Create evaluations run selection

curl --request POST \
  --url https://evalgate.com/api/evaluations/{id}/playground/run-selection \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "environment": "dev",
  "idempotencyKey": "<string>",
  "variantId": 123,
  "testCaseId": 123,
  "testCaseIds": [
    123
  ]
}
'

import requests

url = "https://evalgate.com/api/evaluations/{id}/playground/run-selection"

payload = {
    "environment": "dev",
    "idempotencyKey": "<string>",
    "variantId": 123,
    "testCaseId": 123,
    "testCaseIds": [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({
    environment: 'dev',
    idempotencyKey: '<string>',
    variantId: 123,
    testCaseId: 123,
    testCaseIds: [123]
  })
};

fetch('https://evalgate.com/api/evaluations/{id}/playground/run-selection', 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}/playground/run-selection",
  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([
    'environment' => 'dev',
    'idempotencyKey' => '<string>',
    'variantId' => 123,
    'testCaseId' => 123,
    'testCaseIds' => [
        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/evaluations/{id}/playground/run-selection"

	payload := strings.NewReader("{\n  \"environment\": \"dev\",\n  \"idempotencyKey\": \"<string>\",\n  \"variantId\": 123,\n  \"testCaseId\": 123,\n  \"testCaseIds\": [\n    123\n  ]\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}/playground/run-selection")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"environment\": \"dev\",\n  \"idempotencyKey\": \"<string>\",\n  \"variantId\": 123,\n  \"testCaseId\": 123,\n  \"testCaseIds\": [\n    123\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://evalgate.com/api/evaluations/{id}/playground/run-selection")

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  \"environment\": \"dev\",\n  \"idempotencyKey\": \"<string>\",\n  \"variantId\": 123,\n  \"testCaseId\": 123,\n  \"testCaseIds\": [\n    123\n  ]\n}"

