Get TaskAgent Eval Run

GET

/org/:org_id/project/:project_id/task-agent/:task_agent_id/eval/run/:task_agent_eval_run_id

GET

/api/v1/org/:org_id/project/:project_id/task-agent/:task_agent_id/eval/run/:task_agent_eval_run_id

$ curl https://app.rightbrain.ai/api/v1/org/org_id/project/project_id/task-agent/task_agent_id/eval/run/task_agent_eval_run_id \
>      -H "Authorization: Bearer <token>"

1 {
2   "id": "string",
3   "task_agent_id": "string",
4   "project_id": "string",
5   "candidate_revision_id": "string",
6   "status": "pending",
7   "pass_count": 1,
8   "fail_count": 1,
9   "error_count": 1,
10   "created": "string",
11   "modified": "string",
12   "judge_model": {
13     "name": "string",
14     "provider": "string"
15   },
16   "task_agent_run_ids": [
17     "string"
18   ],
19   "pass_rate": 1.1,
20   "eval_set_id": "string",
21   "started_at": "string",
22   "completed_at": "string",
23   "last_activity_at": "string",
24   "error_message": "string",
25   "created_by_user_id": "string",
26   "metrics": {
27     "token_cost": {
28       "reference_avg": 1.1,
29       "candidate_avg": 1.1,
30       "delta_pct": 1.1
31     },
32     "charged_credits": {
33       "reference_avg": 1.1,
34       "candidate_avg": 1.1,
35       "delta_pct": 1.1
36     },
37     "duration_ms": {
38       "reference_avg": 1.1,
39       "candidate_avg": 1.1,
40       "delta_pct": 1.1
41     }
42   },
43   "results": [
44     {
45       "id": "string",
46       "eval_run_id": "string",
47       "eval_case_id": "string",
48       "reference_run_id": "string",
49       "judge_input_tokens": 1,
50       "judge_output_tokens": 1,
51       "is_error": true,
52       "created": "string",
53       "candidate_run_id": "string",
54       "verdict": "pass",
55       "reasoning": "string",
56       "error_message": "string",
57       "metrics": {
58         "reference": {
59           "total_tokens": 1,
60           "charged_credits": "string",
61           "duration_ms": 1.1
62         },
63         "candidate": {
64           "total_tokens": 1,
65           "charged_credits": "string",
66           "duration_ms": 1.1
67         }
68       }
69     }
70   ]
71 }

Get TaskAgent eval run detail, including verdicts, aggregate metrics, and per-result run metrics when the underlying source rows still exist. Encrypted reference and candidate output snapshots are not exposed.

Authentication

AuthorizationBearer

Bearer token authentication using JWT tokens from Ory Kratos/Hydra

Path parameters

org_idstringRequiredformat: "uuid"

The organization ID

project_idstringRequiredformat: "uuid"

The project ID

task_agent_idstringRequiredformat: "uuid"

The task agent ID

task_agent_eval_run_idstringRequiredformat: "uuid"

The TaskAgent eval run ID

Response

Successful Response

idstringformat: "uuid"

task_agent_idstringformat: "uuid"

project_idstringformat: "uuid"

candidate_revision_idstringformat: "uuid"

statusenum

Status of a TaskAgent eval run.

pass_countinteger

fail_countinteger

error_countinteger

createdstring

modifiedstring

judge_modelobject

task_agent_run_idslist of stringsRead-only

pass_ratedouble or nullRead-only

eval_set_idstring or nullformat: "uuid"

started_atstring or null

completed_atstring or null

last_activity_atstring or null

error_messagestring or null

created_by_user_idstring or nullformat: "uuid"

metricsobject or null

resultslist of objects

Errors

400

Bad Request Error

403

Forbidden Error

404

Not Found Error

422

Unprocessable Entity Error