Agent orients itself with task context

get-task-context

Given a full mock company, the runner should call get_task_context before answering an implicit orientation prompt.

Prompt

Please orient yourself to your assigned task and tell me what you should work on next.

Fixture

../fixtures/companies/orientation.json

Authority

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

Current results

Model	Configuration	Result	Estimated cost	Run time
global.anthropic.claude-sonnet-4-6	live-aws-agentcore-global-anthropic-claude-sonnet-4-6	FAIL	$0.000000 estimated	2026-09-06T17:23:47.132Z

Assertions

context-call

semantic_operation

{
  "id": "context-call",
  "kind": "semantic_operation",
  "minCalls": 1,
  "operationId": "get_task_context",
  "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": "context-call",
      "kind": "semantic_operation",
      "minCalls": 1,
      "operationId": "get_task_context",
      "requireSuccess": true
    },
    {
      "id": "terminal-completed",
      "kind": "terminal",
      "status": "completed"
    },
    {
      "id": "transcript-complete",
      "kind": "transcript_complete"
    },
    {
      "id": "mock-only",
      "kind": "network",
      "realPaperclipRequests": 0
    }
  ],
  "description": "Given a full mock company, the runner should call get_task_context before answering an implicit orientation prompt.",
  "fixture": "../fixtures/companies/orientation.json",
  "id": "get-task-context",
  "prompt": "Please orient yourself to your assigned task and tell me what you should work on next.",
  "schema": "paperclip-runner/eval-case/v1",
  "title": "Agent orients itself with task context"
}