evaluations
Create evaluations import
Requires scopes: runs:write
POST
/
api
/
evaluations
/
{id}
/
runs
/
import
Create evaluations import
curl --request POST \
--url https://evalgate.com/api/evaluations/{id}/runs/import \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"environment": "dev",
"importClientVersion": "<string>",
"runManifest": {
"expectedTrialsPerCase": 123,
"createdAt": "<string>",
"dataset": {
"id": "<string>",
"versionId": "<string>"
},
"execution": {
"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>"
}
},
"cancelled": false,
"infrastructureAttempts": [
{
"testCaseId": 123,
"logicalTrialIndex": 123,
"physicalAttemptIndex": 123,
"attemptKind": "infrastructure_retry",
"status": "cancelled",
"errorCode": "<string>",
"startedAt": "<string>",
"completedAt": "<string>",
"evidence": {}
}
],
"ci": {
"provider": "circle",
"repo": "<string>",
"sha": "<string>",
"branch": "<string>",
"pr": 123,
"runUrl": "<string>",
"actor": "<string>"
},
"trajectoryBaselines": [
{
"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>"
}
],
"checkReport": {},
"results": [
{
"testCaseId": 123,
"status": "failed",
"output": "<string>",
"logicalTrialIndex": 123,
"physicalAttemptIndex": 123,
"attemptKind": "infrastructure_retry",
"input": "<string>",
"latencyMs": 123,
"costUsd": 123,
"assertionsJson": {},
"messages": [
{}
],
"toolCalls": [
{}
],
"behavior": "classification",
"taskType": "<string>",
"traceId": "<string>"
}
]
}
'import requests
url = "https://evalgate.com/api/evaluations/{id}/runs/import"
payload = {
"environment": "dev",
"importClientVersion": "<string>",
"runManifest": {
"expectedTrialsPerCase": 123,
"createdAt": "<string>",
"dataset": {
"id": "<string>",
"versionId": "<string>"
},
"execution": {
"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>"
}
},
"cancelled": False,
"infrastructureAttempts": [
{
"testCaseId": 123,
"logicalTrialIndex": 123,
"physicalAttemptIndex": 123,
"attemptKind": "infrastructure_retry",
"status": "cancelled",
"errorCode": "<string>",
"startedAt": "<string>",
"completedAt": "<string>",
"evidence": {}
}
],
"ci": {
"provider": "circle",
"repo": "<string>",
"sha": "<string>",
"branch": "<string>",
"pr": 123,
"runUrl": "<string>",
"actor": "<string>"
},
"trajectoryBaselines": [
{
"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>"
}
],
"checkReport": {},
"results": [
{
"testCaseId": 123,
"status": "failed",
"output": "<string>",
"logicalTrialIndex": 123,
"physicalAttemptIndex": 123,
"attemptKind": "infrastructure_retry",
"input": "<string>",
"latencyMs": 123,
"costUsd": 123,
"assertionsJson": {},
"messages": [{}],
"toolCalls": [{}],
"behavior": "classification",
"taskType": "<string>",
"traceId": "<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({
environment: 'dev',
importClientVersion: '<string>',
runManifest: {
expectedTrialsPerCase: 123,
createdAt: '<string>',
dataset: {id: '<string>', versionId: '<string>'},
execution: {
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>'
}
},
cancelled: false,
infrastructureAttempts: [
{
testCaseId: 123,
logicalTrialIndex: 123,
physicalAttemptIndex: 123,
attemptKind: 'infrastructure_retry',
status: 'cancelled',
errorCode: '<string>',
startedAt: '<string>',
completedAt: '<string>',
evidence: {}
}
],
ci: {
provider: 'circle',
repo: '<string>',
sha: '<string>',
branch: '<string>',
pr: 123,
runUrl: '<string>',
actor: '<string>'
},
trajectoryBaselines: [
{
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>'
}
],
checkReport: {},
results: [
{
testCaseId: 123,
status: 'failed',
