paperclip-runner evalsstatic evidence

← Overview

Agent sets task dependencies

set-task-dependencies

The active task receives the requested first-class blocker set.

Prompt

Replace this task's dependencies so that task-fixtures is its only blocker.

Fixture

../fixtures/companies/orientation.json

Authority

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

Current results

ModelConfigurationResultEstimated costRun time
claude-sonnet-5live-acpx-0.13.1-claude-acp-0.70.0-sonnet-5PASS$0.075747 estimated2026-09-06T21:22:12.434Z
claude-sonnet-5live-claude-managed-agents-2026-04-01-sonnet-5PASS$0.015605 estimated2026-09-06T21:22:11.366Z
global.anthropic.claude-sonnet-4-6live-aws-agentcore-global-anthropic-claude-sonnet-4-6PASS$0.039480 estimated2026-09-06T21:22:24.042Z
gpt-5.4-minilive-codex-pinnedPASS$0.004286 estimated2026-09-06T21:24:03.225Z
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$0.044684 estimated2026-09-06T21:24:22.648Z
openrouter/deepseek/deepseek-v4-flash-0731live-opencode-1.18.17-openrouter-deepseek-v4-flash-0731PASS$0.001850 estimated2026-09-06T21:28:49.807Z
openrouter/google/gemini-3.8-flashlive-opencode-1.18.17-openrouter-gemini-3.8-flashPASS$0.013818 estimated2026-09-06T21:24:55.750Z
openrouter/openai/gpt-6-astralive-opencode-1.18.17-openrouter-gpt-6-astraPASS$0.029407 estimated2026-09-06T21:26:14.504Z
openrouter/qwen/qwen3.8-max-0902live-opencode-1.18.17-openrouter-qwen3.8-max-0902PASS$0.012416 estimated2026-09-06T21:27:22.201Z
openrouter/z-ai/glm-5.3live-opencode-1.18.17-openrouter-glm-5.3PASS$0.019250 estimated2026-09-06T21:28:41.680Z

Assertions

set-dependencies
semantic_operation
{
  "id": "set-dependencies",
  "kind": "semantic_operation",
  "maxCalls": 1,
  "minCalls": 1,
  "operationId": "set_dependencies",
  "requireSuccess": true
}
blocker-state
state_match
{
  "collection": "blockers",
  "id": "blocker-state",
  "kind": "state_match",
  "where": {
    ".": {
      "matches": "task-fixtures"
    }
  }
}
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": [
      "dependencies:write"
    ],
    "explicitClaims": [
      "dependencies:write"
    ],
    "taskId": "task-orientation"
  },
  "checks": [
    {
      "id": "set-dependencies",
      "kind": "semantic_operation",
      "maxCalls": 1,
      "minCalls": 1,
      "operationId": "set_dependencies",
      "requireSuccess": true
    },
    {
      "collection": "blockers",
      "id": "blocker-state",
      "kind": "state_match",
      "where": {
        ".": {
          "matches": "task-fixtures"
        }
      }
    },
    {
      "id": "terminal-completed",
      "kind": "terminal",
      "status": "completed"
    },
    {
      "id": "mock-only",
      "kind": "network",
      "realPaperclipRequests": 0
    }
  ],
  "description": "The active task receives the requested first-class blocker set.",
  "fixture": "../fixtures/companies/orientation.json",
  "id": "set-task-dependencies",
  "prompt": "Replace this task's dependencies so that task-fixtures is its only blocker.",
  "schema": "paperclip-runner/eval-case/v1",
  "title": "Agent sets task dependencies"
}