Create experiments decision

curl --request POST \
  --url https://evalgate.com/api/experiments/{id}/decision \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "decision": "needs_review",
  "rationale": "<string>",
  "idempotencyKey": "<string>",
  "comparisonHash": "<string>",
  "winningVariantKey": "<string>"
}
'

import requests

url = "https://evalgate.com/api/experiments/{id}/decision"

payload = {
    "decision": "needs_review",
    "rationale": "<string>",
    "idempotencyKey": "<string>",
    "comparisonHash": "<string>",
    "winningVariantKey": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    decision: 'needs_review',
    rationale: '<string>',
    idempotencyKey: '<string>',
    comparisonHash: '<string>',
    winningVariantKey: '<string>'
  })
};

fetch('https://evalgate.com/api/experiments/{id}/decision', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://evalgate.com/api/experiments/{id}/decision",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'decision' => 'needs_review',
    'rationale' => '<string>',
    'idempotencyKey' => '<string>',
    'comparisonHash' => '<string>',
    'winningVariantKey' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://evalgate.com/api/experiments/{id}/decision"

	payload := strings.NewReader("{\n  \"decision\": \"needs_review\",\n  \"rationale\": \"<string>\",\n  \"idempotencyKey\": \"<string>\",\n  \"comparisonHash\": \"<string>\",\n  \"winningVariantKey\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://evalgate.com/api/experiments/{id}/decision")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"decision\": \"needs_review\",\n  \"rationale\": \"<string>\",\n  \"idempotencyKey\": \"<string>\",\n  \"comparisonHash\": \"<string>\",\n  \"winningVariantKey\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://evalgate.com/api/experiments/{id}/decision")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"decision\": \"needs_review\",\n  \"rationale\": \"<string>\",\n  \"idempotencyKey\": \"<string>\",\n  \"comparisonHash\": \"<string>\",\n  \"winningVariantKey\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "idempotentReplay": true,
  "id": "<string>",
  "organizationId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "experimentId": "<string>",
  "executionId": "<string>",
  "decision": "<string>",
  "winningVariantId": "<string>",
  "rationale": "<string>",
  "comparisonHash": "<string>",
  "comparisonJson": {
    "bindingVersion": "evalgate.experiment-decision-binding.v2",
    "baselineVariantKey": "<string>",
    "candidateVariantKey": "<string>",
    "classification": "invalid",
    "decisionLogic": [
      "<string>"
    ],
    "comparable": true,
    "evidenceState": "invalid",
    "comparisonHash": "<string>",
    "policyHash": "<string>",
    "resolvedPolicy": {
      "schemaVersion": "evalgate.experiment-winner-policy.v2",
      "minimumPassRateDelta": 123,
      "maximumCostIncreasePercent": 123,
      "maximumP95LatencyIncreasePercent": 123,
      "allowIncomparableJudges": false,
      "allowRegressions": true,
      "minimumSampleSize": 123,
      "confidenceLevel": 123,
      "requireConfidenceInterval": true,
      "statisticalMethod": "paired-bonferroni-wilson-v1"
    },
    "reconciliation": {
      "expectedLogicalObservations": 123,
      "reconciledLogicalObservations": 123,
      "acceptedPhysicalAttempts": 123,
      "deduplicatedDeliveries": 123,
      "diagnostics": [
        {
          "code": "missing_expected_frame",
          "severity": "invalid",
          "message": "<string>",
          "variantKey": "<string>",
          "caseId": 123,
          "logicalTrialIndex": 123,
          "attemptId": "<string>"
        }
      ]
    },
    "metrics": {
      "quality": {
        "baselinePassRate": 123,
        "candidatePassRate": 123,
        "delta": 123,
        "confidence95": {
          "low": 123,
