263 lines
8.1 KiB
JSON
263 lines
8.1 KiB
JSON
{
|
|
"schema": "paperclip-runner/native-execution/v1",
|
|
"provenance": "seeded",
|
|
"identity": {
|
|
"runId": "run_evals_seeded",
|
|
"caseId": "case_semantic_denial",
|
|
"configId": "config_deterministic_v1",
|
|
"attemptId": "attempt_semantic_denial_0001"
|
|
},
|
|
"input": {
|
|
"caseSha256": "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
"configSha256": "sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
"deterministicSeed": "paperclip-evals-v1-seed"
|
|
},
|
|
"runner": {
|
|
"package": {
|
|
"name": "@paperclipai/paperclip-runner",
|
|
"version": "0.0.0"
|
|
},
|
|
"binary": {
|
|
"name": "paperclip-runnerd",
|
|
"sha256": "sha256:cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc"
|
|
},
|
|
"prpVersion": 1,
|
|
"nativeExecutionVersion": 1,
|
|
"catalogVersion": 1,
|
|
"catalogSha256": "sha256:f4d9e13a542b476b89c13793ae5c540406cd4cdc47941569beb22556de957dcc",
|
|
"driverContractVersion": 1,
|
|
"driverKind": "paperclip-deterministic",
|
|
"driverVersion": "1.0.0"
|
|
},
|
|
"events": [
|
|
{
|
|
"schema": "paperclip.prp.event.v1",
|
|
"sourceEventId": "evals_seeded_01",
|
|
"sourceSeq": 1,
|
|
"sourceInstanceId": "runner_evals_seeded",
|
|
"sourceKind": "runner",
|
|
"runId": "run_evals_seeded",
|
|
"normalizedSessionId": "session_evals_seeded",
|
|
"turnId": "turn_evals_seeded",
|
|
"itemId": "item_evals_seeded",
|
|
"eventType": "mcp_app.tool_input",
|
|
"schemaVersion": 1,
|
|
"priority": 1,
|
|
"emittedAt": "2026-08-11T12:00:00.000Z",
|
|
"payload": {
|
|
"semantic_tool": {
|
|
"schema": "paperclip.prp.semantic_tool.v1",
|
|
"schemaVersion": 1,
|
|
"phase": "input",
|
|
"operationId": "decide_approval",
|
|
"callId": "call_evals_seeded",
|
|
"correlation": {
|
|
"runId": "run_evals_seeded",
|
|
"normalizedSessionId": "session_evals_seeded",
|
|
"turnId": "turn_evals_seeded",
|
|
"itemId": "item_evals_seeded"
|
|
},
|
|
"idempotencyKey": "decide_evals_seeded",
|
|
"content": {
|
|
"digest": "sha256:dddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd",
|
|
"redactionDisposition": "redacted",
|
|
"references": []
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"schema": "paperclip.prp.event.v1",
|
|
"sourceEventId": "evals_seeded_02",
|
|
"sourceSeq": 2,
|
|
"sourceInstanceId": "runner_evals_seeded",
|
|
"sourceKind": "runner",
|
|
"runId": "run_evals_seeded",
|
|
"normalizedSessionId": "session_evals_seeded",
|
|
"turnId": "turn_evals_seeded",
|
|
"itemId": "item_evals_seeded",
|
|
"eventType": "mcp_app.tool_result",
|
|
"schemaVersion": 1,
|
|
"priority": 1,
|
|
"emittedAt": "2026-08-11T12:00:00.010Z",
|
|
"payload": {
|
|
"semantic_tool": {
|
|
"schema": "paperclip.prp.semantic_tool.v1",
|
|
"schemaVersion": 1,
|
|
"phase": "result",
|
|
"operationId": "decide_approval",
|
|
"callId": "call_evals_seeded",
|
|
"correlation": {
|
|
"runId": "run_evals_seeded",
|
|
"normalizedSessionId": "session_evals_seeded",
|
|
"turnId": "turn_evals_seeded",
|
|
"itemId": "item_evals_seeded"
|
|
},
|
|
"idempotencyKey": "decide_evals_seeded",
|
|
"content": {
|
|
"digest": "sha256:eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee",
|
|
"redactionDisposition": "redacted",
|
|
"references": []
|
|
},
|
|
"outcome": "denied",
|
|
"code": "required_claim_missing",
|
|
"retryable": false,
|
|
"authorizationBoundary": "grant",
|
|
"operationReceiptId": "receipt_evals_seeded",
|
|
"auditReceiptId": "audit_evals_seeded"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"schema": "paperclip.prp.event.v1",
|
|
"sourceEventId": "evals_seeded_03",
|
|
"sourceSeq": 3,
|
|
"sourceInstanceId": "runner_evals_seeded",
|
|
"sourceKind": "runner",
|
|
"runId": "run_evals_seeded",
|
|
"normalizedSessionId": "session_evals_seeded",
|
|
"turnId": "turn_evals_seeded",
|
|
