Skip to content
Judgment Labs
Esc
↑↓navigate↵open⌘Jpreview

Prepare and queue test run

Create a Supabase-backed v1 test run, create linked evaluation_runs, and enqueue judge evaluation work.

POST/v1/projects/{projectId}/test-runs
Authorization
AuthorizationPersonal API key · headerrequired

Your personal API key from Settings > Personal API Keys, sent as Bearer <key>.

X-Organization-IdOrganization ID · headerrequired

The organization to act in. Copy it with Copy organization ID in the organization menu or the settings sidebar.

Path parameters
projectIdstringrequired
Request body
requiredapplication/json
test_run_idstring<uuid>

Reuse an owned, pending platform agent run instead of creating a new run.

test_config_idstringrequired
namestring
dataset_version_idstring
dataset_version_numbernumber
judge_versionsobject[]
Show properties
Array of object
judge_idstring
namestring
versionstring
major_versionnumber
minor_versionnumber
sourcestring
Allowed:sdkclimcpplatformlegacy
agent_errorsobject[]
Show properties
Array of object
example_idstringrequired
errorstringrequired
min length 1
agent_tracesobject[]
Show properties
Array of object
example_idstringrequired
agent_offline_trace_idstringrequired
Responses
200

Response for status 200

test_runobjectrequired
Show properties
idstringrequired
organization_idstring
project_idstringrequired
user_idstringrequired
test_config_idstringrequired
dataset_idstringrequired
dataset_version_idstringrequired
sourcestringrequired
Allowed:sdkclimcpplatformlegacy
statusstringrequired
Allowed:pendingrunningcompletederrorcancelled
namestringrequired
error_messagestring | null
Show properties
Any of:
string
string
null
null
created_atstring
updated_atstring
started_atstring | null
Show properties
Any of:
string
string
null
null
completed_atstring | null
Show properties
Any of:
string
string
null
null
datasetobjectrequired
Show properties
dataset_idstringrequired
organization_idstring
project_idstring
namestringrequired
schemaobject | null
Show properties
Any of:
object
object
null
null
current_versionnumber
created_atstring
updated_atstring
creator_idstring | nullrequired
Show properties
Any of:
string
string
null
null
entriesnumber
test_config_countnumber
dataset_versionobjectrequired
Show properties
version_idstringrequired
dataset_idstringrequired
organization_idstringrequired
project_idstringrequired
version_numbernumberrequired
created_atstringrequired
user_idstring | nullrequired
Show properties
Any of:
string
string
null
null
item_countnumberrequired
examplesobject[]required
Show properties
Array of object
example_idstringrequired
organization_idstring
project_idstring
dataobjectrequired
metadataobject | null
Show properties
Any of:
object
object
null
null
managed_metadataobjectrequired
created_atstring
user_idstringrequired
judgesobject[]required
Show properties
Array of object
judge_idstringrequired
judge_namestringrequired
judge_typestringrequired
score_typestringrequired
judge_major_versionnumberrequired
judge_minor_versionnumberrequired
evaluation_runsobject[]required
Show properties
Array of object
run_idstringrequired
judge_namestringrequired
example_idstringrequired
test_run_idstringrequired
judge_idstringrequired
judge_major_versionnumberrequired
judge_minor_versionnumberrequired
ui_results_urlstringrequired
402

Response for status 402

errorstringrequired
messagestring
codestring
detailsstring[]
404

Response for status 404

errorstringrequired
messagestring
codestring
detailsstring[]
409

Response for status 409

errorstringrequired
messagestring
codestring
detailsstring[]
422

Response for status 422

errorstringrequired
messagestring
codestring
detailsstring[]
429

Response for status 429

errorstringrequired
messagestring
codestring
detailsstring[]
Try it
Server
Authorization
Parameters
Bodyapplication/json
Request
curl -X POST 'https://api.judgmentlabs.ai/v1/projects/YOUR_PROJECT_ID/test-runs' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'X-Organization-Id: YOUR_ORGANIZATION_ID' \
  -H 'Accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
  "test_run_id": "01dbc221-8963-4bd7-8591-4a1f9d286862",
  "test_config_id": "string",
  "name": "string",
  "dataset_version_id": "string",
  "dataset_version_number": 0,
  "judge_versions": [
    {
      "judge_id": "string",
      "name": "string",
      "version": "string",
      "major_version": 0,
      "minor_version": 0
    }
  ],
  "source": "sdk",
  "agent_errors": [
    {
      "example_id": "string",
      "error": "string"
    }
  ],
  "agent_traces": [
    {
      "example_id": "string",
      "agent_offline_trace_id": "string"
    }
  ]
}'
Response
{
  "test_run": {
    "id": "string",
    "organization_id": "string",
    "project_id": "string",
    "user_id": "string",
    "test_config_id": "string",
    "dataset_id": "string",
    "dataset_version_id": "string",
    "source": "sdk",
    "status": "pending",
    "name": "string",
    "error_message": "string",
    "created_at": "string",
    "updated_at": "string",
    "started_at": "string",
    "completed_at": "string"
  },
  "dataset": {
    "dataset_id": "string",
    "organization_id": "string",
    "project_id": "string",
    "name": "string",
    "schema": {},
    "current_version": 0,
    "created_at": "string",
    "updated_at": "string",
    "creator_id": "string",
    "entries": 0,
    "test_config_count": 0
  },
  "dataset_version": {
    "version_id": "string",
    "dataset_id": "string",
    "organization_id": "string",
    "project_id": "string",
    "version_number": 0,
    "created_at": "string",
    "user_id": "string",
    "item_count": 0
  },
  "examples": [
    {
      "example_id": "string",
      "organization_id": "string",
      "project_id": "string",
      "data": {},
      "metadata": {},
      "managed_metadata": {},
      "created_at": "string",
      "user_id": "string"
    }
  ],
  "judges": [
    {
      "judge_id": "string",
      "judge_name": "string",
      "judge_type": "string",
      "score_type": "string",
      "judge_major_version": 0,
      "judge_minor_version": 0
    }
  ],
  "evaluation_runs": [
    {
      "run_id": "string",
      "judge_name": "string",
      "example_id": "string",
      "test_run_id": "string",
      "judge_id": "string",
      "judge_major_version": 0,
      "judge_minor_version": 0
    }
  ],
  "ui_results_url": "string"
}

Was this page helpful?