runs

Creates, updates, deletes, gets or lists a runs resource.

Overview

Name	runs
Type	Resource
Id	azure.ai_agents.runs

Fields

The following fields are returned by SELECT queries:

get

Name	Datatype	Description
id	string	The identifier, which can be referenced in API endpoints. Required.
assistant_id	string	The ID of the agent associated with the thread this run was performed against. Required.
thread_id	string	The ID of the thread associated with this run. Required.
cancelled_at	string (date-time)	The Unix timestamp, in seconds, representing when this was cancelled. Required.
completed_at	string (date-time)	The Unix timestamp, in seconds, representing when this completed. Required.
created_at	string (date-time)	The Unix timestamp, in seconds, representing when this object was created. Required.
expires_at	string (date-time)	The Unix timestamp, in seconds, representing when this item expires. Required.
failed_at	string (date-time)	The Unix timestamp, in seconds, representing when this failed. Required.
incomplete_details	object	Details on why the run is incomplete. Will be null if the run is not incomplete. Required.
instructions	string	The overridden system instructions used for this agent thread run. Required.
last_error	object	The last error, if any, encountered by this agent thread run. Required.
max_completion_tokens	integer	The maximum number of completion tokens specified to have been used over the course of the run. Required.
max_prompt_tokens	integer	The maximum number of prompt tokens specified to have been used over the course of the run. Required.
metadata	object	A set of up to 16 key/value pairs that can be attached to an object, used for storing additional information about that object in a structured format. Keys may be up to 64 characters in length and values may be up to 512 characters in length. Required.
model	string	The ID of the model to use. Required.
object	string	The object type, which is always 'thread.run'. Required. Default value is "thread.run".
parallel_tool_calls	boolean	Determines if tools can be executed in parallel within the run. Required.
required_action	object	The details of the action required for the agent thread run to continue.
response_format	object	The response format of the tool calls used in this run. Required. Is one of the following types: str, Union[str, "_models.AgentsResponseFormatMode"], AgentsResponseFormat, ResponseFormatJsonSchemaType
started_at	string (date-time)	The Unix timestamp, in seconds, representing when this item was started. Required.
status	string	The status of the agent thread run. Required. Known values are: "queued", "in_progress", "requires_action", "cancelling", "cancelled", "failed", "completed", and "expired". (queued, in_progress, requires_action, cancelling, cancelled, failed, completed, expired)
temperature	number	The sampling temperature used for this run. If not set, defaults to 1.
tool_choice	object	Controls whether or not and which tool is called by the model. Required. Is one of the following types: str, Union[str, "_models.AgentsToolChoiceOptionMode"], AgentsNamedToolChoice
tool_resources	object	Override the tools the agent can use for this run. This is useful for modifying the behavior on a per-run basis.
tools	array	The overridden enabled tools used for this agent thread run. Required.
top_p	number	The nucleus sampling value used for this run. If not set, defaults to 1.
truncation_strategy	object	The strategy to use for dropping messages as the context windows moves forward. Required.
usage	object	Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.). Required.

list

Name	Datatype	Description
id	string	The identifier, which can be referenced in API endpoints. Required.
assistant_id	string	The ID of the agent associated with the thread this run was performed against. Required.
thread_id	string	The ID of the thread associated with this run. Required.
cancelled_at	string (date-time)	The Unix timestamp, in seconds, representing when this was cancelled. Required.
completed_at	string (date-time)	The Unix timestamp, in seconds, representing when this completed. Required.
created_at	string (date-time)	The Unix timestamp, in seconds, representing when this object was created. Required.
expires_at	string (date-time)	The Unix timestamp, in seconds, representing when this item expires. Required.
failed_at	string (date-time)	The Unix timestamp, in seconds, representing when this failed. Required.
incomplete_details	object	Details on why the run is incomplete. Will be null if the run is not incomplete. Required.
instructions	string	The overridden system instructions used for this agent thread run. Required.
last_error	object	The last error, if any, encountered by this agent thread run. Required.
max_completion_tokens	integer	The maximum number of completion tokens specified to have been used over the course of the run. Required.
max_prompt_tokens	integer	The maximum number of prompt tokens specified to have been used over the course of the run. Required.
metadata	object	A set of up to 16 key/value pairs that can be attached to an object, used for storing additional information about that object in a structured format. Keys may be up to 64 characters in length and values may be up to 512 characters in length. Required.
model	string	The ID of the model to use. Required.
object	string	The object type, which is always 'thread.run'. Required. Default value is "thread.run".
parallel_tool_calls	boolean	Determines if tools can be executed in parallel within the run. Required.
required_action	object	The details of the action required for the agent thread run to continue.
response_format	object	The response format of the tool calls used in this run. Required. Is one of the following types: str, Union[str, "_models.AgentsResponseFormatMode"], AgentsResponseFormat, ResponseFormatJsonSchemaType
started_at	string (date-time)	The Unix timestamp, in seconds, representing when this item was started. Required.
status	string	The status of the agent thread run. Required. Known values are: "queued", "in_progress", "requires_action", "cancelling", "cancelled", "failed", "completed", and "expired". (queued, in_progress, requires_action, cancelling, cancelled, failed, completed, expired)
temperature	number	The sampling temperature used for this run. If not set, defaults to 1.
tool_choice	object	Controls whether or not and which tool is called by the model. Required. Is one of the following types: str, Union[str, "_models.AgentsToolChoiceOptionMode"], AgentsNamedToolChoice
tool_resources	object	Override the tools the agent can use for this run. This is useful for modifying the behavior on a per-run basis.
tools	array	The overridden enabled tools used for this agent thread run. Required.
top_p	number	The nucleus sampling value used for this run. If not set, defaults to 1.
truncation_strategy	object	The strategy to use for dropping messages as the context windows moves forward. Required.
usage	object	Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.). Required.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get	select	thread_id, run_id, endpoint		Gets an existing run from an existing thread.
list	select	thread_id, endpoint	limit, order, after, before	Gets a list of runs for a specified thread.
create	insert	thread_id, endpoint	include[]	Creates a new run for an agent thread.
update	exec	thread_id, run_id, endpoint		Modifies an existing thread run.
submit_tool_outputs	exec	thread_id, run_id, endpoint		Submits outputs from tools as requested by tool calls in a run.
cancel	exec	thread_id, run_id, endpoint		Cancels a run of an in‐progress thread.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
endpoint	string	The service endpoint host (no scheme), e.g. myaccount.table.cosmos.azure.com:443 - value of the client endpoint parameter. (default: )
run_id	string	Identifier of the run. Required.
thread_id	string	Identifier of the thread. Required.
after	string
before	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. Default value is None.
include[]	array	A list of additional fields to include in the response. Currently the only supported value is step_details.tool_calls[*].file_search.results[*].content to fetch the file search result content. Default value is None.
limit	integer	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20. Default value is None.
order	string	Sort order by the created_at timestamp of the objects. asc for ascending order and desc for descending order. Known values are: "asc" and "desc". Default value is None.

