soulcraft/brainy
1
0
Fork 0
Code Issues 1 Pull requests Projects Releases 335 Packages Wiki Activity Actions

refactor(8.0): remove dead, unreachable, and unwired modules

Browse source 
Pre-GA dead-code sweep. A deterministic import-reachability walk from the
package's real entry points (the exports map, the CLI bin, the conversation
surface) found 34 source modules that nothing reachable imports — they
compile and ship as dist output that no consumer or internal path can ever
reach. All were superseded duplicates, abandoned parallel implementations,
or built-but-never-wired features:

  - superseded duplicates of live modules: an older "unified" entry, a
    standalone neural-import variant, a static NLP processor + its matcher,
    a parallel API-types module, a duplicate progress-types module
  - an abandoned import path (orchestrator + entity deduplicator + barrels)
    left behind when ingestion moved to the coordinator
  - unwired feature modules (instance pool, import presets, cached
    embeddings, relationship-confidence scorer) reachable only from tests
  - dead leaf utilities (write buffer, deleted-items index, bounded
    registry, two crypto shims, a cache manager, a structured logger, a
    stale v5 type-migration helper, a browser-only FS type shim) and
    several dead re-export barrels
  - a CLI catalog command wired into no command

Also removed two tests that only exercised deleted modules, repointed two
VFS tests off a deleted barrel onto the implementation module, and deleted
one example that demoed removed features.

Verified: clean build (both tsc passes), unit 1505 + integration 607 green,
and a re-run of the reachability walk reports zero remaining orphans.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
David Snelling 2026-06-24 15:18:40 -07:00
parent 03d654061f
commit bf0afe8563
39 changed files with 2 additions and 10497 deletions
Download patch file Download diff file Expand all files Collapse all files

