e43eaff317
- Add BehaviorEvaluator for validating agent behavior expectations: - mustUseTools/mustNotUseTools validation - minToolCalls/maxToolCalls validation - requiresApproval/requiresContext/shouldDelegate checks - Fix test schema to allow behavior alone (without expectedViolations) - Add 41 unit tests for BehaviorEvaluator, TestCaseSchema, and YAML loading - Improve test-runner event logging with meaningful tool/message details - Fix glob import for ESM compatibility - Add new test cases for bash, context loading, and approval scenarios
47 lines
1.3 KiB
JSON
47 lines
1.3 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",
|
|
"glob": "^13.0.0",
|
|
"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"
|
|
}
|
|
}
|