Get Auto-Improve Progress

Poll the progress of metric optimization from feedback processing. Returns the improved metric description and evaluation trigger when complete.

GET /test_framework/metric-reviews/process_feedbacks_progress

cURL

cURL

curl --request GET \
  --url https://api.cekura.ai/test_framework/metric-reviews/process_feedbacks_progress/ \
  --header 'X-CEKURA-API-KEY: <api-key>'

200

{
  "improved_metric_description": "<string>",
  "improved_evaluation_trigger": "<string>",
  "trigger_type": "llm_judge",
  "metric_description_program": "<unknown>",
  "metric_description_variables": [
    "<unknown>"
  ],
  "evaluation_trigger_program": "<unknown>",
  "evaluation_trigger_variables": [
    "<unknown>"
  ],
  "review_results": [
    {
      "review_id": 123,
      "test_set_id": 123,
      "actual_value": null,
      "explanation": null,
      "success": true,
      "error": "<string>"
    }
  ]
}

Authorizations

X-CEKURA-API-KEY · string · header · required

API Key Authentication. It should be included in the header of each request.

Query Parameters

progress_id · string · required

Progress ID returned from the process_feedbacks endpoint

agent_id · integer

Agent ID for permission validation

project_id · integer

Project ID for permission validation

Response

200 - application/json

improved_metric_description · string

Improved metric description

improved_evaluation_trigger · string

Improved evaluation trigger

trigger_type · enum<string>

Type of evaluation trigger (llm_judge or custom_code)

• llm_judge - LLM Judge
• custom_code - Custom Code

Available options: llm_judge, custom_code

metric_description_program · any

Advanced metric configuration

metric_description_variables · any[]

Variables used in metric description

evaluation_trigger_program · any

Advanced trigger configuration

evaluation_trigger_variables · any[]

Variables used in evaluation trigger

review_results · object[]

Evaluation results for each test set

Show child attributes