Get evaluations integrity

curl --request GET \
  --url https://evalgate.com/api/evaluations/{id}/integrity \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://evalgate.com/api/evaluations/{id}/integrity"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://evalgate.com/api/evaluations/{id}/integrity', 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}/integrity",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://evalgate.com/api/evaluations/{id}/integrity"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.get("https://evalgate.com/api/evaluations/{id}/integrity")
  .header("Authorization", "Bearer <token>")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

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

{
  "workflowCoverage": {
    "totalCases": 123,
    "agentWorkflowCases": 123,
    "coverageRate": 123,
    "workflowClassDistribution": {
      "approval_gated_mutation": 123,
      "background_execution": 123,
      "recovery_required": 123,
      "policy_conflict": 123,
      "handoff_heavy": 123,
      "memory_sensitive": 123,
      "parallel_tool_use": 123
    },
    "autonomyDistribution": {
      "manual": 123,
      "default_approvals": 123,
      "bypass_approvals": 123,
      "autopilot": 123
    },
    "generatedCandidateCount": 123,
    "experimentRecipeCount": 123,
    "gaps": [
      {
        "id": "<string>",
        "workflowClass": "approval_gated_mutation",
        "severity": "critical",
        "description": "<string>",
        "recommendation": "<string>"
      }
    ]
  },
  "schemaVersion": 123,
  "configVersion": "<string>",
  "evaluationId": 123,
  "evaluationRunId": 123,
  "summary": {
    "byBehavior": {
      "retrieval": {
        "mean": 123,
        "stdDev": 123,
        "n": 123,
        "confidenceInterval": {
          "lower": 123,
          "upper": 123,
          "method": "normal"
        },
        "composition": {
          "percentageOfDataset": 123
        },
        "status": "valid",
        "warnings": [
          "metric_missing_data"
        ]
      },
      "tool_use": {
        "mean": 123,
        "stdDev": 123,
        "n": 123,
        "confidenceInterval": {
          "lower": 123,
          "upper": 123,
          "method": "normal"
        },
        "composition": {
          "percentageOfDataset": 123
        },
        "status": "valid",
        "warnings": [
          "metric_missing_data"
        ]
      },
      "classification": {
        "mean": 123,
        "stdDev": 123,
        "n": 123,
        "confidenceInterval": {
          "lower": 123,
          "upper": 123,
          "method": "normal"
        },
        "composition": {
          "percentageOfDataset": 123
        },
        "status": "valid",
        "warnings": [
          "metric_missing_data"
        ]
      },
      "extraction": {
        "mean": 123,
        "stdDev": 123,
        "n": 123,
        "confidenceInterval": {
          "lower": 123,
          "upper": 123,
          "method": "normal"
        },
        "composition": {
          "percentageOfDataset": 123
        },
        "status": "valid",
        "warnings": [
          "metric_missing_data"
        ]
      },
      "multi_step_reasoning": {
        "mean": 123,
        "stdDev": 123,
        "n": 123,
        "confidenceInterval": {
          "lower": 123,
          "upper": 123,
          "method": "normal"
        },
        "composition": {
          "percentageOfDataset": 123
        },
        "status": "valid",
        "warnings": [
          "metric_missing_data"
        ]
      }
    },
    "byDifficulty": {
      "medium": {
        "mean": 123,
        "stdDev": 123,
        "n": 123,
        "confidenceInterval": {
          "lower": 123,
          "upper": 123,
          "method": "normal"
        },
        "composition": {
          "percentageOfDataset": 123
        },
        "status": "valid",
        "warnings": [
          "metric_missing_data"
        ]
      },
      "hard": {
        "mean": 123,
        "stdDev": 123,
        "n": 123,
        "confidenceInterval": {
          "lower": 123,
          "upper": 123,
          "method": "normal"
        },
        "composition": {
          "percentageOfDataset": 123
        },
        "status": "valid",
        "warnings": [
          "metric_missing_data"
        ]
      },
      "easy": {
        "mean": 123,
        "stdDev": 123,
        "n": 123,
        "confidenceInterval": {
          "lower": 123,
          "upper": 123,
          "method": "normal"
        },
        "composition": {
          "percentageOfDataset": 123
        },
        "status": "valid",
        "warnings": [
          "metric_missing_data"
        ]
      },
      "flaky": {
        "mean": 123,
        "stdDev": 123,
        "n": 123,
        "confidenceInterval": {
          "lower": 123,
          "upper": 123,
          "method": "normal"
        },
        "composition": {
          "percentageOfDataset": 123
        },
        "status": "valid",
        "warnings": [
          "metric_missing_data"
        ]
      }
    },
    "metadata": {
      "totalCases": 123,
      "evaluatedAt": "<string>",
      "evaluationRunId": 123,
      "uncategorizedBehaviorCount": 123,
      "uncategorizedDifficultyCount": 123
    },
    "trajectory": {
      "efficiency": {
        "mean": 123,
        "stdDev": 123,
        "n": 123,
        "confidenceInterval": {
          "lower": 123,
          "upper": 123,
          "method": "normal"
        },
        "composition": {
