paperclip-runner evalsstatic evidence

← Overview

Agent comments on an approval

comment-on-approval

The agent adds exactly one durable approval comment.

Prompt

Add the comment Waiting for deployment evidence. to approval approval-release-pending.

Fixture

../fixtures/companies/orientation.json

Authority

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

Current results

ModelConfigurationResultEstimated costRun time
claude-sonnet-5live-acpx-0.13.1-claude-acp-0.70.0-sonnet-5PASS$0.033077 estimated2026-09-06T21:22:16.696Z
claude-sonnet-5live-claude-managed-agents-2026-04-01-sonnet-5PASS$0.017757 estimated2026-09-06T21:23:06.438Z
global.anthropic.claude-sonnet-4-6live-aws-agentcore-global-anthropic-claude-sonnet-4-6PASS$0.023859 estimated2026-09-06T21:22:28.183Z
gpt-5.4-minilive-codex-pinnedPASS$0.001045 estimated2026-09-06T21:24:06.365Z
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$0.020809 estimated2026-09-06T21:24:25.274Z
openrouter/deepseek/deepseek-v4-flash-0731live-opencode-1.18.17-openrouter-deepseek-v4-flash-0731PASS$0.000736 estimated2026-09-06T21:28:55.408Z
openrouter/google/gemini-3.8-flashlive-opencode-1.18.17-openrouter-gemini-3.8-flashPASS$0.020693 estimated2026-09-06T21:25:21.258Z
openrouter/openai/gpt-6-astralive-opencode-1.18.17-openrouter-gpt-6-astraPASS$0.029511 estimated2026-09-06T21:26:16.704Z
openrouter/qwen/qwen3.8-max-0902live-opencode-1.18.17-openrouter-qwen3.8-max-0902PASS$0.021522 estimated2026-09-06T21:27:22.475Z
openrouter/z-ai/glm-5.3live-opencode-1.18.17-openrouter-glm-5.3PASS$0.009868 estimated2026-09-06T21:25:30.983Z

Assertions

comment-approval
semantic_operation
{
  "id": "comment-approval",
  "kind": "semantic_operation",
  "maxCalls": 1,
  "minCalls": 1,
  "operationId": "comment_on_approval",
  "requireSuccess": true
}
comment-state
state_match
{
  "collection": "approvals",
  "id": "comment-state",
  "kind": "state_match",
  "recordId": "approval-release-pending",
  "where": {
    ".": {
      "matches": "Waiting for deployment evidence"
    },
    "comments": {
      "length": {
        "min": 1
      }
    }
  }
}
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-engineer",
    "capabilities": [
      "governance:approvals:comment"
    ],
    "explicitClaims": [
      "governance:approvals:comment"
    ],
    "taskId": "task-orientation"
  },
  "checks": [
    {
      "id": "comment-approval",
      "kind": "semantic_operation",
      "maxCalls": 1,
      "minCalls": 1,
      "operationId": "comment_on_approval",
      "requireSuccess": true
    },
    {
      "collection": "approvals",
      "id": "comment-state",
      "kind": "state_match",
      "recordId": "approval-release-pending",
      "where": {
        ".": {
          "matches": "Waiting for deployment evidence"
        },
        "comments": {
          "length": {
            "min": 1
          }
        }
      }
    },
    {
      "id": "terminal-completed",
      "kind": "terminal",
      "status": "completed"
    },
    {
      "id": "mock-only",
      "kind": "network",
      "realPaperclipRequests": 0
    }
  ],
  "description": "The agent adds exactly one durable approval comment.",
  "fixture": "../fixtures/companies/orientation.json",
  "id": "comment-on-approval",
  "prompt": "Add the comment Waiting for deployment evidence. to approval approval-release-pending.",
  "schema": "paperclip-runner/eval-case/v1",
  "title": "Agent comments on an approval"
}