items

Creates, updates, deletes, gets or lists an items resource.

Overview

Name	items
Type	Resource
Id	openai.conversations.items

Fields

The following fields are returned by SELECT queries:

get

Name	Datatype	Description
id	string	The unique ID of the message.
name	string	The name of the function to run.
approval_request_id	string	The ID of the approval request being answered.
call_id	string	The unique ID of the function tool call generated by the model.
container_id	string	The ID of the container used to run the code.
acknowledged_safety_checks	array	The safety checks reported by the API that have been acknowledged by the developer.
action	object	An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page). (title: Search action)
actions	array	Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields. (title: Computer Action List)
approve	boolean	Whether the request was approved.
arguments	string	A JSON string of the arguments to pass to the function.
code	string	The code to run, or null if not available.
content	array	The content of the message
created_by	string	The identifier of the actor that created the item.
encrypted_content	string	The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
environment	string (json)
error	string	Error message if the server could not list tools.
execution	string	Whether tool search was executed by the server or by the client. (server, client)
input	string	The input for the custom tool call generated by the model.
max_output_length	integer	The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
namespace	string	The namespace of the function to run.
operation	object	One of the create_file, delete_file, or update_file operations applied via apply_patch. (title: Apply patch operation)
output	string	The output from the function call generated by your code. Can be a string or an list of output content. (title: string output)
outputs	array	The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
pending_safety_checks	array	The pending safety checks for the computer call.
phase	string	(commentary, final_answer)
queries	array	The queries used to search for files.
reason	string	Optional reason for the decision.
result	string	The generated image encoded in base64.
results	array	The results of the file search tool call.
role	string	The role of the message. One of unknown, user, assistant, system, critic, discriminator, developer, or tool. (unknown, user, assistant, system, critic, discriminator, developer, tool)
server_label	string	The label of the MCP server.
status	string	The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API. (in_progress, completed, incomplete)
summary	array	Reasoning summary content.
tools	array	The loaded tool definitions returned by tool search.
type	string	The type of the message. Always set to message. (message) (default: message)

list

Name	Datatype	Description
id	string	The unique ID of the message.
name	string	The name of the function to run.
approval_request_id	string	The ID of the approval request being answered.
call_id	string	The unique ID of the function tool call generated by the model.
container_id	string	The ID of the container used to run the code.
acknowledged_safety_checks	array	The safety checks reported by the API that have been acknowledged by the developer.
action	object	An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page). (title: Search action)
actions	array	Flattened batched actions for computer_use. Each action includes an type discriminator and action-specific fields. (title: Computer Action List)
approve	boolean	Whether the request was approved.
arguments	string	A JSON string of the arguments to pass to the function.
code	string	The code to run, or null if not available.
content	array	The content of the message
created_by	string	The identifier of the actor that created the item.
encrypted_content	string	The encrypted content of the reasoning item - populated when a response is generated with reasoning.encrypted_content in the include parameter.
environment	string (json)
error	string	Error message if the server could not list tools.
execution	string	Whether tool search was executed by the server or by the client. (server, client)
input	string	The input for the custom tool call generated by the model.
max_output_length	integer	The maximum length of the shell command output. This is generated by the model and should be passed back with the raw output.
namespace	string	The namespace of the function to run.
operation	object	One of the create_file, delete_file, or update_file operations applied via apply_patch. (title: Apply patch operation)
output	string	The output from the function call generated by your code. Can be a string or an list of output content. (title: string output)
outputs	array	The outputs generated by the code interpreter, such as logs or images. Can be null if no outputs are available.
pending_safety_checks	array	The pending safety checks for the computer call.
phase	string	(commentary, final_answer)
queries	array	The queries used to search for files.
reason	string	Optional reason for the decision.
result	string	The generated image encoded in base64.
results	array	The results of the file search tool call.
role	string	The role of the message. One of unknown, user, assistant, system, critic, discriminator, developer, or tool. (unknown, user, assistant, system, critic, discriminator, developer, tool)
server_label	string	The label of the MCP server.
status	string	The status of item. One of in_progress, completed, or incomplete. Populated when items are returned via API. (in_progress, completed, incomplete)
summary	array	Reasoning summary content.
tools	array	The loaded tool definitions returned by tool search.
type	string	The type of the message. Always set to message. (message) (default: message)

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get	select	conversation_id, item_id	include, openai-organization, openai-project
list	select	conversation_id	limit, order, after, include, openai-organization, openai-project
create	insert	conversation_id, items	include, openai-organization, openai-project
delete	delete	conversation_id, item_id	openai-organization, openai-project

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
conversation_id	string	The ID of the conversation that contains the item.
item_id	string	The ID of the item to delete.
after	string	An item ID to list items after, used in pagination.
include	array	Additional fields to include in the response. See the include parameter for listing Conversation items above for more information.
limit	integer	A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20. Automatically applied from a SQL LIMIT clause - SELECT ... LIMIT 10 sends limit=10 on the wire. Setting it explicitly in a WHERE clause is not required.
openai-organization	string	Optionally scope the request to a specific organization (overrides the default associated with the API key). Addressable in SQL as openai_organization.
openai-project	string	Optionally scope the request to a specific project (overrides the default associated with the API key). Addressable in SQL as openai_project.
order	string	The order to return the input items in. Default is desc. - asc: Return the input items in ascending order. - desc: Return the input items in descending order.

