paperclip-runner evalsstatic evidence

← Overview

Agent inspects document revision history

read-document-revisions

The agent reads the bounded revision history for eval-notes.

Prompt

Inspect the revision history for the task document with key eval-notes and tell me how many revisions it currently has. Do not change state.

Fixture

../fixtures/companies/orientation.json

Authority

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

Current results

ModelConfigurationResultEstimated costRun time
claude-sonnet-5live-acpx-0.13.1-claude-acp-0.70.0-sonnet-5PASS$0.044913 estimated2026-09-06T21:22:38.479Z
claude-sonnet-5live-claude-managed-agents-2026-04-01-sonnet-5PASS$0.013083 estimated2026-09-06T21:22:18.027Z
global.anthropic.claude-sonnet-4-6live-aws-agentcore-global-anthropic-claude-sonnet-4-6PASS$0.023373 estimated2026-09-06T21:22:15.631Z
gpt-5.4-minilive-codex-pinnedPASS$0.001245 estimated2026-09-06T21:24:04.252Z
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$0.013138 estimated2026-09-06T21:24:27.034Z
openrouter/deepseek/deepseek-v4-flash-0731live-opencode-1.18.17-openrouter-deepseek-v4-flash-0731PASS$0.000646 estimated2026-09-06T21:27:32.114Z
openrouter/google/gemini-3.8-flashlive-opencode-1.18.17-openrouter-gemini-3.8-flashPASS$0.019386 estimated2026-09-06T21:24:35.716Z
openrouter/openai/gpt-6-astralive-opencode-1.18.17-openrouter-gpt-6-astraPASS$0.023044 estimated2026-09-06T21:26:00.146Z
openrouter/qwen/qwen3.8-max-0902live-opencode-1.18.17-openrouter-qwen3.8-max-0902PASS$0.022126 estimated2026-09-06T21:27:22.407Z
openrouter/z-ai/glm-5.3live-opencode-1.18.17-openrouter-glm-5.3PASS$0.014280 estimated2026-09-06T21:25:26.881Z

Assertions

revision-history
semantic_operation
{
  "id": "revision-history",
  "kind": "semantic_operation",
  "minCalls": 1,
  "operationId": "list_document_revisions",
  "requireSuccess": true
}
terminal-completed
terminal
{
  "id": "terminal-completed",
  "kind": "terminal",
  "status": "completed"
}
transcript-complete
transcript_complete
{
  "id": "transcript-complete",
  "kind": "transcript_complete"
}
mock-only
network
{
  "id": "mock-only",
  "kind": "network",
  "realPaperclipRequests": 0
}
Full authored test definition
{
  "authority": {
    "actorId": "actor-engineer",
    "capabilities": [],
    "explicitClaims": [],
    "taskId": "task-orientation"
  },
  "checks": [
    {
      "id": "revision-history",
      "kind": "semantic_operation",
      "minCalls": 1,
      "operationId": "list_document_revisions",
      "requireSuccess": true
    },
    {
      "id": "terminal-completed",
      "kind": "terminal",
      "status": "completed"
    },
    {
      "id": "transcript-complete",
      "kind": "transcript_complete"
    },
    {
      "id": "mock-only",
      "kind": "network",
      "realPaperclipRequests": 0
    }
  ],
  "description": "The agent reads the bounded revision history for eval-notes.",
  "fixture": "../fixtures/companies/orientation.json",
  "id": "read-document-revisions",
  "prompt": "Inspect the revision history for the task document with key eval-notes and tell me how many revisions it currently has. Do not change state.",
  "schema": "paperclip-runner/eval-case/v1",
  "title": "Agent inspects document revision history"
}