Microsoft Foundry - agents

API Version: v1

Server: {endpoint} — Microsoft Foundry

Server Variables:

Variable	Default	Description
endpoint		Foundry Project endpoint in the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/{project-name}". If you only have one Project in your Foundry Hub, or to target the default Project in your Hub, use the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/_project"

Authentication

OAuth2Auth (OAuth 2.0)

Flow: implicit

Authorization URL: https://login.microsoftonline.com/common/oauth2/v2.0/authorize

Scopes:

https://ai.azure.com/.default

Security Requirements

All endpoints require OAuth2Auth (scopes: https://ai.azure.com/.default).

Agents - create agent

POST {endpoint}/agents?api-version=v1

Creates the agent.

URI Parameters

Name	In	Required	Type	Description
endpoint	server	Yes	string	Foundry Project endpoint in the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/{project-name}". If you only have one Project in your Foundry Hub, or to target the default Project in your Hub, use the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/_project"
api-version	query	Yes	string	The API version to use for this operation. Serialization: explode: false

Request Header

Name	Required	Type	Description
Foundry-Features	No	string Possible values: `HostedAgents=V1Preview`, `WorkflowAgents=V1Preview`	A feature flag opt-in required when using preview operations or modifying persisted preview resources.

Request Body

Content-Type: application/json

Name	Type	Description	Required
definition	AgentDefinition		Yes
└─ kind	AgentKind		Yes
└─ rai_config	RaiConfig	Configuration for Responsible AI (RAI) content filtering and safety features.	No
description	string	A human-readable description of the agent. Constraints: maxLength: 512	No
metadata	object	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.	No
name	string	The unique name that identifies the agent. Name can be used to retrieve/update/delete the agent. - Must start and end with alphanumeric characters, - Can contain hyphens in the middle - Must not exceed 63 characters. Constraints: maxLength: 63	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	AgentObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	ApiErrorResponse

Agents - list agents

GET {endpoint}/agents?api-version=v1

Returns the list of all agents.

URI Parameters

Name	In	Required	Type	Description
endpoint	server	Yes	string	Foundry Project endpoint in the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/{project-name}". If you only have one Project in your Foundry Hub, or to target the default Project in your Hub, use the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/_project"
kind	query	No	string Possible values: `prompt`, `hosted`, `workflow`	Filter agents by kind. If not provided, all agents are returned. Serialization: explode: false
limit	query	No	integer (int32)	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20. Serialization: explode: false
order	query	No	string Possible values: `asc`, `desc`	Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and`desc` for descending order. Serialization: explode: false
after	query	No	string	A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list. Serialization: explode: false
before	query	No	string	A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list. Serialization: explode: false
api-version	query	Yes	string	The API version to use for this operation. Serialization: explode: false

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object	The response data for a requested list of items.

Name	Type	Description	Required
data	array of AgentObject	The requested list of items.	Yes
first_id	string	The first ID represented in this list.	No
has_more	boolean	A value indicating whether there are additional values available not captured in this list.	Yes
last_id	string	The last ID represented in this list.	No

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	ApiErrorResponse

Agents - get agent

GET {endpoint}/agents/{agent_name}?api-version=v1

Retrieves the agent.

URI Parameters

Name	In	Required	Type	Description
endpoint	server	Yes	string	Foundry Project endpoint in the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/{project-name}". If you only have one Project in your Foundry Hub, or to target the default Project in your Hub, use the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/_project"
agent_name	path	Yes	string	The name of the agent to retrieve.
api-version	query	Yes	string	The API version to use for this operation. Serialization: explode: false

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	AgentObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	ApiErrorResponse

Agents - update agent

POST {endpoint}/agents/{agent_name}?api-version=v1

Updates the agent by adding a new version if there are any changes to the agent definition. If no changes, returns the existing agent version.

URI Parameters

Name	In	Required	Type	Description
endpoint	server	Yes	string	Foundry Project endpoint in the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/{project-name}". If you only have one Project in your Foundry Hub, or to target the default Project in your Hub, use the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/_project"
agent_name	path	Yes	string	The name of the agent to retrieve.
api-version	query	Yes	string	The API version to use for this operation. Serialization: explode: false

Request Header

Name	Required	Type	Description
Foundry-Features	No	string Possible values: `HostedAgents=V1Preview`, `WorkflowAgents=V1Preview`	A feature flag opt-in required when using preview operations or modifying persisted preview resources.

Request Body

Content-Type: application/json

Name	Type	Description	Required
definition	AgentDefinition		Yes
└─ kind	AgentKind		Yes
└─ rai_config	RaiConfig	Configuration for Responsible AI (RAI) content filtering and safety features.	No
description	string	A human-readable description of the agent. Constraints: maxLength: 512	No
metadata	object	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	AgentObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	ApiErrorResponse

Agents - delete agent

DELETE {endpoint}/agents/{agent_name}?api-version=v1

Deletes an agent.

URI Parameters

Name	In	Required	Type	Description
endpoint	server	Yes	string	Foundry Project endpoint in the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/{project-name}". If you only have one Project in your Foundry Hub, or to target the default Project in your Hub, use the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/_project"
agent_name	path	Yes	string	The name of the agent to delete.
api-version	query	Yes	string	The API version to use for this operation. Serialization: explode: false

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	DeleteAgentResponse

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	ApiErrorResponse

Agents - update agent from manifest

POST {endpoint}/agents/{agent_name}/import?api-version=v1

Updates the agent from a manifest by adding a new version if there are any changes to the agent definition. If no changes, returns the existing agent version.

URI Parameters

Name	In	Required	Type	Description
endpoint	server	Yes	string	Foundry Project endpoint in the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/{project-name}". If you only have one Project in your Foundry Hub, or to target the default Project in your Hub, use the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/_project"
agent_name	path	Yes	string	The name of the agent to update.
api-version	query	Yes	string	The API version to use for this operation. Serialization: explode: false

Request Body

Content-Type: application/json

Name	Type	Description	Required
description	string	A human-readable description of the agent. Constraints: maxLength: 512	No
manifest_id	string	The manifest ID to import the agent version from.	Yes
metadata	object	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.	No
parameter_values	object	The inputs to the manifest that will result in a fully materialized Agent.	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	AgentObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	ApiErrorResponse

Agents - create agent version

POST {endpoint}/agents/{agent_name}/versions?api-version=v1

Create a new agent version.

URI Parameters

Name	In	Required	Type	Description
endpoint	server	Yes	string	Foundry Project endpoint in the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/{project-name}". If you only have one Project in your Foundry Hub, or to target the default Project in your Hub, use the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/_project"
agent_name	path	Yes	string	The unique name that identifies the agent. Name can be used to retrieve/update/delete the agent. - Must start and end with alphanumeric characters, - Can contain hyphens in the middle - Must not exceed 63 characters.
api-version	query	Yes	string	The API version to use for this operation. Serialization: explode: false

Request Header

Name	Required	Type	Description
Foundry-Features	No	string Possible values: `HostedAgents=V1Preview`, `WorkflowAgents=V1Preview`	A feature flag opt-in required when using preview operations or modifying persisted preview resources.

Request Body

Content-Type: application/json

Name	Type	Description	Required
definition	AgentDefinition		Yes
└─ kind	AgentKind		Yes
└─ rai_config	RaiConfig	Configuration for Responsible AI (RAI) content filtering and safety features.	No
description	string	A human-readable description of the agent. Constraints: maxLength: 512	No
metadata	object	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.	No

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	AgentVersionObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	ApiErrorResponse

Agents - list agent versions

GET {endpoint}/agents/{agent_name}/versions?api-version=v1

Returns the list of versions of an agent.

URI Parameters

Name	In	Required	Type	Description
endpoint	server	Yes	string	Foundry Project endpoint in the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/{project-name}". If you only have one Project in your Foundry Hub, or to target the default Project in your Hub, use the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/_project"
agent_name	path	Yes	string	The name of the agent to retrieve versions for.
limit	query	No	integer (int32)	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20. Serialization: explode: false
order	query	No	string Possible values: `asc`, `desc`	Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and`desc` for descending order. Serialization: explode: false
after	query	No	string	A cursor for use in pagination. `after` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include after=obj_foo in order to fetch the next page of the list. Serialization: explode: false
before	query	No	string	A cursor for use in pagination. `before` is an object ID that defines your place in the list. For instance, if you make a list request and receive 100 objects, ending with obj_foo, your subsequent call can include before=obj_foo in order to fetch the previous page of the list. Serialization: explode: false
api-version	query	Yes	string	The API version to use for this operation. Serialization: explode: false

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	object	The response data for a requested list of items.