          "high": 123
        },
        "independentPairCount": 123
      },
      "scoreDistribution": {
        "baseline": [
          123
        ],
        "candidate": [
          123
        ],
        "meanDelta": 123
      },
      "cost": {
        "baselineUsd": 123,
        "candidateUsd": 123,
        "deltaUsd": 123,
        "unknownBaselineRows": 123,
        "unknownCandidateRows": 123
      },
      "latency": {
        "baselineP50Ms": 123,
        "candidateP50Ms": 123,
        "p50DeltaMs": 123,
        "baselineP95Ms": 123,
        "candidateP95Ms": 123,
        "p95DeltaMs": 123
      },
      "failures": {
        "baseline": {},
        "candidate": {},
        "newRegressions": 123,
        "fixedRegressions": 123,
        "toolCallDelta": 123,
        "toolErrorDelta": 123,
        "policyBlockDelta": 123
      }
    },
    "pairedRows": [
      {
        "caseId": 123,
        "baseline": {
          "variantKey": "<string>",
          "caseId": 123,
          "testResultId": 123,
          "runId": 123,
          "status": "<string>",
          "output": "<string>",
          "score": 123,
          "durationMs": 123,
          "costUsd": 123,
          "costKnown": true,
          "failureMode": "<string>",
          "toolError": true,
          "toolCallCount": 123,
          "policyBlocked": true,
          "judgeIdentity": "<string>",
          "traceId": 123,
          "modelCallId": "<string>",
          "evidenceComplete": true,
          "executionId": "<string>",
          "executionAttempt": 123,
          "logicalTrialIndex": 123,
          "physicalAttemptIndex": 123,
          "attemptId": "<string>",
          "attemptKind": "initial",
          "attemptStatus": "completed",
          "attemptCompletedAt": "<string>",
          "artifactHash": "<string>",
          "caseContentHash": "<string>",
          "variantConfigurationHash": "<string>",
          "actualEvaluatorIdentity": "<string>",
          "actualCalibrationIdentity": "<string>",
          "artifacts": [
            {
              "kind": "score_provenance",
              "contentHash": "<string>"
            }
          ]
        },
        "candidate": {
          "variantKey": "<string>",
          "caseId": 123,
          "testResultId": 123,
          "runId": 123,
          "status": "<string>",
          "output": "<string>",
          "score": 123,
          "durationMs": 123,
          "costUsd": 123,
          "costKnown": true,
          "failureMode": "<string>",
          "toolError": true,
          "toolCallCount": 123,
          "policyBlocked": true,
          "judgeIdentity": "<string>",
          "traceId": 123,
          "modelCallId": "<string>",
          "evidenceComplete": true,
          "executionId": "<string>",
          "executionAttempt": 123,
          "logicalTrialIndex": 123,
          "physicalAttemptIndex": 123,
          "attemptId": "<string>",
          "attemptKind": "initial",
          "attemptStatus": "completed",
          "attemptCompletedAt": "<string>",
          "artifactHash": "<string>",
          "caseContentHash": "<string>",
          "variantConfigurationHash": "<string>",
          "actualEvaluatorIdentity": "<string>",
          "actualCalibrationIdentity": "<string>",
          "artifacts": [
            {
              "kind": "score_provenance",
              "contentHash": "<string>"
            }
          ]
        },
        "qualityDelta": 123,
        "costDeltaUsd": 123,
        "latencyDeltaMs": 123,
        "classification": "regression",
        "warnings": [
          "<string>"
        ],
        "logicalTrialIndex": 123
      }
    ],
    "warnings": [
      "<string>"
    ],
    "missingData": [
      "<string>"
    ]
  },
  "idempotencyKey": "<string>",
  "decidedBy": "<string>",
  "decidedAt": "2023-11-07T05:31:56Z"
}