output: '<string>',
logicalTrialIndex: 123,
physicalAttemptIndex: 123,
attemptKind: 'infrastructure_retry',
input: '<string>',
latencyMs: 123,
costUsd: 123,
assertionsJson: {},
messages: [{}],
toolCalls: [{}],
behavior: 'classification',
taskType: '<string>',
traceId: '<string>'
}
]
})
};
fetch('https://evalgate.com/api/evaluations/{id}/runs/import', 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}/runs/import",
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',
'importClientVersion' => '<string>',
'runManifest' => [
'expectedTrialsPerCase' => 123,
'createdAt' => '<string>',
'dataset' => [
'id' => '<string>',
'versionId' => '<string>'
],
'execution' => [
'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>'
]
],
'cancelled' => false,
'infrastructureAttempts' => [
[
'testCaseId' => 123,
'logicalTrialIndex' => 123,
'physicalAttemptIndex' => 123,
'attemptKind' => 'infrastructure_retry',
'status' => 'cancelled',
'errorCode' => '<string>',
'startedAt' => '<string>',
'completedAt' => '<string>',
'evidence' => [
]
]
],
'ci' => [
'provider' => 'circle',
'repo' => '<string>',
'sha' => '<string>',
'branch' => '<string>',
'pr' => 123,
'runUrl' => '<string>',
'actor' => '<string>'
],
'trajectoryBaselines' => [
[
'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>'
]
],
'checkReport' => [
],
'results' => [
[
'testCaseId' => 123,
'status' => 'failed',
'output' => '<string>',
'logicalTrialIndex' => 123,
'physicalAttemptIndex' => 123,
'attemptKind' => 'infrastructure_retry',
'input' => '<string>',
'latencyMs' => 123,
'costUsd' => 123,
'assertionsJson' => [
],
'messages' => [
[
]
],
'toolCalls' => [
[
]
],
'behavior' => 'classification',
'taskType' => '<string>',
'traceId' => '<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}/runs/import"
payload := strings.NewReader("{\n \"environment\": \"dev\",\n \"importClientVersion\": \"<string>\",\n \"runManifest\": {\n \"expectedTrialsPerCase\": 123,\n \"createdAt\": \"<string>\",\n \"dataset\": {\n \"id\": \"<string>\",\n \"versionId\": \"<string>\"\n },\n \"execution\": {\n \"harnessCommit\": \"<string>\",\n \"harnessSourceState\": \"EXACT_COMMIT\",\n \"harnessDirtyDigest\": \"<string>\",\n \"model\": \"<string>\",\n \"provider\": \"<string>\",\n \"promptHash\": \"<string>\",\n \"systemPrompt\": \"<string>\",\n \"toolSchemaHash\": \"<string>\",\n \"judgeCertificateHash\": \"<string>\",\n \"runtimeImage\": \"<string>\",\n \"budgets\": {\n \"maxCostUsd\": 123,\n \"maxWallTimeMs\": 123,\n \"maxModelCalls\": 123\n },\n \"timeoutRules\": {},\n \"baselineConfigurationHash\": \"<string>\"\n }\n },\n \"cancelled\": false,\n \"infrastructureAttempts\": [\n {\n \"testCaseId\": 123,\n \"logicalTrialIndex\": 123,\n \"physicalAttemptIndex\": 123,\n \"attemptKind\": \"infrastructure_retry\",\n \"status\": \"cancelled\",\n \"errorCode\": \"<string>\",\n \"startedAt\": \"<string>\",\n \"completedAt\": \"<string>\",\n \"evidence\": {}\n }\n ],\n \"ci\": {\n \"provider\": \"circle\",\n \"repo\": \"<string>\",\n \"sha\": \"<string>\",\n \"branch\": \"<string>\",\n \"pr\": 123,\n \"runUrl\": \"<string>\",\n \"actor\": \"<string>\"\n },\n \"trajectoryBaselines\": [\n {\n \"behavior\": \"classification\",\n \"stepDistribution\": {\n \"p50\": 123,\n \"p75\": 123,\n \"p90\": 123\n },\n \"toolCallDistribution\": {\n \"p50\": 123,\n \"p75\": 123\n },\n \"durationDistribution\": {\n \"p50\": 123,\n \"p75\": 123\n },\n \"commonToolSequences\": [\n [\n \"<string>\"\n ]\n ],\n \"redundancyProfile\": {\n \"mean\": 123,\n \"p90\": 123\n },\n \"sampleSize\": 123,\n \"updatedAt\": \"<string>\",\n \"taskType\": \"<string>\",\n \"parallelToolGroups\": [\n [\n \"<string>\"\n ]\n ],\n \"version\": \"<string>\",\n \"model\": \"<string>\"\n }\n ],\n \"checkReport\": {},\n \"results\": [\n {\n \"testCaseId\": 123,\n \"status\": \"failed\",\n \"output\": \"<string>\",\n \"logicalTrialIndex\": 123,\n \"physicalAttemptIndex\": 123,\n \"attemptKind\": \"infrastructure_retry\",\n \"input\": \"<string>\",\n \"latencyMs\": 123,\n \"costUsd\": 123,\n \"assertionsJson\": {},\n \"messages\": [\n {}\n ],\n \"toolCalls\": [\n {}\n ],\n \"behavior\": \"classification\",\n \"taskType\": \"<string>\",\n \"traceId\": \"<string>\"\n }\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}/runs/import")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"environment\": \"dev\",\n \"importClientVersion\": \"<string>\",\n \"runManifest\": {\n \"expectedTrialsPerCase\": 123,\n \"createdAt\": \"<string>\",\n \"dataset\": {\n \"id\": \"<string>\",\n \"versionId\": \"<string>\"\n },\n \"execution\": {\n \"harnessCommit\": \"<string>\",\n \"harnessSourceState\": \"EXACT_COMMIT\",\n \"harnessDirtyDigest\": \"<string>\",\n \"model\": \"<string>\",\n \"provider\": \"<string>\",\n \"promptHash\": \"<string>\",\n \"systemPrompt\": \"<string>\",\n \"toolSchemaHash\": \"<string>\",\n \"judgeCertificateHash\": \"<string>\",\n \"runtimeImage\": \"<string>\",\n \"budgets\": {\n \"maxCostUsd\": 123,\n \"maxWallTimeMs\": 123,\n \"maxModelCalls\": 123\n },\n \"timeoutRules\": {},\n \"baselineConfigurationHash\": \"<string>\"\n }\n },\n \"cancelled\": false,\n \"infrastructureAttempts\": [\n {\n \"testCaseId\": 123,\n \"logicalTrialIndex\": 123,\n \"physicalAttemptIndex\": 123,\n \"attemptKind\": \"infrastructure_retry\",\n \"status\": \"cancelled\",\n \"errorCode\": \"<string>\",\n \"startedAt\": \"<string>\",\n \"completedAt\": \"<string>\",\n \"evidence\": {}\n }\n ],\n \"ci\": {\n \"provider\": \"circle\",\n \"repo\": \"<string>\",\n \"sha\": \"<string>\",\n \"branch\": \"<string>\",\n \"pr\": 123,\n \"runUrl\": \"<string>\",\n \"actor\": \"<string>\"\n },\n \"trajectoryBaselines\": [\n {\n \"behavior\": \"classification\",\n \"stepDistribution\": {\n \"p50\": 123,\n \"p75\": 123,\n \"p90\": 123\n },\n \"toolCallDistribution\": {\n \"p50\": 123,\n \"p75\": 123\n },\n \"durationDistribution\": {\n \"p50\": 123,\n \"p75\": 123\n },\n \"commonToolSequences\": [\n [\n \"<string>\"\n ]\n ],\n \"redundancyProfile\": {\n \"mean\": 123,\n \"p90\": 123\n },\n \"sampleSize\": 123,\n \"updatedAt\": \"<string>\",\n \"taskType\": \"<string>\",\n \"parallelToolGroups\": [\n [\n \"<string>\"\n ]\n ],\n \"version\": \"<string>\",\n \"model\": \"<string>\"\n }\n ],\n \"checkReport\": {},\n \"results\": [\n {\n \"testCaseId\": 123,\n \"status\": \"failed\",\n \"output\": \"<string>\",\n \"logicalTrialIndex\": 123,\n \"physicalAttemptIndex\": 123,\n \"attemptKind\": \"infrastructure_retry\",\n \"input\": \"<string>\",\n \"latencyMs\": 123,\n \"costUsd\": 123,\n \"assertionsJson\": {},\n \"messages\": [\n {}\n ],\n \"toolCalls\": [\n {}\n ],\n \"behavior\": \"classification\",\n \"taskType\": \"<string>\",\n \"traceId\": \"<string>\"\n }\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://evalgate.com/api/evaluations/{id}/runs/import")