          "percentageOfDataset": 123
        },
        "status": "valid",
        "warnings": [
          "metric_missing_data"
        ]
      },
      "toolUsage": {
        "mean": 123,
        "stdDev": 123,
        "n": 123,
        "confidenceInterval": {
          "lower": 123,
          "upper": 123,
          "method": "normal"
        },
        "composition": {
          "percentageOfDataset": 123
        },
        "status": "valid",
        "warnings": [
          "metric_missing_data"
        ]
      }
    },
    "workflow": {
      "axes": {
        "autonomyFit": {
          "mean": 123,
          "stdDev": 123,
          "n": 123,
          "confidenceInterval": {
            "lower": 123,
            "upper": 123,
            "method": "normal"
          },
          "composition": {
            "percentageOfDataset": 123
          },
          "status": "valid",
          "warnings": [
            "metric_missing_data"
          ]
        },
        "escalationQuality": {
          "mean": 123,
          "stdDev": 123,
          "n": 123,
          "confidenceInterval": {
            "lower": 123,
            "upper": 123,
            "method": "normal"
          },
          "composition": {
            "percentageOfDataset": 123
          },
          "status": "valid",
          "warnings": [
            "metric_missing_data"
          ]
        },
        "approvalSafety": {
          "mean": 123,
          "stdDev": 123,
          "n": 123,
          "confidenceInterval": {
            "lower": 123,
            "upper": 123,
            "method": "normal"
          },
          "composition": {
            "percentageOfDataset": 123
          },
          "status": "valid",
          "warnings": [
            "metric_missing_data"
          ]
        },
        "hookCompliance": {
          "mean": 123,
          "stdDev": 123,
          "n": 123,
          "confidenceInterval": {
            "lower": 123,
            "upper": 123,
            "method": "normal"
          },
          "composition": {
            "percentageOfDataset": 123
          },
          "status": "valid",
          "warnings": [
            "metric_missing_data"
          ]
        },
        "memoryCorrectness": {
          "mean": 123,
          "stdDev": 123,
          "n": 123,
          "confidenceInterval": {
            "lower": 123,
            "upper": 123,
            "method": "normal"
          },
          "composition": {
            "percentageOfDataset": 123
          },
          "status": "valid",
          "warnings": [
            "metric_missing_data"
          ]
        },
        "recoveryQuality": {
          "mean": 123,
          "stdDev": 123,
          "n": 123,
          "confidenceInterval": {
            "lower": 123,
            "upper": 123,
            "method": "normal"
          },
          "composition": {
            "percentageOfDataset": 123
          },
          "status": "valid",
          "warnings": [
            "metric_missing_data"
          ]
        },
        "handoffQuality": {
          "mean": 123,
          "stdDev": 123,
          "n": 123,
          "confidenceInterval": {
            "lower": 123,
            "upper": 123,
            "method": "normal"
          },
          "composition": {
            "percentageOfDataset": 123
          },
          "status": "valid",
          "warnings": [
            "metric_missing_data"
          ]
        },
        "debuggability": {
          "mean": 123,
          "stdDev": 123,
          "n": 123,
          "confidenceInterval": {
            "lower": 123,
            "upper": 123,
            "method": "normal"
          },
          "composition": {
            "percentageOfDataset": 123
          },
          "status": "valid",
          "warnings": [
            "metric_missing_data"
          ]
        }
      },
      "slices": {
        "byAutonomy": {
          "manual": {
            "mean": 123,
            "stdDev": 123,
            "n": 123,
            "confidenceInterval": {
              "lower": 123,
              "upper": 123,
              "method": "normal"
            },
            "composition": {
              "percentageOfDataset": 123
            },
            "status": "valid",
            "warnings": [
              "metric_missing_data"
            ]
          },
          "default_approvals": {
            "mean": 123,
            "stdDev": 123,
            "n": 123,
            "confidenceInterval": {
              "lower": 123,
              "upper": 123,
              "method": "normal"
            },
            "composition": {
              "percentageOfDataset": 123
            },
            "status": "valid",
            "warnings": [
              "metric_missing_data"
            ]
          },
          "bypass_approvals": {
            "mean": 123,
            "stdDev": 123,
            "n": 123,
            "confidenceInterval": {
              "lower": 123,
              "upper": 123,
              "method": "normal"
            },
            "composition": {
              "percentageOfDataset": 123
            },
            "status": "valid",
            "warnings": [
              "metric_missing_data"
            ]
          },
          "autopilot": {
            "mean": 123,
            "stdDev": 123,
            "n": 123,
            "confidenceInterval": {
              "lower": 123,
              "upper": 123,
              "method": "normal"
            },
