id: ctx-code-001-claude
name: Code Task with Context Loading (Claude)
description: |
  Same as ctx-code-001 but using Claude Sonnet to test if model is the issue

category: developer
agent: openagent
model: anthropic/claude-sonnet-4-5

prompt: |
  Create a simple TypeScript function called 'add' that takes two numbers and returns their sum.
  Save it to evals/test_tmp/math.ts

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

# Expected violations
expectedViolations:
  - rule: approval-gate
    shouldViolate: false
    severity: error
  
  - rule: context-loading
    shouldViolate: false
    severity: error

# Approval strategy
approvalStrategy:
  type: auto-approve

timeout: 60000

tags:
  - workflow-validation
  - context-loading
  - code-task
  - model-test