SELECT examples

get

Gets an existing run from an existing thread.

SELECT
id,
assistant_id,
thread_id,
cancelled_at,
completed_at,
created_at,
expires_at,
failed_at,
incomplete_details,
instructions,
last_error,
max_completion_tokens,
max_prompt_tokens,
metadata,
model,
object,
parallel_tool_calls,
required_action,
response_format,
started_at,
status,
temperature,
tool_choice,
tool_resources,
tools,
top_p,
truncation_strategy,
usage
FROM azure.ai_agents.runs
WHERE thread_id = '{{ thread_id }}' -- required
AND run_id = '{{ run_id }}' -- required
AND endpoint = '{{ endpoint }}' -- required
;

list

Gets a list of runs for a specified thread.

SELECT
id,
assistant_id,
thread_id,
cancelled_at,
completed_at,
created_at,
expires_at,
failed_at,
incomplete_details,
instructions,
last_error,
max_completion_tokens,
max_prompt_tokens,
metadata,
model,
object,
parallel_tool_calls,
required_action,
response_format,
started_at,
status,
temperature,
tool_choice,
tool_resources,
tools,
top_p,
truncation_strategy,
usage
FROM azure.ai_agents.runs
WHERE thread_id = '{{ thread_id }}' -- required
AND endpoint = '{{ endpoint }}' -- required
AND limit = '{{ limit }}'
AND order = '{{ order }}'
AND after = '{{ after }}'
AND before = '{{ before }}'
;

INSERT examples

create

Creates a new run for an agent thread.

INSERT INTO azure.ai_agents.runs (
thread_id,
endpoint,
include[]
)
SELECT 
'{{ thread_id }}',
'{{ endpoint }}',
'{{ include[] }}'
RETURNING
id,
assistant_id,
thread_id,
cancelled_at,
completed_at,
created_at,
expires_at,
failed_at,
incomplete_details,
instructions,
last_error,
max_completion_tokens,
max_prompt_tokens,
metadata,
model,
object,
parallel_tool_calls,
required_action,
response_format,
started_at,
status,
temperature,
tool_choice,
tool_resources,
tools,
top_p,
truncation_strategy,
usage
;

Manifest

# Description fields are for documentation purposes
- name: runs
props:
  - name: thread_id
    value: "{{ thread_id }}"
    description: Required parameter for the runs resource.
  - name: endpoint
    value: "{{ endpoint }}"
    description: Required parameter for the runs resource.
  - name: include[]
    value: "{{ include[] }}"
    description: A list of additional fields to include in the response. Currently the only supported value is `step_details.tool_calls[*].file_search.results[*].content` to fetch the file search result content. Default value is None.
    description: A list of additional fields to include in the response. Currently the only supported value is `step_details.tool_calls[*].file_search.results[*].content` to fetch the file search result content. Default value is None.

Lifecycle Methods

update

Modifies an existing thread run.

EXEC azure.ai_agents.runs.update 
@thread_id='{{ thread_id }}' --required, 
@run_id='{{ run_id }}' --required, 
@endpoint='{{ endpoint }}' --required
;

submit_tool_outputs

Submits outputs from tools as requested by tool calls in a run.

EXEC azure.ai_agents.runs.submit_tool_outputs 
@thread_id='{{ thread_id }}' --required, 
@run_id='{{ run_id }}' --required, 
@endpoint='{{ endpoint }}' --required
;

cancel

Cancels a run of an in‐progress thread.

EXEC azure.ai_agents.runs.cancel 
@thread_id='{{ thread_id }}' --required, 
@run_id='{{ run_id }}' --required, 
@endpoint='{{ endpoint }}' --required
;