Name	Type	Description	Required
data	array of AgentVersionObject	The requested list of items.	Yes
first_id	string	The first ID represented in this list.	No
has_more	boolean	A value indicating whether there are additional values available not captured in this list.	Yes
last_id	string	The last ID represented in this list.	No

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	ApiErrorResponse

Agents - get agent version

GET {endpoint}/agents/{agent_name}/versions/{agent_version}?api-version=v1

Retrieves a specific version of an agent.

URI Parameters

Name	In	Required	Type	Description
endpoint	server	Yes	string	Foundry Project endpoint in the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/{project-name}". If you only have one Project in your Foundry Hub, or to target the default Project in your Hub, use the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/_project"
agent_name	path	Yes	string	The name of the agent to retrieve.
agent_version	path	Yes	string	The version of the agent to retrieve.
api-version	query	Yes	string	The API version to use for this operation. Serialization: explode: false

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	AgentVersionObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	ApiErrorResponse

Agents - delete agent version

DELETE {endpoint}/agents/{agent_name}/versions/{agent_version}?api-version=v1

Deletes a specific version of an agent.

URI Parameters

Name	In	Required	Type	Description
endpoint	server	Yes	string	Foundry Project endpoint in the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/{project-name}". If you only have one Project in your Foundry Hub, or to target the default Project in your Hub, use the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/_project"
agent_name	path	Yes	string	The name of the agent to delete.
agent_version	path	Yes	string	The version of the agent to delete
api-version	query	Yes	string	The API version to use for this operation. Serialization: explode: false

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	DeleteAgentVersionResponse

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	ApiErrorResponse

Agents - create agent version from manifest

POST {endpoint}/agents/{agent_name}/versions:import?api-version=v1

Create a new agent version from a manifest.

URI Parameters

Name	In	Required	Type	Description
endpoint	server	Yes	string	Foundry Project endpoint in the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/{project-name}". If you only have one Project in your Foundry Hub, or to target the default Project in your Hub, use the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/_project"
agent_name	path	Yes	string	The unique name that identifies the agent. Name can be used to retrieve/update/delete the agent. - Must start and end with alphanumeric characters, - Can contain hyphens in the middle - Must not exceed 63 characters.
api-version	query	Yes	string	The API version to use for this operation. Serialization: explode: false

Request Body

Content-Type: application/json

Name	Type	Description	Required
description	string	A human-readable description of the agent. Constraints: maxLength: 512	No
manifest_id	string	The manifest ID to import the agent version from.	Yes
metadata	object	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.	No
parameter_values	object	The inputs to the manifest that will result in a fully materialized Agent.	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	AgentVersionObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	ApiErrorResponse

Agents - create agent from manifest

POST {endpoint}/agents:import?api-version=v1

Creates an agent from a manifest.

URI Parameters

Name	In	Required	Type	Description
endpoint	server	Yes	string	Foundry Project endpoint in the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/{project-name}". If you only have one Project in your Foundry Hub, or to target the default Project in your Hub, use the form "https://{ai-services-account-name}.services.ai.azure.com/api/projects/_project"
api-version	query	Yes	string	The API version to use for this operation. Serialization: explode: false

Request Body

Content-Type: application/json

Name	Type	Description	Required
description	string	A human-readable description of the agent. Constraints: maxLength: 512	No
manifest_id	string	The manifest ID to import the agent version from.	Yes
metadata	object	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.	No
name	string	The unique name that identifies the agent. Name can be used to retrieve/update/delete the agent. - Must start and end with alphanumeric characters, - Can contain hyphens in the middle - Must not exceed 63 characters. Constraints: maxLength: 63	Yes
parameter_values	object	The inputs to the manifest that will result in a fully materialized Agent.	Yes

Responses

Status Code: 200

Description: The request has succeeded.

Content-Type	Type	Description
application/json	AgentObject

Status Code: default

Description: An unexpected error response.

Content-Type	Type	Description
application/json	ApiErrorResponse

Components

A2APreviewTool

An agent implementing the A2A protocol.

Name	Type	Description	Required
agent_card_path	string	The path to the agent card relative to the `base_url`. If not provided, defaults to `/.well-known/agent-card.json`	No
base_url	string (uri)	Base URL of the agent.	No
project_connection_id	string	The connection ID in the project for the A2A server. The connection stores authentication and other connection details needed to connect to the A2A server.	No
type	enum	The type of the tool. Always `"a2a_preview`. Possible values: `a2a_preview`	Yes

AISearchIndexResource

A AI Search Index resource.

Name	Type	Description	Required
filter	string	filter string for search resource. Learn more here.	No
index_asset_id	string	Index asset id for search resource.	No
index_name	string	The name of an index in an IndexResource attached to this agent.	No
project_connection_id	string	An index connection ID in an IndexResource attached to this agent.	No
query_type	AzureAISearchQueryType	Available query types for Azure AI Search tool.	No
top_k	integer (int32)	Number of documents to retrieve from search and present to the model.	No

AgentDefinition

Discriminator for AgentDefinition

This component uses the property kind to discriminate between different types:

Type Value	Schema
`prompt`	PromptAgentDefinition
`workflow`	WorkflowAgentDefinition
`hosted`	HostedAgentDefinition

Name	Type	Description	Required
kind	AgentKind		Yes
rai_config	RaiConfig	Configuration for Responsible AI (RAI) content filtering and safety features.	No
└─ rai_policy_name	string	The name of the RAI policy to apply.	Yes

AgentDefinitionOptInKeys

Feature opt-in keys for agent definition operations supporting hosted or workflow agents.

Property	Value
Type	string
Values	`HostedAgents=V1Preview` `WorkflowAgents=V1Preview`

AgentKind

Property	Value
Type	string
Values	`prompt` `hosted` `workflow`

AgentObject

Name	Type	Description	Required
id	string	The unique identifier of the agent.	Yes
name	string	The name of the agent. Constraints: maxLength: 63	Yes
object	enum	The object type, which is always 'agent'. Possible values: `agent`	Yes
versions	object	The latest version of the agent.	Yes
└─ latest	AgentVersionObject		Yes

AgentProtocol

Property	Value
Type	string
Values	`activity_protocol` `responses`

AgentVersionObject

Name	Type	Description	Required
created_at	FoundryTimestamp		Yes
definition	AgentDefinition		Yes
description	string	A human-readable description of the agent. Constraints: maxLength: 512	No
id	string	The unique identifier of the agent version.	Yes
metadata	object (nullable)	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.	Yes
name	string	The name of the agent. Name can be used to retrieve/update/delete the agent. Constraints: maxLength: 256	Yes
object	enum	The object type, which is always 'agent.version'. Possible values: `agent.version`	Yes
version	string	The version identifier of the agent. Agents are immutable and every update creates a new version while keeping the name same.	Yes

ApiErrorResponse

Error response for API failures.

Name	Type	Description	Required	Default
error	OpenAI.Error		Yes

AzureAISearchQueryType

Available query types for Azure AI Search tool.

Property	Value
Description	Available query types for Azure AI Search tool.
Type	string
Values	`simple` `semantic` `vector` `vector_simple_hybrid` `vector_semantic_hybrid`

AzureAISearchTool

The input definition information for an Azure AI search tool as used to configure an agent.

Name	Type	Description	Required
azure_ai_search	AzureAISearchToolResource	A set of index resources used by the `azure_ai_search` tool.	Yes
└─ indexes	array of AISearchIndexResource	The indices attached to this agent. There can be a maximum of 1 index resource attached to the agent. Constraints: maxItems: 1	Yes
type	enum	The object type, which is always 'azure_ai_search'. Possible values: `azure_ai_search`	Yes

AzureAISearchToolResource

A set of index resources used by the azure_ai_search tool.

Name	Type	Description	Required	Default
indexes	array of AISearchIndexResource	The indices attached to this agent. There can be a maximum of 1 index resource attached to the agent. Constraints: maxItems: 1	Yes

AzureFunctionBinding

The structure for keeping storage queue name and URI.

Name	Type	Description	Required
storage_queue	AzureFunctionStorageQueue	The structure for keeping storage queue name and URI.	Yes
└─ queue_name	string	The name of an Azure function storage queue.	Yes
└─ queue_service_endpoint	string	URI to the Azure Storage Queue service allowing you to manipulate a queue.	Yes
type	enum	The type of binding, which is always 'storage_queue'. Possible values: `storage_queue`	Yes

AzureFunctionDefinition

The definition of Azure function.