{
  "idempotentReplay": true,
  "id": "<string>",
  "organizationId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "experimentId": "<string>",
  "executionId": "<string>",
  "decision": "<string>",
  "winningVariantId": "<string>",
  "rationale": "<string>",
  "comparisonHash": "<string>",
  "comparisonJson": {
    "bindingVersion": "evalgate.experiment-decision-binding.v2",
    "baselineVariantKey": "<string>",
    "candidateVariantKey": "<string>",
    "classification": "invalid",
    "decisionLogic": [
      "<string>"
    ],
    "comparable": true,
    "evidenceState": "invalid",
    "comparisonHash": "<string>",
    "policyHash": "<string>",
    "resolvedPolicy": {
      "schemaVersion": "evalgate.experiment-winner-policy.v2",
      "minimumPassRateDelta": 123,
      "maximumCostIncreasePercent": 123,
      "maximumP95LatencyIncreasePercent": 123,
      "allowIncomparableJudges": false,
      "allowRegressions": true,
      "minimumSampleSize": 123,
      "confidenceLevel": 123,
      "requireConfidenceInterval": true,
      "statisticalMethod": "paired-bonferroni-wilson-v1"
    },
    "reconciliation": {
      "expectedLogicalObservations": 123,
      "reconciledLogicalObservations": 123,
      "acceptedPhysicalAttempts": 123,
      "deduplicatedDeliveries": 123,
      "diagnostics": [
        {
          "code": "missing_expected_frame",
          "severity": "invalid",
          "message": "<string>",
          "variantKey": "<string>",
          "caseId": 123,
          "logicalTrialIndex": 123,
          "attemptId": "<string>"
        }
      ]
    },
    "metrics": {
      "quality": {
        "baselinePassRate": 123,
        "candidatePassRate": 123,
        "delta": 123,
        "confidence95": {
          "low": 123,
          "high": 123
        },
        "independentPairCount": 123
      },
      "scoreDistribution": {
        "baseline": [
          123
        ],
        "candidate": [
          123
        ],
        "meanDelta": 123
      },
      "cost": {
        "baselineUsd": 123,
        "candidateUsd": 123,
        "deltaUsd": 123,
        "unknownBaselineRows": 123,
        "unknownCandidateRows": 123
      },
      "latency": {
        "baselineP50Ms": 123,
        "candidateP50Ms": 123,
        "p50DeltaMs": 123,
        "baselineP95Ms": 123,
        "candidateP95Ms": 123,
        "p95DeltaMs": 123
      },
      "failures": {
        "baseline": {},
        "candidate": {},
        "newRegressions": 123,
        "fixedRegressions": 123,
        "toolCallDelta": 123,
        "toolErrorDelta": 123,
        "policyBlockDelta": 123
      }
    },
    "pairedRows": [
      {
        "caseId": 123,
        "baseline": {
          "variantKey": "<string>",
          "caseId": 123,
          "testResultId": 123,
          "runId": 123,
          "status": "<string>",
          "output": "<string>",
          "score": 123,
          "durationMs": 123,
          "costUsd": 123,
          "costKnown": true,
          "failureMode": "<string>",
          "toolError": true,
          "toolCallCount": 123,
          "policyBlocked": true,
          "judgeIdentity": "<string>",
          "traceId": 123,
          "modelCallId": "<string>",
          "evidenceComplete": true,
          "executionId": "<string>",
          "executionAttempt": 123,
          "logicalTrialIndex": 123,
          "physicalAttemptIndex": 123,
          "attemptId": "<string>",
          "attemptKind": "initial",
          "attemptStatus": "completed",
          "attemptCompletedAt": "<string>",
          "artifactHash": "<string>",
          "caseContentHash": "<string>",
          "variantConfigurationHash": "<string>",
          "actualEvaluatorIdentity": "<string>",
          "actualCalibrationIdentity": "<string>",
          "artifacts": [
            {
              "kind": "score_provenance",
              "contentHash": "<string>"
            }
          ]
        },
        "candidate": {
          "variantKey": "<string>",
          "caseId": 123,
          "testResultId": 123,
          "runId": 123,
          "status": "<string>",
          "output": "<string>",
          "score": 123,
          "durationMs": 123,
          "costUsd": 123,
          "costKnown": true,
          "failureMode": "<string>",
          "toolError": true,
          "toolCallCount": 123,
          "policyBlocked": true,
          "judgeIdentity": "<string>",
          "traceId": 123,
          "modelCallId": "<string>",
          "evidenceComplete": true,
          "executionId": "<string>",
          "executionAttempt": 123,
          "logicalTrialIndex": 123,
          "physicalAttemptIndex": 123,
          "attemptId": "<string>",
          "attemptKind": "initial",
          "attemptStatus": "completed",
          "attemptCompletedAt": "<string>",
          "artifactHash": "<string>",
          "caseContentHash": "<string>",
          "variantConfigurationHash": "<string>",
          "actualEvaluatorIdentity": "<string>",
          "actualCalibrationIdentity": "<string>",
          "artifacts": [
            {
              "kind": "score_provenance",
              "contentHash": "<string>"
            }
          ]
        },
        "qualityDelta": 123,
        "costDeltaUsd": 123,
        "latencyDeltaMs": 123,
        "classification": "regression",
        "warnings": [
          "<string>"
        ],
        "logicalTrialIndex": 123
      }
    ],
    "warnings": [
      "<string>"
    ],
    "missingData": [
      "<string>"
    ]
  },
  "idempotencyKey": "<string>",
  "decidedBy": "<string>",
  "decidedAt": "2023-11-07T05:31:56Z"
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}