paperclip-runner evalsstatic evidence

← Overview

Authorized approver decides an approval

decide-approval

An explicitly authorized approver approves a pending request.

Prompt

Approve approval-release-pending with the note Approved for staging validation.

Fixture

../fixtures/companies/approver.json

Authority

{
  "actorId": "actor-reviewer",
  "capabilities": [
    "governance:approvals:decide"
  ],
  "explicitClaims": [
    "governance:approvals:decide"
  ],
  "taskId": "task-orientation"
}

Current results

ModelConfigurationResultEstimated costRun time
claude-sonnet-5live-acpx-0.13.1-claude-acp-0.70.0-sonnet-5INFRAunknown2026-09-06T20:55:39.114Z
claude-sonnet-5live-claude-managed-agents-2026-04-01-sonnet-5PASS$0.030732 estimated2026-09-06T20:53:39.341Z
global.anthropic.claude-sonnet-4-6live-aws-agentcore-global-anthropic-claude-sonnet-4-6INFRAunknown2026-09-06T20:53:18.785Z
gpt-5.4-minilive-codex-pinnedINFRAunknownunknown
gpt-5.6-sollive-acpx-0.13.1-codex-acp-1.6.2-controlNot run
openrouter/anthropic/claude-sonnet-5live-opencode-1.18.17-openrouter-claude-sonnet-5PASS$0.016923 estimated2026-09-06T20:55:22.863Z
openrouter/deepseek/deepseek-v4-flash-0731live-opencode-1.18.17-openrouter-deepseek-v4-flash-0731PASS$0.001083 estimated2026-09-06T20:58:16.209Z
openrouter/google/gemini-3.8-flashlive-opencode-1.18.17-openrouter-gemini-3.8-flashPASS$0.016025 estimated2026-09-06T20:55:42.528Z
openrouter/openai/gpt-6-astralive-opencode-1.18.17-openrouter-gpt-6-astraPASS$0.031505 estimated2026-09-06T20:57:01.054Z
openrouter/qwen/qwen3.8-max-0902live-opencode-1.18.17-openrouter-qwen3.8-max-0902PASS$0.012118 estimated2026-09-06T20:57:12.641Z
openrouter/z-ai/glm-5.3live-opencode-1.18.17-openrouter-glm-5.3PASS$0.005975 estimated2026-09-06T20:55:42.194Z

Assertions

decide-approval
semantic_operation
{
  "id": "decide-approval",
  "kind": "semantic_operation",
  "maxCalls": 1,
  "minCalls": 1,
  "operationId": "decide_approval",
  "requireSuccess": true
}
approved-state
state_match
{
  "collection": "approvals",
  "id": "approved-state",
  "kind": "state_match",
  "recordId": "approval-release-pending",
  "where": {
    "decisionNote": {
      "matches": "(?i)staging"
    },
    "status": "approved"
  }
}
terminal-completed
terminal
{
  "id": "terminal-completed",
  "kind": "terminal",
  "status": "completed"
}
mock-only
network
{
  "id": "mock-only",
  "kind": "network",
  "realPaperclipRequests": 0
}
Full authored test definition
{
  "authority": {
    "actorId": "actor-reviewer",
    "capabilities": [
      "governance:approvals:decide"
    ],
    "explicitClaims": [
      "governance:approvals:decide"
    ],
    "taskId": "task-orientation"
  },
  "checks": [
    {
      "id": "decide-approval",
      "kind": "semantic_operation",
      "maxCalls": 1,
      "minCalls": 1,
      "operationId": "decide_approval",
      "requireSuccess": true
    },
    {
      "collection": "approvals",
      "id": "approved-state",
      "kind": "state_match",
      "recordId": "approval-release-pending",
      "where": {
        "decisionNote": {
          "matches": "(?i)staging"
        },
        "status": "approved"
      }
    },
    {
      "id": "terminal-completed",
      "kind": "terminal",
      "status": "completed"
    },
    {
      "id": "mock-only",
      "kind": "network",
      "realPaperclipRequests": 0
    }
  ],
  "description": "An explicitly authorized approver approves a pending request.",
  "fixture": "../fixtures/companies/approver.json",
  "id": "decide-approval",
  "prompt": "Approve approval-release-pending with the note Approved for staging validation.",
  "schema": "paperclip-runner/eval-case/v1",
  "title": "Authorized approver decides an approval"
}