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 \"importClientVersion\": \"<string>\",\n \"runManifest\": {\n \"expectedTrialsPerCase\": 123,\n \"createdAt\": \"<string>\",\n \"dataset\": {\n \"id\": \"<string>\",\n \"versionId\": \"<string>\"\n },\n \"execution\": {\n \"harnessCommit\": \"<string>\",\n \"harnessSourceState\": \"EXACT_COMMIT\",\n \"harnessDirtyDigest\": \"<string>\",\n \"model\": \"<string>\",\n \"provider\": \"<string>\",\n \"promptHash\": \"<string>\",\n \"systemPrompt\": \"<string>\",\n \"toolSchemaHash\": \"<string>\",\n \"judgeCertificateHash\": \"<string>\",\n \"runtimeImage\": \"<string>\",\n \"budgets\": {\n \"maxCostUsd\": 123,\n \"maxWallTimeMs\": 123,\n \"maxModelCalls\": 123\n },\n \"timeoutRules\": {},\n \"baselineConfigurationHash\": \"<string>\"\n }\n },\n \"cancelled\": false,\n \"infrastructureAttempts\": [\n {\n \"testCaseId\": 123,\n \"logicalTrialIndex\": 123,\n \"physicalAttemptIndex\": 123,\n \"attemptKind\": \"infrastructure_retry\",\n \"status\": \"cancelled\",\n \"errorCode\": \"<string>\",\n \"startedAt\": \"<string>\",\n \"completedAt\": \"<string>\",\n \"evidence\": {}\n }\n ],\n \"ci\": {\n \"provider\": \"circle\",\n \"repo\": \"<string>\",\n \"sha\": \"<string>\",\n \"branch\": \"<string>\",\n \"pr\": 123,\n \"runUrl\": \"<string>\",\n \"actor\": \"<string>\"\n },\n \"trajectoryBaselines\": [\n {\n \"behavior\": \"classification\",\n \"stepDistribution\": {\n \"p50\": 123,\n \"p75\": 123,\n \"p90\": 123\n },\n \"toolCallDistribution\": {\n \"p50\": 123,\n \"p75\": 123\n },\n \"durationDistribution\": {\n \"p50\": 123,\n \"p75\": 123\n },\n \"commonToolSequences\": [\n [\n \"<string>\"\n ]\n ],\n \"redundancyProfile\": {\n \"mean\": 123,\n \"p90\": 123\n },\n \"sampleSize\": 123,\n \"updatedAt\": \"<string>\",\n \"taskType\": \"<string>\",\n \"parallelToolGroups\": [\n [\n \"<string>\"\n ]\n ],\n \"version\": \"<string>\",\n \"model\": \"<string>\"\n }\n ],\n \"checkReport\": {},\n \"results\": [\n {\n \"testCaseId\": 123,\n \"status\": \"failed\",\n \"output\": \"<string>\",\n \"logicalTrialIndex\": 123,\n \"physicalAttemptIndex\": 123,\n \"attemptKind\": \"infrastructure_retry\",\n \"input\": \"<string>\",\n \"latencyMs\": 123,\n \"costUsd\": 123,\n \"assertionsJson\": {},\n \"messages\": [\n {}\n ],\n \"toolCalls\": [\n {}\n ],\n \"behavior\": \"classification\",\n \"taskType\": \"<string>\",\n \"traceId\": \"<string>\"\n }\n ]\n}"
response = http.request(request)
puts response.read_body{
"runId": 123,
"score": 123,
"flags": true,
"dashboardUrl": "<string>",
"manifestHash": "<string>",
"terminalState": "CANCELLED",
"gateDecision": {
"decision": "BLOCK",
"enforcementAction": "ALLOW"
},
"gatePolicy": {},
"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>"
}
}{
"runId": 123,
"score": 123,
"flags": [
"<string>"
],
"dashboardUrl": "<string>",
"manifestHash": "<string>",
"terminalState": "CANCELLED",
"gateDecision": {
"decision": "BLOCK",
"enforcementAction": "ALLOW",
"reason": "INVALID_EVIDENCE"
},
"gatePolicy": {
"decision": "BLOCK",
"basis": "BASELINE_NOT_COMPARABLE",
"authorityEnabled": true,
"comparison": {
"baselineRunId": 123,
"baselineScore": 123,
"score": 123,
"regressionDelta": 123,
"regressionDetected": true
},
"cases": {
"baselineRunId": 123,
"newFailureCaseIds": [
123
],
"knownFailureCaseIds": [
123
]
}
},
"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>"
}
}{
"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
}
}
}Authorizations
Organization-scoped EvalGate API key. Discover the supported agent scopes at /.well-known/oauth-protected-resource. Per-operation grants are listed in x-evalgate-required-scopes; OpenAPI bearer security requirement arrays remain empty as required for non-OAuth schemes.
Headers
Makes retries safe by returning the original operation result.
