Create evaluations reviews

curl --request POST \
  --url https://evalgate.com/api/evaluations/{id}/human-review/reviews \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "sampleId": 123,
  "batchId": 123,
  "reviewVerdict": "pass",
  "labels": {
    "tags": [
      "<string>"
    ],
    "taxonomyVersion": "<string>",
    "assertionLabels": [
      {
        "verdict": "rejected",
        "assertionKey": "safety",
        "severity": "medium",
        "evidence": [
          "trajectory"
        ],
        "notes": "<string>"
      }
    ],
    "failureModes": [
      "<string>"
    ],
    "calibrationLabel": "standard"
  },
  "rating": 123,
  "feedback": "<string>"
}
'

import requests

url = "https://evalgate.com/api/evaluations/{id}/human-review/reviews"

payload = {
    "sampleId": 123,
    "batchId": 123,
    "reviewVerdict": "pass",
    "labels": {
        "tags": ["<string>"],
        "taxonomyVersion": "<string>",
        "assertionLabels": [
            {
                "verdict": "rejected",
                "assertionKey": "safety",
                "severity": "medium",
                "evidence": ["trajectory"],
                "notes": "<string>"
            }
        ],
        "failureModes": ["<string>"],
        "calibrationLabel": "standard"
    },
    "rating": 123,
    "feedback": "<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({
    sampleId: 123,
    batchId: 123,
    reviewVerdict: 'pass',
    labels: {
      tags: ['<string>'],
      taxonomyVersion: '<string>',
      assertionLabels: [
        {
          verdict: 'rejected',
          assertionKey: 'safety',
          severity: 'medium',
          evidence: ['trajectory'],
          notes: '<string>'
        }
      ],
      failureModes: ['<string>'],
      calibrationLabel: 'standard'
    },
    rating: 123,
    feedback: '<string>'
  })
};

fetch('https://evalgate.com/api/evaluations/{id}/human-review/reviews', 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/evaluations/{id}/human-review/reviews",
  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([
    'sampleId' => 123,
    'batchId' => 123,
    'reviewVerdict' => 'pass',
    'labels' => [
        'tags' => [
                '<string>'
        ],
        'taxonomyVersion' => '<string>',
        'assertionLabels' => [
                [
                                'verdict' => 'rejected',
                                'assertionKey' => 'safety',
                                'severity' => 'medium',
                                'evidence' => [
                                                                'trajectory'
                                ],
                                'notes' => '<string>'
                ]
        ],
        'failureModes' => [
                '<string>'
        ],
        'calibrationLabel' => 'standard'
    ],
    'rating' => 123,
    'feedback' => '<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/evaluations/{id}/human-review/reviews"

	payload := strings.NewReader("{\n  \"sampleId\": 123,\n  \"batchId\": 123,\n  \"reviewVerdict\": \"pass\",\n  \"labels\": {\n    \"tags\": [\n      \"<string>\"\n    ],\n    \"taxonomyVersion\": \"<string>\",\n    \"assertionLabels\": [\n      {\n        \"verdict\": \"rejected\",\n        \"assertionKey\": \"safety\",\n        \"severity\": \"medium\",\n        \"evidence\": [\n          \"trajectory\"\n        ],\n        \"notes\": \"<string>\"\n      }\n    ],\n    \"failureModes\": [\n      \"<string>\"\n    ],\n    \"calibrationLabel\": \"standard\"\n  },\n  \"rating\": 123,\n  \"feedback\": \"<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/evaluations/{id}/human-review/reviews")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"sampleId\": 123,\n  \"batchId\": 123,\n  \"reviewVerdict\": \"pass\",\n  \"labels\": {\n    \"tags\": [\n      \"<string>\"\n    ],\n    \"taxonomyVersion\": \"<string>\",\n    \"assertionLabels\": [\n      {\n        \"verdict\": \"rejected\",\n        \"assertionKey\": \"safety\",\n        \"severity\": \"medium\",\n        \"evidence\": [\n          \"trajectory\"\n        ],\n        \"notes\": \"<string>\"\n      }\n    ],\n    \"failureModes\": [\n      \"<string>\"\n    ],\n    \"calibrationLabel\": \"standard\"\n  },\n  \"rating\": 123,\n  \"feedback\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://evalgate.com/api/evaluations/{id}/human-review/reviews")

