Create llm judge test

curl --request POST \
  --url https://evalgate.com/api/llm-judge/test \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": "<string>",
  "output": "<string>",
  "promptTemplate": "<string>",
  "provider": "local",
  "model": "<string>",
  "expectedOutput": "<string>",
  "context": "<string>",
  "aggregation": "all_pass",
  "criteria": {},
  "criteriaList": [
    {
      "id": "<string>",
      "title": "<string>",
      "matchCriteria": "<string>"
    }
  ],
  "settings": {},
  "behavior": "<string>",
  "taskType": "<string>",
  "passThreshold": 123,
  "judges": [
    {
      "type": "decision",
      "id": "<string>",
      "purpose": "customer_evaluation",
      "provider": "local",
      "model": "<string>",
      "temperature": 123,
      "maxTokens": 123,
      "seed": 123,
      "threshold": 123,
      "weight": 123,
      "topP": 123,
      "timeoutMs": 123,
      "rule": "json_schema",
      "passThreshold": 123,
      "top_p": 123,
      "calibrationVersion": "<string>",
      "decisionPolicyVersion": "<string>",
      "cacheEnabled": false,
      "questions": [
        {}
      ],
      "primaryQuestionId": "<string>",
      "evidenceQuestionIds": [
        "<string>"
      ],
      "aggregationPolicy": "all_pass",
      "pinnedQuestionSchemaHash": "<string>",
      "releaseBlocking": false
    }
  ],
  "instabilityThreshold": 123,
  "stabilityRuns": 123
}
'

import requests

url = "https://evalgate.com/api/llm-judge/test"

payload = {
    "input": "<string>",
    "output": "<string>",
    "promptTemplate": "<string>",
    "provider": "local",
    "model": "<string>",
    "expectedOutput": "<string>",
    "context": "<string>",
    "aggregation": "all_pass",
    "criteria": {},
    "criteriaList": [
        {
            "id": "<string>",
            "title": "<string>",
            "matchCriteria": "<string>"
        }
    ],
    "settings": {},
    "behavior": "<string>",
    "taskType": "<string>",
    "passThreshold": 123,
    "judges": [
        {
            "type": "decision",
            "id": "<string>",
            "purpose": "customer_evaluation",
            "provider": "local",
            "model": "<string>",
            "temperature": 123,
            "maxTokens": 123,
            "seed": 123,
            "threshold": 123,
            "weight": 123,
            "topP": 123,
            "timeoutMs": 123,
            "rule": "json_schema",
            "passThreshold": 123,
            "top_p": 123,
            "calibrationVersion": "<string>",
            "decisionPolicyVersion": "<string>",
            "cacheEnabled": False,
            "questions": [{}],
            "primaryQuestionId": "<string>",
            "evidenceQuestionIds": ["<string>"],
            "aggregationPolicy": "all_pass",
            "pinnedQuestionSchemaHash": "<string>",
            "releaseBlocking": False
        }
    ],
    "instabilityThreshold": 123,
    "stabilityRuns": 123
}
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({
    input: '<string>',
    output: '<string>',
    promptTemplate: '<string>',
    provider: 'local',
    model: '<string>',
    expectedOutput: '<string>',
    context: '<string>',
    aggregation: 'all_pass',
    criteria: {},
    criteriaList: [{id: '<string>', title: '<string>', matchCriteria: '<string>'}],
    settings: {},
    behavior: '<string>',
    taskType: '<string>',
    passThreshold: 123,
    judges: [
      {
        type: 'decision',
        id: '<string>',
        purpose: 'customer_evaluation',
        provider: 'local',
        model: '<string>',
        temperature: 123,
        maxTokens: 123,
        seed: 123,
        threshold: 123,
        weight: 123,
        topP: 123,
        timeoutMs: 123,
        rule: 'json_schema',
        passThreshold: 123,
        top_p: 123,
        calibrationVersion: '<string>',
        decisionPolicyVersion: '<string>',
        cacheEnabled: false,
        questions: [{}],
        primaryQuestionId: '<string>',
        evidenceQuestionIds: ['<string>'],
        aggregationPolicy: 'all_pass',
        pinnedQuestionSchemaHash: '<string>',
        releaseBlocking: false
      }
    ],
    instabilityThreshold: 123,
    stabilityRuns: 123
  })
};

fetch('https://evalgate.com/api/llm-judge/test', 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/llm-judge/test",
  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([
    'input' => '<string>',
    'output' => '<string>',
    'promptTemplate' => '<string>',
    'provider' => 'local',
    'model' => '<string>',
    'expectedOutput' => '<string>',
    'context' => '<string>',
    'aggregation' => 'all_pass',
    'criteria' => [
        
    ],
    'criteriaList' => [
        [
                'id' => '<string>',
                'title' => '<string>',
                'matchCriteria' => '<string>'
        ]
    ],
    'settings' => [
        