440
src/cli/catalog.ts
View file

@ -1,440 +0,0 @@
/**
* Augmentation Catalog for CLI
*
* Displays available augmentations catalog
* Local catalog with caching support
*/
import chalk from 'chalk'
import { readFileSync, writeFileSync, existsSync, mkdirSync } from 'node:fs'
import { join } from 'node:path'
import { homedir } from 'node:os'
const CATALOG_API = process.env.BRAINY_CATALOG_URL || null
const CACHE_PATH = join(homedir(), '.brainy', 'catalog-cache.json')
const CACHE_TTL = 24 * 60 * 60 * 1000 // 24 hours
interface Augmentation {
id: string
name: string
description: string
category: string
status: 'available' | 'coming_soon' | 'deprecated'
popular?: boolean
eta?: string
}
interface Category {
id: string
name: string
icon: string
description: string
}
interface Catalog {
version: string
categories: Category[]
augmentations: Augmentation[]
}
/**
* Fetch catalog from API with caching
*/
export async function fetchCatalog(): Promise<Catalog | null> {
try {
// Check cache first
const cached = loadCache()
if (cached) return cached
// If external catalog API is configured, try to fetch
if (CATALOG_API) {
const response = await fetch(`${CATALOG_API}/api/catalog/cli`)
if (!response.ok) throw new Error('API unavailable')
const catalog = await response.json()
// Save to cache
saveCache(catalog)
return catalog
}
// Fall back to local catalog
return getDefaultCatalog()
} catch (error) {
// Try loading from cache even if expired
const cached = loadCache(true)
if (cached) {
console.log(chalk.yellow('📡 Using cached catalog'))
return cached
}
// Fall back to hardcoded catalog
return getDefaultCatalog()
}
}
/**
* Display catalog in CLI
*/
export async function showCatalog(options: {
category?: string
search?: string
detailed?: boolean
}) {
const catalog = await fetchCatalog()
if (!catalog) {
console.log(chalk.red('❌ Could not load augmentation catalog'))
return
}
console.log(chalk.cyan.bold('🧠 Brainy Augmentation Catalog'))
console.log(chalk.gray(`Version ${catalog.version}`))
console.log('')
// Filter augmentations
let augmentations = catalog.augmentations
if (options.category) {
augmentations = augmentations.filter(a => a.category === options.category)
}
if (options.search) {
const query = options.search.toLowerCase()
augmentations = augmentations.filter(a =>
a.name.toLowerCase().includes(query) ||
a.description.toLowerCase().includes(query)
)
}
// Group by category
const grouped = groupByCategory(augmentations, catalog.categories)
// Display
for (const [category, augs] of Object.entries(grouped)) {
if (augs.length === 0) continue
const cat = catalog.categories.find(c => c.id === category)
console.log(chalk.bold(`${cat?.icon || '📦'} ${cat?.name || category}`))
for (const aug of augs) {
const status = getStatusIcon(aug.status)
const popular = aug.popular ? chalk.yellow(' ⭐') : ''
const eta = aug.eta ? chalk.gray(` (${aug.eta})`) : ''
console.log(` ${status} ${aug.name}${popular}${eta}`)
if (options.detailed) {
console.log(chalk.gray(` ${aug.description}`))
}
}
console.log('')
}
// Show summary
const available = augmentations.filter(a => a.status === 'available').length
const coming = augmentations.filter(a => a.status === 'coming_soon').length
console.log(chalk.gray('─'.repeat(50)))
console.log(chalk.green(`✅ ${available} available`) + chalk.gray(` • `) +
chalk.yellow(`🔜 ${coming} coming soon`))
console.log('')
console.log(chalk.dim('Configure augmentations with "brainy augment"'))
console.log(chalk.dim('Run "brainy augment info <name>" for details'))
}
/**
* Show detailed info about an augmentation
*/
export async function showAugmentationInfo(id: string) {
const catalog = await fetchCatalog()
if (!catalog) {
console.log(chalk.red('❌ Could not load augmentation catalog'))
return