Name	Type	Description	Required
function	object	The definition of azure function and its parameters.	Yes
└─ description	string	A description of what the function does, used by the model to choose when and how to call the function.	No
└─ name	string	The name of the function to be called.	Yes
└─ parameters	object	The parameters the functions accepts, described as a JSON Schema object.	Yes
input_binding	AzureFunctionBinding	The structure for keeping storage queue name and URI.	Yes
└─ storage_queue	AzureFunctionStorageQueue	Storage queue.	Yes
└─ type	enum	The type of binding, which is always 'storage_queue'. Possible values: `storage_queue`	Yes
output_binding	AzureFunctionBinding	The structure for keeping storage queue name and URI.	Yes
└─ storage_queue	AzureFunctionStorageQueue	Storage queue.	Yes
└─ type	enum	The type of binding, which is always 'storage_queue'. Possible values: `storage_queue`	Yes

AzureFunctionStorageQueue

The structure for keeping storage queue name and URI.

Name	Type	Description	Required	Default
queue_name	string	The name of an Azure function storage queue.	Yes
queue_service_endpoint	string	URI to the Azure Storage Queue service allowing you to manipulate a queue.	Yes

AzureFunctionTool

The input definition information for an Azure Function Tool, as used to configure an Agent.

Name	Type	Description	Required
azure_function	AzureFunctionDefinition	The definition of Azure function.	Yes
└─ function	object	The definition of azure function and its parameters.	Yes
└─ description	string	A description of what the function does, used by the model to choose when and how to call the function.	No
└─ name	string	The name of the function to be called.	Yes
└─ parameters	object	The parameters the functions accepts, described as a JSON Schema object.	Yes
└─ input_binding	AzureFunctionBinding	Input storage queue. The queue storage trigger runs a function as messages are added to it.	Yes
└─ output_binding	AzureFunctionBinding	Output storage queue. The function writes output to this queue when the input items are processed.	Yes
type	enum	The object type, which is always 'browser_automation'. Possible values: `azure_function`	Yes

BingCustomSearchConfiguration

A bing custom search configuration.

Name	Type	Description	Required
count	integer (int64)	The number of search results to return in the bing api response	No
freshness	string	Filter search results by a specific time range. See accepted values here.	No
instance_name	string	Name of the custom configuration instance given to config.	Yes
market	string	The market where the results come from.	No
project_connection_id	string	Project connection id for grounding with bing search	Yes
set_lang	string	The language to use for user interface strings when calling Bing API.	No

BingCustomSearchPreviewTool

The input definition information for a Bing custom search tool as used to configure an agent.

Name	Type	Description	Required
bing_custom_search_preview	BingCustomSearchToolParameters	The bing custom search tool parameters.	Yes
└─ search_configurations	array of BingCustomSearchConfiguration	The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. Constraints: maxItems: 1	Yes
type	enum	The object type, which is always 'bing_custom_search_preview'. Possible values: `bing_custom_search_preview`	Yes

BingCustomSearchToolParameters

The bing custom search tool parameters.

Name	Type	Description	Required	Default
search_configurations	array of BingCustomSearchConfiguration	The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. Constraints: maxItems: 1	Yes

BingGroundingSearchConfiguration

Search configuration for Bing Grounding

Name	Type	Description	Required
count	integer (int64)	The number of search results to return in the bing api response	No
freshness	string	Filter search results by a specific time range. See accepted values here.	No
market	string	The market where the results come from.	No
project_connection_id	string	Project connection id for grounding with bing search	Yes
set_lang	string	The language to use for user interface strings when calling Bing API.	No

BingGroundingSearchToolParameters

The bing grounding search tool parameters.

Name	Type	Description	Required	Default
search_configurations	array of BingGroundingSearchConfiguration	The search configurations attached to this tool. There can be a maximum of 1 search configuration resource attached to the tool. Constraints: maxItems: 1	Yes

BingGroundingTool

The input definition information for a bing grounding search tool as used to configure an agent.

Name	Type	Description	Required
bing_grounding	BingGroundingSearchToolParameters	The bing grounding search tool parameters.	Yes
└─ search_configurations	array of BingGroundingSearchConfiguration	The search configurations attached to this tool. There can be a maximum of 1 search configuration resource attached to the tool. Constraints: maxItems: 1	Yes
type	enum	The object type, which is always 'bing_grounding'. Possible values: `bing_grounding`	Yes

BrowserAutomationPreviewTool

The input definition information for a Browser Automation Tool, as used to configure an Agent.

Name	Type	Description	Required
browser_automation_preview	BrowserAutomationToolParameters	Definition of input parameters for the Browser Automation Tool.	Yes
└─ connection	BrowserAutomationToolConnectionParameters	The project connection parameters associated with the Browser Automation Tool.	Yes
type	enum	The object type, which is always 'browser_automation_preview'. Possible values: `browser_automation_preview`	Yes

BrowserAutomationToolConnectionParameters

Definition of input parameters for the connection used by the Browser Automation Tool.

Name	Type	Description	Required	Default
project_connection_id	string	The ID of the project connection to your Azure Playwright resource.	Yes

BrowserAutomationToolParameters

Definition of input parameters for the Browser Automation Tool.

Name	Type	Description	Required	Default
connection	BrowserAutomationToolConnectionParameters	Definition of input parameters for the connection used by the Browser Automation Tool.	Yes
└─ project_connection_id	string	The ID of the project connection to your Azure Playwright resource.	Yes

CaptureStructuredOutputsTool

A tool for capturing structured outputs

Name	Type	Description	Required
outputs	StructuredOutputDefinition	A structured output that can be produced by the agent.	Yes
└─ description	string	A description of the output to emit. Used by the model to determine when to emit the output.	Yes
└─ name	string	The name of the structured output.	Yes
└─ schema	object	The JSON schema for the structured output.	Yes
└─ strict	boolean (nullable)	Whether to enforce strict validation. Default `true`.	Yes
type	enum	The type of the tool. Always `capture_structured_outputs`. Possible values: `capture_structured_outputs`	Yes

CreateAgentFromManifestRequest

Name	Type	Description	Required
description	string	A human-readable description of the agent. Constraints: maxLength: 512	No
manifest_id	string	The manifest ID to import the agent version from.	Yes
metadata	object	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.	No
name	string	The unique name that identifies the agent. Name can be used to retrieve/update/delete the agent. - Must start and end with alphanumeric characters, - Can contain hyphens in the middle - Must not exceed 63 characters. Constraints: maxLength: 63	Yes
parameter_values	object	The inputs to the manifest that will result in a fully materialized Agent.	Yes

CreateAgentRequest

Name	Type	Description	Required
definition	AgentDefinition		Yes
└─ kind	AgentKind		Yes
└─ rai_config	RaiConfig	Configuration for Responsible AI (RAI) content filtering and safety features.	No
description	string	A human-readable description of the agent. Constraints: maxLength: 512	No
metadata	object	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.	No
name	string	The unique name that identifies the agent. Name can be used to retrieve/update/delete the agent. - Must start and end with alphanumeric characters, - Can contain hyphens in the middle - Must not exceed 63 characters. Constraints: maxLength: 63	Yes

CreateAgentVersionFromManifestRequest

Name	Type	Description	Required
description	string	A human-readable description of the agent. Constraints: maxLength: 512	No
manifest_id	string	The manifest ID to import the agent version from.	Yes
metadata	object	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.	No
parameter_values	object	The inputs to the manifest that will result in a fully materialized Agent.	Yes

CreateAgentVersionRequest

Name	Type	Description	Required
definition	AgentDefinition		Yes
└─ kind	AgentKind		Yes
└─ rai_config	RaiConfig	Configuration for Responsible AI (RAI) content filtering and safety features.	No
description	string	A human-readable description of the agent. Constraints: maxLength: 512	No
metadata	object	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.	No

DeleteAgentResponse

A deleted agent Object

Name	Type	Description	Required
deleted	boolean	Whether the agent was successfully deleted.	Yes
name	string	The name of the agent.	Yes
object	enum	The object type. Always 'agent.deleted'. Possible values: `agent.deleted`	Yes

DeleteAgentVersionResponse

A deleted agent version Object

Name	Type	Description	Required
deleted	boolean	Whether the agent was successfully deleted.	Yes
name	string	The name of the agent.	Yes
object	enum	The object type. Always 'agent.version.deleted'. Possible values: `agent.version.deleted`	Yes
version	string	The version identifier of the agent.	Yes

FabricDataAgentToolParameters

The fabric data agent tool parameters.

