- 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
46 lines
1.2 KiB
JSON
46 lines
1.2 KiB
JSON
{
|
|
"name": "@opencode-agents/eval-framework",
|
|
"version": "0.1.0",
|
|
"type": "module",
|
|
"description": "Evaluation framework for OpenCode agents",
|
|
"main": "dist/index.js",
|
|
"types": "dist/index.d.ts",
|
|
"scripts": {
|
|
"build": "tsc",
|
|
"build:watch": "tsc --watch",
|
|
"test": "vitest",
|
|
"test:watch": "vitest --watch",
|
|
"test:integration": "vitest --config vitest.integration.config.ts",
|
|
"lint": "eslint src/**/*.ts",
|
|
"lint:fix": "eslint src/**/*.ts --fix",
|
|
"eval": "node dist/cli.js",
|
|
"report": "node dist/cli.js report",
|
|
"eval:sdk": "tsx src/sdk/run-sdk-tests.ts",
|
|
"eval:sdk:debug": "tsx src/sdk/run-sdk-tests.ts --debug",
|
|
"eval:sdk:interactive": "tsx src/sdk/run-sdk-tests.ts --interactive"
|
|
},
|
|
"keywords": [
|
|
"opencode",
|
|
"evaluation",
|
|
"testing",
|
|
"agents",
|
|
"ai"
|
|
],
|
|
"author": "",
|
|
"license": "MIT",
|
|
"dependencies": {
|
|
"@opencode-ai/sdk": "^1.0.90",
|
|
"yaml": "^2.3.4",
|
|
"zod": "^3.25.76"
|
|
},
|
|
"devDependencies": {
|
|
"@types/glob": "^8.1.0",
|
|
"@types/node": "^20.10.0",
|
|
"@typescript-eslint/eslint-plugin": "^6.13.0",
|
|
"@typescript-eslint/parser": "^6.13.0",
|
|
"eslint": "^8.54.0",
|
|
"tsx": "^4.20.6",
|
|
"typescript": "^5.3.0",
|
|
"vitest": "^1.0.0"
|
|
}
|
|
}
|