The few causes behind a run’s failures

GET

/v1/runs/{id}/failure-groups

curl --request GET \
  --url https://beta-api.plune.ai/v1/runs/2489E9AD-2EE2-8E00-8EC9-32D5F69181C0/failure-groups \
  --header 'Authorization: Bearer <token>'

• beta
• production
• local

A separate path rather than a field on the run: GET /v1/runs/{id} returns the CLI’s RunResult verbatim, and that round trip is the sync contract.

Authorizations

• bearerAuth
• cookieAuth

Parameters

Path Parameters

id

required

string format: uuid

Responses

200

Grouped failures (empty for a clean run)

Media type application/json

object

groups

required

Largest cause first; ties ordered by signature so the list is stable.

Array<object>

One cause behind several failures in a run. The signature hashes the reason with its numbers and quoted values replaced, so per-row differences collapse; it is mixed with the eval id, so identical wording in two evals stays two groups.

object

signature

required

Stable id for this kind of failure.

string

evalId

required

string

count

required

Dataset rows that failed this way.

integer

reason

required

One cause verbatim, as an example.

string

rows

required

Row indexes within the eval, for expanding the group.

Array<integer>

Example ^generated

{
  "groups": [
    {
      "signature": "example",
      "evalId": "example",
      "count": 1,
      "reason": "example",
      "rows": [
        1
      ]
    }
  ]
}

401

No / invalid token or session

404

Not found or not yours

Media type application/json

object

error

required

string

Example ^generated

{
  "error": "example"
}