Name	Type	Description	Required	Default
project_connections	array of ToolProjectConnection	The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. Constraints: maxItems: 1	No

FoundryTimestamp

Type: integer

Format: unixtime

HostedAgentDefinition

The hosted agent definition.

Name	Type	Description	Required
container_protocol_versions	array of ProtocolVersionRecord	The protocols that the agent supports for ingress communication of the containers.	Yes
cpu	string	The CPU configuration for the hosted agent.	Yes
environment_variables	object	Environment variables to set in the hosted agent container.	No
image	string	The image ID for the agent, applicable to image-based hosted agents.	No
kind	enum	Possible values: `hosted`	Yes
memory	string	The memory configuration for the hosted agent.	Yes
rai_config	RaiConfig	Configuration for Responsible AI (RAI) content filtering and safety features.	No
└─ rai_policy_name	string	The name of the RAI policy to apply.	Yes
tools	array of OpenAI.Tool	An array of tools the hosted agent's model may call while generating a response. You can specify which tool to use by setting the `tool_choice` parameter.	No

MemorySearchOptions

Memory search options.

Name	Type	Description	Required	Default
max_memories	integer (int32)	Maximum number of memory items to return.	No

MemorySearchPreviewTool

A tool for integrating memories into the agent.

Name	Type	Description	Required	Default
memory_store_name	string	The name of the memory store to use.	Yes
scope	string	The namespace used to group and isolate memories, such as a user ID. Limits which memories can be retrieved or updated. Use special variable `{{$userId}}` to scope memories to the current signed-in user.	Yes
search_options	MemorySearchOptions	Memory search options.	No
└─ max_memories	integer (int32)	Maximum number of memory items to return.	No
type	enum	The type of the tool. Always `memory_search_preview`. Possible values: `memory_search_preview`	Yes
update_delay	integer (int32)	Time to wait before updating memories after inactivity (seconds). Default 300.	No	300

MicrosoftFabricPreviewTool

The input definition information for a Microsoft Fabric tool as used to configure an agent.

Name	Type	Description	Required
fabric_dataagent_preview	FabricDataAgentToolParameters	The fabric data agent tool parameters.	Yes
└─ project_connections	array of ToolProjectConnection	The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. Constraints: maxItems: 1	No
type	enum	The object type, which is always 'fabric_dataagent_preview'. Possible values: `fabric_dataagent_preview`	Yes

OpenAI.ApplyPatchToolParam

Apply patch tool

Allows the assistant to create, delete, or update files using unified diffs.

Name	Type	Description	Required	Default
type	enum	The type of the tool. Always `apply_patch`. Possible values: `apply_patch`	Yes	apply_patch

OpenAI.ApproximateLocation

Name	Type	Description	Required	Default
city	string (nullable)		No
country	string (nullable)		No
region	string (nullable)		No
timezone	string (nullable)		No
type	enum	The type of location approximation. Always `approximate`. Possible values: `approximate`	Yes	approximate

OpenAI.AutoCodeInterpreterToolParam

Automatic Code Interpreter Tool Parameters

Configuration for a code interpreter container. Optionally specify the IDs of the files to run the code on.

Name	Type	Description	Required	Default
file_ids	array of string	An optional list of uploaded files to make available to your code. Constraints: maxItems: 50	No
memory_limit	OpenAI.ContainerMemoryLimit (nullable)		No
network_policy	OpenAI.ContainerNetworkPolicyParam	Network access policy for the container.	No
type	enum	Always `auto`. Possible values: `auto`	Yes	auto

OpenAI.CodeInterpreterTool

Code interpreter

A tool that runs Python code to help generate a response to a prompt.

Name	Type	Description	Required	Default
container	string or OpenAI.AutoCodeInterpreterToolParam	The code interpreter container. Can be a container ID or an object that specifies uploaded file IDs to make available to your code, along with an optional `memory_limit` setting. If not provided, the service assumes auto.	No
type	enum	The type of the code interpreter tool. Always `code_interpreter`. Possible values: `code_interpreter`	Yes

OpenAI.ComparisonFilter

Comparison Filter

A filter used to compare a specified attribute key to a given value using a defined comparison operation.

Name	Type	Description	Required	Default
key	string	The key to compare against the value.	Yes
type	enum	Specifies the comparison operator: `eq`, `ne`, `gt`, `gte`, `lt`, `lte`, `in`, `nin`. - `eq`: equals - `ne`: not equal - `gt`: greater than - `gte`: greater than or equal - `lt`: less than - `lte`: less than or equal - `in`: in - `nin`: not in Possible values: `eq`, `ne`, `gt`, `gte`, `lt`, `lte`	Yes	eq
value	string or OpenAI.numeric or boolean or array of string or OpenAI.numeric	The value to compare against the attribute key; supports string, number, or boolean types.	Yes

OpenAI.CompoundFilter

Compound Filter

Combine multiple filters using and or or.

Name	Type	Description	Required	Default
filters	array of OpenAI.ComparisonFilter or object	Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`.	Yes
type	enum	Type of operation: `and` or `or`. Possible values: `and`, `or`	Yes

OpenAI.ComputerEnvironment

Property	Value
Type	string
Values	`windows` `mac` `linux` `ubuntu` `browser`

OpenAI.ComputerUsePreviewTool

Computer use preview

A tool that controls a virtual computer.

Name	Type	Description	Required	Default
display_height	OpenAI.integer		Yes
display_width	OpenAI.integer		Yes
environment	OpenAI.ComputerEnvironment		Yes
type	enum	The type of the computer use tool. Always `computer_use_preview`. Possible values: `computer_use_preview`	Yes	computer_use_preview

OpenAI.ContainerAutoParam

Name	Type	Description	Required	Default
file_ids	array of string	An optional list of uploaded files to make available to your code. Constraints: maxItems: 50	No
memory_limit	OpenAI.ContainerMemoryLimit (nullable)		No
network_policy	OpenAI.ContainerNetworkPolicyParam	Network access policy for the container.	No
skills	array of OpenAI.ContainerSkill	An optional list of skills referenced by id or inline data. Constraints: maxItems: 200	No
type	enum	Automatically creates a container for this request Possible values: `container_auto`	Yes	container_auto

OpenAI.ContainerMemoryLimit

Property	Value
Type	string
Values	`1g` `4g` `16g` `64g`

OpenAI.ContainerNetworkPolicyAllowlistParam

Name	Type	Description	Required	Default
allowed_domains	array of string	A list of allowed domains when type is `allowlist`. Constraints: minItems: 1	Yes
domain_secrets	array of OpenAI.ContainerNetworkPolicyDomainSecretParam	Optional domain-scoped secrets for allowlisted domains. Constraints: minItems: 1	No
type	enum	Allow outbound network access only to specified domains. Always `allowlist`. Possible values: `allowlist`	Yes	allowlist

OpenAI.ContainerNetworkPolicyDisabledParam

Name	Type	Description	Required	Default
type	enum	Disable outbound network access. Always `disabled`. Possible values: `disabled`	Yes	disabled

OpenAI.ContainerNetworkPolicyDomainSecretParam

Name	Type	Description	Required
domain	string	The domain associated with the secret. Constraints: minLength: 1	Yes
name	string	The name of the secret to inject for the domain. Constraints: minLength: 1	Yes
value	string	The secret value to inject for the domain. Constraints: minLength: 1, maxLength: 10485760	Yes

OpenAI.ContainerNetworkPolicyParam

Network access policy for the container.

Discriminator for OpenAI.ContainerNetworkPolicyParam

This component uses the property type to discriminate between different types:

Type Value	Schema
`disabled`	OpenAI.ContainerNetworkPolicyDisabledParam
`allowlist`	OpenAI.ContainerNetworkPolicyAllowlistParam

Name	Type	Description	Required	Default
type	OpenAI.ContainerNetworkPolicyParamType		Yes

OpenAI.ContainerNetworkPolicyParamType

Property	Value
Type	string
Values	`disabled` `allowlist`

OpenAI.ContainerSkill

Discriminator for OpenAI.ContainerSkill

This component uses the property type to discriminate between different types:

Type Value	Schema
`skill_reference`	OpenAI.SkillReferenceParam
`inline`	OpenAI.InlineSkillParam

Name	Type	Description	Required	Default
type	OpenAI.ContainerSkillType		Yes

OpenAI.ContainerSkillType

Property	Value
Type	string
Values	`skill_reference` `inline`

OpenAI.CustomGrammarFormatParam

Grammar format

A grammar defined by the user.