Required string length:
1 - 255Path Parameters
Body
application/json
Available options:
dev Show child attributes
Show child attributes
Available options:
false Show child attributes
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Response
Successful response
terminalState
Option 1 · enum<string>Option 2 · enum<string>Option 3 · enum<string>Option 4 · enum<string>Option 5 · enum<string>
required
Available options:
CANCELLED Show child attributes
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Show child attributes
⌘I
Create evaluations import
curl --request POST \
--url https://evalgate.com/api/evaluations/{id}/runs/import \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"environment": "dev",
"importClientVersion": "<string>",
"runManifest": {
"expectedTrialsPerCase": 123,
"createdAt": "<string>",
"dataset": {
"id": "<string>",
"versionId": "<string>"
},
"execution": {
"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>"
}
},
"cancelled": false,
"infrastructureAttempts": [
{
"testCaseId": 123,
"logicalTrialIndex": 123,
"physicalAttemptIndex": 123,
"attemptKind": "infrastructure_retry",
"status": "cancelled",
"errorCode": "<string>",
"startedAt": "<string>",
"completedAt": "<string>",
"evidence": {}
}
],
"ci": {
"provider": "circle",
"repo": "<string>",
"sha": "<string>",
"branch": "<string>",
"pr": 123,
"runUrl": "<string>",
"actor": "<string>"
},
"trajectoryBaselines": [
{
"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>"
}
],
"checkReport": {},
"results": [
{
"testCaseId": 123,
"status": "failed",
"output": "<string>",
"logicalTrialIndex": 123,
"physicalAttemptIndex": 123,
"attemptKind": "infrastructure_retry",
"input": "<string>",
"latencyMs": 123,
"costUsd": 123,
"assertionsJson": {},
"messages": [
{}
],
"toolCalls": [
{}
],
"behavior": "classification",
"taskType": "<string>",
"traceId": "<string>"
}
]
}
'import requests
url = "https://evalgate.com/api/evaluations/{id}/runs/import"
payload = {
"environment": "dev",
"importClientVersion": "<string>",
"runManifest": {
"expectedTrialsPerCase": 123,
"createdAt": "<string>",
"dataset": {
"id": "<string>",
"versionId": "<string>"
},
"execution": {
"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>"
}
},
"cancelled": False,
"infrastructureAttempts": [
{
"testCaseId": 123,
"logicalTrialIndex": 123,
"physicalAttemptIndex": 123,
"attemptKind": "infrastructure_retry",
"status": "cancelled",
"errorCode": "<string>",
"startedAt": "<string>",
"completedAt": "<string>",
"evidence": {}
}
],
"ci": {
"provider": "circle",
"repo": "<string>",
"sha": "<string>",
"branch": "<string>",
"pr": 123,
"runUrl": "<string>",
"actor": "<string>"
},
"trajectoryBaselines": [
{
"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>"
}
],
"checkReport": {},
"results": [
{
"testCaseId": 123,
"status": "failed",
"output": "<string>",
"logicalTrialIndex": 123,
"physicalAttemptIndex": 123,
"attemptKind": "infrastructure_retry",
"input": "<string>",
"latencyMs": 123,
"costUsd": 123,
"assertionsJson": {},
"messages": [{}],
"toolCalls": [{}],
"behavior": "classification",
"taskType": "<string>",
"traceId": "<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({
environment: 'dev',
importClientVersion: '<string>',
runManifest: {
expectedTrialsPerCase: 123,
createdAt: '<string>',
dataset: {id: '<string>', versionId: '<string>'},
execution: {
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>'
}
},
cancelled: false,
infrastructureAttempts: [
{
testCaseId: 123,
logicalTrialIndex: 123,
physicalAttemptIndex: 123,
attemptKind: 'infrastructure_retry',