}
const aug = catalog.augmentations.find(a => a.id === id)
if (!aug) {
console.log(chalk.red(`❌ Augmentation not found: ${id}`))
console.log('')
console.log('Available augmentations:')
catalog.augmentations.forEach(a => {
console.log(` • ${a.id}`)
})
return
}
// Fetch full details from API if available
try {
if (!CATALOG_API) throw new Error('No external catalog configured')
const response = await fetch(`${CATALOG_API}/api/catalog/augmentation/${id}`)
const details = await response.json()
console.log(chalk.cyan.bold(`📦 ${details.name}`))
if (details.popular) console.log(chalk.yellow('⭐ Popular'))
console.log('')
console.log(chalk.bold('Category:'), getCategoryName(details.category, catalog.categories))
console.log(chalk.bold('Status:'), getStatusText(details.status))
if (details.eta) console.log(chalk.bold('Expected:'), details.eta)
console.log('')
console.log(chalk.bold('Description:'))
console.log(details.longDescription || details.description)
console.log('')
if (details.features) {
console.log(chalk.bold('Features:'))
details.features.forEach((f: string) => console.log(` ✓ ${f}`))
console.log('')
}
if (details.example) {
console.log(chalk.bold('Example:'))
console.log(chalk.gray('─'.repeat(50)))
console.log(details.example.code)
console.log(chalk.gray('─'.repeat(50)))
console.log('')
}
if (details.requirements?.config) {
console.log(chalk.bold('Required Configuration:'))
details.requirements.config.forEach((c: string) => console.log(` • ${c}`))
console.log('')
}
if (details.pricing) {
console.log(chalk.bold('Available in:'))
details.pricing.tiers.forEach((t: string) => console.log(` • ${t}`))
console.log('')
}
console.log(chalk.dim('To activate: brainy augment activate'))
} catch (error) {
// Show basic info if API fails
console.log(chalk.cyan.bold(`📦 ${aug.name}`))
console.log(aug.description)
console.log('')
console.log(chalk.dim('Full details unavailable (no external catalog configured)'))
}
}
/**
* Show user's available augmentations
*/
export async function showAvailable(licenseKey?: string) {
// Show local catalog as default
const catalog = await fetchCatalog()
if (!catalog) {
console.log(chalk.red('❌ Could not load augmentation catalog'))
return
}
console.log(chalk.cyan.bold('🧠 Available Augmentations'))
console.log('')
const available = catalog.augmentations.filter(a => a.status === 'available')
const grouped = groupByCategory(available, catalog.categories)
for (const [category, augs] of Object.entries(grouped)) {
if (augs.length === 0) continue
const cat = catalog.categories.find(c => c.id === category)
console.log(chalk.bold(`${cat?.icon || '📦'} ${cat?.name || category}`))
augs.forEach(aug => {
console.log(` ✅ ${aug.name}`)
console.log(chalk.gray(` ${aug.description}`))
})
console.log('')
}
console.log(chalk.green(`✅ ${available.length} augmentations available`))
// If external API is configured and license key provided, try to fetch personalized data
if (CATALOG_API && licenseKey) {
try {
const response = await fetch(`${CATALOG_API}/api/catalog/available`, {
headers: { 'x-license-key': licenseKey }
})
if (response.ok) {
const data = await response.json()
console.log(chalk.gray(`Plan: ${data.plan || 'Standard'}`))
if (data.operations) {
const used = data.operations.used || 0
const limit = data.operations.limit
const percent = limit === 'unlimited' ? 0 : Math.round((used / limit) * 100)
console.log(chalk.bold('Usage:'))
if (limit === 'unlimited') {
console.log(` Unlimited operations`)
} else {
console.log(` ${used.toLocaleString()} / ${limit.toLocaleString()} operations (${percent}%)`)
}
}
}
} catch (error) {
// Ignore external API errors - local catalog is sufficient
}
}
}
// Helper functions
function loadCache(ignoreExpiry = false): Catalog | null {
try {
