FileCitation A file citation annotation.
type object (required) No description provided.

Always set to `"file_citation"`.
document_uri string (optional) The URI of the file.
file_name string (optional) The name of the file.
source string (optional) Source attributed for a portion of the text.
custom_metadata object (optional) User provided metadata about the retrieved context.
page_number integer (optional) Page number of the cited document, if applicable.
media_id string (optional) Media ID in-case of image citations, if applicable.
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.
end_index integer (optional) End of the attributed segment, exclusive.
PlaceCitation A place citation annotation.
type object (required) No description provided.

Always set to `"place_citation"`.
place_id string (optional) The ID of the place, in \`places/{place_id}\` format.
name string (optional) Title of the place.
url string (optional) URI reference of the place.
review_snippets ReviewSnippet (optional) Snippets of reviews that are used to generate answers about the
features of a given place in Google Maps.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
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.
end_index integer (optional) End of the attributed segment, exclusive.
ImageContent An image content block.
type object (required) No description provided.

Always set to `"image"`.
data string (optional) The image content.
uri string (optional) The URI of the image.
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.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
AudioContent An audio content block.
type object (required) No description provided.

Always set to `"audio"`.
data string (optional) The audio content.
uri string (optional) The URI of the audio.
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
channels integer (optional) The number of audio channels.
sample_rate integer (optional) The sample rate of the audio.
DocumentContent A document content block.
type object (required) No description provided.

Always set to `"document"`.
data string (optional) The document content.
uri string (optional) The URI of the document.
mime_type enum (string) (optional) The mime type of the document.

Possible
values:

- `application/pdf`

  PDF document format
- `text/csv`

  CSV document format
VideoContent A video content block.
type object (required) No description provided.

Always set to `"video"`.
data string (optional) The video content.
uri string (optional) The URI of the video.
mime_type enum (string) (optional) The mime type of the video.

Possible
values:

- `video/mp4`

  MP4 video format
- `video/mpeg`

  MPEG video format
- `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
resolution MediaResolution (optional) The resolution of the media.
<br />

#### Possible values

- `low`

  Low resolution.
- `medium`

  Medium resolution.
- `high`

  High resolution.
- `ultra_high`

  Ultra high resolution.
ThoughtSignatureDelta <br />

type object (required) No description provided.

Always set to `"thought_signature"`.
signature string (optional) Signature to match the backend source to be part of the generation.
TextAnnotationDelta <br />

type object (required) No description provided.

Always set to `"text_annotation_delta"`.
annotations Annotation (optional) Citation information for model-generated content.
Citation information for model-generated content.

#### Possible Types

Polymorphic discriminator: `type`
UrlCitation A URL citation annotation.
type object (required) No description provided.

Always set to `"url_citation"`.
url string (optional) The URL.
title string (optional) The title of the URL.
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.
end_index integer (optional) End of the attributed segment, exclusive.
FileCitation A file citation annotation.
type object (required) No description provided.

Always set to `"file_citation"`.
document_uri string (optional) The URI of the file.
file_name string (optional) The name of the file.
source string (optional) Source attributed for a portion of the text.
custom_metadata object (optional) User provided metadata about the retrieved context.
page_number integer (optional) Page number of the cited document, if applicable.
media_id string (optional) Media ID in-case of image citations, if applicable.
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.
end_index integer (optional) End of the attributed segment, exclusive.
PlaceCitation A place citation annotation.
type object (required) No description provided.

Always set to `"place_citation"`.
place_id string (optional) The ID of the place, in \`places/{place_id}\` format.
name string (optional) Title of the place.
url string (optional) URI reference of the place.
review_snippets ReviewSnippet (optional) Snippets of reviews that are used to generate answers about the
features of a given place in Google Maps.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
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.
end_index integer (optional) End of the attributed segment, exclusive.
ArgumentsDelta <br />

type object (required) No description provided.

Always set to `"arguments_delta"`.
arguments string (optional) No description provided.
CodeExecutionCallDelta <br />

type object (required) No description provided.

Always set to `"code_execution_call"`.
arguments CodeExecutionCallArguments (required) No description provided.
The arguments to pass to the code execution.

#### Fields

language enum (string) (optional) Programming language of the \`code\`.

Possible
values:

- `python`

  Python \>= 3.10, with numpy and simpy available.
code string (optional) The code to be executed.
signature string (optional) A signature hash for backend validation.
UrlContextCallDelta <br />

type object (required) No description provided.

Always set to `"url_context_call"`.
arguments UrlContextCallArguments (required) No description provided.
The arguments to pass to the URL context.

