| 1 | {
|
| 2 | "$schema": "https://json-schema.org/draft/2020-12/schema",
|
| 3 | "type": "object",
|
| 4 | "properties": {
|
| 5 | "protocolVersion": {
|
| 6 | "type": "string",
|
| 7 | "const": "0.1"
|
| 8 | },
|
| 9 | "evaluationId": {
|
| 10 | "type": "string",
|
| 11 | "format": "uuid",
|
| 12 | "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
|
| 13 | },
|
| 14 | "interactionId": {
|
| 15 | "type": "string",
|
| 16 | "format": "uuid",
|
| 17 | "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
|
| 18 | },
|
| 19 | "contractHash": {
|
| 20 | "type": "string",
|
| 21 | "minLength": 1
|
| 22 | },
|
| 23 | "targetAgentId": {
|
| 24 | "type": "string",
|
| 25 | "minLength": 1
|
| 26 | },
|
| 27 | "targetAgentVersion": {
|
| 28 | "type": "string",
|
| 29 | "minLength": 1,
|
| 30 | "maxLength": 200
|
| 31 | },
|
| 32 | "taskCategory": {
|
| 33 | "type": "string",
|
| 34 | "minLength": 1,
|
| 35 | "maxLength": 100
|
| 36 | },
|
| 37 | "completionReportId": {
|
| 38 | "type": "string",
|
| 39 | "format": "uuid",
|
| 40 | "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
|
| 41 | },
|
| 42 | "outcomeValue": {
|
| 43 | "type": "number",
|
| 44 | "minimum": 0,
|
| 45 | "maximum": 1
|
| 46 | },
|
| 47 | "predictionScores": {
|
| 48 | "maxItems": 20,
|
| 49 | "type": "array",
|
| 50 | "items": {
|
| 51 | "type": "object",
|
| 52 | "properties": {
|
| 53 | "predictionId": {
|
| 54 | "type": "string",
|
| 55 | "format": "uuid",
|
| 56 | "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
|
| 57 | },
|
| 58 | "stage": {
|
| 59 | "type": "string",
|
| 60 | "enum": [
|
| 61 | "baseline",
|
| 62 | "after_probe",
|
| 63 | "after_safeguard",
|
| 64 | "final"
|
| 65 | ]
|
| 66 | },
|
| 67 | "probability": {
|
| 68 | "type": "number",
|
| 69 | "minimum": 0.05,
|
| 70 | "maximum": 0.95
|
| 71 | },
|
| 72 | "brierScore": {
|
| 73 | "type": "number",
|
| 74 | "minimum": 0,
|
| 75 | "maximum": 1
|
| 76 | }
|
| 77 | },
|
| 78 | "required": [
|
| 79 | "predictionId",
|
| 80 | "stage",
|
| 81 | "probability",
|
| 82 | "brierScore"
|
| 83 | ],
|
| 84 | "additionalProperties": false
|
| 85 | }
|
| 86 | },
|
| 87 | "questionScores": {
|
| 88 | "maxItems": 6,
|
| 89 | "type": "array",
|
| 90 | "items": {
|
| 91 | "type": "object",
|
| 92 | "properties": {
|
| 93 | "probeId": {
|
| 94 | "type": "string",
|
| 95 | "format": "uuid",
|
| 96 | "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
|
| 97 | },
|
| 98 | "questionCode": {
|
| 99 | "type": "string",
|
| 100 | "minLength": 1
|
| 101 | },
|
| 102 | "questionFamily": {
|
| 103 | "type": "string",
|
| 104 | "enum": [
|
| 105 | "capability",
|
| 106 | "scope",
|
| 107 | "deadline",
|
| 108 | "tool_access",
|
| 109 | "data_access",
|
| 110 | "evidence",
|
| 111 | "dependency",
|
| 112 | "authority",
|
| 113 | "safety",
|
| 114 | "delivery"
|
| 115 | ]
|
| 116 | },
|
| 117 | "answered": {
|
| 118 | "type": "boolean"
|
| 119 | },
|
| 120 | "exposedMaterialRisk": {
|
| 121 | "type": "boolean"
|
| 122 | },
|
| 123 | "predictionDelta": {
|
| 124 | "type": "number",
|
| 125 | "minimum": -0.9,
|
| 126 | "maximum": 0.9
|
| 127 | }
|
| 128 | },
|
| 129 | "required": [
|
| 130 | "probeId",
|
| 131 | "questionCode",
|
| 132 | "questionFamily",
|
| 133 | "answered",
|
| 134 | "exposedMaterialRisk",
|
| 135 | "predictionDelta"
|
| 136 | ],
|
| 137 | "additionalProperties": false
|
| 138 | }
|
| 139 | },
|
| 140 | "safeguardScores": {
|
| 141 | "maxItems": 10,
|
| 142 | "type": "array",
|
| 143 | "items": {
|
| 144 | "type": "object",
|
| 145 | "properties": {
|
| 146 | "safeguardId": {
|
| 147 | "type": "string",
|
| 148 | "format": "uuid",
|
| 149 | "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
|
| 150 | },
|
| 151 | "type": {
|
| 152 | "type": "string",
|
| 153 | "enum": [
|
| 154 | "require_evidence",
|
| 155 | "narrow_scope",
|
| 156 | "extend_deadline",
|
| 157 | "grant_tool_access",
|
| 158 | "require_human_approval",
|
| 159 | "limit_delegation",
|
| 160 | "add_checkpoint",
|
| 161 | "choose_another_agent"
|
| 162 | ]
|
| 163 | },
|
| 164 | "status": {
|
| 165 | "type": "string",
|
| 166 | "enum": [
|
| 167 | "recommended",
|
| 168 | "accepted",
|
| 169 | "rejected",
|
| 170 | "modified"
|
| 171 | ]
|
| 172 | },
|
| 173 | "outcomeAssociation": {
|
| 174 | "type": "string",
|
| 175 | "enum": [
|
| 176 | "positive",
|
| 177 | "negative",
|
| 178 | "unclear"
|
| 179 | ]
|
| 180 | },
|
| 181 | "causalClaim": {
|
| 182 | "type": "boolean",
|
| 183 | "const": false
|
| 184 | }
|
| 185 | },
|
| 186 | "required": [
|
| 187 | "safeguardId",
|
| 188 | "type",
|
| 189 | "status",
|
| 190 | "outcomeAssociation",
|
| 191 | "causalClaim"
|
| 192 | ],
|
| 193 | "additionalProperties": false
|
| 194 | }
|
| 195 | },
|
| 196 | "evaluatedAt": {
|
| 197 | "type": "string",
|
| 198 | "format": "date-time",
|
| 199 | "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$"
|
| 200 | }
|
| 201 | },
|
| 202 | "required": [
|
| 203 | "protocolVersion",
|
| 204 | "evaluationId",
|
| 205 | "interactionId",
|
| 206 | "contractHash",
|
| 207 | "targetAgentId",
|
| 208 | "targetAgentVersion",
|
| 209 | "taskCategory",
|
| 210 | "completionReportId",
|
| 211 | "outcomeValue",
|
| 212 | "predictionScores",
|
| 213 | "questionScores",
|
| 214 | "safeguardScores",
|
| 215 | "evaluatedAt"
|
| 216 | ],
|
| 217 | "additionalProperties": false
|
| 218 | }
|