Core fix: For cases with expectedBehaviours, reasoningQuality.status is now set exclusively from behaviour evaluation results (required behaviour pass/fail). Legacy concept checks remain visible as diagnostic-only metrics and do not influence the authoritative result. Key changes: - Behaviour-based scoring determines reasoning status (passed/failed) instead of legacy concept literal matching - Schema failure correctly forces not_evaluated (no vacuous truth) - Saved live results re-evaluator preserves provenance metadata - Classification tolerance map works bidirectionally for interchangeable types - normalise() treats underscores as word characters, hyphens as spaces Tests: 74 passing across both evaluator test suites - tests/evaluator-behaviour-authoritative.test.mjs (47 tests, new) - tests/evaluator-semantic.test.mjs (27 tests)
38 lines
1.1 KiB
JSON
38 lines
1.1 KiB
JSON
{
|
|
"type": "module",
|
|
"name": "confidence-engine",
|
|
"version": "0.2.0-experimental",
|
|
"private": true,
|
|
"description": "Experimental prototype for evidence-based situation reconstruction using local LLMs",
|
|
"scripts": {
|
|
"dev": "next dev",
|
|
"build": "next build",
|
|
"start": "next start",
|
|
"lint": "next lint",
|
|
"test": "vitest run",
|
|
"test:watch": "vitest",
|
|
"evaluate": "node tests/evaluator.mjs",
|
|
"evaluate:mock": "EVAL_REAL=0 node tests/evaluator.mjs",
|
|
"evaluate:diagnostic": "EVAL_DIAGNOSTIC=1 EVAL_REAL=0 node tests/evaluator.mjs",
|
|
"evaluate:live": "EVAL_REAL=1 node tests/evaluator.mjs",
|
|
"evaluate:saved": "node tests/evaluator.mjs"
|
|
},
|
|
"dependencies": {
|
|
"next": "^14.2.0",
|
|
"react": "^18.3.0",
|
|
"react-dom": "^18.3.0",
|
|
"zod": "^3.23.0"
|
|
},
|
|
"devDependencies": {
|
|
"@types/node": "^20.14.0",
|
|
"@types/react": "^18.3.0",
|
|
"@types/react-dom": "^18.3.0",
|
|
"autoprefixer": "^10.4.0",
|
|
"eslint": "^8.57.0",
|
|
"eslint-config-next": "^14.2.0",
|
|
"postcss": "^8.4.0",
|
|
"tailwindcss": "^3.4.0",
|
|
"vitest": "^2.0.0"
|
|
}
|
|
}
|