Name	Type	Description	Required	Default
definition	string	The grammar definition.	Yes
syntax	OpenAI.GrammarSyntax1		Yes
type	enum	Grammar format. Always `grammar`. Possible values: `grammar`	Yes	grammar

OpenAI.CustomTextFormatParam

Text format

Unconstrained free-form text.

Name	Type	Description	Required	Default
type	enum	Unconstrained text format. Always `text`. Possible values: `text`	Yes	text

OpenAI.CustomToolParam

Custom tool

A custom tool that processes input using a specified format. Learn more about custom tools

Name	Type	Description	Required	Default
description	string	Optional description of the custom tool, used to provide more context.	No
format	OpenAI.CustomToolParamFormat	The input format for the custom tool. Default is unconstrained text.	No
└─ type	OpenAI.CustomToolParamFormatType		Yes
name	string	The name of the custom tool, used to identify it in tool calls.	Yes
type	enum	The type of the custom tool. Always `custom`. Possible values: `custom`	Yes	custom

OpenAI.CustomToolParamFormat

The input format for the custom tool. Default is unconstrained text.

Discriminator for OpenAI.CustomToolParamFormat

This component uses the property type to discriminate between different types:

Type Value	Schema
`text`	OpenAI.CustomTextFormatParam
`grammar`	OpenAI.CustomGrammarFormatParam

Name	Type	Description	Required	Default
type	OpenAI.CustomToolParamFormatType		Yes

OpenAI.CustomToolParamFormatType

Property	Value
Type	string
Values	`text` `grammar`

OpenAI.Error

Name	Type	Required
additionalInfo	object	No
code	string (nullable)	Yes
debugInfo	object	No
details	array of OpenAI.Error	No
message	string	Yes
param	string (nullable)	No
type	string	No

OpenAI.FileSearchTool

File search

A tool that searches for relevant content from uploaded files.

Name	Type	Description	Required	Default
filters	OpenAI.Filters (nullable)		No
max_num_results	OpenAI.integer		No
ranking_options	OpenAI.RankingOptions		No
└─ hybrid_search	OpenAI.HybridSearchOptions	Weights that control how reciprocal rank fusion balances semantic embedding matches versus sparse keyword matches when hybrid search is enabled.	No
└─ ranker	OpenAI.RankerVersionType	The ranker to use for the file search.	No
└─ score_threshold	OpenAI.numeric	The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results.	No
type	enum	The type of the file search tool. Always `file_search`. Possible values: `file_search`	Yes	file_search
vector_store_ids	array of string	The IDs of the vector stores to search.	Yes

OpenAI.Filters

Type: OpenAI.ComparisonFilter or OpenAI.CompoundFilter

OpenAI.FunctionShellToolParam

Shell tool

A tool that allows the model to execute shell commands.

Name	Type	Description	Required	Default
environment	OpenAI.FunctionShellToolParamEnvironment (nullable)		No
└─ type	OpenAI.FunctionShellToolParamEnvironmentType		Yes
type	enum	The type of the shell tool. Always `shell`. Possible values: `shell`	Yes	shell

OpenAI.FunctionShellToolParamEnvironment

Discriminator for OpenAI.FunctionShellToolParamEnvironment

This component uses the property type to discriminate between different types:

Type Value	Schema
`local`	OpenAI.FunctionShellToolParamEnvironmentLocalEnvironmentParam
`container_reference`	OpenAI.FunctionShellToolParamEnvironmentContainerReferenceParam
`container_auto`	OpenAI.ContainerAutoParam

Name	Type	Description	Required	Default
type	OpenAI.FunctionShellToolParamEnvironmentType		Yes

OpenAI.FunctionShellToolParamEnvironmentContainerReferenceParam

Name	Type	Description	Required	Default
container_id	string	The ID of the referenced container.	Yes
type	enum	References a container created with the /v1/containers endpoint Possible values: `container_reference`	Yes	container_reference

OpenAI.FunctionShellToolParamEnvironmentLocalEnvironmentParam

Name	Type	Description	Required	Default
skills	array of OpenAI.LocalSkillParam	An optional list of skills. Constraints: maxItems: 200	No
type	enum	Use a local computer environment. Possible values: `local`	Yes	local

OpenAI.FunctionShellToolParamEnvironmentType

Property	Value
Type	string
Values	`container_auto` `local` `container_reference`

OpenAI.FunctionTool

Function

Defines a function in your own code the model can choose to call.

Name	Type	Description	Required	Default
description	string (nullable)		No
name	string	The name of the function to call.	Yes
parameters	object (nullable)		Yes
strict	boolean (nullable)		Yes
type	enum	The type of the function tool. Always `function`. Possible values: `function`	Yes	function

OpenAI.GrammarSyntax1

Property	Value
Type	string
Values	`lark` `regex`

OpenAI.HybridSearchOptions

Name	Type	Description	Required	Default
embedding_weight	OpenAI.numeric		Yes
text_weight	OpenAI.numeric		Yes

OpenAI.ImageGenActionEnum

Property	Value
Type	string
Values	`generate` `edit` `auto`

OpenAI.ImageGenTool

Image generation tool

A tool that generates images using the GPT image models.

Valid models:

gpt-image-1
gpt-image-1-mini
gpt-image-1.5

Name	Type	Description	Required	Default
action	OpenAI.ImageGenActionEnum		No
background	enum	Background type for the generated image. One of `transparent`, `opaque`, or `auto`. Default: `auto`. Possible values: `transparent`, `opaque`, `auto`	No	auto
input_fidelity	OpenAI.InputFidelity (nullable)	Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for `gpt-image-1` and `gpt-image-1.5` and later models, unsupported for `gpt-image-1-mini`. Supports `high` and `low`. Defaults to `low`.	No
input_image_mask	OpenAI.ImageGenToolInputImageMask		No
└─ file_id	string		No
└─ image_url	string (uri)		No
model	string (see valid models below)		No
moderation	enum	Moderation level for the generated image. Default: `auto`. Possible values: `auto`, `low`	No	auto
output_compression	OpenAI.integer	Constraints: min: 0, max: 100	No	100
output_format	enum	The output format of the generated image. One of `png`, `webp`, or `jpeg`. Default: `png`. Possible values: `png`, `webp`, `jpeg`	No	png
partial_images	OpenAI.integer	Constraints: min: 0, max: 3	No
quality	enum	The quality of the generated image. One of `low`, `medium`, `high`, or `auto`. Default: `auto`. Possible values: `low`, `medium`, `high`, `auto`	No	auto
size	enum	The size of the generated image. One of `1024x1024`, `1024x1536`, `1536x1024`, or `auto`. Default: `auto`. Possible values: `1024x1024`, `1024x1536`, `1536x1024`, `auto`	No	auto
type	enum	The type of the image generation tool. Always `image_generation`. Possible values: `image_generation`	Yes	image_generation

OpenAI.ImageGenToolInputImageMask

Name	Type	Description	Required	Default
file_id	string		No
image_url	string (uri)		No

OpenAI.InlineSkillParam

Name	Type	Description	Required	Default
description	string	The description of the skill.	Yes
name	string	The name of the skill.	Yes
source	OpenAI.InlineSkillSourceParam	Inline skill payload	Yes
└─ data	string	Base64-encoded skill zip bundle. Constraints: minLength: 1, maxLength: 70254592	Yes
└─ media_type	enum	The media type of the inline skill payload. Must be `application/zip`. Possible values: `application/zip`	Yes	application/zip
└─ type	enum	The type of the inline skill source. Must be `base64`. Possible values: `base64`	Yes	base64
type	enum	Defines an inline skill for this request. Possible values: `inline`	Yes	inline

OpenAI.InlineSkillSourceParam

Inline skill payload

Name	Type	Description	Required	Default
data	string	Base64-encoded skill zip bundle. Constraints: minLength: 1, maxLength: 70254592	Yes
media_type	enum	The media type of the inline skill payload. Must be `application/zip`. Possible values: `application/zip`	Yes	application/zip
type	enum	The type of the inline skill source. Must be `base64`. Possible values: `base64`	Yes	base64

OpenAI.InputFidelity

Control how much effort the model will exert to match the style and features, especially facial features, of input images. This parameter is only supported for gpt-image-1 and gpt-image-1.5 and later models, unsupported for gpt-image-1-mini. Supports high and low. Defaults to low.

Property	Value
Type	string
Values	`high` `low`

OpenAI.LocalShellToolParam

Local shell tool

A tool that allows the model to execute shell commands in a local environment.