if (!existsSync(CACHE_PATH)) return null
const data = JSON.parse(readFileSync(CACHE_PATH, 'utf8'))
if (!ignoreExpiry && Date.now() - data.timestamp > CACHE_TTL) {
return null
}
return data.catalog
} catch {
return null
}
}
function saveCache(catalog: Catalog): void {
try {
const dir = join(homedir(), '.brainy')
if (!existsSync(dir)) {
mkdirSync(dir, { recursive: true })
}
writeFileSync(CACHE_PATH, JSON.stringify({
catalog,
timestamp: Date.now()
}))
} catch {
// Ignore cache save errors
}
}
function groupByCategory(augmentations: Augmentation[], categories: Category[]) {
const grouped: Record<string, Augmentation[]> = {}
for (const aug of augmentations) {
if (!grouped[aug.category]) {
grouped[aug.category] = []
}
grouped[aug.category].push(aug)
}
// Sort by category order
const ordered: Record<string, Augmentation[]> = {}
const categoryOrder = ['memory', 'coordination', 'enterprise', 'perception', 'dialog', 'activation', 'cognition', 'websocket']
for (const cat of categoryOrder) {
if (grouped[cat]) {
ordered[cat] = grouped[cat]
}
}
return ordered
}
function getStatusIcon(status: string): string {
switch (status) {
case 'available': return chalk.green('✅')
case 'coming_soon': return chalk.yellow('🔜')
case 'deprecated': return chalk.red('⚠️')
default: return '❓'
}
}
function getStatusText(status: string): string {
switch (status) {
case 'available': return chalk.green('Available')
case 'coming_soon': return chalk.yellow('Coming Soon')
case 'deprecated': return chalk.red('Deprecated')
default: return 'Unknown'
}
}
function getCategoryName(categoryId: string, categories: Category[]): string {
const cat = categories.find(c => c.id === categoryId)
return cat ? `${cat.icon} ${cat.name}` : categoryId
}
function readLicenseFile(): string | null {
try {
const licensePath = join(homedir(), '.brainy', 'license')
if (existsSync(licensePath)) {
return readFileSync(licensePath, 'utf8').trim()
}
} catch (error) {
// License file read failed, return null
console.debug('Failed to read license file:', error)
}
return null
}
function getDefaultCatalog(): Catalog {
// Local catalog with current features
return {
version: '1.5.0',
categories: [
{ id: 'core', name: 'Core Features', icon: '🧠', description: 'Essential brainy functionality' },
{ id: 'neural', name: 'Neural API', icon: '🔗', description: 'Semantic similarity and clustering' },
{ id: 'enterprise', name: 'Enterprise', icon: '🏢', description: 'Business integrations' },
{ id: 'storage', name: 'Storage', icon: '💾', description: 'Data persistence and caching' }
],
augmentations: [
{
id: 'vector-search',
name: 'Vector Search',
category: 'core',
description: 'High-performance semantic search with HNSW indexing',
status: 'available',
popular: true
},
{
id: 'neural-similarity',
name: 'Neural Similarity API',
category: 'neural',
description: 'Advanced semantic similarity, clustering, and hierarchy detection',
status: 'available',
popular: true
},
{
id: 'intelligent-verb-scoring',
name: 'Intelligent Verb Scoring',
category: 'neural',
description: 'Smart relationship scoring with taxonomy understanding',
status: 'available'
},
{
id: 'connection-pooling',
name: 'Connection Pooling',
category: 'enterprise',
description: 'Efficient database connection management',
status: 'available'
},
{
id: 'batch-processing',
name: 'Batch Processing',
category: 'enterprise',
description: 'High-throughput batch operations with deduplication',
status: 'available'
},
{
id: 's3-storage',
name: 'S3 Compatible Storage',
category: 'storage',
description: 'Cloud storage with optimized batch operations',
status: 'available'
},
{
id: 'opfs-storage',
name: 'OPFS Storage',
category: 'storage',
description: 'Browser-based persistent storage',
status: 'available'
}
]
}
}

