opensearch-project · dbwiddis · Mar 31, 2026
@@ -61,6 +61,7 @@ Field | Data type | Required/Optional | Agent type | Description
 `model.model_provider` | String | Required (if using `model`) | `conversational`, `plan_execute_and_reflect` | The model provider. Supported values: `bedrock/converse`, `gemini/v1beta/generatecontent`, `openai/v1/chat/completions`.
 `model.credential` | Object | Required (if using `model`) | `conversational`, `plan_execute_and_reflect` | Credentials for accessing the model. Accepts any credential format supported by connectors. For details, see [Connector blueprints]({{site.url}}{{site.baseurl}}/ml-commons-plugin/remote-models/blueprints#configuration-parameters).
 `model.model_parameters` | Object | Optional (if using `model`) | `conversational`, `plan_execute_and_reflect` | Model-specific parameters such as system prompts and other configuration options.
+`created_by` | String | Optional | All | An optional attribution tag identifying the plugin or client that registered the agent (for example, `"flow-framework"`). Included in ML stats metrics.
 
 ### Using agentic memory
 

@@ -57,6 +57,7 @@ Field | Data type | Required/Optional | Description
 `model_format` | String | Required | The portable format of the model file. Valid values are `TORCH_SCRIPT` and `ONNX`. |
 `description` | String | Optional| The model description. |
 `model_group_id` | String | Optional | The ID of the model group to which to register the model.
+`created_by` | String | Optional | An optional attribution tag identifying the plugin or client that registered the model (for example, `"flow-framework"`). Included in ML stats metrics.
 
 ## Example request: OpenSearch-provided text embedding model
 
@@ -89,6 +90,7 @@ Field | Data type | Required/Optional | Description
 `url` | String | Required | The URL that contains the model. |
 `description` | String | Optional| The model description. |
 `model_group_id` | String | Optional | The ID of the model group to which to register this model.
+`created_by` | String | Optional | An optional attribution tag identifying the plugin or client that registered the model (for example, `"flow-framework"`). Included in ML stats metrics.
 
 ## Example request: OpenSearch-provided sparse encoding model
 
@@ -125,6 +127,7 @@ Field | Data type | Required/Optional | Description
 `is_enabled`| Boolean | Optional | Specifies whether the model is enabled. Disabling the model makes it unavailable for Predict API requests, regardless of the model's deployment status. Default is `true`.
 `rate_limiter` | Object | Optional | Limits the number of times that any user can call the Predict API on the model. For more information, see [Rate limiting inference calls]({{site.url}}{{site.baseurl}}/ml-commons-plugin/integrating-ml-models/#rate-limiting-inference-calls).
 `interface`| Object | Optional | The interface for the model. For more information, see [Interface](#the-interface-parameter).|
+`created_by` | String | Optional | An optional attribution tag identifying the plugin or client that registered the model (for example, `"flow-framework"`). Included in ML stats metrics.
 
 #### The `model_config` object
 
@@ -188,6 +191,7 @@ Field | Data type | Required/Optional | Description
 `rate_limiter` | Object | Optional | Limits the number of times that any user can call the Predict API on the model. For more information, see [Rate limiting inference calls]({{site.url}}{{site.baseurl}}/ml-commons-plugin/integrating-ml-models/#rate-limiting-inference-calls).
 `guardrails`| Object | Optional | The guardrails for the model input. For more information, see [Guardrails](#the-guardrails-parameter).|
 `interface`| Object | Optional | The interface for the model. For more information, see [Interface](#the-interface-parameter).|
+`created_by` | String | Optional | An optional attribution tag identifying the plugin or client that registered the model (for example, `"flow-framework"`). Included in ML stats metrics.
 
 ## Example request: Externally hosted with a standalone connector
 

@@ -69,6 +69,7 @@ As an ML developer, you can build connector blueprints for other platforms. Usin
 | `add_all_backend_roles`                          | Boolean  | Yes         | When set to `true`, adds all `backend_roles` to the access list, which only a user with admin permissions can adjust. When set to `false`, non-admins can add `backend_roles`.                                                                                                                                                                                                       |
 | `client_config`                                  | JSON object | No          | The client configuration object, which provides settings that control the behavior of the client connections used by the connector. These settings allow you to manage connection limits and timeouts, ensuring efficient and reliable communication.                                                                                                                                |
 | `parameters.skip_validating_missing_parameters`  | Boolean | No          | When set to `true`, this option allows you to send a request using a connector without validating any missing parameters. Default is `false`.                                                                                                                                                                                                                                                            |
+| `created_by`                                     | String | No          | An optional attribution tag identifying the plugin or client that created the connector (for example, `"flow-framework"`). Included in ML stats metrics. Set at creation time only; ignored by the Update Connector API.                                                                                                                                                            |
 
 
 The `actions` parameter supports the following options.