Create harness compare

curl --request POST \
  --url https://evalgate.com/api/harness/experiments/compare \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "policy": {
    "confidenceLevel": 123,
    "minimumMeaningfulDelta": 123,
    "minimumSampleSize": 123,
    "qualityFloor": 123,
    "nonRegressionMargin": 123,
    "efficiencyMetrics": [
      "<string>"
    ]
  },
  "candidate": {
    "schemaVersion": 1,
    "batchId": "<string>",
    "correctness": {
      "max": 123,
      "min": 123,
      "mean": 123,
      "median": 123,
      "sampleStdDev": 123
    },
    "n": 123,
    "hardFailureCounts": {},
    "categoryScores": {},
    "summaryHash": "<string>"
  },
  "baseline": {
    "schemaVersion": 1,
    "batchId": "<string>",
    "correctness": {
      "max": 123,
      "min": 123,
      "mean": 123,
      "median": 123,
      "sampleStdDev": 123
    },
    "n": 123,
    "hardFailureCounts": {},
    "categoryScores": {},
    "summaryHash": "<string>"
  },
  "qualityMetric": "<string>"
}
'

import requests

url = "https://evalgate.com/api/harness/experiments/compare"

payload = {
    "policy": {
        "confidenceLevel": 123,
        "minimumMeaningfulDelta": 123,
        "minimumSampleSize": 123,
        "qualityFloor": 123,
        "nonRegressionMargin": 123,
        "efficiencyMetrics": ["<string>"]
    },
    "candidate": {
        "schemaVersion": 1,
        "batchId": "<string>",
        "correctness": {
            "max": 123,
            "min": 123,
            "mean": 123,
            "median": 123,
            "sampleStdDev": 123
        },
        "n": 123,
        "hardFailureCounts": {},
        "categoryScores": {},
        "summaryHash": "<string>"
    },
    "baseline": {
        "schemaVersion": 1,
        "batchId": "<string>",
        "correctness": {
            "max": 123,
            "min": 123,
            "mean": 123,
            "median": 123,
            "sampleStdDev": 123
        },
        "n": 123,
        "hardFailureCounts": {},
        "categoryScores": {},
        "summaryHash": "<string>"
    },
    "qualityMetric": "<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({
    policy: {
      confidenceLevel: 123,
      minimumMeaningfulDelta: 123,
      minimumSampleSize: 123,
      qualityFloor: 123,
      nonRegressionMargin: 123,
      efficiencyMetrics: ['<string>']
    },
    candidate: {
      schemaVersion: 1,
      batchId: '<string>',
      correctness: {max: 123, min: 123, mean: 123, median: 123, sampleStdDev: 123},
      n: 123,
      hardFailureCounts: {},
      categoryScores: {},
      summaryHash: '<string>'
    },
    baseline: {
      schemaVersion: 1,
      batchId: '<string>',
      correctness: {max: 123, min: 123, mean: 123, median: 123, sampleStdDev: 123},
      n: 123,
      hardFailureCounts: {},
      categoryScores: {},
      summaryHash: '<string>'
    },
    qualityMetric: '<string>'
  })
};

fetch('https://evalgate.com/api/harness/experiments/compare', 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/harness/experiments/compare",
  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([
    'policy' => [
        'confidenceLevel' => 123,
        'minimumMeaningfulDelta' => 123,
        'minimumSampleSize' => 123,
        'qualityFloor' => 123,
        'nonRegressionMargin' => 123,
        'efficiencyMetrics' => [
                '<string>'
        ]
    ],
    'candidate' => [
        'schemaVersion' => 1,
        'batchId' => '<string>',
        'correctness' => [
                'max' => 123,
                'min' => 123,
                'mean' => 123,
                'median' => 123,
                'sampleStdDev' => 123
        ],
        'n' => 123,
        'hardFailureCounts' => [
                
        ],
        'categoryScores' => [
                
        ],
        'summaryHash' => '<string>'
    ],
    'baseline' => [
        'schemaVersion' => 1,
        'batchId' => '<string>',
        'correctness' => [
                'max' => 123,
                'min' => 123,
                'mean' => 123,
                'median' => 123,
                'sampleStdDev' => 123
        ],
        'n' => 123,
        'hardFailureCounts' => [
                