Name	Type	Description	Required	Default
type	enum	The type of the local shell tool. Always `local_shell`. Possible values: `local_shell`	Yes	local_shell

OpenAI.LocalSkillParam

Name	Type	Description	Required
description	string	The description of the skill.	Yes
name	string	The name of the skill.	Yes
path	string	The path to the directory containing the skill.	Yes

OpenAI.MCPTool

MCP tool

Give the model access to additional tools via remote Model Context Protocol (MCP) servers.

Name	Type	Description	Required
allowed_tools	array of string or OpenAI.MCPToolFilter		No
authorization	string	An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here.	No
connector_id	enum	Identifier for service connectors, like those available in ChatGPT. One of `server_url` or `connector_id` must be provided. Learn more about service connectors here. Currently supported `connector_id` values are: - Dropbox: `connector_dropbox` - Gmail: `connector_gmail` - Google Calendar: `connector_googlecalendar` - Google Drive: `connector_googledrive` - Microsoft Teams: `connector_microsoftteams` - Outlook Calendar: `connector_outlookcalendar` - Outlook Email: `connector_outlookemail` - SharePoint: `connector_sharepoint` Possible values: `connector_dropbox`, `connector_gmail`, `connector_googlecalendar`, `connector_googledrive`, `connector_microsoftteams`, `connector_outlookcalendar`, `connector_outlookemail`, `connector_sharepoint`	No
headers	object (nullable)		No
project_connection_id	string	The connection ID in the project for the MCP server. The connection stores authentication and other connection details needed to connect to the MCP server.	No
require_approval	OpenAI.MCPToolRequireApproval or string		No
server_description	string	Optional description of the MCP server, used to provide more context.	No
server_label	string	A label for this MCP server, used to identify it in tool calls.	Yes
server_url	string (uri)	The URL for the MCP server. One of `server_url` or `connector_id` must be provided.	No
type	enum	The type of the MCP tool. Always `mcp`. Possible values: `mcp`	Yes

OpenAI.MCPToolFilter

MCP tool filter

A filter object to specify which tools are allowed.

Name	Type	Description	Required	Default
read_only	boolean	Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with `readOnlyHint`, it will match this filter.	No
tool_names	array of string	List of allowed tool names.	No

OpenAI.MCPToolRequireApproval

Name	Type	Description	Required	Default
always	OpenAI.MCPToolFilter	A filter object to specify which tools are allowed.	No
never	OpenAI.MCPToolFilter	A filter object to specify which tools are allowed.	No

OpenAI.RankerVersionType

Property	Value
Type	string
Values	`auto` `default-2024-11-15`

OpenAI.RankingOptions

Name	Type	Description	Required
hybrid_search	OpenAI.HybridSearchOptions		No
└─ embedding_weight	OpenAI.numeric	The weight of the embedding in the reciprocal ranking fusion.	Yes
└─ text_weight	OpenAI.numeric	The weight of the text in the reciprocal ranking fusion.	Yes
ranker	OpenAI.RankerVersionType		No
score_threshold	OpenAI.numeric		No

OpenAI.Reasoning

Reasoning

gpt-5 and o-series models only Configuration options for reasoning models.

Name	Type	Description	Required
effort	OpenAI.ReasoningEffort	Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool calls are supported for all reasoning values in gpt-5.1. - All models before `gpt-5.1` default to `medium` reasoning effort, and do not support `none`. - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort. - `xhigh` is supported for all models after `gpt-5.1-codex-max`.	No
generate_summary	enum (nullable)	Possible values: `auto`, `concise`, `detailed`	No
summary	enum (nullable)	Possible values: `auto`, `concise`, `detailed`	No

OpenAI.ReasoningEffort

Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
All models before gpt-5.1 default to medium reasoning effort, and do not support none.
The gpt-5-pro model defaults to (and only supports) high reasoning effort.
xhigh is supported for all models after gpt-5.1-codex-max.

Property	Value
Type	string
Nullable	Yes
Values	`none` `minimal` `low` `medium` `high` `xhigh`

OpenAI.ResponseFormatJsonSchemaSchema

JSON schema

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

Type: object

OpenAI.SearchContextSize

Property	Value
Type	string
Values	`low` `medium` `high`

OpenAI.SkillReferenceParam

Name	Type	Description	Required	Default
skill_id	string	The ID of the referenced skill. Constraints: minLength: 1, maxLength: 64	Yes
type	enum	References a skill created with the /v1/skills endpoint. Possible values: `skill_reference`	Yes	skill_reference
version	string	Optional skill version. Use a positive integer or 'latest'. Omit for default.	No

OpenAI.SpecificApplyPatchParam

Specific apply patch tool choice

Forces the model to call the apply_patch tool when executing a tool call.

Name	Type	Description	Required	Default
type	enum	The tool to call. Always `apply_patch`. Possible values: `apply_patch`	Yes	apply_patch

OpenAI.SpecificFunctionShellParam

Specific shell tool choice

Forces the model to call the shell tool when a tool call is required.

Name	Type	Description	Required	Default
type	enum	The tool to call. Always `shell`. Possible values: `shell`	Yes	shell

OpenAI.TextResponseFormatConfiguration

An object specifying the format that the model must output. Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the

The default format is { "type": "text" } with no additional options. Not recommended for gpt-4o and newer models: Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

Discriminator for OpenAI.TextResponseFormatConfiguration

This component uses the property type to discriminate between different types:

Type Value	Schema
`json_schema`	OpenAI.TextResponseFormatJsonSchema
`text`	OpenAI.TextResponseFormatConfigurationResponseFormatText
`json_object`	OpenAI.TextResponseFormatConfigurationResponseFormatJsonObject

Name	Type	Description	Required	Default
type	OpenAI.TextResponseFormatConfigurationType		Yes

OpenAI.TextResponseFormatConfigurationResponseFormatJsonObject

JSON object

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

Name	Type	Description	Required	Default
type	enum	The type of response format being defined. Always `json_object`. Possible values: `json_object`	Yes

OpenAI.TextResponseFormatConfigurationResponseFormatText

Text

Default response format. Used to generate text responses.

Name	Type	Description	Required	Default
type	enum	The type of response format being defined. Always `text`. Possible values: `text`	Yes

OpenAI.TextResponseFormatConfigurationType

Property	Value
Type	string
Values	`text` `json_schema` `json_object`

OpenAI.TextResponseFormatJsonSchema

JSON schema

JSON Schema response format. Used to generate structured JSON responses.

Name	Type	Description	Required
description	string	A description of what the response format is for, used by the model to determine how to respond in the format.	No
name	string	The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.	Yes
schema	OpenAI.ResponseFormatJsonSchemaSchema	The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.	Yes
strict	boolean (nullable)		No
type	enum	The type of response format being defined. Always `json_schema`. Possible values: `json_schema`	Yes

OpenAI.Tool

A tool that can be used to generate a response.

Discriminator for OpenAI.Tool

This component uses the property type to discriminate between different types:

Type Value	Schema
`bing_grounding`	BingGroundingTool
`fabric_dataagent_preview`	MicrosoftFabricPreviewTool
`sharepoint_grounding_preview`	SharepointPreviewTool
`azure_ai_search`	AzureAISearchTool
`openapi`	OpenApiTool
`bing_custom_search_preview`	BingCustomSearchPreviewTool
`browser_automation_preview`	BrowserAutomationPreviewTool
`azure_function`	AzureFunctionTool
`capture_structured_outputs`	CaptureStructuredOutputsTool
`a2a_preview`	A2APreviewTool
`memory_search_preview`	MemorySearchPreviewTool
`code_interpreter`	OpenAI.CodeInterpreterTool
`function`	OpenAI.FunctionTool
`file_search`	OpenAI.FileSearchTool
`computer_use_preview`	OpenAI.ComputerUsePreviewTool
`web_search`	OpenAI.WebSearchTool
`mcp`	OpenAI.MCPTool
`image_generation`	OpenAI.ImageGenTool
`local_shell`	OpenAI.LocalShellToolParam
`shell`	OpenAI.FunctionShellToolParam
`custom`	OpenAI.CustomToolParam
`web_search_preview`	OpenAI.WebSearchPreviewTool
`apply_patch`	OpenAI.ApplyPatchToolParam

Name	Type	Description	Required	Default
type	OpenAI.ToolType		Yes

OpenAI.ToolChoiceAllowed

Allowed tools

Constrains the tools available to the model to a pre-defined set.