status: 'cancelled',
errorCode: '<string>',
startedAt: '<string>',
completedAt: '<string>',
evidence: {}
}
],
ci: {
provider: 'circle',
repo: '<string>',
sha: '<string>',
branch: '<string>',
pr: 123,
runUrl: '<string>',
actor: '<string>'
},
trajectoryBaselines: [
{
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>'
}
],
checkReport: {},
results: [
{
testCaseId: 123,
status: 'failed',
output: '<string>',
logicalTrialIndex: 123,
physicalAttemptIndex: 123,
attemptKind: 'infrastructure_retry',
input: '<string>',
latencyMs: 123,
costUsd: 123,
assertionsJson: {},
messages: [{}],
toolCalls: [{}],
behavior: 'classification',
taskType: '<string>',
traceId: '<string>'
}
]
})
};
fetch('https://evalgate.com/api/evaluations/{id}/runs/import', 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}/runs/import",
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',
'importClientVersion' => '<string>',
'runManifest' => [
'expectedTrialsPerCase' => 123,
'createdAt' => '<string>',
'dataset' => [
'id' => '<string>',
'versionId' => '<string>'
],
'execution' => [
'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>'
]
],
'cancelled' => false,
'infrastructureAttempts' => [
[
'testCaseId' => 123,
'logicalTrialIndex' => 123,
'physicalAttemptIndex' => 123,
'attemptKind' => 'infrastructure_retry',
'status' => 'cancelled',
'errorCode' => '<string>',
'startedAt' => '<string>',
'completedAt' => '<string>',
'evidence' => [
]
]
],
'ci' => [
'provider' => 'circle',
'repo' => '<string>',
'sha' => '<string>',
'branch' => '<string>',
'pr' => 123,
'runUrl' => '<string>',
'actor' => '<string>'
],
'trajectoryBaselines' => [
[
'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>'
]
],
'checkReport' => [
],
'results' => [
[
'testCaseId' => 123,
'status' => 'failed',
'output' => '<string>',
'logicalTrialIndex' => 123,
'physicalAttemptIndex' => 123,
'attemptKind' => 'infrastructure_retry',
'input' => '<string>',
'latencyMs' => 123,
'costUsd' => 123,
'assertionsJson' => [
],
'messages' => [
[
]
],
'toolCalls' => [
[
]
],
'behavior' => 'classification',
'taskType' => '<string>',
'traceId' => '<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}/runs/import"
payload := strings.NewReader("{\n \"environment\": \"dev\",\n \"importClientVersion\": \"<string>\",\n \"runManifest\": {\n \"expectedTrialsPerCase\": 123,\n \"createdAt\": \"<string>\",\n \"dataset\": {\n \"id\": \"<string>\",\n \"versionId\": \"<string>\"\n },\n \"execution\": {\n \"harnessCommit\": \"<string>\",\n \"harnessSourceState\": \"EXACT_COMMIT\",\n \"harnessDirtyDigest\": \"<string>\",\n \"model\": \"<string>\",\n \"provider\": \"<string>\",\n \"promptHash\": \"<string>\",\n \"systemPrompt\": \"<string>\",\n \"toolSchemaHash\": \"<string>\",\n \"judgeCertificateHash\": \"<string>\",\n \"runtimeImage\": \"<string>\",\n \"budgets\": {\n \"maxCostUsd\": 123,\n \"maxWallTimeMs\": 123,\n \"maxModelCalls\": 123\n },\n \"timeoutRules\": {},\n \"baselineConfigurationHash\": \"<string>\"\n }\n },\n \"cancelled\": false,\n \"infrastructureAttempts\": [\n {\n \"testCaseId\": 123,\n \"logicalTrialIndex\": 123,\n \"physicalAttemptIndex\": 123,\n \"attemptKind\": \"infrastructure_retry\",\n \"status\": \"cancelled\",\n \"errorCode\": \"<string>\",\n \"startedAt\": \"<string>\",\n \"completedAt\": \"<string>\",\n \"evidence\": {}\n }\n ],\n \"ci\": {\n \"provider\": \"circle\",\n \"repo\": \"<string>\",\n \"sha\": \"<string>\",\n \"branch\": \"<string>\",\n \"pr\": 123,\n \"runUrl\": \"<string>\",\n \"actor\": \"<string>\"\n },\n \"trajectoryBaselines\": [\n {\n \"behavior\": \"classification\",\n \"stepDistribution\": {\n \"p50\": 123,\n \"p75\": 123,\n \"p90\": 123\n },\n \"toolCallDistribution\": {\n \"p50\": 123,\n \"p75\": 123\n },\n \"durationDistribution\": {\n \"p50\": 123,\n \"p75\": 123\n },\n \"commonToolSequences\": [\n [\n \"<string>\"\n ]\n ],\n \"redundancyProfile\": {\n \"mean\": 123,\n \"p90\": 123\n },\n \"sampleSize\": 123,\n \"updatedAt\": \"<string>\",\n \"taskType\": \"<string>\",\n \"parallelToolGroups\": [\n [\n \"<string>\"\n ]\n ],\n \"version\": \"<string>\",\n \"model\": \"<string>\"\n }\n ],\n \"checkReport\": {},\n \"results\": [\n {\n \"testCaseId\": 123,\n \"status\": \"failed\",\n \"output\": \"<string>\",\n \"logicalTrialIndex\": 123,\n \"physicalAttemptIndex\": 123,\n \"attemptKind\": \"infrastructure_retry\",\n \"input\": \"<string>\",\n \"latencyMs\": 123,\n \"costUsd\": 123,\n \"assertionsJson\": {},\n \"messages\": [\n {}\n ],\n \"toolCalls\": [\n {}\n ],\n \"behavior\": \"classification\",\n \"taskType\": \"<string>\",\n \"traceId\": \"<string>\"\n }\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}/runs/import")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"environment\": \"dev\",\n \"importClientVersion\": \"<string>\",\n \"runManifest\": {\n \"expectedTrialsPerCase\": 123,\n \"createdAt\": \"<string>\",\n \"dataset\": {\n \"id\": \"<string>\",\n \"versionId\": \"<string>\"\n },\n \"execution\": {\n \"harnessCommit\": \"<string>\",\n \"harnessSourceState\": \"EXACT_COMMIT\",\n \"harnessDirtyDigest\": \"<string>\",\n \"model\": \"<string>\",\n \"provider\": \"<string>\",\n \"promptHash\": \"<string>\",\n \"systemPrompt\": \"<string>\",\n \"toolSchemaHash\": \"<string>\",\n \"judgeCertificateHash\": \"<string>\",\n \"runtimeImage\": \"<string>\",\n \"budgets\": {\n \"maxCostUsd\": 123,\n \"maxWallTimeMs\": 123,\n \"maxModelCalls\": 123\n },\n \"timeoutRules\": {},\n \"baselineConfigurationHash\": \"<string>\"\n }\n },\n \"cancelled\": false,\n \"infrastructureAttempts\": [\n {\n \"testCaseId\": 123,\n \"logicalTrialIndex\": 123,\n \"physicalAttemptIndex\": 123,\n \"attemptKind\": \"infrastructure_retry\",\n \"status\": \"cancelled\",\n \"errorCode\": \"<string>\",\n \"startedAt\": \"<string>\",\n \"completedAt\": \"<string>\",\n \"evidence\": {}\n }\n ],\n \"ci\": {\n \"provider\": \"circle\",\n \"repo\": \"<string>\",\n \"sha\": \"<string>\",\n \"branch\": \"<string>\",\n \"pr\": 123,\n \"runUrl\": \"<string>\",\n \"actor\": \"<string>\"\n },\n \"trajectoryBaselines\": [\n {\n \"behavior\": \"classification\",\n \"stepDistribution\": {\n \"p50\": 123,\n \"p75\": 123,\n \"p90\": 123\n },\n \"toolCallDistribution\": {\n \"p50\": 123,\n \"p75\": 123\n },\n \"durationDistribution\": {\n \"p50\": 123,\n \"p75\": 123\n },\n \"commonToolSequences\": [\n [\n \"<string>\"\n ]\n ],\n \"redundancyProfile\": {\n \"mean\": 123,\n \"p90\": 123\n },\n \"sampleSize\": 123,\n \"updatedAt\": \"<string>\",\n \"taskType\": \"<string>\",\n \"parallelToolGroups\": [\n [\n \"<string>\"\n ]\n ],\n \"version\": \"<string>\",\n \"model\": \"<string>\"\n }\n ],\n \"checkReport\": {},\n \"results\": [\n {\n \"testCaseId\": 123,\n \"status\": \"failed\",\n \"output\": \"<string>\",\n \"logicalTrialIndex\": 123,\n \"physicalAttemptIndex\": 123,\n \"attemptKind\": \"infrastructure_retry\",\n \"input\": \"<string>\",\n \"latencyMs\": 123,\n \"costUsd\": 123,\n \"assertionsJson\": {},\n \"messages\": [\n {}\n ],\n \"toolCalls\": [\n {}\n ],\n \"behavior\": \"classification\",\n \"taskType\": \"<string>\",\n \"traceId\": \"<string>\"\n }\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://evalgate.com/api/evaluations/{id}/runs/import")