    ],
    'behavior' => '<string>',
    'taskType' => '<string>',
    'passThreshold' => 123,
    'judges' => [
        [
                'type' => 'decision',
                'id' => '<string>',
                'purpose' => 'customer_evaluation',
                'provider' => 'local',
                'model' => '<string>',
                'temperature' => 123,
                'maxTokens' => 123,
                'seed' => 123,
                'threshold' => 123,
                'weight' => 123,
                'topP' => 123,
                'timeoutMs' => 123,
                'rule' => 'json_schema',
                'passThreshold' => 123,
                'top_p' => 123,
                'calibrationVersion' => '<string>',
                'decisionPolicyVersion' => '<string>',
                'cacheEnabled' => false,
                'questions' => [
                                [
                                                                
                                ]
                ],
                'primaryQuestionId' => '<string>',
                'evidenceQuestionIds' => [
                                '<string>'
                ],
                'aggregationPolicy' => 'all_pass',
                'pinnedQuestionSchemaHash' => '<string>',
                'releaseBlocking' => false
        ]
    ],
    'instabilityThreshold' => 123,
    'stabilityRuns' => 123
  ]),
  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/llm-judge/test"

	payload := strings.NewReader("{\n  \"input\": \"<string>\",\n  \"output\": \"<string>\",\n  \"promptTemplate\": \"<string>\",\n  \"provider\": \"local\",\n  \"model\": \"<string>\",\n  \"expectedOutput\": \"<string>\",\n  \"context\": \"<string>\",\n  \"aggregation\": \"all_pass\",\n  \"criteria\": {},\n  \"criteriaList\": [\n    {\n      \"id\": \"<string>\",\n      \"title\": \"<string>\",\n      \"matchCriteria\": \"<string>\"\n    }\n  ],\n  \"settings\": {},\n  \"behavior\": \"<string>\",\n  \"taskType\": \"<string>\",\n  \"passThreshold\": 123,\n  \"judges\": [\n    {\n      \"type\": \"decision\",\n      \"id\": \"<string>\",\n      \"purpose\": \"customer_evaluation\",\n      \"provider\": \"local\",\n      \"model\": \"<string>\",\n      \"temperature\": 123,\n      \"maxTokens\": 123,\n      \"seed\": 123,\n      \"threshold\": 123,\n      \"weight\": 123,\n      \"topP\": 123,\n      \"timeoutMs\": 123,\n      \"rule\": \"json_schema\",\n      \"passThreshold\": 123,\n      \"top_p\": 123,\n      \"calibrationVersion\": \"<string>\",\n      \"decisionPolicyVersion\": \"<string>\",\n      \"cacheEnabled\": false,\n      \"questions\": [\n        {}\n      ],\n      \"primaryQuestionId\": \"<string>\",\n      \"evidenceQuestionIds\": [\n        \"<string>\"\n      ],\n      \"aggregationPolicy\": \"all_pass\",\n      \"pinnedQuestionSchemaHash\": \"<string>\",\n      \"releaseBlocking\": false\n    }\n  ],\n  \"instabilityThreshold\": 123,\n  \"stabilityRuns\": 123\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/llm-judge/test")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"input\": \"<string>\",\n  \"output\": \"<string>\",\n  \"promptTemplate\": \"<string>\",\n  \"provider\": \"local\",\n  \"model\": \"<string>\",\n  \"expectedOutput\": \"<string>\",\n  \"context\": \"<string>\",\n  \"aggregation\": \"all_pass\",\n  \"criteria\": {},\n  \"criteriaList\": [\n    {\n      \"id\": \"<string>\",\n      \"title\": \"<string>\",\n      \"matchCriteria\": \"<string>\"\n    }\n  ],\n  \"settings\": {},\n  \"behavior\": \"<string>\",\n  \"taskType\": \"<string>\",\n  \"passThreshold\": 123,\n  \"judges\": [\n    {\n      \"type\": \"decision\",\n      \"id\": \"<string>\",\n      \"purpose\": \"customer_evaluation\",\n      \"provider\": \"local\",\n      \"model\": \"<string>\",\n      \"temperature\": 123,\n      \"maxTokens\": 123,\n      \"seed\": 123,\n      \"threshold\": 123,\n      \"weight\": 123,\n      \"topP\": 123,\n      \"timeoutMs\": 123,\n      \"rule\": \"json_schema\",\n      \"passThreshold\": 123,\n      \"top_p\": 123,\n      \"calibrationVersion\": \"<string>\",\n      \"decisionPolicyVersion\": \"<string>\",\n      \"cacheEnabled\": false,\n      \"questions\": [\n        {}\n      ],\n      \"primaryQuestionId\": \"<string>\",\n      \"evidenceQuestionIds\": [\n        \"<string>\"\n      ],\n      \"aggregationPolicy\": \"all_pass\",\n      \"pinnedQuestionSchemaHash\": \"<string>\",\n      \"releaseBlocking\": false\n    }\n  ],\n  \"instabilityThreshold\": 123,\n  \"stabilityRuns\": 123\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://evalgate.com/api/llm-judge/test")

