paperclip-runner evalsstatic evidence

← Overview

Core task context needs no discovery

lazy-core-no-search

An always-present operation should not trigger optional capability search.

Prompt

Read your active task context and briefly tell me the task title. Do not search for optional capabilities.

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$0.031465 estimated2026-09-06T21:22:06.626Z
claude-sonnet-5live-claude-managed-agents-2026-04-01-sonnet-5PASS$0.003779 estimated2026-09-06T21:23:10.121Z
global.anthropic.claude-sonnet-4-6live-aws-agentcore-global-anthropic-claude-sonnet-4-6PASS$0.024582 estimated2026-09-06T21:21:52.674Z
gpt-5.4-minilive-codex-pinnedPASS$0.001576 estimated2026-09-06T21:24:07.409Z
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$0.016275 estimated2026-09-06T21:24:25.842Z
openrouter/deepseek/deepseek-v4-flash-0731live-opencode-1.18.17-openrouter-deepseek-v4-flash-0731PASS$0.000269 estimated2026-09-06T21:28:56.880Z
openrouter/google/gemini-3.8-flashlive-opencode-1.18.17-openrouter-gemini-3.8-flashPASS$0.023989 estimated2026-09-06T21:25:23.973Z
openrouter/openai/gpt-6-astralive-opencode-1.18.17-openrouter-gpt-6-astraPASS$0.021978 estimated2026-09-06T21:26:22.570Z
openrouter/qwen/qwen3.8-max-0902live-opencode-1.18.17-openrouter-qwen3.8-max-0902PASS$0.029910 estimated2026-09-06T21:27:29.697Z
openrouter/z-ai/glm-5.3live-opencode-1.18.17-openrouter-glm-5.3PASS$0.068628 estimated2026-09-06T21:25:40.862Z

Assertions

context
semantic_operation
{
  "id": "context",
  "kind": "semantic_operation",
  "minCalls": 1,
  "operationId": "get_task_context",
  "requireSuccess": true
}
no-discovery
evidence_match
{
  "count": {
    "max": 0
  },
  "evidenceKind": "tool_discovery",
  "id": "no-discovery",
  "kind": "evidence_match"
}
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": [],
    "explicitClaims": [],
    "taskId": "task-orientation"
  },
  "checks": [
    {
      "id": "context",
      "kind": "semantic_operation",
      "minCalls": 1,
      "operationId": "get_task_context",
      "requireSuccess": true
    },
    {
      "count": {
        "max": 0
      },
      "evidenceKind": "tool_discovery",
      "id": "no-discovery",
      "kind": "evidence_match"
    },
    {
      "id": "terminal-completed",
      "kind": "terminal",
      "status": "completed"
    },
    {
      "id": "mock-only",
      "kind": "network",
      "realPaperclipRequests": 0
    }
  ],
  "description": "An always-present operation should not trigger optional capability search.",
  "fixture": "../fixtures/companies/orientation.json",
  "id": "lazy-core-no-search",
  "prompt": "Read your active task context and briefly tell me the task title. Do not search for optional capabilities.",
  "schema": "paperclip-runner/eval-case/v1",
  "title": "Core task context needs no discovery",
  "toolExposure": "lazy"
}