Query the current agent configuration

Read the configuration view of the specified agent version in the current system.

GET https://moi.matrixorigin.cn/newmoi/workspaces/{workspace_id}/agent-builder/agents/{agent_id}/versions/{version}/current-agent

Preparation before calling

First confirm the agent candidate, use load_version in the response as version, do not infer based on the candidate version. Prepare a personal access token with access to the target workspace, target workspace ID, agent ID, and version ID.

The example below uses:

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

  • $WORKSPACE_ID: Target workspace ID, passed through the X-Workspace-ID Header and also as workspace_id in the path.

  • $AGENT_ID: Agent ID, as agent_id in the path.

  • $VERSION: The version identifier to query, as version in the path; use load_version in the confirmation candidate response.

Request example

curl "https://moi.matrixorigin.cn/newmoi/workspaces/$WORKSPACE_ID/agent-builder/agents/$AGENT_ID/versions/$VERSION/current-agent" \
  -H "X-API-Key: $AI_STUDIO_API_KEY" \
  -H "X-Workspace-ID: $WORKSPACE_ID"

Path parameters

Parameters

Type

Is it required

Description

workspace_id

string

Yes

Workspace ID.

agent_id

string

Yes

Agent ID.

version

string

Yes

Version identifier.

Query parameters

Parameters

Type

Is it required

Description

agent_workspace_id

string

No

The workspace to which the agent version belongs. If not provided, the current workspace is used; only the current workspace or the system workspace can be specified.

Successful response

Returns 200 on success. Use load_version as version in the confirmed candidate response and do not infer from the candidate version.

{
  "code": 0,
  "data": {
    "agent_id": "agent_01",
    "name": "产品助手",
    "description": "回答产品问题。",
    "model_name": "<MODEL_NAME>",
    "model_config_ref": "mc_01",
    "tool_names": [],
    "skill_names": [],
    "knowledge_base_names": [],
    "channel_bindings": [],
    "agent_md": "<AGENT_MARKDOWN>",
    "change_reason": "<CHANGE_REASON>"
  }
}

The response fields are as follows.

Field

Type

Description

code

integer

0 on success.

data.agent_id

string

Agent ID, name and description.

data.name

string

Agent ID, name and description.

data.description

string

Agent ID, name and description.

data.model_name

string

Model name and model configuration reference.

data.model_config_ref

string

Model name and model configuration reference.

data.tool_names

string[]

Tool, skill, and knowledge base names in the candidate configuration.

data.skill_names

string[]

Tool, skill, and knowledge base names in the candidate configuration.

data.knowledge_base_names

string[]

Tool, skill, and knowledge base names in the candidate configuration.

data.channel_bindings

array

Channel binding configuration.

data.agent_md

string

Editable agent description content and reason for change.

data.change_reason

string

Editable agent description content and reason for change.

[] after a type denotes an array. [] in a field path denotes each item in an array.

Error response

{
  "code": 3,
  "message": "<错误信息>"
}

Common HTTP errors

HTTP status code

error code

Common causes

Recommended actions

400

2INVALID_ARGUMENT

The path or agent_workspace_id is invalid, or the loaded version cannot be projected as an editable configuration.

Check version, workspace scope and package contents.

401

6UNAUTHENTICATED

Lack of valid identity credentials.

Check API Key.

403

5PERMISSION_DENIED

The current caller does not have permission to modify the agent.

Check workspace and agent authorizations.

404

3NOT_FOUND

Agent version does not exist.

Use load_version in the confirmation candidate response.

500

1INTERNAL

Current version of editable configuration projection fails.

Check package contents; contact support if it continues to fail.

503

15UNAVAILABLE

Smart package projection or licensing services are temporarily unavailable.

Try again later.

Follow-up operations

When the candidate content needs to be modified Regenerate agent candidate solutions.

Last updated on