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

id: ctx-multi-turn-001
name: Multi-Turn Context Loading
description: |
  Tests that context is loaded FRESH for each new task in a multi-turn conversation.
  
  Turn 1: Ask a question (conversational, no context needed)
  Turn 2: Request to create docs (should load docs.md context)
  
  This validates that the agent doesn't skip context loading on subsequent messages.
  
  Critical rule from openagent.md (Line 162-193):
  "Docs tasks → .opencode/context/core/standards/docs.md (MANDATORY)"

category: developer
agent: openagent

# Multi-turn conversation
prompts:
  - text: "What is the purpose of this project?"
    expectContext: false
    
  - text: "Create a CONTRIBUTING.md file with guidelines for contributors"
    expectContext: true
    contextFile: ".opencode/context/core/standards/docs.md"
    delayMs: 2000

# Expected behavior
behavior:
  mustUseTools: [read, write]  # Must read context, then write docs
  requiresApproval: true
  requiresContext: true         # MUST load docs.md before writing
  minToolCalls: 2               # At least: read context + write file

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

# Approval strategy
approvalStrategy:
  type: auto-approve

timeout: 90000

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