"eventType": "run.result.proposed",
|
|
"schemaVersion": 1,
|
|
"priority": 0,
|
|
"emittedAt": "2026-08-11T12:00:00.020Z",
|
|
"payload": {
|
|
"schema": "paperclip.run_result.v1",
|
|
"reportedWorkDisposition": "needs_review",
|
|
"summary": "The governed tool effect was rejected and preserved as a denial.",
|
|
"completionClaim": {
|
|
"contractRevision": "evals-native-execution-v1",
|
|
"objectiveSatisfied": false,
|
|
"criteria": [],
|
|
"remainingWork": [
|
|
{
|
|
"description": "An authorized approver must decide.",
|
|
"blocksCompletion": true
|
|
}
|
|
]
|
|
},
|
|
"evidence": [
|
|
{
|
|
"receiptId": "receipt_evals_seeded"
|
|
}
|
|
],
|
|
"verification": [
|
|
{
|
|
"commandOrCheck": "rejected tool effect stays denied",
|
|
"status": "passed"
|
|
}
|
|
],
|
|
"attentionRequests": [],
|
|
"artifacts": []
|
|
}
|
|
},
|
|
{
|
|
"schema": "paperclip.prp.event.v1",
|
|
"sourceEventId": "evals_seeded_04",
|
|
"sourceSeq": 4,
|
|
"sourceInstanceId": "runner_evals_seeded",
|
|
"sourceKind": "runner",
|
|
"runId": "run_evals_seeded",
|
|
"normalizedSessionId": "session_evals_seeded",
|
|
"turnId": "turn_evals_seeded",
|
|
"eventType": "run.terminal",
|
|
"schemaVersion": 1,
|
|
"priority": 0,
|
|
"emittedAt": "2026-08-11T12:00:00.030Z",
|
|
"payload": {
|
|
"schema": "paperclip.prp.terminal.v1",
|
|
"turnTerminalState": "completed",
|
|
"runTerminalState": "succeeded",
|
|
"reportedWorkDisposition": "needs_review",
|
|
"workAssessmentId": "assessment_evals_seeded",
|
|
"statusDecisionId": "decision_evals_seeded"
|
|
}
|
|
}
|
|
],
|
|
"semanticTools": {
|
|
"definitions": [
|
|
{
|
|
"operationId": "decide_approval",
|
|
"schemaVersion": 1,
|
|
"availability": "denied"
|
|
}
|
|
],
|
|
"calls": [
|
|
{
|
|
"callId": "call_evals_seeded",
|
|
"operationId": "decide_approval",
|
|
"eventId": "evals_seeded_01"
|
|
}
|
|
],
|
|
"results": [
|
|
{
|
|
"callId": "call_evals_seeded",
|
|
"operationId": "decide_approval",
|
|
"eventId": "evals_seeded_02",
|
|
"outcome": "denied"
|
|
}
|
|
],
|
|
"denials": [
|
|
{
|
|
"callId": "call_evals_seeded",
|
|
"code": "required_claim_missing",
|
|
"authorizationBoundary": "grant",
|
|
"retryable": false
|
|
}
|
|
]
|
|
},
|
|
"terminal": {
|
|
"schema": "paperclip.prp.terminal.v1",
|
|
"turnTerminalState": "completed",
|
|
"runTerminalState": "succeeded",
|
|
"reportedWorkDisposition": "needs_review",
|
|
"workAssessmentId": "assessment_evals_seeded",
|
|
"statusDecisionId": "decision_evals_seeded"
|
|
},
|
|
"observations": {
|
|
"checks": [
|
|
{
|
|
"id": "tool-effect-denied",
|
|
"passed": true,
|
|
"receiptId": "receipt_evals_seeded"
|
|
}
|
|
]
|
|
},
|
|
"usage": {
|
|
"inputTokens": 12,
|
|
"outputTokens": 8,
|
|
"totalTokens": 20,
|
|
"requestCount": 1,
|
|
"durationMs": 30,
|
|
"cost": {
|
|
"currency": "USD",
|
|
"amountMicros": 0
|
|
}
|
|
},
|
|
"transcript": {
|
|
"uri": "artifact://native/attempt_semantic_denial_0001/transcript.jsonl",
|
|
"sha256": "sha256:ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff",
|
|
"byteSize": 2048,
|
|
"mediaType": "application/x-ndjson",
|
|
"complete": true,
|
|
"eventCount": 4,
|
|
"omissionReason": null
|
|
},
|
|
"artifactRoot": {
|
|
"uri": "artifact://native/attempt_semantic_denial_0001/",
|
|
"sha256": "sha256:1212121212121212121212121212121212121212121212121212121212121212",
|
|
"byteSize": 4096,
|
|
"mediaType": "application/vnd.paperclip.runner-artifact-root+json"
|
|
},
|
|
"artifacts": [
|
|
{
|
|
"uri": "artifact://native/attempt_semantic_denial_0001/denial-receipt.json",
|
|
"sha256": "sha256:1313131313131313131313131313131313131313131313131313131313131313",
|
|
"byteSize": 512,
|
|
"mediaType": "application/json"
|
|
}
|
|
],
|
|
"failure": null,
|
|
"x_fixturePurpose": "Proves seeded provenance, denied effects, and additive field preservation."
|
|
}
|