<span id="选择任务回答引用"></span>

# Select citations for a task answer

```{raw} html
<div class="mo-api-page-show-toc" aria-hidden="true"></div>
```

Select evidence sources actually used in the same task's answer.

```text
POST https://api.moi.matrixorigin.cn/v5/semantic-models/runtime/cite
```

<span id="调用前准备"></span>

## Before you call this API

Use injected service URLs, technical credentials, Workspace, and short-lived authorization only in the current task environment. Retain original authorization header values. An ordinary PAT cannot replace task identity or establish authorization. Examples use jq. See [Shared information](../../ai-studio/agents/message-connections/objects.md) for variables, objects, and states.

<span id="请求体"></span>

## Request body

:::::::{div} mo-api-tabs
::::::{tab-set}
:::::{tab-item} Request example

```bash
curl -X POST "${MOI_ENDPOINT%/}/semantic-models/runtime/cite" \
  -H "X-API-Key: $MOI_API_KEY" \
  -H "X-Workspace-ID: $MOI_WORKSPACE_ID" \
  -H "X-MOI-Runtime-Authorization: $MOI_RUNTIME_AUTHORIZATION" \
  -H 'Content-Type: application/json' \
  --data-binary "$(jq -n --arg REQUEST_ID "$REQUEST_ID" --slurpfile CITATION_SOURCES_FILE "$CITATION_SOURCES_FILE" '
{
  "request_id": $REQUEST_ID,
  "sources": $CITATION_SOURCES_FILE[0],
  "complete_read_requirements": true
}
')"
```

:::::
:::::{tab-item} Parameters

Select from persisted evidence in the current task; do not fabricate sources from names. Check accepted and complete returned read requirements before resubmitting if rejected. After selection, write the answer from evidence. HTTP 200 does not mean answer facts were verified.

| Fields | Type | Required | Description |
| --- | --- | --- | --- |
| `request_id` | string | Yes | Unique ID for this operation, 1–256 bytes, without surrounding whitespace or an audit: prefix. Retain for replay of identical input. |
| `sources` | object (array of objects) | No | Explicitly supply the complete source set; send [] without evidence to avoid an unintended empty selection from omission. |
| `complete_read_requirements` | boolean | No | Return complete unread requirements for further reading before retrying selection. |

:::::
::::::
:::::::

<span id="成功响应"></span>

## Successful response

:::::::{div} mo-api-tabs mo-api-response-tabs
::::::{tab-set}
:::::{tab-item} Response example

```json
{
  "code": "OK",
  "msg": "OK",
  "data": {
    "call_id": "request_example",
    "output": {
      "accepted": true,
      "selected": true,
      "sources": []
    }
  }
}
```

:::::
:::::{tab-item} Fields

| Field | Type | Description |
| --- | --- | --- |
| `code` | string | OK on success. |
| `msg` | string | Response explanation. |
| `data.call_id` | string | Corresponding original request_id. |
| `data.failed` | boolean | true indicates business failure; false may be omitted. |
| `data.output` | object | Current operation result. |
| `data.artifacts` | object (array of objects) | Original artifacts and evidence from the same task. |
| `data.metadata` | object | Operation metadata, returned when present. |
| `data.output.accepted` | boolean | Whether citation selection was accepted. Must explicitly be true before answering. |
| `data.output.selected` | boolean | Raw value returned by the current operation; retain according to common objects. |
| `data.output.sources` | array | Raw value returned by the current operation; retain according to common objects. |

:::::
::::::
:::::::

<span id="错误响应"></span>

## Error response

Handle HTTP status, business results, and error fields separately. See [Errors and environments](../../ai-studio/agents/message-connections/objects.md#错误与环境). On source or version conflicts, read current state; do not automatically retry with a different identity, resource, or request ID.
