tractatus/package.json
TheFlow 2ddae65b18 feat: Phase 5 Memory Tool PoC - Week 1 Complete
Week 1 Objectives (All Met):
- API research and capabilities assessment 
- Comprehensive findings document 
- Basic persistence PoC implementation 
- Anthropic integration test framework 
- Governance rules testing (inst_001, inst_016, inst_017) 

Key Achievements:
- Updated @anthropic-ai/sdk: 0.9.1 → 0.65.0 (memory tool support)
- Built FilesystemMemoryBackend (create, view, exists operations)
- Validated 100% persistence and data integrity
- Performance: 1ms overhead (filesystem) - exceeds <500ms target
- Simulation mode: Test workflow without API costs

Deliverables:
- docs/research/phase-5-memory-tool-poc-findings.md (42KB API assessment)
- docs/research/phase-5-week-1-implementation-log.md (comprehensive log)
- tests/poc/memory-tool/basic-persistence-test.js (291 lines)
- tests/poc/memory-tool/anthropic-memory-integration-test.js (390 lines)

Test Results:
 Basic Persistence: 100% success (1ms latency)
 Governance Rules: 3 rules tested successfully
 Data Integrity: 100% validation
 Memory Structure: governance/, sessions/, audit/ directories

Next Steps (Week 2):
- Context editing experimentation (50+ turn conversations)
- Real API integration with CLAUDE_API_KEY
- Multi-rule storage (all 18 Tractatus rules)
- Performance measurement vs. baseline

Research Status: Week 1 of 3 complete, GREEN LIGHT for Week 2

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-10 12:03:39 +13:00

74 lines
2.4 KiB
JSON

{
"name": "tractatus-website",
"version": "0.1.0",
"description": "Tractatus-Based LLM Safety Framework website platform",
"main": "src/server.js",
"scripts": {
"start": "node src/server.js",
"dev": "concurrently -n \"SERVER,WATCHDOG\" -c \"cyan,magenta\" \"nodemon src/server.js\" \"node scripts/framework-watchdog.js\"",
"dev:simple": "nodemon src/server.js",
"build:css": "npx tailwindcss -i ./public/css/src/tailwind.css -o ./public/css/tailwind.css --minify",
"watch:css": "npx tailwindcss -i ./public/css/src/tailwind.css -o ./public/css/tailwind.css --watch",
"test": "jest --coverage",
"test:watch": "jest --watch",
"test:unit": "jest tests/unit",
"test:integration": "jest tests/integration",
"test:security": "jest tests/security",
"lint": "eslint src/ tests/",
"lint:fix": "eslint src/ tests/ --fix",
"migrate:docs": "node scripts/migrate-documents.js",
"init:db": "node scripts/init-db.js",
"init:koha": "node scripts/init-koha.js",
"seed:admin": "node scripts/seed-admin.js",
"generate:pdfs": "node scripts/generate-pdfs.js",
"deploy": "bash scripts/deploy-frontend.sh",
"framework:init": "node scripts/session-init.js",
"framework:watchdog": "node scripts/framework-watchdog.js",
"framework:check": "node scripts/pre-action-check.js",
"framework:recover": "node scripts/recover-framework.js"
},
"keywords": [
"ai-safety",
"llm",
"tractatus",
"digital-sovereignty",
"ai-governance"
],
"author": "John Stroh <john.stroh.nz@pm.me>",
"license": "Apache-2.0",
"dependencies": {
"bcrypt": "^5.1.1",
"cors": "^2.8.5",
"dotenv": "^16.3.1",
"express": "^4.18.2",
"express-rate-limit": "^7.1.5",
"helmet": "^7.1.0",
"highlight.js": "^11.9.0",
"jsonwebtoken": "^9.0.2",
"marked": "^11.0.0",
"mongodb": "^6.3.0",
"puppeteer": "^24.23.0",
"sanitize-html": "^2.11.0",
"stripe": "^14.25.0",
"validator": "^13.11.0",
"winston": "^3.11.0"
},
"devDependencies": {
"@anthropic-ai/sdk": "^0.65.0",
"autoprefixer": "^10.4.21",
"axe-core": "^4.10.3",
"concurrently": "^9.2.1",
"eslint": "^8.56.0",
"jest": "^29.7.0",
"nodemon": "^3.0.2",
"pa11y": "^9.0.1",
"pa11y-reporter-html": "^2.0.0",
"postcss": "^8.5.6",
"supertest": "^6.3.3",
"tailwindcss": "^3.4.18"
},
"engines": {
"node": ">=18.0.0",
"npm": ">=9.0.0"
}
}