DocsICP FilingConsole
Documentation
Home Page AgentLoop Developer Reference API Reference API catalog Evaluation Evaluation tasks GetEvaluationTask

GetEvaluationTask

Updated at:
Copy as MD
Product
My Favorites

Retrieves the details of an evaluation task.

Try it now

Try this API in OpenAPI Explorer, no manual signing needed. Successful calls auto-generate SDK code matching your parameters. Download it with built-in credential security for local usage.

Test

RAM authorization

No authorization for this operation. If you encounter issues with this operation, contact technical support.

Request syntax

GET /api/v1/evaluation-task/{agentSpace}/{taskId} HTTP/1.1

Path Parameters

Parameter

Type

Required

Description

Example
agentSpace

string

No

The AgentSpace name.

prod-agentspace
taskId

string

No

The evaluation task ID.

eval-task-8b36f2e2b1f94f9c91ce7a4b0f6d9c25

Request parameters

Parameter

Type

Required

Description

Example

No parameters required.

Response elements

Element

Type

Description

Example

object

Schema of Response

requestId

string

The request ID.

3FE4CD1E-FF41-56BE-B590-7A021D9C1524
taskId

string

The evaluation task ID.

eval-task-8b36f2e2b1f94f9c91ce7a4b0f6d9c25
taskName

string

The task name.

trace_task_completion_eval
agentSpace

string

The AgentSpace name.

prod-agentspace
taskMode

string

The evaluation task mode.

Valid values:

  • batch :

    batch

batch
dataType

string

The data source type of the evaluation object.

Valid values:

  • trace :

    trace

  • log :

    log

  • atif :

    atif

  • dataset :

    dataset

trace
evaluators

array

The list of evaluator configurations.

[{"evaluatorRef":"Builtin.agent_task_completion","resultName":"agent_task_completion","resultType":"score","variableMapping":{"input":"trace.input","output":"trace.output","agent_trajectory":"trace.agent_trajectory"}}]
Evaluator

The configuration object of a single evaluator.

{"evaluatorRef":"Builtin.agent_task_completion"}
status

string

The evaluation task status.

Valid values:

  • Failed :

    Failed

  • Running :

    Running

  • Completed :

    Completed

  • Scheduling :

    Scheduling

  • Deleted :

    Deleted

  • Terminated :

    Terminated

  • Pending :

    Pending

Running
createdAt

integer

The creation time, in seconds-level UNIX timestamp.

1782816000
updatedAt

integer

The last update time, in seconds-level UNIX timestamp.

1782816600
dataFilter

string

The filter conditions for evaluation data, returned by the backend as a JSON string.

{"query":"serviceName='checkout-service'","maxRecords":10,"samplingRate":100}
channel

string

The task source.

Valid values:

  • default :

    default

default
config

object

The data source and execution configuration. Tasks with dataType=trace typically include project, storeName, and dataScope fields populated by the backend.

{"project":"agentspace-project","storeName":"logstore-tracing","dataScope":"trace"}

string

The value of a single configuration item. The key name is determined by the specific field convention.

trace
tags

object

The key-value pairs of task tags. Empty if not set.

{"serviceId":"checkout-service","env":"prod"}

string

The value of a single task tag. The key name is customized by business dimension.

prod
regionId

string

The region to which the task belongs.

cn-hangzhou
runStrategyConfig

RunStrategies

The structured configuration of the run strategy, including the parsed backfill strategy and continuous evaluation strategy.

{"backfill":{"enabled":true,"startTime":1782816000000,"endTime":1782902400000},"continuous":{"enabled":true,"intervalUnit":"HOUR","intervalValue":1,"dataDelayMinutes":5}}
description

string

The evaluation task description.

评估线上 Agent 链路任务完成度

In the latest API contract, the query response no longer returns the runStrategies raw JSON string field. Use runStrategyConfig to obtain the structured run strategy instead.

Examples

Success response

JSON format

{
  "requestId": "3FE4CD1E-FF41-56BE-B590-7A021D9C1524",
  "taskId": "eval-task-8b36f2e2b1f94f9c91ce7a4b0f6d9c25",
  "taskName": "trace_task_completion_eval",
  "agentSpace": "prod-agentspace",
  "taskMode": "batch",
  "dataType": "trace",
  "evaluators": [
    {
      "evaluatorRef": "Builtin.agent_task_completion",
      "name": "agent_task_completion",
      "type": "AGENT",
      "resultName": "agent_task_completion",
      "resultType": "score",
      "config": {
        "version": "1.0.0"
      },
      "filters": {
        "query": "serviceName='checkout-service'"
      },
      "variableMapping": {
        "key": "trace.input"
      }
    }
  ],
  "status": "Running",
  "createdAt": 1782816000,
  "updatedAt": 1782816600,
  "dataFilter": "{\"query\":\"serviceName='checkout-service'\",\"maxRecords\":10,\"samplingRate\":100}",
  "channel": "default",
  "config": {
    "key": "trace"
  },
  "tags": {
    "key": "prod"
  },
  "regionId": "cn-hangzhou",
  "runStrategyConfig": {
    "backfill": {
      "enabled": true,
      "startTime": 1782816000000,
      "endTime": 1782902400000
    },
    "continuous": {
      "enabled": true,
      "intervalUnit": "HOUR",
      "intervalValue": 1,
      "dataDelayMinutes": 5
    }
  },
  "description": "评估线上 Agent 链路任务完成度"
}

Error codes

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.

Previous：ListEvaluationTasksNext：CreateEvaluationTask