Create a run strategy

Create a run policy configuration that is referenced by the agent.

POST https://moi.matrixorigin.cn/newmoi/workspaces/{workspace_id}/runtime-policy-profiles

Preparation before calling

Prepare a personal access token and target workspace ID that has access to the target workspace.

The example below uses:

• $AI_STUDIO_API_KEY: The actual personal access token, passed through the X-API-Key Header.

• $WORKSPACE_ID: The workspace ID for which the policy is to be created, passed in the X-Workspace-ID header and also as workspace_id in the path.

Request example

curl -X POST "https://moi.matrixorigin.cn/newmoi/workspaces/$WORKSPACE_ID/runtime-policy-profiles" \
  -H "X-API-Key: $AI_STUDIO_API_KEY" \
  -H "X-Workspace-ID: $WORKSPACE_ID" \
  -H 'Content-Type: application/json' \
  -d '{
    "name": "默认运行限制",
    "budgets": {
      "max_steps": 20
    }
  }'

Path parameters

Parameters	Type	Is it required	Description
workspace_id	string	Yes	Current workspace ID, must be consistent with X-Workspace-ID.

Request body

Parameters	Type	Is it required	Description
name	string	Yes	Policy name.
description	string	No	Policy description.
status	string	No	Policy status.
scope_type	string	No	Policy scope type.
scope_ref	string	No	Scope reference.
admission	object	No	Access conditions.
budgets	object	No	Budget limit.
retry	object	No	Retry policy.
data_policy	object	No	Data policy.
artifact_policy	object	No	Product strategy.
provider_constraints	object	No	Run provider constraints.
labels	object	No	Tag key-value pair.
annotations	object	No	Annotation key-value pair.
metadata	object	No	Extended metadata.

Successful response

Returns 201 on success. data is the new strategy.

{
  "code": 0,
  "data": {
    "id": "policy_01",
    "workspace_id": "ws_01",
    "name": "默认运行限制",
    "status": "active",
    "scope_type": "workspace",
    "budgets": {
      "max_steps": 20
    },
    "version": 1,
    "created_at": "2026-08-18T01:00:00Z",
    "updated_at": "2026-08-18T01:00:00Z"
  }
}

The response fields are as follows.

Field	Type	Description
code	integer	0 on success.
data.id	string	Run policy ID.
data.workspace_id	string	ID of the workspace to which it belongs.
data.name	string	Policy name and status.
data.status	string	Policy name and status.
data.scope_type	string	Scope types and references; references are only returned if they have a value.
data.scope_ref	string	Scope types and references; references are only returned if they have a value.
data.admission	object	Admission, budget, and retry configuration; returned only if there is a value.
data.budgets	object	Admission, budget, and retry configuration; returned only if there is a value.
data.retry	object	Admission, budget, and retry configuration; returned only if there is a value.
data.data_policy	object	Data, product, and provider constraints; only returned if there is a value.
data.artifact_policy	object	Data, product, and provider constraints; only returned if there is a value.
data.provider_constraints	object	Data, product, and provider constraints; only returned if there is a value.
data.version	integer	Policy version.
data.created_at	string	Creation and update time.
data.updated_at	string	Creation and update time.

Error response

{
  "code": 2,
  "message": "运行策略参数无效"
}

Common HTTP errors

HTTP status code	error code	Common causes	Recommended actions
400	2（INVALID_ARGUMENT）	The request body or policy field is invalid.	Check request fields.
401	6（UNAUTHENTICATED）	Credentials are missing or invalid.	Check API Key.
403	5（PERMISSION_DENIED）	The current identity does not have permission to create.	Use valid credentials, or contact your administrator for authorization.
409	4（ALREADY_EXISTS）	Policy ID or name conflict.	Modify identification or process existing policies.
503	15（UNAVAILABLE）	The running policy service is unavailable.	Try again later.

Follow-up operations

Save data.id and reference it as the agent run strategy.

Last updated on Sep 3, 2026