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  \"sampleId\": 123,\n  \"batchId\": 123,\n  \"reviewVerdict\": \"pass\",\n  \"labels\": {\n    \"tags\": [\n      \"<string>\"\n    ],\n    \"taxonomyVersion\": \"<string>\",\n    \"assertionLabels\": [\n      {\n        \"verdict\": \"rejected\",\n        \"assertionKey\": \"safety\",\n        \"severity\": \"medium\",\n        \"evidence\": [\n          \"trajectory\"\n        ],\n        \"notes\": \"<string>\"\n      }\n    ],\n    \"failureModes\": [\n      \"<string>\"\n    ],\n    \"calibrationLabel\": \"standard\"\n  },\n  \"rating\": 123,\n  \"feedback\": \"<string>\"\n}"

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

{
  "batch": {
    "id": 123,
    "evaluationId": 123,
    "evaluationRunId": 123,
    "sampleSize": 123,
    "samplingStrategy": "<string>",
    "seed": "<string>",
    "assignedReviewerId": "<string>",
    "createdBy": "<string>",
    "createdAt": "<string>"
  },
  "items": [
    {
      "sampleId": 123,
      "testCaseId": 123,
      "testResultId": 123,
      "snapshot": {
        "testCaseId": 123,
        "testResultId": 123,
        "systemVerdict": "pass",
        "executionState": "unknown",
        "systemVerdictComparable": true,
        "systemVerdictSummary": "<string>",
        "caseName": "<string>",
        "input": "<string>",
        "expectedOutput": "<string>",
        "output": "<string>",
        "error": "<string>",
        "assertions": {},
        "messages": [
          {
            "role": "<string>",
            "content": "<string>",
            "timestamp": "<string>"
          }
        ],
        "toolCalls": [
          {
            "name": "<string>",
            "arguments": {},
            "output": "<string>",
            "timestamp": "<string>"
          }
        ],
        "trajectory": {
          "testCaseId": 123,
          "status": "passed",
          "trajectory": {
            "id": "<string>",
            "input": "<string>",
            "finalOutput": "<string>",
            "steps": [
              {
                "index": 123,
                "type": "final",
                "content": "<string>",
                "toolName": "<string>",
                "toolArgs": {},
                "timestamp": 123
              }
            ],
            "totalSteps": 123,
            "totalToolCalls": 123,
            "durationMs": 123,
            "terminatedEarly": false,
            "error": "<string>"
          },
          "behavior": "retrieval",
          "taskType": "<string>",
          "idealTrajectory": {
            "expectedSteps": 123,
            "expectedToolCalls": 123,
            "requiredTools": [
              "<string>"
            ],
            "forbiddenTools": [
              "<string>"
            ],
            "allowParallel": false,
            "maxRedundantSteps": 123,
            "referenceToolCalls": [
              {
                "name": "<string>",
                "args": {}
              }
            ],
            "trajectoryMatchMode": "strict",
            "toolArgsMatchMode": "exact",
            "toolArgsMatchOverrides": {}
          },
          "baseline": {
            "behavior": "retrieval",
            "stepDistribution": {
              "p50": 123,
              "p75": 123,
              "p90": 123
            },
            "toolCallDistribution": {
              "p50": 123,
              "p75": 123
            },
            "durationDistribution": {
              "p50": 123,
              "p75": 123
            },
            "commonToolSequences": [
              [
                "<string>"
              ]
            ],
            "redundancyProfile": {
              "mean": 123,
              "p90": 123
            },
            "sampleSize": 123,
            "updatedAt": "<string>",
            "taskType": "<string>",
            "parallelToolGroups": [
              [
                "<string>"
              ]
            ],
            "version": "<string>",
            "model": "<string>"
          },
          "evaluation": {
            "schemaVersion": 123,
            "valid": true,
            "score": 123,
            "failureModes": [
              "inefficient_path"
            ],