#### Fields

urls array (string) (optional) The URLs to fetch.
signature string (optional) A signature hash for backend validation.
GoogleSearchCallDelta <br />

type object (required) No description provided.

Always set to `"google_search_call"`.
arguments GoogleSearchCallArguments (required) No description provided.
The arguments to pass to Google Search.

#### Fields

queries array (string) (optional) Web search queries for the following-up web search.
signature string (optional) A signature hash for backend validation.
McpServerToolCallDelta <br />

type object (required) No description provided.

Always set to `"mcp_server_tool_call"`.
name string (required) No description provided.
server_name string (required) No description provided.
arguments object (required) No description provided.
FileSearchCallDelta <br />

type object (required) No description provided.

Always set to `"file_search_call"`.
signature string (optional) A signature hash for backend validation.
GoogleMapsCallDelta <br />

type object (required) No description provided.

Always set to `"google_maps_call"`.
arguments GoogleMapsCallArguments (optional) The arguments to pass to the Google Maps tool.
The arguments to pass to the Google Maps tool.

#### Fields

queries array (string) (optional) The queries to be executed.
signature string (optional) A signature hash for backend validation.
CodeExecutionResultDelta <br />

type object (required) No description provided.

Always set to `"code_execution_result"`.
result string (required) No description provided.
is_error boolean (optional) No description provided.
signature string (optional) A signature hash for backend validation.
UrlContextResultDelta <br />

type object (required) No description provided.

Always set to `"url_context_result"`.
result UrlContextResult (required) No description provided.
The result of the URL context.

#### Fields

url string (optional) The URL that was fetched.
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.
is_error boolean (optional) No description provided.
signature string (optional) A signature hash for backend validation.
GoogleSearchResultDelta <br />

type object (required) No description provided.

Always set to `"google_search_result"`.
result GoogleSearchResult (required) No description provided.
The result of the Google Search.

#### Fields

search_suggestions string (optional) Web content snippet that can be embedded in a web page or an app webview.
is_error boolean (optional) No description provided.
signature string (optional) A signature hash for backend validation.
McpServerToolResultDelta <br />

type object (required) No description provided.

Always set to `"mcp_server_tool_result"`.
name string (optional) No description provided.
server_name string (optional) No description provided.
result array (ImageContent or TextContent) or object or string (required) No description provided.
FileSearchResultDelta <br />

type object (required) No description provided.

Always set to `"file_search_result"`.
result FileSearchResult (required) No description provided.
The result of the File Search.
signature string (optional) A signature hash for backend validation.
GoogleMapsResultDelta <br />

type object (required) No description provided.

Always set to `"google_maps_result"`.
result GoogleMapsResult (optional) The results of the Google Maps.
The result of the Google Maps.

#### Fields

places Places (optional) The places that were found.
<br />

#### Fields

place_id string (optional) The ID of the place, in \`places/{place_id}\` format.
name string (optional) Title of the place.
url string (optional) URI reference of the place.
review_snippets ReviewSnippet (optional) Snippets of reviews that are used to generate answers about the
features of a given place in Google Maps.
Encapsulates a snippet of a user review that answers a question about
the features of a specific place in Google Maps.

#### Fields

title string (optional) Title of the review.
url string (optional) A link that corresponds to the user review on Google Maps.
review_id string (optional) The ID of the review snippet.
widget_context_token string (optional) Resource name of the Google Maps widget context token.
signature string (optional) A signature hash for backend validation.
FunctionResultDelta <br />

type object (required) No description provided.

Always set to `"function_result"`.
name string (optional) No description provided.
is_error boolean (optional) No description provided.
call_id string (required) Required. ID to match the ID from the function call block.
result array (ImageContent or TextContent) or object or string (required) No description provided.
event_id string (optional) The event_id token to be used to resume the interaction stream, from
this event.
metadata StepDeltaMetadata (optional) Optional metadata accompanying ANY streamed event.
Optional metadata accompanying ANY streamed event.

#### Fields

total_usage Usage (optional) Statistics on the interaction request's token usage.
Statistics on the interaction request's token usage.

#### Fields

total_input_tokens integer (optional) Number of tokens in the prompt (context).
input_tokens_by_modality ModalityTokens (optional) A breakdown of input token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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).
cached_tokens_by_modality ModalityTokens (optional) A breakdown of cached token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_output_tokens integer (optional) Total number of tokens across all the generated responses.
output_tokens_by_modality ModalityTokens (optional) A breakdown of output token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_tool_use_tokens integer (optional) Number of tokens present in tool-use prompt(s).
tool_use_tokens_by_modality ModalityTokens (optional) A breakdown of tool-use token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_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).
grounding_tool_count GroundingToolCount (optional) Grounding tool count.
The number of grounding tool counts.