        ],
        'categoryScores' => [
                
        ],
        'summaryHash' => '<string>'
    ],
    'qualityMetric' => '<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/harness/experiments/compare"

	payload := strings.NewReader("{\n  \"policy\": {\n    \"confidenceLevel\": 123,\n    \"minimumMeaningfulDelta\": 123,\n    \"minimumSampleSize\": 123,\n    \"qualityFloor\": 123,\n    \"nonRegressionMargin\": 123,\n    \"efficiencyMetrics\": [\n      \"<string>\"\n    ]\n  },\n  \"candidate\": {\n    \"schemaVersion\": 1,\n    \"batchId\": \"<string>\",\n    \"correctness\": {\n      \"max\": 123,\n      \"min\": 123,\n      \"mean\": 123,\n      \"median\": 123,\n      \"sampleStdDev\": 123\n    },\n    \"n\": 123,\n    \"hardFailureCounts\": {},\n    \"categoryScores\": {},\n    \"summaryHash\": \"<string>\"\n  },\n  \"baseline\": {\n    \"schemaVersion\": 1,\n    \"batchId\": \"<string>\",\n    \"correctness\": {\n      \"max\": 123,\n      \"min\": 123,\n      \"mean\": 123,\n      \"median\": 123,\n      \"sampleStdDev\": 123\n    },\n    \"n\": 123,\n    \"hardFailureCounts\": {},\n    \"categoryScores\": {},\n    \"summaryHash\": \"<string>\"\n  },\n  \"qualityMetric\": \"<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/harness/experiments/compare")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"policy\": {\n    \"confidenceLevel\": 123,\n    \"minimumMeaningfulDelta\": 123,\n    \"minimumSampleSize\": 123,\n    \"qualityFloor\": 123,\n    \"nonRegressionMargin\": 123,\n    \"efficiencyMetrics\": [\n      \"<string>\"\n    ]\n  },\n  \"candidate\": {\n    \"schemaVersion\": 1,\n    \"batchId\": \"<string>\",\n    \"correctness\": {\n      \"max\": 123,\n      \"min\": 123,\n      \"mean\": 123,\n      \"median\": 123,\n      \"sampleStdDev\": 123\n    },\n    \"n\": 123,\n    \"hardFailureCounts\": {},\n    \"categoryScores\": {},\n    \"summaryHash\": \"<string>\"\n  },\n  \"baseline\": {\n    \"schemaVersion\": 1,\n    \"batchId\": \"<string>\",\n    \"correctness\": {\n      \"max\": 123,\n      \"min\": 123,\n      \"mean\": 123,\n      \"median\": 123,\n      \"sampleStdDev\": 123\n    },\n    \"n\": 123,\n    \"hardFailureCounts\": {},\n    \"categoryScores\": {},\n    \"summaryHash\": \"<string>\"\n  },\n  \"qualityMetric\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://evalgate.com/api/harness/experiments/compare")

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  \"policy\": {\n    \"confidenceLevel\": 123,\n    \"minimumMeaningfulDelta\": 123,\n    \"minimumSampleSize\": 123,\n    \"qualityFloor\": 123,\n    \"nonRegressionMargin\": 123,\n    \"efficiencyMetrics\": [\n      \"<string>\"\n    ]\n  },\n  \"candidate\": {\n    \"schemaVersion\": 1,\n    \"batchId\": \"<string>\",\n    \"correctness\": {\n      \"max\": 123,\n      \"min\": 123,\n      \"mean\": 123,\n      \"median\": 123,\n      \"sampleStdDev\": 123\n    },\n    \"n\": 123,\n    \"hardFailureCounts\": {},\n    \"categoryScores\": {},\n    \"summaryHash\": \"<string>\"\n  },\n  \"baseline\": {\n    \"schemaVersion\": 1,\n    \"batchId\": \"<string>\",\n    \"correctness\": {\n      \"max\": 123,\n      \"min\": 123,\n      \"mean\": 123,\n      \"median\": 123,\n      \"sampleStdDev\": 123\n    },\n    \"n\": 123,\n    \"hardFailureCounts\": {},\n    \"categoryScores\": {},\n    \"summaryHash\": \"<string>\"\n  },\n  \"qualityMetric\": \"<string>\"\n}"

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

{
  "automaticApply": true,
  "decision": "candidate_better",
  "policy": {
    "confidenceLevel": 123,
    "minimumSampleSize": 123,
    "qualityFloor": 123,
    "nonRegressionMargin": 123,
    "minimumMeaningfulDelta": 123
  },
  "quality": {
    "metric": "<string>",
    "baselineEstimate": 123,
    "candidateEstimate": 123,
    "delta": 123,
    "baselineInterval": {
      "lower": 123,
      "upper": 123,
      "confidenceLevel": 123
    },
    "candidateInterval": {
      "lower": 123,
      "upper": 123,
      "confidenceLevel": 123
    },
    "deltaInterval": {
      "lower": 123,
      "upper": 123,
      "confidenceLevel": 123
    },
    "evidenceSufficient": true,
    "improved": true,
    "regressed": true,
    "passesQualityFloor": true,
    "nonRegression": true,
    "meaningfulImprovement": true,
    "meaningfullyRegressed": true
  },
  "efficiency": {
    "metrics": {},
    "savingsRecommendation": {
      "supported": true,
      "metrics": [
        "<string>"
      ]
    }
  },
  "confidence": {
    "qualityEvidenceSufficient": true,
    "efficiencyEvidenceSufficient": true,
    "baseN": 123,
    "candidateN": 123
  },
  "reasonCodes": [
    "<string>"
  ]
}

{
  "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
    }
  }
}