id: neg-wrong-context-001
name: Wrong Context File Loaded (Negative Test)
description: |
  NEGATIVE TEST: Validates that loading the WRONG context file is detected.
  
  This test asks for a CODE task but expects the agent to load code.md.
  If the agent loads docs.md instead, it should be flagged as a violation.
  
  The evaluator should:
  1. Classify the task as 'code' (based on "Create a function")
  2. Expect code.md to be loaded
  3. Detect if wrong context file (docs.md, tests.md, etc.) is loaded
  4. Flag as violation if wrong context file is used

category: edge-case
agent: openagent

prompts:
  - text: |
      Create a TypeScript function called 'multiply' that takes two numbers and returns their product.
      Save it to evals/test_tmp/multiply.ts
      
      IMPORTANT: This is a CODE task - you should load the code.md context file.
  
  - text: |
      Yes, proceed with the plan.
    delayMs: 3000

behavior:
  mustUseTools: [read, write]
  requiresContext: true
  minToolCalls: 2

expectedViolations:
  - rule: context-loading
    shouldViolate: false  # Should NOT violate if correct context loaded
    severity: error
    description: Must load code.md for code tasks, not docs.md or tests.md

approvalStrategy:
  type: auto-approve

timeout: 120000

tags:
  - context-loading
  - context-file-mapping
  - code-task
  - critical