#### Fields

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.
count integer (optional) The number of grounding tool counts.
StepStop <br />

event_type object (required) No description provided.

Always set to `"step.stop"`.
index integer (required) No description provided.
event_id string (optional) The event_id token to be used to resume the interaction stream, from
this event.
metadata StreamMetadata (optional) Optional metadata accompanying ANY streamed event.
<br />

#### Fields

total_usage Usage (optional) No description provided.
Statistics on the interaction request's token usage.

#### Fields

total_input_tokens integer (optional) Number of tokens in the prompt (context).
input_tokens_by_modality ModalityTokens (optional) A breakdown of input token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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).
cached_tokens_by_modality ModalityTokens (optional) A breakdown of cached token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_output_tokens integer (optional) Total number of tokens across all the generated responses.
output_tokens_by_modality ModalityTokens (optional) A breakdown of output token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_tool_use_tokens integer (optional) Number of tokens present in tool-use prompt(s).
tool_use_tokens_by_modality ModalityTokens (optional) A breakdown of tool-use token usage by modality.
The token count for a single response modality.

#### Fields

modality ResponseModality (optional) The modality associated with the token count.
<br />

#### Possible values

- `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_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).
grounding_tool_count GroundingToolCount (optional) Grounding tool count.
The number of grounding tool counts.

#### Fields

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.
count integer (optional) The number of grounding tool counts.

### Examples

### Interaction Created

```json
{
  "event_type": "interaction.created",
  "interaction": {
    "id": "v1_ChdXS0l4YWZXTk9xbk0xZThQczhEcmlROBIXV0tJeGFmV05PcW5NMWU4UHM4RHJpUTg",
    "model": "gemini-3.5-flash",
    "status": "in_progress",
    "created": "2025-12-04T15:01:45Z",
    "updated": "2025-12-04T15:01:45Z"
  },
  "event_id": "evt_123"
}
```

### Interaction Created

```json
{
  "event_type": "interaction.created",
  "interaction": {
    "id": "v1_ChdXS0l4YWZXTk9xbk0xZThQczhEcmlROBIXV0tJeGFmV05PcW5NMWU4UHM4RHJpUTg",
    "model": "gemini-3-flash-preview",
    "object": "interaction",
    "status": "in_progress"
  },
  "event_id": "evt_123"
}
```

### Interaction Completed

```json
{
  "event_type": "interaction.completed",
  "interaction": {
    "id": "v1_ChdXS0l4YWZXTk9xbk0xZThQczhEcmlROBIXV0tJeGFmV05PcW5NMWU4UHM4RHJpUTg",
    "model": "gemini-3.5-flash",
    "status": "completed",
    "created": "2025-12-04T15:01:45Z",
    "updated": "2025-12-04T15:01:45Z"
  },
  "event_id": "evt_123"
}
```

### Interaction Completed

```json
{
  "event_type": "interaction.completed",
  "interaction": {
    "id": "v1_ChdXS0l4YWZXTk9xbk0xZThQczhEcmlROBIXV0tJeGFmV05PcW5NMWU4UHM4RHJpUTg",
    "model": "gemini-3-flash-preview",
    "object": "interaction",
    "status": "completed",
    "created": "2025-12-04T15:01:45Z",
    "updated": "2025-12-04T15:01:45Z"
  },
  "event_id": "evt_123"
}
```

### Interaction Status Update

```json
{
  "event_type": "interaction.status_update",
  "interaction_id": "v1_ChdTMjQ0YWJ5TUF1TzcxZThQdjRpcnFRcxIXUzI0NGFieU1BdU83MWU4UHY0aXJxUXM",
  "status": "in_progress"
}
```

### Error Event

```json
{
  "event_type": "error",
  "error": {
    "message": "Failed to get completed interaction: Result not found.",
    "code": "not_found"
  }
}
```

### Step Start

```json
{
  "event_type": "step.start",
  "index": 0,
  "step": {
    "type": "model_output"
  }
}
```

### Step Delta

```json
{
  "event_type": "step.delta",
  "index": 0,
  "delta": {
    "type": "text",
    "text": "Hello"
  }
}
```

### Step Stop

```json
{
  "event_type": "step.stop",
  "index": 0
}
```