163
src/embeddings/CachedEmbeddings.ts
View file

@ -1,163 +0,0 @@
/**
* Cached Embeddings - Performance Optimization Layer
*
* Provides pre-computed embeddings for common terms to avoid
* unnecessary model calls. Falls back to EmbeddingManager for
* unknown terms.
*
* This is purely a performance optimization - it doesn't affect
* the consistency or accuracy of embeddings.
*/
import { Vector } from '../coreTypes.js'
import { embeddingManager } from './EmbeddingManager.js'
// Pre-computed embeddings for top common terms
// In production, this could be loaded from a file or expanded significantly
const PRECOMPUTED_EMBEDDINGS: Record<string, Vector> = {
// Programming languages
'javascript': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.1)),
'python': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.1)),
'typescript': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.15)),
'java': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.15)),
'rust': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.2)),
'go': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.2)),
'c++': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.22)),
'c#': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.22)),
// Web frameworks
'react': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.25)),
'vue': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.25)),
'angular': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.3)),
'svelte': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.3)),
'nextjs': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.32)),
'nuxt': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.32)),
// Databases
'postgresql': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.35)),
'mysql': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.35)),
'mongodb': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.4)),
'redis': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.4)),
'elasticsearch': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.42)),
// Common tech terms
'database': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.45)),
'api': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.45)),
'server': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.5)),
'client': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.5)),
'frontend': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.55)),
'backend': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.55)),
'fullstack': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.57)),
'devops': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.57)),
'cloud': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.6)),
'docker': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.6)),
'kubernetes': new Array(384).fill(0).map((_, i) => Math.sin(i * 0.62)),
'microservices': new Array(384).fill(0).map((_, i) => Math.cos(i * 0.62)),
}
/**
* Simple character n-gram based embedding for short text
* This is much faster than using the model for simple terms
*/
function computeSimpleEmbedding(text: string): Vector {
const normalized = text.toLowerCase().trim()
const vector = new Array(384).fill(0)
// Character trigrams for simple semantic similarity
for (let i = 0; i < normalized.length - 2; i++) {
const trigram = normalized.slice(i, i + 3)
const hash = trigram.charCodeAt(0) * 31 +
trigram.charCodeAt(1) * 7 +
trigram.charCodeAt(2)
const index = Math.abs(hash) % 384
vector[index] += 1 / (normalized.length - 2)
}
// Normalize vector
const magnitude = Math.sqrt(vector.reduce((sum, val) => sum + val * val, 0))
if (magnitude > 0) {
for (let i = 0; i < vector.length; i++) {
vector[i] /= magnitude
}
}
return vector
}
/**
* Cached Embeddings with fallback to EmbeddingManager
*/
export class CachedEmbeddings {
private stats = {
cacheHits: 0,
simpleComputes: 0,
modelCalls: 0
}
/**
* Generate embedding with caching
*/
async embed(text: string | string[]): Promise<Vector | Vector[]> {
if (Array.isArray(text)) {
return Promise.all(text.map(t => this.embedSingle(t)))
}
return this.embedSingle(text)
}
/**
* Embed single text with cache lookup
*/
private async embedSingle(text: string): Promise<Vector> {
const normalized = text.toLowerCase().trim()
// 1. Check pre-computed cache (instant, zero cost)
if (PRECOMPUTED_EMBEDDINGS[normalized]) {
this.stats.cacheHits++
return PRECOMPUTED_EMBEDDINGS[normalized]
}
// 2. Check for partial matches in cache
for (const [term, embedding] of Object.entries(PRECOMPUTED_EMBEDDINGS)) {
if (normalized.includes(term) || term.includes(normalized)) {
this.stats.cacheHits++
// Return slightly modified version to maintain uniqueness
return embedding.map(v => v * 0.95)
}
}
// 3. For short text, use simple embedding (fast, low cost)
if (normalized.length < 50 && normalized.split(' ').length < 5) {
this.stats.simpleComputes++
return computeSimpleEmbedding(normalized)
}
// 4. Fall back to EmbeddingManager for complex text
this.stats.modelCalls++
return await embeddingManager.embed(text)
}
/**
* Get cache statistics
*/
getStats() {
return {
...this.stats,
totalEmbeddings: this.stats.cacheHits + this.stats.simpleComputes + this.stats.modelCalls,
cacheHitRate: this.stats.cacheHits /
(this.stats.cacheHits + this.stats.simpleComputes + this.stats.modelCalls) || 0
}
}
/**
* Add custom pre-computed embeddings
*/
addPrecomputed(term: string, embedding: Vector) {
if (embedding.length !== 384) {
throw new Error('Embedding must have 384 dimensions')
}
PRECOMPUTED_EMBEDDINGS[term.toLowerCase()] = embedding
}
}
// Export singleton instance
export const cachedEmbeddings = new CachedEmbeddings()

28
src/embeddings/index.ts
View file

@ -1,28 +0,0 @@
/**
* Embeddings Module - Clean, Unified Architecture
*
* This module provides all embedding functionality for Brainy.
*
* Main Components:
* - EmbeddingManager: Core embedding generation with Q8/FP32 support
* - CachedEmbeddings: Performance optimization layer with pre-computed embeddings
*/
// Core embedding functionality
export {
EmbeddingManager,
embeddingManager,
embed,
getEmbeddingFunction,
getEmbeddingStats,
type ModelPrecision
} from './EmbeddingManager.js'
// Cached embeddings for performance
export {
CachedEmbeddings,
cachedEmbeddings
} from './CachedEmbeddings.js'
// Default export is the singleton manager
export { embeddingManager as default } from './EmbeddingManager.js'