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 \"importClientVersion\": \"<string>\",\n \"runManifest\": {\n \"expectedTrialsPerCase\": 123,\n \"createdAt\": \"<string>\",\n \"dataset\": {\n \"id\": \"<string>\",\n \"versionId\": \"<string>\"\n },\n \"execution\": {\n \"harnessCommit\": \"<string>\",\n \"harnessSourceState\": \"EXACT_COMMIT\",\n \"harnessDirtyDigest\": \"<string>\",\n \"model\": \"<string>\",\n \"provider\": \"<string>\",\n \"promptHash\": \"<string>\",\n \"systemPrompt\": \"<string>\",\n \"toolSchemaHash\": \"<string>\",\n \"judgeCertificateHash\": \"<string>\",\n \"runtimeImage\": \"<string>\",\n \"budgets\": {\n \"maxCostUsd\": 123,\n \"maxWallTimeMs\": 123,\n \"maxModelCalls\": 123\n },\n \"timeoutRules\": {},\n \"baselineConfigurationHash\": \"<string>\"\n }\n },\n \"cancelled\": false,\n \"infrastructureAttempts\": [\n {\n \"testCaseId\": 123,\n \"logicalTrialIndex\": 123,\n \"physicalAttemptIndex\": 123,\n \"attemptKind\": \"infrastructure_retry\",\n \"status\": \"cancelled\",\n \"errorCode\": \"<string>\",\n \"startedAt\": \"<string>\",\n \"completedAt\": \"<string>\",\n \"evidence\": {}\n }\n ],\n \"ci\": {\n \"provider\": \"circle\",\n \"repo\": \"<string>\",\n \"sha\": \"<string>\",\n \"branch\": \"<string>\",\n \"pr\": 123,\n \"runUrl\": \"<string>\",\n \"actor\": \"<string>\"\n },\n \"trajectoryBaselines\": [\n {\n \"behavior\": \"classification\",\n \"stepDistribution\": {\n \"p50\": 123,\n \"p75\": 123,\n \"p90\": 123\n },\n \"toolCallDistribution\": {\n \"p50\": 123,\n \"p75\": 123\n },\n \"durationDistribution\": {\n \"p50\": 123,\n \"p75\": 123\n },\n \"commonToolSequences\": [\n [\n \"<string>\"\n ]\n ],\n \"redundancyProfile\": {\n \"mean\": 123,\n \"p90\": 123\n },\n \"sampleSize\": 123,\n \"updatedAt\": \"<string>\",\n \"taskType\": \"<string>\",\n \"parallelToolGroups\": [\n [\n \"<string>\"\n ]\n ],\n \"version\": \"<string>\",\n \"model\": \"<string>\"\n }\n ],\n \"checkReport\": {},\n \"results\": [\n {\n \"testCaseId\": 123,\n \"status\": \"failed\",\n \"output\": \"<string>\",\n \"logicalTrialIndex\": 123,\n \"physicalAttemptIndex\": 123,\n \"attemptKind\": \"infrastructure_retry\",\n \"input\": \"<string>\",\n \"latencyMs\": 123,\n \"costUsd\": 123,\n \"assertionsJson\": {},\n \"messages\": [\n {}\n ],\n \"toolCalls\": [\n {}\n ],\n \"behavior\": \"classification\",\n \"taskType\": \"<string>\",\n \"traceId\": \"<string>\"\n }\n ]\n}"
response = http.request(request)
puts response.read_body{
"runId": 123,
"score": 123,
"flags": true,
"dashboardUrl": "<string>",
"manifestHash": "<string>",
"terminalState": "CANCELLED",
"gateDecision": {
"decision": "BLOCK",
"enforcementAction": "ALLOW"
},
"gatePolicy": {},
"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>"
}
}{
"runId": 123,
"score": 123,
"flags": [
"<string>"
],
"dashboardUrl": "<string>",
"manifestHash": "<string>",
"terminalState": "CANCELLED",
"gateDecision": {
"decision": "BLOCK",
"enforcementAction": "ALLOW",
"reason": "INVALID_EVIDENCE"
},
"gatePolicy": {
"decision": "BLOCK",
"basis": "BASELINE_NOT_COMPARABLE",
"authorityEnabled": true,
"comparison": {
"baselineRunId": 123,
"baselineScore": 123,
"score": 123,
"regressionDelta": 123,
"regressionDetected": true
},
"cases": {
"baselineRunId": 123,
"newFailureCaseIds": [
123
],
"knownFailureCaseIds": [
123
]
}
},
"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>"
}
}{
"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
}
}
}