            "composition": {
              "percentageOfDataset": 123
            },
            "status": "valid",
            "warnings": [
              "metric_missing_data"
            ]
          }
        },
        "byWorkflowClass": {
          "approval_gated_mutation": {
            "mean": 123,
            "stdDev": 123,
            "n": 123,
            "confidenceInterval": {
              "lower": 123,
              "upper": 123,
              "method": "normal"
            },
            "composition": {
              "percentageOfDataset": 123
            },
            "status": "valid",
            "warnings": [
              "metric_missing_data"
            ]
          },
          "background_execution": {
            "mean": 123,
            "stdDev": 123,
            "n": 123,
            "confidenceInterval": {
              "lower": 123,
              "upper": 123,
              "method": "normal"
            },
            "composition": {
              "percentageOfDataset": 123
            },
            "status": "valid",
            "warnings": [
              "metric_missing_data"
            ]
          },
          "recovery_required": {
            "mean": 123,
            "stdDev": 123,
            "n": 123,
            "confidenceInterval": {
              "lower": 123,
              "upper": 123,
              "method": "normal"
            },
            "composition": {
              "percentageOfDataset": 123
            },
            "status": "valid",
            "warnings": [
              "metric_missing_data"
            ]
          },
          "policy_conflict": {
            "mean": 123,
            "stdDev": 123,
            "n": 123,
            "confidenceInterval": {
              "lower": 123,
              "upper": 123,
              "method": "normal"
            },
            "composition": {
              "percentageOfDataset": 123
            },
            "status": "valid",
            "warnings": [
              "metric_missing_data"
            ]
          },
          "handoff_heavy": {
            "mean": 123,
            "stdDev": 123,
            "n": 123,
            "confidenceInterval": {
              "lower": 123,
              "upper": 123,
              "method": "normal"
            },
            "composition": {
              "percentageOfDataset": 123
            },
            "status": "valid",
            "warnings": [
              "metric_missing_data"
            ]
          },
          "memory_sensitive": {
            "mean": 123,
            "stdDev": 123,
            "n": 123,
            "confidenceInterval": {
              "lower": 123,
              "upper": 123,
              "method": "normal"
            },
            "composition": {
              "percentageOfDataset": 123
            },
            "status": "valid",
            "warnings": [
              "metric_missing_data"
            ]
          },
          "parallel_tool_use": {
            "mean": 123,
            "stdDev": 123,
            "n": 123,
            "confidenceInterval": {
              "lower": 123,
              "upper": 123,
              "method": "normal"
            },
            "composition": {
              "percentageOfDataset": 123
            },
            "status": "valid",
            "warnings": [
              "metric_missing_data"
            ]
          }
        }
      }
    }
  },
  "datasetIntegrity": {
    "behaviorDistribution": {
      "retrieval": 123,
      "tool_use": 123,
      "classification": 123,
      "extraction": 123,
      "multi_step_reasoning": 123
    },
    "difficultyDistribution": {
      "medium": 123,
      "hard": 123,
      "easy": 123,
      "flaky": 123
    },
    "failureOriginShare": 123,
    "syntheticOnly": true,
    "coverageWarnings": [
      "metric_missing_data"
    ]
  },
  "metricValidity": {
    "historicalSnapshotsChecked": 123,
    "driftSignals": [
      {
        "metric": "<string>",
        "currentMean": 123,
        "previousMean": 123,
        "delta": 123,
        "triggered": true
      }
    ],
    "improvementWithoutFailureReduction": true
  },
  "antiGaming": {
    "improvedEasyBucketOnly": true,
    "failureDistributionStagnant": true,
    "redundancyIncreaseWithScoreGain": true,
    "detected": true
  },
  "coverageIntegrity": {
    "coverageByBehavior": {
      "retrieval": 123,
      "tool_use": 123,
      "classification": 123,
      "extraction": 123,
      "multi_step_reasoning": 123
    },
    "dominantFailureMode": {
      "mode": "<string>",
      "share": 123
    },
    "lowFailureDiversity": true
  },
  "lifecycle": {
    "counts": {
      "active": 123,
      "validated": 123,
      "superseded": 123,
      "deprecated": 123,
      "archived": 123,
      "candidate": 123,
      "active_gate": 123
    },
    "recommendedTransitions": [
      {
        "testCaseId": 123,
        "currentState": "active",
        "nextState": "active",
        "reason": "manual_approval"
      }
    ]
  },
  "warnings": [
    {
      "code": "metric_missing_data",
      "severity": "critical",
      "message": "<string>",
      "context": {}
    }
  ],
  "events": [
    {
      "type": "metric_drift_detected",
      "message": "<string>",
      "context": {}
    }
  ],
  "metadata": {
    "totalWarnings": 123,
    "refreshedAt": "<string>",
    "sourceTrajectoryMetricsAvailable": true,
    "overallPassRate": 123,
    "averageTrajectoryRedundancy": 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
    }
  }
}