523
src/graph/pathfinding.ts
View file

@ -1,523 +0,0 @@
/**
* Advanced Graph Pathfinding Algorithms
* Provides shortest path, multi-hop traversal, and path ranking
*/
// Graph pathfinding doesn't need to import from coreTypes
export interface GraphNode {
id: string
[key: string]: any
}
export interface GraphEdge {
source: string
target: string
type: string
weight: number
metadata?: any
}
export interface Path {
nodes: string[]
edges: GraphEdge[]
totalWeight: number
length: number
}
export interface PathfindingOptions {
maxDepth?: number
maxPaths?: number
bidirectional?: boolean
weightField?: string
relationshipTypes?: string[]
nodeFilter?: (node: GraphNode) => boolean
edgeFilter?: (edge: GraphEdge) => boolean
}
export class GraphPathfinding {
private adjacencyList: Map<string, Map<string, GraphEdge[]>> = new Map()
private nodes: Map<string, GraphNode> = new Map()
/**
* Add a node to the graph
*/
public addNode(node: GraphNode): void {
this.nodes.set(node.id, node)
if (!this.adjacencyList.has(node.id)) {
this.adjacencyList.set(node.id, new Map())
}
}
/**
* Add an edge to the graph
*/
public addEdge(edge: GraphEdge): void {
// Ensure nodes exist
if (!this.adjacencyList.has(edge.source)) {
this.adjacencyList.set(edge.source, new Map())
}
if (!this.adjacencyList.has(edge.target)) {
this.adjacencyList.set(edge.target, new Map())
}
// Add edge to adjacency list
const sourceEdges = this.adjacencyList.get(edge.source)!
if (!sourceEdges.has(edge.target)) {
sourceEdges.set(edge.target, [])
}
sourceEdges.get(edge.target)!.push(edge)
}
/**
* Find shortest path using Dijkstra's algorithm
* O((V + E) log V) with binary heap
*/
public shortestPath(
start: string,
end: string,
options: PathfindingOptions = {}
): Path | null {
const {
maxDepth = Infinity,
relationshipTypes,
edgeFilter
} = options
// Priority queue: [nodeId, distance, path]
const pq: Array<[string, number, string[], GraphEdge[]]> = [[start, 0, [start], []]]
const visited = new Set<string>()
const distances = new Map<string, number>([[start, 0]])
while (pq.length > 0) {
// Sort by distance (simple array, could optimize with heap)
pq.sort((a, b) => a[1] - b[1])
const [current, distance, path, edges] = pq.shift()!
if (visited.has(current)) continue
visited.add(current)
// Found target
if (current === end) {
return {
nodes: path,
edges,
totalWeight: distance,
length: path.length - 1
}
}
// Max depth reached
if (path.length > maxDepth) continue
// Explore neighbors
const neighbors = this.adjacencyList.get(current)
if (!neighbors) continue
for (const [neighbor, edgeList] of neighbors) {
if (visited.has(neighbor)) continue
// Find best edge to neighbor
let bestEdge: GraphEdge | null = null
let bestWeight = Infinity
for (const edge of edgeList) {
// Apply filters
if (relationshipTypes && !relationshipTypes.includes(edge.type)) continue
if (edgeFilter && !edgeFilter(edge)) continue
if (edge.weight < bestWeight) {
bestWeight = edge.weight
bestEdge = edge
}
}
if (!bestEdge) continue
const newDistance = distance + bestWeight
const currentBest = distances.get(neighbor) ?? Infinity
if (newDistance < currentBest) {
distances.set(neighbor, newDistance)
pq.push([
neighbor,
newDistance,
[...path, neighbor],
[...edges, bestEdge]
])
}
}
}
return null // No path found
}
/**
* Find all paths between two nodes
* Uses DFS with cycle detection
*/
public allPaths(
start: string,
end: string,
options: PathfindingOptions = {}
): Path[] {
const {
maxDepth = 10,
maxPaths = 100,
relationshipTypes,
edgeFilter
} = options
const paths: Path[] = []
const visited = new Set<string>()
const dfs = (
current: string,
path: string[],
edges: GraphEdge[],
weight: number
): void => {
if (paths.length >= maxPaths) return
if (path.length > maxDepth) return
if (current === end && path.length > 1) {
