Thanks to visit codestin.com
Credit goes to docs.futureagi.com

Codestin Search App

Update Eval Config

Update an evaluation configuration for a test run. Modify config, mapping, model, name, or error localizer. Optionally trigger an immediate rerun after saving.

POST https://api.futureagi.com/simulate/run-tests/{run_test_id}/eval-configs/{eval_config_id}/update/

Authentication

X-Api-Key API Key Required

Your Future AGI API key used to authenticate requests. You can find and manage your API keys in the Dashboard under Settings.

X-Secret-Key Secret Key Required

Your Future AGI secret key, used alongside the API key for request authentication. This is generated when you create an API key in the Dashboard.

Path parameters

run_test_id UUID Required

The test run ID.

eval_config_id UUID Required

The evaluation configuration ID.

Request body

config object Optional

Updated evaluation configuration parameters. Supports nested config and mapping keys.

mapping object Optional

Updated field mapping between test data and evaluation inputs.

model string Optional

Model to use for evaluations.

error_localizer boolean Optional

Enable granular error localization in evaluation results.

kb_id string Optional

UUID of a knowledge base to use for grounding. Pass null to clear.

name string Optional

Updated name for the evaluation configuration. Cannot be blank.

run boolean Optional

When true, triggers an immediate rerun after updating. Defaults to false. Requires test_execution_id when set to true.

test_execution_id string Optional

UUID of the test execution to rerun against. Required when run is true.

Response

200 OK
message string
Confirmation of successful update.
eval_config_id string
UUID of the updated evaluation config.
run_test_id string
UUID of the parent test run.
test_execution_id string
UUID of the test execution that was rerun. Only present when run=true.
call_execution_count integer
Number of call executions queued for re-evaluation. Only present when run=true.
note string
Additional context about parallel task spawning. Only present when run=true.

Errors

400 Bad Request Optional

Validation error. The response includes a details object with per-field errors.

{
  "test_execution_id": ["test_execution_id is required when run is true"]
}

Or when the test execution has an incompatible status:

{"error": "Only test executions with COMPLETED, CANCELLED, or FAILED status can have evaluations rerun"}
401 Unauthorized Optional

Invalid or missing API credentials.

404 Not Found Optional

Test run or evaluation configuration not found.

{"detail": "No RunTest matches the given query."}
500 Internal Server Error Optional

Unexpected server error.

{"error": "Failed to update evaluation config: <message>"}
GET /
Authentication
REQUEST
 
RESPONSE