Name	Type	Description	Required
mode	enum	Constrains the tools available to the model to a pre-defined set. `auto` allows the model to pick from among the allowed tools and generate a message. `required` requires the model to call one or more of the allowed tools. Possible values: `auto`, `required`	Yes
tools	array of object	A list of tool definitions that the model should be allowed to call. For the Responses API, the list of tool definitions might look like: `json<br> [<br> { "type": "function", "name": "get_weather" },<br> { "type": "mcp", "server_label": "deepwiki" },<br> { "type": "image_generation" }<br> ]<br>`	Yes
type	enum	Allowed tool configuration type. Always `allowed_tools`. Possible values: `allowed_tools`	Yes

OpenAI.ToolChoiceCodeInterpreter

Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.

Name	Type	Description	Required	Default
type	enum	Possible values: `code_interpreter`	Yes

OpenAI.ToolChoiceComputerUsePreview

Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.

Name	Type	Description	Required	Default
type	enum	Possible values: `computer_use_preview`	Yes

OpenAI.ToolChoiceCustom

Custom tool

Use this option to force the model to call a specific custom tool.

Name	Type	Description	Required	Default
name	string	The name of the custom tool to call.	Yes
type	enum	For custom tool calling, the type is always `custom`. Possible values: `custom`	Yes

OpenAI.ToolChoiceFileSearch

Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.

Name	Type	Description	Required	Default
type	enum	Possible values: `file_search`	Yes

OpenAI.ToolChoiceFunction

Function tool

Use this option to force the model to call a specific function.

Name	Type	Description	Required	Default
name	string	The name of the function to call.	Yes
type	enum	For function calling, the type is always `function`. Possible values: `function`	Yes

OpenAI.ToolChoiceImageGeneration

Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.

Name	Type	Description	Required	Default
type	enum	Possible values: `image_generation`	Yes

OpenAI.ToolChoiceMCP

MCP tool

Use this option to force the model to call a specific tool on a remote MCP server.

Name	Type	Description	Required
name	string (nullable)		No
server_label	string	The label of the MCP server to use.	Yes
type	enum	For MCP tools, the type is always `mcp`. Possible values: `mcp`	Yes

OpenAI.ToolChoiceParam

How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.

Discriminator for OpenAI.ToolChoiceParam

This component uses the property type to discriminate between different types:

Type Value	Schema
`allowed_tools`	OpenAI.ToolChoiceAllowed
`function`	OpenAI.ToolChoiceFunction
`mcp`	OpenAI.ToolChoiceMCP
`custom`	OpenAI.ToolChoiceCustom
`apply_patch`	OpenAI.SpecificApplyPatchParam
`shell`	OpenAI.SpecificFunctionShellParam
`file_search`	OpenAI.ToolChoiceFileSearch
`web_search_preview`	OpenAI.ToolChoiceWebSearchPreview
`computer_use_preview`	OpenAI.ToolChoiceComputerUsePreview
`web_search_preview_2025_03_11`	OpenAI.ToolChoiceWebSearchPreview20250311
`image_generation`	OpenAI.ToolChoiceImageGeneration
`code_interpreter`	OpenAI.ToolChoiceCodeInterpreter

Name	Type	Description	Required	Default
type	OpenAI.ToolChoiceParamType		Yes

OpenAI.ToolChoiceParamType

Property	Value
Type	string
Values	`allowed_tools` `function` `mcp` `custom` `apply_patch` `shell` `file_search` `web_search_preview` `computer_use_preview` `web_search_preview_2025_03_11` `image_generation` `code_interpreter`

OpenAI.ToolChoiceWebSearchPreview

Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.

Name	Type	Description	Required	Default
type	enum	Possible values: `web_search_preview`	Yes

OpenAI.ToolChoiceWebSearchPreview20250311

Indicates that the model should use a built-in tool to generate a response. Learn more about built-in tools.

Name	Type	Description	Required	Default
type	enum	Possible values: `web_search_preview_2025_03_11`	Yes

OpenAI.ToolType

Property Value

Type string

Values function
file_search
computer_use_preview
web_search
mcp
code_interpreter
image_generation
local_shell
shell
custom
web_search_preview
apply_patch
a2a_preview
bing_custom_search_preview
browser_automation_preview
fabric_dataagent_preview
sharepoint_grounding_preview
memory_search_preview
azure_ai_search
azure_function
bing_grounding
capture_structured_outputs
openapi

OpenAI.WebSearchApproximateLocation

Web search approximate location

The approximate location of the user.

Name	Type	Description	Required	Default
city	string (nullable)		No
country	string (nullable)		No
region	string (nullable)		No
timezone	string (nullable)		No
type	enum	The type of location approximation. Always `approximate`. Possible values: `approximate`	Yes	approximate

OpenAI.WebSearchPreviewTool

Web search preview

This tool searches the web for relevant results to use in a response. Learn more about the web search tool.

Name	Type	Description	Required	Default
search_context_size	OpenAI.SearchContextSize		No
type	enum	The type of the web search tool. One of `web_search_preview` or `web_search_preview_2025_03_11`. Possible values: `web_search_preview`	Yes	web_search_preview
user_location	OpenAI.ApproximateLocation (nullable)		No
└─ city	string (nullable)		No
└─ country	string (nullable)		No
└─ region	string (nullable)		No
└─ timezone	string (nullable)		No
└─ type	enum	The type of location approximation. Always `approximate`. Possible values: `approximate`	Yes	approximate

OpenAI.WebSearchTool

Web search

Search the Internet for sources related to the prompt. Learn more about the web search tool.

Name	Type	Description	Required	Default
custom_search_configuration	WebSearchConfiguration	A web search configuration for bing custom search	No
└─ instance_name	string	Name of the custom configuration instance given to config.	Yes
└─ project_connection_id	string	Project connection id for grounding with bing custom search	Yes
filters	OpenAI.WebSearchToolFilters (nullable)		No
└─ allowed_domains	array of string (nullable)		No
search_context_size	enum	High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default. Possible values: `low`, `medium`, `high`	No	medium
type	enum	The type of the web search tool. One of `web_search` or `web_search_2025_08_26`. Possible values: `web_search`	Yes	web_search
user_location	OpenAI.WebSearchApproximateLocation (nullable)	The approximate location of the user.	No
└─ city	string (nullable)		No
└─ country	string (nullable)		No
└─ region	string (nullable)		No
└─ timezone	string (nullable)		No
└─ type	enum	The type of location approximation. Always `approximate`. Possible values: `approximate`	Yes	approximate

OpenAI.WebSearchToolFilters

Name	Type	Description	Required	Default
allowed_domains	array of string (nullable)		No

OpenAI.integer

Type: integer

Format: int64

OpenAI.numeric

Type: number

Format: double

OpenApiAnonymousAuthDetails

Security details for OpenApi anonymous authentication

Name	Type	Description	Required	Default
type	enum	The object type, which is always 'anonymous'. Possible values: `anonymous`	Yes

OpenApiAuthDetails

authentication details for OpenApiFunctionDefinition

Discriminator for OpenApiAuthDetails

This component uses the property type to discriminate between different types:

Type Value	Schema
`anonymous`	OpenApiAnonymousAuthDetails
`project_connection`	OpenApiProjectConnectionAuthDetails
`managed_identity`	OpenApiManagedAuthDetails

Name	Type	Description	Required	Default
type	OpenApiAuthType	Authentication type for OpenApi endpoint. Allowed types are: - Anonymous (no authentication required) - Project Connection (requires project_connection_id to endpoint, as setup in AI Foundry) - Managed_Identity (requires audience for identity based auth)	Yes

OpenApiAuthType

Authentication type for OpenApi endpoint. Allowed types are:

Anonymous (no authentication required)
Project Connection (requires project_connection_id to endpoint, as setup in AI Foundry)
Managed_Identity (requires audience for identity based auth)

Property	Value
Description	Authentication type for OpenApi endpoint. Allowed types are: - Anonymous (no authentication required) - Project Connection (requires project_connection_id to endpoint, as setup in AI Foundry) - Managed_Identity (requires audience for identity based auth)
Type	string
Values	`anonymous` `project_connection` `managed_identity`

OpenApiFunctionDefinition

The input definition information for an openapi function.