SELECT examples

get

OK

SELECT
id,
name,
approval_request_id,
call_id,
container_id,
acknowledged_safety_checks,
action,
actions,
approve,
arguments,
code,
content,
created_by,
encrypted_content,
environment,
error,
execution,
input,
max_output_length,
namespace,
operation,
output,
outputs,
pending_safety_checks,
phase,
queries,
reason,
result,
results,
role,
server_label,
status,
summary,
tools,
type
FROM openai.conversations.items
WHERE conversation_id = '{{ conversation_id }}' -- required
AND item_id = '{{ item_id }}' -- required
AND include = '{{ include }}'
AND "openai-organization" = '{{ openai-organization }}'
AND "openai-project" = '{{ openai-project }}'
;

list

OK

SELECT
id,
name,
approval_request_id,
call_id,
container_id,
acknowledged_safety_checks,
action,
actions,
approve,
arguments,
code,
content,
created_by,
encrypted_content,
environment,
error,
execution,
input,
max_output_length,
namespace,
operation,
output,
outputs,
pending_safety_checks,
phase,
queries,
reason,
result,
results,
role,
server_label,
status,
summary,
tools,
type
FROM openai.conversations.items
WHERE conversation_id = '{{ conversation_id }}' -- required
AND "order" = '{{ order }}'
AND after = '{{ after }}'
AND include = '{{ include }}'
AND "openai-organization" = '{{ openai-organization }}'
AND "openai-project" = '{{ openai-project }}'
;

INSERT examples

create

No description available.

INSERT INTO openai.conversations.items (
items,
conversation_id,
include,
"openai-organization",
"openai-project"
)
SELECT 
'{{ items }}' /* required */,
'{{ conversation_id }}',
'{{ include }}',
'{{ openai-organization }}',
'{{ openai-project }}'
RETURNING
first_id,
last_id,
data,
has_more,
object
;

Manifest

# Description fields are for documentation purposes
- name: items
props:
  - name: conversation_id
    value: "{{ conversation_id }}"
    description: Required parameter for the items resource.
  - name: items
    description: |
      The items to add to the conversation. You may add up to 20 items at a time.
    value:
      - role: "{{ role }}"
        content: "{{ content }}"
        phase: "{{ phase }}"
        type: "{{ type }}"
        status: "{{ status }}"
        id: "{{ id }}"
        queries: "{{ queries }}"
        results: "{{ results }}"
        call_id: "{{ call_id }}"
        action:
          type: "{{ type }}"
          button: "{{ button }}"
          x: {{ x }}
          y: {{ y }}
          keys:
            - "{{ keys }}"
          path:
            - x: {{ x }}
              y: {{ y }}
          scroll_x: {{ scroll_x }}
          scroll_y: {{ scroll_y }}
          text: "{{ text }}"
        actions: "{{ actions }}"
        pending_safety_checks: "{{ pending_safety_checks }}"
        output:
          type: "{{ type }}"
          image_url: "{{ image_url }}"
          file_id: "{{ file_id }}"
        acknowledged_safety_checks: "{{ acknowledged_safety_checks }}"
        namespace: "{{ namespace }}"
        name: "{{ name }}"
        arguments: "{{ arguments }}"
        execution: "{{ execution }}"
        tools: "{{ tools }}"
        encrypted_content: "{{ encrypted_content }}"
        summary: "{{ summary }}"
        result: "{{ result }}"
        container_id: "{{ container_id }}"
        code: "{{ code }}"
        outputs: "{{ outputs }}"
        environment: "{{ environment }}"
        max_output_length: {{ max_output_length }}
        operation:
          type: "{{ type }}"
          path: "{{ path }}"
          diff: "{{ diff }}"
        server_label: "{{ server_label }}"
        error: "{{ error }}"
        approval_request_id: "{{ approval_request_id }}"
        approve: {{ approve }}
        reason: "{{ reason }}"
        input: "{{ input }}"
  - name: include
    value: "{{ include }}"
    description: Additional fields to include in the response. See the `include` parameter for [listing Conversation items above](https://platform.openai.com/docs/api-reference/conversations/list-items#conversations_list_items-include) for more information. 
    description: Additional fields to include in the response. See the `include` parameter for [listing Conversation items above](https://platform.openai.com/docs/api-reference/conversations/list-items#conversations_list_items-include) for more information. 
  - name: openai-organization
    value: "{{ openai-organization }}"
    description: Optionally scope the request to a specific organization (overrides the default associated with the API key). Addressable in SQL as `openai_organization`.
    description: Optionally scope the request to a specific organization (overrides the default associated with the API key). Addressable in SQL as `openai_organization`.
  - name: openai-project
    value: "{{ openai-project }}"
    description: Optionally scope the request to a specific project (overrides the default associated with the API key). Addressable in SQL as `openai_project`.
    description: Optionally scope the request to a specific project (overrides the default associated with the API key). Addressable in SQL as `openai_project`.

DELETE examples

delete

No description available.

DELETE FROM openai.conversations.items
WHERE conversation_id = '{{ conversation_id }}' --required
AND item_id = '{{ item_id }}' --required
AND "openai-organization" = '{{ openai-organization }}'
AND "openai-project" = '{{ openai-project }}'
;