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

{
  "id": 123,
  "evaluationId": 123,
  "organizationId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "status": "<string>",
  "executionMode": "<string>",
  "runManifest": {
    "schemaVersion": 1,
    "evaluationId": 123,
    "organizationId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "dataset": {
      "cases": [
        {
          "testCaseId": 123,
          "caseHash": "<string>",
          "snapshot": {
            "name": "<string>",
            "input": "<string>",
            "expectedOutput": "<string>",
            "datasetVersionId": "<string>",
            "datasetRowContentHash": "<string>",
            "metadata": {}
          }
        }
      ],
      "id": "<string>",
      "versionId": "<string>"
    },
    "expectedTrialsPerCase": 123,
    "execution": {
      "requestHash": "<string>",
      "executionSettings": {},
      "executionSettingsHash": "<string>",
      "executorConfigHash": "<string>",
      "experimentEvidence": {
        "snapshotHash": "<string>",
        "executionId": "<string>",
        "variantKey": "<string>",
        "variantConfigurationHash": "<string>"
      },
      "harnessCommit": "<string>",
      "harnessSourceState": "EXACT_COMMIT",
      "harnessDirtyDigest": "<string>",
      "model": "<string>",
      "provider": "<string>",
      "promptHash": "<string>",
      "systemPrompt": "<string>",
      "toolSchemaHash": "<string>",
      "judgeCertificateHash": "<string>",
      "runtimeImage": "<string>",
      "budgets": {
        "maxCostUsd": 123,
        "maxWallTimeMs": 123,
        "maxModelCalls": 123
      },
      "timeoutRules": {},
      "baselineConfigurationHash": "<string>"
    },
    "createdAt": "<string>"
  },
  "runManifestHash": "<string>",
  "reconciliationSummary": {
    "schemaVersion": 1,
    "manifestHash": "<string>",
    "expectedCaseCount": 123,
    "expectedLogicalTrialCount": 123,
    "receivedPhysicalAttemptCount": 123,
    "completedLogicalTrialCount": 123,
    "passedLogicalTrialCount": 123,
    "failedLogicalTrialCount": 123,
    "infrastructureFailureCount": 123,
    "missingLogicalTrials": [
      {
        "testCaseId": 123,
        "logicalTrialIndex": 123
      }
    ],
    "invalidAttempts": [
      {
        "testCaseId": 123,
        "logicalTrialIndex": 123,
        "physicalAttemptIndex": 123,
        "reason": "ATTEMPT_AFTER_COMPLETION"
      }
    ],
    "invalidRunReasons": [
      "<string>"
    ],
    "terminalState": "CANCELLED",
    "reconciledAt": "<string>"
  },
  "terminalState": "CANCELLED",
  "gateDecision": "BLOCK",
  "gateEnforcementAction": "ALLOW",
  "totalCases": 123,
  "passedCases": 123,
  "failedCases": 123,
  "processedCount": 123,
  "traceLog": {
    "portableMeteringSettlement": {},
    "resultUnitReservation": {
      "version": 1,
      "lockId": "<string>",
      "units": 123,
      "producerFinished": false
    },
    "messages": [
      {
        "role": "assistant",
        "content": "<string>",
        "timestamp": "<string>"
      }
    ],
    "originalEvaluationId": 123,
    "shadowEvalType": "<string>",
    "resolvedTraceIds": [
      "<string>"
    ],
    "jobId": 123,
    "requestedAt": "<string>",
    "enqueuedAt": "<string>",
    "enqueueError": "<string>",
    "lastError": "<string>",
    "completedAt": "<string>",
    "averageScore": 123,
    "trajectoryCoverageRate": 123,
    "trajectoryAverageScore": 123,
    "trajectoryFailureCounts": {},
    "error": "<string>",
    "failedAt": "<string>",
    "totalCases": 123,
    "processedCount": 123,
    "manifestHash": "<string>",
    "reconciliation": {
      "schemaVersion": 1,
      "manifestHash": "<string>",
      "expectedCaseCount": 123,
      "expectedLogicalTrialCount": 123,
      "receivedPhysicalAttemptCount": 123,
      "completedLogicalTrialCount": 123,
      "passedLogicalTrialCount": 123,
      "failedLogicalTrialCount": 123,
      "infrastructureFailureCount": 123,
      "missingLogicalTrials": [
        {
          "testCaseId": 123,
          "logicalTrialIndex": 123
        }
      ],
      "invalidAttempts": [
        {
          "testCaseId": 123,
          "logicalTrialIndex": 123,
          "physicalAttemptIndex": 123,
          "reason": "ATTEMPT_AFTER_COMPLETION"
        }
      ],
      "invalidRunReasons": [
        "<string>"
      ],
      "terminalState": "CANCELLED",
      "reconciledAt": "<string>"
    },
    "cancelledAt": "<string>",
    "traceIds": [
      "<string>"
    ],
    "import": {
      "sourceTraceId": "<string>",
      "sourceOrgId": "<string>",
      "importedAt": "<string>",
      "source": "<string>",
      "checkReport": {},
      "gateCheckedAt": "<string>",
      "requestHash": "<string>",
      "manifestHash": "<string>",
      "reconciliation": {
        "schemaVersion": 1,
        "manifestHash": "<string>",
        "expectedCaseCount": 123,