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  \"input\": \"<string>\",\n  \"output\": \"<string>\",\n  \"promptTemplate\": \"<string>\",\n  \"provider\": \"local\",\n  \"model\": \"<string>\",\n  \"expectedOutput\": \"<string>\",\n  \"context\": \"<string>\",\n  \"aggregation\": \"all_pass\",\n  \"criteria\": {},\n  \"criteriaList\": [\n    {\n      \"id\": \"<string>\",\n      \"title\": \"<string>\",\n      \"matchCriteria\": \"<string>\"\n    }\n  ],\n  \"settings\": {},\n  \"behavior\": \"<string>\",\n  \"taskType\": \"<string>\",\n  \"passThreshold\": 123,\n  \"judges\": [\n    {\n      \"type\": \"decision\",\n      \"id\": \"<string>\",\n      \"purpose\": \"customer_evaluation\",\n      \"provider\": \"local\",\n      \"model\": \"<string>\",\n      \"temperature\": 123,\n      \"maxTokens\": 123,\n      \"seed\": 123,\n      \"threshold\": 123,\n      \"weight\": 123,\n      \"topP\": 123,\n      \"timeoutMs\": 123,\n      \"rule\": \"json_schema\",\n      \"passThreshold\": 123,\n      \"top_p\": 123,\n      \"calibrationVersion\": \"<string>\",\n      \"decisionPolicyVersion\": \"<string>\",\n      \"cacheEnabled\": false,\n      \"questions\": [\n        {}\n      ],\n      \"primaryQuestionId\": \"<string>\",\n      \"evidenceQuestionIds\": [\n        \"<string>\"\n      ],\n      \"aggregationPolicy\": \"all_pass\",\n      \"pinnedQuestionSchemaHash\": \"<string>\",\n      \"releaseBlocking\": false\n    }\n  ],\n  \"instabilityThreshold\": 123,\n  \"stabilityRuns\": 123\n}"

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

{
  "promptPreview": "<string>",
  "judgement": {
    "provider": "local",
    "model": "<string>",
    "score": 123,
    "passed": true,
    "latencyMs": 123,
    "aggregation": "all_pass",
    "reasoning": "<string>",
    "flags": [
      "<string>"
    ],
    "signals": {},
    "judgeId": "<string>",
    "retries": 123,
    "parseStatus": "failed",
    "judgeResults": [
      {
        "type": "decision",
        "latencyMs": 123,
        "judgeId": "<string>",
        "provider": "local",
        "model": "<string>",
        "errorCode": "<string>",
        "error": "<string>",
        "result": {
          "provider": "local",
          "model": "<string>",
          "score": 123,
          "passed": true,
          "latencyMs": 123,
          "reasoning": "<string>",
          "signals": {},
          "judgeId": "<string>",
          "retries": 123,
          "parseStatus": "failed",
          "confidence": 123,
          "modelCallId": "<string>",
          "decisions": [
            {
              "type": "choice",
              "confidence": 123,
              "question": "<string>",
              "questionId": "<string>",
              "choice": "<string>",
              "probabilities": {}
            }
          ],
          "tokenUsage": {
            "input": 123,
            "output": 123,
            "total": 123
          },
          "modelProvenance": {
            "provider": "local",
            "model": "<string>",
            "temperature": 123,
            "prompt_hash": "<string>",
            "top_p": 123,
            "max_tokens": 123,
            "seed": 123
          },
          "cached": false,
          "judgeFingerprint": {},
          "criterionResults": [
            {
              "title": "<string>",
              "score": 123,
              "passed": true,
              "reasoning": "<string>",
              "criterionId": "<string>"
            }
          ],
          "decisionProvenance": {
            "purpose": "platform_assistance",
            "provider": "typesafe",
            "model": "<string>",
            "disposition": "pass",
            "fallbackUsed": true,
            "questionSchemaHash": "<string>",
            "inputConstructionVersion": "<string>",
            "modelVersion": "<string>",
            "threshold": 123,
            "inputDigest": "<string>",
            "calibrationVersion": "<string>",
            "decisionPolicyVersion": "<string>",
            "fallbackReason": "<string>"
          }
        },
        "modelCallId": "<string>",
        "weight": 123,
        "modelProvenance": {
          "provider": "local",
          "model": "<string>",
          "temperature": 123,
          "prompt_hash": "<string>",
          "top_p": 123,
          "max_tokens": 123,
          "seed": 123
        },
        "providerExecutionState": "cancelled"
      }
    ],
    "disagreement": {
      "rate": 123,
      "reasoningDivergence": 123,
      "outlierJudgeIds": [
        "<string>"
      ],
      "requiresEscalation": true,
      "nonPassRate": 123,
      "interJudgeRate": 123
    },
    "judgeResultId": 123,
    "judgeConfigHash": "<string>",
    "comparabilityStatus": "not_comparable",
    "confidence": 123,
    "totalCostUsd": 123,
    "tokenUsage": {
      "input": 123,
      "output": 123,
      "total": 123
    },
    "executionCompleteness": {
      "state": "unknown",
      "expected": 123,
      "successful": 123,
      "incomplete": 123,
      "complete": false
    },
    "variance": 123
  }
}

{
  "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
    }
  }
}