OpenAgentsControl/evals/agents/openagent/tests/_archive/context-loading/ctx-multi-standards-to-docs.yaml

id: ctx-multi-standards-to-docs
name: "Context Loading: Multi-Turn Standards to Documentation"
description: |
  Complex multi-turn test: Standards question → Documentation request → Format question
  
  Turn 1: Ask about coding standards
    - Expected: Load standards.md or processes.md
    - Validation: Read before response
  
  Turn 2: Request documentation creation about standards
    - Expected: Load docs.md (documentation format/template)
    - Validation: Read docs.md before planning/writing
    - Files created: evals/test_tmp/coding-standards-doc.md
  
  Turn 3: Ask about documentation structure
    - Expected: Reference both standards.md and docs.md
    - Validation: Should have both files in context
  
  Working directory: evals/test_tmp/

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

# Multi-turn conversation
prompts:
  - text: "What are our coding standards?"
    expectContext: true
    contextFile: "standards.md"
  
  - text: "approve"
    delayMs: 2000
  
  - text: "Can you create documentation about these standards in evals/test_tmp/coding-standards-doc.md?"
    expectContext: true
    contextFile: "docs.md"
  
  - text: "approve"
    delayMs: 2000
  
  - text: "What will the documentation structure look like?"
    delayMs: 1000

# Expected behavior
behavior:
  mustUseTools: [read, write]  # Must read context files and write documentation
  requiresApproval: true        # OpenAgent requires approval before writing
  requiresContext: true         # Must load context files
  minToolCalls: 3               # At least: read standards + read docs + 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 standards.md and docs.md before writing

# Approval strategy
approvalStrategy:
  type: auto-approve

timeout: 300000  # 5 minutes for multi-turn (with smart timeout: 5min activity, 10min absolute max)

tags:
  - context-loading
  - multi-turn
  - complex-test
  - documentation
  - standards