        "expectedLogicalTrialCount": 123,
        "receivedPhysicalAttemptCount": 123,
        "completedLogicalTrialCount": 123,
        "passedLogicalTrialCount": 123,
        "failedLogicalTrialCount": 123,
        "infrastructureFailureCount": 123,
        "missingLogicalTrials": [
          {
            "testCaseId": 123,
            "logicalTrialIndex": 123
          }
        ],
        "invalidAttempts": [
          {
            "testCaseId": 123,
            "logicalTrialIndex": 123,
            "physicalAttemptIndex": 123,
            "reason": "ATTEMPT_AFTER_COMPLETION"
          }
        ],
        "invalidRunReasons": [
          "<string>"
        ],
        "terminalState": "CANCELLED",
        "reconciledAt": "<string>"
      },
      "gatePolicy": {}
    },
    "type": "<string>",
    "scoreImprovement": 123,
    "dateRange": {
      "start": "<string>",
      "end": "<string>"
    },
    "filters": {},
    "createdBy": "<string>"
  },
  "trajectory": {
    "schemaVersion": 123,
    "entries": [
      {
        "testCaseId": 123,
        "status": "failed",
        "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": "classification",
        "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": "classification",
          "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": "classification",
          "taskType": "<string>",
          "baselineVersion": "<string>"
        }
      }
    ]
  },
  "trajectoryMetrics": {
    "schemaVersion": 123,
    "totalResults": 123,
    "evaluatedResults": 123,
    "coverageRate": 123,
    "averageTrajectoryScore": 123,
    "failureCounts": {
      "inefficient_path": 123,
      "looping_behavior": 123,
      "missed_tool_call": 123,
      "non_parallel_execution": 123,
      "premature_termination": 123,
      "trajectory_mismatch": 123,
      "unnecessary_tool_call": 123
    },
    "byTestCase": [
      {
        "testCaseId": 123,
        "status": "failed",
        "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": "classification",
        "taskType": "<string>",
        "baselineVersion": "<string>"
      }
    ]
  },
  "baselineVersion": "<string>",
  "scoreProvenance": {
    "scoringVersion": "<string>",
    "assertionSetVersion": "<string>",
    "taskType": "<string>",
    "judgeConfigHash": "<string>",
    "promptTemplateHash": "<string>",
    "aggregationVersion": "<string>",
    "embeddingModel": "<string>",
    "behaviorVersion": "<string>",
    "calibrationStudyId": "<string>"
  },
  "measurementStatus": "<string>",
  "measurementSummary": {
    "version": "evalgate.measurement.v1",
    "status": "complete",
    "sampleSize": 123,
    "metrics": {},
    "warnings": [
      "<string>"
    ],
    "computationHash": "<string>",
    "uncertainty": {
      "lower": 123,
      "upper": 123,
      "confidenceLevel": 123,
      "method": "newcombe-hybrid-score",
      "resamples": 123,
      "seed": 123
    }
  },
  "measurementCompletedAt": "2023-11-07T05:31:56Z",
  "activeMeasurementRevisionId": "<string>",
  "qualitySummary": {
    "version": "evalgate.measurement.v1",
    "status": "complete",
    "sampleSize": 123,
    "metrics": {},
    "warnings": [
      "<string>"
    ],
    "computationHash": "<string>",
    "uncertainty": {
      "lower": 123,
      "upper": 123,
      "confidenceLevel": 123,
      "method": "newcombe-hybrid-score",
      "resamples": 123,
      "seed": 123
    }
  },
  "qualitySummaryCompletedAt": "2023-11-07T05:31:56Z",
  "orchestrationGraph": {
    "schemaVersion": 1,
    "rootNodeId": "<string>",
    "nodes": [
      {
        "id": "<string>",
        "type": "baseline",
        "label": "<string>",
        "agentIndex": 123,
        "strategyTrack": "<string>",
        "passRate": 123,
        "kept": false,
        "metadata": {}
      }
    ],
    "edges": [
      {
        "from": "<string>",
        "to": "<string>",
        "label": "<string>"
      }
    ],
    "capturedAt": "<string>",
    "gateDecisions": [
      {
        "timestamp": "<string>",
        "passed": true,
        "exitCode": 123,
        "reasonCode": "<string>",
        "thresholds": {
          "minScore": 123,
          "maxDrop": 123,
          "warnDrop": 123
        },
        "reasonMessage": "<string>",
        "policy": "<string>",
        "score": 123,
        "baselineScore": 123,
        "regressionDelta": 123,
        "baselineRunId": 123,
        "ciRunUrl": "<string>",
        "failedTestCaseIds": [
          123
        ]
      }
    ]
  },
  "startedAt": "2023-11-07T05:31:56Z",
  "completedAt": "2023-11-07T05:31:56Z",
  "environment": "<string>",
  "playgroundId": 123,
  "variantId": 123,
  "promptVersionId": "<string>",
  "baselineVariantId": 123,
  "triggerSource": "<string>",
  "createdAt": "2023-11-07T05:31:56Z",
  "snapshotId": 123,
  "idempotencyKey": "<string>",
  "idempotentReplay": true
}

{
  "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
    }
  }
}