Name	Type	Description	Required
auth	OpenApiAuthDetails	authentication details for OpenApiFunctionDefinition	Yes
└─ type	OpenApiAuthType	The type of authentication, must be anonymous/project_connection/managed_identity	Yes
default_params	array of string	List of OpenAPI spec parameters that will use user-provided defaults	No
description	string	A description of what the function does, used by the model to choose when and how to call the function.	No
functions	array of object (read-only)	List of function definitions used by OpenApi tool	No
name	string	The name of the function to be called.	Yes
spec	object	The openapi function shape, described as a JSON Schema object.	Yes

OpenApiManagedAuthDetails

Security details for OpenApi managed_identity authentication

Name	Type	Description	Required
security_scheme	OpenApiManagedSecurityScheme	Security scheme for OpenApi managed_identity authentication	Yes
└─ audience	string	Authentication scope for managed_identity auth type	Yes
type	enum	The object type, which is always 'managed_identity'. Possible values: `managed_identity`	Yes

OpenApiManagedSecurityScheme

Security scheme for OpenApi managed_identity authentication

Name	Type	Description	Required	Default
audience	string	Authentication scope for managed_identity auth type	Yes

OpenApiProjectConnectionAuthDetails

Security details for OpenApi project connection authentication

Name	Type	Description	Required
security_scheme	OpenApiProjectConnectionSecurityScheme	Security scheme for OpenApi managed_identity authentication	Yes
└─ project_connection_id	string	Project connection id for Project Connection auth type	Yes
type	enum	The object type, which is always 'project_connection'. Possible values: `project_connection`	Yes

OpenApiProjectConnectionSecurityScheme

Security scheme for OpenApi managed_identity authentication

Name	Type	Description	Required	Default
project_connection_id	string	Project connection id for Project Connection auth type	Yes

OpenApiTool

The input definition information for an OpenAPI tool as used to configure an agent.

Name	Type	Description	Required
openapi	OpenApiFunctionDefinition	The input definition information for an openapi function.	Yes
└─ auth	OpenApiAuthDetails	Open API authentication details	Yes
└─ default_params	array of string	List of OpenAPI spec parameters that will use user-provided defaults	No
└─ description	string	A description of what the function does, used by the model to choose when and how to call the function.	No
└─ functions	array of object (read-only)	List of function definitions used by OpenApi tool	No
└─ description	string	A description of what the function does, used by the model to choose when and how to call the function.	No
└─ name	string	The name of the function to be called.	Yes
└─ parameters	object	The parameters the functions accepts, described as a JSON Schema object.	Yes
└─ name	string	The name of the function to be called.	Yes
└─ spec	object	The openapi function shape, described as a JSON Schema object.	Yes
type	enum	The object type, which is always 'openapi'. Possible values: `openapi`	Yes

PageOrder

Property	Value
Type	string
Values	`asc` `desc`

PromptAgentDefinition

The prompt agent definition

Name	Type	Description	Required	Default
instructions	string (nullable)	A system (or developer) message inserted into the model's context.	No
kind	enum	Possible values: `prompt`	Yes
model	string	The model deployment to use for this agent.	Yes
rai_config	RaiConfig	Configuration for Responsible AI (RAI) content filtering and safety features.	No
└─ rai_policy_name	string	The name of the RAI policy to apply.	Yes
reasoning	OpenAI.Reasoning (nullable)	gpt-5 and o-series models only Configuration options for reasoning models.	No
└─ effort	OpenAI.ReasoningEffort	Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool calls are supported for all reasoning values in gpt-5.1. - All models before `gpt-5.1` default to `medium` reasoning effort, and do not support `none`. - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort. - `xhigh` is supported for all models after `gpt-5.1-codex-max`.	No
└─ generate_summary	enum (nullable)	Possible values: `auto`, `concise`, `detailed`	No
└─ summary	enum (nullable)	Possible values: `auto`, `concise`, `detailed`	No
structured_inputs	object	Set of structured inputs that can participate in prompt template substitution or tool argument bindings.	No
temperature	number (float) (nullable)	What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. Constraints: min: 0, max: 2	No	1
text	PromptAgentDefinitionTextOptions	Configuration options for a text response from the model. Can be plain text or structured JSON data.	No
└─ format	OpenAI.TextResponseFormatConfiguration	An object specifying the format that the model must output. Configuring `{ "type": "json_schema" }` enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the The default format is `{ "type": "text" }` with no additional options. Not recommended for gpt-4o and newer models: Setting to `{ "type": "json_object" }` enables the older JSON mode, which ensures the message the model generates is valid JSON. Using `json_schema` is preferred for models that support it.	No
tool_choice	string or OpenAI.ToolChoiceParam	How the model should select which tool (or tools) to use when generating a response. See the `tools` parameter to see how to specify which tools the model can call.	No
tools	array of OpenAI.Tool	An array of tools the model may call while generating a response. You can specify which tool to use by setting the `tool_choice` parameter.	No
top_p	number (float) (nullable)	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. Constraints: min: 0, max: 1	No	1

PromptAgentDefinitionTextOptions

Configuration options for a text response from the model. Can be plain text or structured JSON data.

Name	Type	Description	Required	Default
format	OpenAI.TextResponseFormatConfiguration	An object specifying the format that the model must output. Configuring `{ "type": "json_schema" }` enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the The default format is `{ "type": "text" }` with no additional options. Not recommended for gpt-4o and newer models: Setting to `{ "type": "json_object" }` enables the older JSON mode, which ensures the message the model generates is valid JSON. Using `json_schema` is preferred for models that support it.	No

ProtocolVersionRecord

A record mapping for a single protocol and its version.

Name	Type	Description	Required	Default
protocol	AgentProtocol		Yes
version	string	The version string for the protocol, e.g. 'v0.1.1'.	Yes

RaiConfig

Configuration for Responsible AI (RAI) content filtering and safety features.

Name	Type	Description	Required	Default
rai_policy_name	string	The name of the RAI policy to apply.	Yes

SharepointGroundingToolParameters

The sharepoint grounding tool parameters.

Name	Type	Description	Required	Default
project_connections	array of ToolProjectConnection	The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. Constraints: maxItems: 1	No

SharepointPreviewTool

The input definition information for a sharepoint tool as used to configure an agent.

Name	Type	Description	Required
sharepoint_grounding_preview	SharepointGroundingToolParameters	The sharepoint grounding tool parameters.	Yes
└─ project_connections	array of ToolProjectConnection	The project connections attached to this tool. There can be a maximum of 1 connection resource attached to the tool. Constraints: maxItems: 1	No
type	enum	The object type, which is always 'sharepoint_grounding_preview'. Possible values: `sharepoint_grounding_preview`	Yes

StructuredInputDefinition

An structured input that can participate in prompt template substitutions and tool argument binding.

Name	Type	Description	Required	Default
default_value		The default value for the input if no run-time value is provided.	No
description	string	A human-readable description of the input.	No
required	boolean	Whether the input property is required when the agent is invoked.	No	False
schema	object	The JSON schema for the structured input (optional).	No

StructuredOutputDefinition

A structured output that can be produced by the agent.

Name	Type	Description	Required
description	string	A description of the output to emit. Used by the model to determine when to emit the output.	Yes
name	string	The name of the structured output.	Yes
schema	object	The JSON schema for the structured output.	Yes
strict	boolean (nullable)	Whether to enforce strict validation. Default `true`.	Yes

ToolProjectConnection

A project connection resource.

Name	Type	Description	Required	Default
project_connection_id	string	A project connection in a ToolProjectConnectionList attached to this tool.	Yes

UpdateAgentFromManifestRequest

Name	Type	Description	Required
description	string	A human-readable description of the agent. Constraints: maxLength: 512	No
manifest_id	string	The manifest ID to import the agent version from.	Yes
metadata	object	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.	No
parameter_values	object	The inputs to the manifest that will result in a fully materialized Agent.	Yes

UpdateAgentRequest

Name	Type	Description	Required
definition	AgentDefinition		Yes
└─ kind	AgentKind		Yes
└─ rai_config	RaiConfig	Configuration for Responsible AI (RAI) content filtering and safety features.	No
description	string	A human-readable description of the agent. Constraints: maxLength: 512	No
metadata	object	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.	No

WebSearchConfiguration

A web search configuration for bing custom search

Name	Type	Description	Required	Default
instance_name	string	Name of the custom configuration instance given to config.	Yes
project_connection_id	string	Project connection id for grounding with bing custom search	Yes

WorkflowAgentDefinition

The workflow agent definition.

Name	Type	Description	Required
kind	enum	Possible values: `workflow`	Yes
rai_config	RaiConfig	Configuration for Responsible AI (RAI) content filtering and safety features.	No
└─ rai_policy_name	string	The name of the RAI policy to apply.	Yes
workflow	string	The CSDL YAML definition of the workflow.	No

Last updated on 2026-05-28