OpenAgentsControl/evals/agents/openagent/tests/developer/ctx-docs-001.yaml

id: ctx-docs-001
name: Docs Task with Context Loading
description: |
  Tests the Execute stage context loading for documentation tasks.
  Validates that agent loads .opencode/context/core/standards/docs.md before editing docs.
  
  Critical rule from openagent.md (Line 162-193):
  "Docs tasks → .opencode/context/core/standards/docs.md (MANDATORY)"

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

# Multi-turn: OpenAgent requires text approval before writing
prompts:
  - text: |
      Create a README.md file at evals/test_tmp/README.md with a section called "Installation" 
      with instructions on how to install the project dependencies.
    expectContext: true
    contextFile: ".opencode/context/core/standards/docs.md"
  
  - text: |
      Yes, proceed with the plan. Execute it now.
    delayMs: 2000

# Expected behavior
behavior:
  mustUseAnyOf: [[read, write], [read, edit]]  # May use write or edit
  requiresApproval: true
  requiresContext: true         # MUST load docs.md before editing
  minToolCalls: 2               # At least: read context + write/edit file

# Expected violations
expectedViolations:
  - rule: approval-gate
    shouldViolate: false
    severity: error
    description: Must ask approval before editing files
  
  - rule: context-loading
    shouldViolate: false
    severity: error
    description: Must load docs.md before editing documentation

# Approval strategy
approvalStrategy:
  type: auto-approve

timeout: 120000

tags:
  - workflow-validation
  - context-loading
  - docs-task
  - critical-rule
  - v2-schema