            "metrics": {
              "actualSteps": 123,
              "actualToolCalls": 123,
              "actualDurationMs": 123,
              "redundancyRatio": 123,
              "redundancySteps": 123,
              "sequenceSimilarity": 123,
              "efficiency": 123,
              "toolUsage": 123,
              "redundancy": 123,
              "latency": 123,
              "parallelizationPenalty": 123,
              "parallelizationScore": 123,
              "requiredToolsMissing": [
                "<string>"
              ],
              "forbiddenToolsUsed": [
                "<string>"
              ],
              "extraToolsUsed": [
                "<string>"
              ],
              "selectedBaselineVersion": "<string>",
              "baselineStepP50": 123,
              "baselineStepP75": 123,
              "baselineToolCallP50": 123,
              "baselineToolCallP75": 123,
              "baselineDurationP50": 123,
              "baselineDurationP75": 123,
              "idealExpectedSteps": 123,
              "idealExpectedToolCalls": 123,
              "trajectoryMatchMode": "strict",
              "trajectoryMatched": false,
              "referenceToolCallCount": 123
            },
            "trajectoryId": "<string>",
            "behavior": "retrieval",
            "taskType": "<string>",
            "baselineVersion": "<string>"
          }
        },
        "trajectoryMetrics": {
          "testCaseId": 123,
          "status": "passed",
          "score": 123,
          "failureModes": [
            "inefficient_path"
          ],
          "metrics": {
            "actualSteps": 123,
            "actualToolCalls": 123,
            "actualDurationMs": 123,
            "redundancyRatio": 123,
            "redundancySteps": 123,
            "sequenceSimilarity": 123,
            "efficiency": 123,
            "toolUsage": 123,
            "redundancy": 123,
            "latency": 123,
            "parallelizationPenalty": 123,
            "parallelizationScore": 123,
            "requiredToolsMissing": [
              "<string>"
            ],
            "forbiddenToolsUsed": [
              "<string>"
            ],
            "extraToolsUsed": [
              "<string>"
            ],
            "selectedBaselineVersion": "<string>",
            "baselineStepP50": 123,
            "baselineStepP75": 123,
            "baselineToolCallP50": 123,
            "baselineToolCallP75": 123,
            "baselineDurationP50": 123,
            "baselineDurationP75": 123,
            "idealExpectedSteps": 123,
            "idealExpectedToolCalls": 123,
            "trajectoryMatchMode": "strict",
            "trajectoryMatched": false,
            "referenceToolCallCount": 123
          },
          "trajectoryId": "<string>",
          "behavior": "retrieval",
          "taskType": "<string>",
          "baselineVersion": "<string>"
        }
      },
      "reviews": [
        {
          "id": 123,
          "batchId": 123,
          "sampleId": 123,
          "testCaseId": 123,
          "reviewerId": "<string>",
          "systemVerdict": "pass",
          "reviewVerdict": "pass",
          "agreedWithSystem": false,
          "rating": 123,
          "feedback": "<string>",
          "labels": {},
          "createdAt": "<string>"
        }
      ],
      "latestReview": {
        "id": 123,
        "batchId": 123,
        "sampleId": 123,
        "testCaseId": 123,
        "reviewerId": "<string>",
        "systemVerdict": "pass",
        "reviewVerdict": "pass",
        "agreedWithSystem": false,
        "rating": 123,
        "feedback": "<string>",
        "labels": {},
        "createdAt": "<string>"
      }
    }
  ],
  "stats": {
    "totalSamples": 123,
    "reviewedSamples": 123,
    "totalReviews": 123,
    "comparableReviews": 123,
    "agreementRate": 123,
    "disagreementRate": 123,
    "uncertainRate": 123,
    "verdictDistribution": {
      "pass": 123,
      "fail": 123,
      "uncertain": 123
    }
  },
  "history": [
    {
      "batchId": 123,
      "createdAt": "<string>",
      "totalReviews": 123,
      "comparableReviews": 123,
      "disagreementRate": 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
    }
  }
}