FruxonDocs
ApiAgent reviews

Checks a recommendation card's latest test again where its change did worse.

Replies vary from one run to the next, and the judge has to pick a side, so a reply judged worse in one test may be noise. This replays each case the card's latest `:compare` found worse — on the card's own conversations, on the others, and on the cases a revision was made from — twice more, with and without the change, judged as the test judged it. A case counts as worse when the change did worse in at least two of its three verdicts: the test's and the two here. The replays are evaluation runs, read like a comparison's: `cardRuns` and `otherRuns` at `evaluationRuns/{id}` until `COMPLETED`, with each case's verdict in its `samples` under the key listed in `cases`. They route connections as the test did, and the card keeps the check on its `comparison` as `recheck`. Name the test you read as `comparisonId` (the card's `comparison.id`); a test is checked again once, and a check that ended without a verdict can be started again. Agent admins only.

POST
/v1/tenants/{tenant}/agents/{agent}/recommendations/{recommendation}:recheck

Authorization

Bearer
AuthorizationBearer <token>

JWT Authorization header using the Bearer scheme. Enter 'Bearer' [space] and then your token.

In: header

Path Parameters

agent*string

The agent ID.

recommendation*string

The recommendation ID.

Formatuuid
tenant*string

The tenant identifier

Request Body

The test you read.

comparisonId?string

The test you read — the card's comparison.id — so what is checked is that test, not one another admin started since.

Formatuuid
[key: string]?never

Response Body

curl -X POST "https://api.fruxon.com/v1/tenants/string/agents/string/recommendations/497f6eca-6276-4993-bfeb-53cbbbba6f08:recheck" \  -H "Content-Type: application/json" \  -d '{}'
{
  "id": "00000000-0000-0000-0000-000000000000",
  "comparisonId": "00000000-0000-0000-0000-000000000000",
  "baseRevision": 0,
  "cardRuns": [
    {
      "id": "00000000-0000-0000-0000-000000000000",
      "agentId": "string",
      "kind": "DATASET",
      "datasetId": "00000000-0000-0000-0000-000000000000",
      "candidateRevision": 0,
      "candidateBaseRevision": 0,
      "candidateProposalId": "00000000-0000-0000-0000-000000000000",
      "candidateSnapshotSeqNo": 0,
      "deployedRevision": 0,
      "status": "PENDING",
      "score": 0,
      "deploymentRecommendation": "string",
      "summary": {
        "totalSamples": 0,
        "successfulEvaluations": 0,
        "failedEvaluations": 0,
        "averageLlmScore": 0,
        "scoreDistribution": {},
        "assessmentDistribution": {},
        "topConcerns": [],
        "keyImprovements": [],
        "pairwise": null,
        "runtime": null,
        "cost": null
      },
      "errorMessage": "string",
      "createdAt": 0,
      "modifiedAt": 0,
      "startedAt": 0,
      "completedAt": 0,
      "createdBy": "string"
    }
  ],
  "otherRuns": [
    {
      "id": "00000000-0000-0000-0000-000000000000",
      "agentId": "string",
      "kind": "DATASET",
      "datasetId": "00000000-0000-0000-0000-000000000000",
      "candidateRevision": 0,
      "candidateBaseRevision": 0,
      "candidateProposalId": "00000000-0000-0000-0000-000000000000",
      "candidateSnapshotSeqNo": 0,
      "deployedRevision": 0,
      "status": "PENDING",
      "score": 0,
      "deploymentRecommendation": "string",
      "summary": {
        "totalSamples": 0,
        "successfulEvaluations": 0,
        "failedEvaluations": 0,
        "averageLlmScore": 0,
        "scoreDistribution": {},
        "assessmentDistribution": {},
        "topConcerns": [],
        "keyImprovements": [],
        "pairwise": null,
        "runtime": null,
        "cost": null
      },
      "errorMessage": "string",
      "createdAt": 0,
      "modifiedAt": 0,
      "startedAt": 0,
      "completedAt": 0,
      "createdBy": "string"
    }
  ],
  "cases": [
    {
      "caseKey": "string",
      "source": "CARD"
    }
  ]
}
{
  "type": "string",
  "title": "string",
  "status": 0,
  "detail": "string",
  "instance": "string",
  "property1": null,
  "property2": null
}
Empty
{
  "type": "string",
  "title": "string",
  "status": 0,
  "detail": "string",
  "instance": "string",
  "property1": null,
  "property2": null
}
{
  "type": "string",
  "title": "string",
  "status": 0,
  "detail": "string",
  "instance": "string",
  "property1": null,
  "property2": null
}
{
  "type": "string",
  "title": "string",
  "status": 0,
  "detail": "string",
  "instance": "string",
  "property1": null,
  "property2": null
}