# Query session list

Query the visible sessions in the workspace. It can be filtered by agent, status, purpose or top status, and can be read in sections through paging parameters.

```text
GET https://moi.matrixorigin.cn/newmoi/workspaces/{workspace_id}/conversations
```

## Preparation before calling

Prepare a personal access token and target workspace ID that has access to the target workspace. If you need to filter by agent, first obtain the agent 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 `X-Workspace-ID` Header.
- `$AGENT_ID`: Optional agent filter ID.

## Request example

```bash
curl --get "https://moi.matrixorigin.cn/newmoi/workspaces/$WORKSPACE_ID/conversations" \
  -H "X-API-Key: $AI_STUDIO_API_KEY" \
  -H "X-Workspace-ID: $WORKSPACE_ID" \
  --data-urlencode "agent_id=$AGENT_ID" \
  --data-urlencode "status=active" \
  --data-urlencode "limit=20" \
  --data-urlencode "offset=0"
```

## Path parameters

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

## Query parameters

| Parameters | Type | Is it required | Description |
| --- | --- | --- | --- |
| `agent_id` | string | No | Only return sessions for the specified agent. |
| `agent_workspace_id` | string | No | ID of the workspace to which the agent belongs. When `agent_id` is specified without this parameter, the current workspace is used; only the current workspace or the system workspace can be specified. |
| `status` | string | No | Filter by session status. |
| `purpose` | string | No | Filter by session purpose, can be `chat` or `workflow`. |
| `pinned` | boolean | No | If it is `true` or `1`, only the pinned conversations will be returned; if it is other values, unpinned conversations will be filtered. |
| `visibility` | string | No | Accepts only `visible`; only returns visible sessions if not provided. |
| `parent_conversation_id` | string | No | Filter by parent session ID. |
| `limit` | integer | No | Single return quantity. `50` when not provided or less than or equal to `0`, up to `200`. |
| `offset` | integer | No | Returns the offset. `0` when not provided or less than `0`. |

## Successful response

Returns `200` on success. `data.items` is the session of this page, `data.total` is the total number of filter results, `data.limit` and `data.offset` are the paging values ​​actually used this time.

```json
{
  "code": 0,
  "data": {
    "items": [
      {
        "id": "conv_01",
        "workspace_id": "ws_01",
        "agent_workspace_id": "ws_01",
        "agent_id": "agent_01",
        "agent_summary": {
          "id": "agent_01",
          "display_name": "销售分析助手",
          "available": true
        },
        "title": "销售分析",
        "status": "active",
        "purpose": "chat",
        "visibility": "visible",
        "pinned": false,
        "created_at": "2026-01-02T15:04:05Z",
        "updated_at": "2026-01-02T15:04:05Z"
      }
    ],
    "total": 1,
    "limit": 20,
    "offset": 0
  }
}
```

The response fields are as follows.

| Field | Type | Description |
| --- | --- | --- |
| `code` | integer | `0` on success. |
| `data.items` | object[] | Session list on this page. |
| `data.items[].id` | string | Session ID. |
| `data.items[].workspace_id` | string | ID of the workspace to which the session belongs. |
| `data.items[].agent_workspace_id` | string | ID of the workspace to which the agent belongs. |
| `data.items[].agent_id` | string | Agent ID. |
| `data.items[].agent_summary` | object | Summary of agent display. |
| `data.items[].title` | string | Session title; not returned if not set. |
| `data.items[].status` | string | Session status. |
| `data.items[].purpose` | string | Session use. |
| `data.items[].visibility` | string | Session visibility. |
| `data.items[].pinned` | boolean | Whether to pin it to the top. |
| `data.items[].head_message_id` | string | Recent message ID; does not return if there is no message. |
| `data.items[].active_task_id` | string | Current active task ID; does not return if there is no active task. |
| `data.items[].last_message_at` | string | Last message time; does not return if there is no message. |
| `data.items[].created_at` | string | Creation and last update times, in RFC 3339 format. |
| `data.items[].updated_at` | string | Creation and last update times, in RFC 3339 format. |
| `data.total` | integer | The total number of sessions that meet the filter criteria. |
| `data.limit` | integer | The upper limit of the actual return quantity used this time. |
| `data.offset` | integer | The offset actually used this time. |

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

## Error response

```json
{
  "code": 2,
  "message": "请求参数无效",
  "details": {
    "cause": "invalid runtime conversation"
  }
}
```

### Common HTTP errors

```{list-table}
:header-rows: 1
:widths: 12 22 32 34

* - HTTP status code
  - error code
  - Common causes
  - Recommended actions
* - `400`
  - `2`（`INVALID_ARGUMENT`）
  - Invalid agent ID, workspace ID, purpose, visibility, or paging parameters.
  - Check query parameters; `visibility` can only be `visible`.
* - `500`
  - `1`（`INTERNAL`）
  - The server cannot query the session or generate session display information.
  - Record the request time and error message and try again.
* - `503`
  - `15`（`UNAVAILABLE`）
  - Session service is temporarily unavailable.
  - Try again later.
```

## Follow-up operations

Use the returned `data.items[].id` to call [Query session details](get-session.md) or [Query session messages](list-session-messages.md).