478c8e3e85
- Replace planned framework with working SDK implementation using @opencode-ai/sdk - Add 6 YAML test cases across developer/business/edge-case categories (100% passing) - Implement 4 evaluators for openagent.md rule compliance (approval-gate, context-loading, delegation, tool-usage) - Add real-time event streaming and session recording - Configure opencode/grok-code-fast as default model (zero API costs) - Add comprehensive documentation (SDK_EVAL_README.md, test-design-guide.md, TEST_SCENARIOS.md) - Support v2 schema with behavior-based expectations instead of message counts - Enable model-agnostic test design that works across Claude, GPT-4, and Grok - Add subagent invocation syntax documentation to openagent.md
35 lines
1,018 B
JSON
35 lines
1,018 B
JSON
{
|
|
"$schema": "https://json-schema.org/draft-07/schema",
|
|
"description": "Configuration for OpenCode evaluation framework",
|
|
"defaultModel": "opencode/grok-code-fast",
|
|
"defaultTimeout": 60000,
|
|
"runEvaluators": true,
|
|
"availableModels": {
|
|
"free": [
|
|
{
|
|
"id": "opencode/grok-code-fast",
|
|
"name": "Grok Code Fast",
|
|
"description": "Free tier model from OpenCode Zen",
|
|
"cost": "$0.00",
|
|
"recommended": true
|
|
}
|
|
],
|
|
"paid": [
|
|
{
|
|
"id": "anthropic/claude-3-5-sonnet-20241022",
|
|
"name": "Claude 3.5 Sonnet",
|
|
"description": "High-quality model for complex tasks"
|
|
},
|
|
{
|
|
"id": "openai/gpt-4-turbo",
|
|
"name": "GPT-4 Turbo",
|
|
"description": "OpenAI's most capable model"
|
|
}
|
|
]
|
|
},
|
|
"notes": [
|
|
"Use opencode/grok-code-fast for development to avoid API costs",
|
|
"Switch to paid models for production evaluation",
|
|
"Test cases can override the default model using the 'model' field"
|
|
]
|
|
}
|