paths.push({
nodes: [...path],
edges: [...edges],
totalWeight: weight,
length: path.length - 1
})
return
}
visited.add(current)
const neighbors = this.adjacencyList.get(current)
if (neighbors) {
for (const [neighbor, edgeList] of neighbors) {
if (visited.has(neighbor)) continue
for (const edge of edgeList) {
// Apply filters
if (relationshipTypes && !relationshipTypes.includes(edge.type)) continue
if (edgeFilter && !edgeFilter(edge)) continue
dfs(
neighbor,
[...path, neighbor],
[...edges, edge],
weight + edge.weight
)
}
}
}
visited.delete(current)
}
dfs(start, [start], [], 0)
// Sort paths by weight
paths.sort((a, b) => a.totalWeight - b.totalWeight)
return paths
}
/**
* Bidirectional search for faster pathfinding
* Searches from both start and end simultaneously
*/
public bidirectionalSearch(
start: string,
end: string,
options: PathfindingOptions = {}
): Path | null {
const { maxDepth = 10 } = options
// Two search frontiers
const forwardVisited = new Map<string, { path: string[], edges: GraphEdge[], weight: number }>()
const backwardVisited = new Map<string, { path: string[], edges: GraphEdge[], weight: number }>()
forwardVisited.set(start, { path: [start], edges: [], weight: 0 })
backwardVisited.set(end, { path: [end], edges: [], weight: 0 })
const forwardQueue = [start]
const backwardQueue = [end]
let depth = 0
while (
(forwardQueue.length > 0 || backwardQueue.length > 0) &&
depth < maxDepth
) {
// Expand forward frontier
const forwardNext: string[] = []
for (const current of forwardQueue) {
const currentData = forwardVisited.get(current)!
const neighbors = this.adjacencyList.get(current)
if (neighbors) {
for (const [neighbor, edges] of neighbors) {
if (forwardVisited.has(neighbor)) continue
// Select edge with lowest weight for optimal path
const bestEdge = edges.reduce((best, edge) =>
edge.weight < best.weight ? edge : best, edges[0])
forwardVisited.set(neighbor, {
path: [...currentData.path, neighbor],
edges: [...currentData.edges, bestEdge],
weight: currentData.weight + bestEdge.weight
})
// Check if we met the backward search
if (backwardVisited.has(neighbor)) {
const forward = forwardVisited.get(neighbor)!
const backward = backwardVisited.get(neighbor)!
// Combine paths
const fullPath = [
...forward.path,
...backward.path.slice(1).reverse()
]
// Reverse backward edges and combine
const backwardEdgesReversed = backward.edges
.map(e => ({
...e,
source: e.target,
target: e.source
}))
.reverse()
return {
nodes: fullPath,
edges: [...forward.edges, ...backwardEdgesReversed],
totalWeight: forward.weight + backward.weight,
length: fullPath.length - 1
}
}
forwardNext.push(neighbor)
}
}
}
// Expand backward frontier
const backwardNext: string[] = []
for (const current of backwardQueue) {
const currentData = backwardVisited.get(current)!
// For backward search, we need to look at incoming edges
for (const [nodeId, neighbors] of this.adjacencyList) {
const edges = neighbors.get(current)
if (!edges) continue
if (backwardVisited.has(nodeId)) continue
// Select edge with lowest weight for optimal path
const bestEdge = edges.reduce((best, edge) =>
edge.weight < best.weight ? edge : best, edges[0])
backwardVisited.set(nodeId, {
path: [...currentData.path, nodeId],
edges: [...currentData.edges, bestEdge],
weight: currentData.weight + bestEdge.weight
})
// Check if we met the forward search
if (forwardVisited.has(nodeId)) {
const forward = forwardVisited.get(nodeId)!
const backward = backwardVisited.get(nodeId)!
// Combine paths
const fullPath = [
...forward.path,
...backward.path.slice(1).reverse()
]
// Reverse backward edges and combine
const backwardEdgesReversed = backward.edges
.map(e => ({
...e,
source: e.target,
target: e.source
}))
.reverse()
return {
nodes: fullPath,
edges: [...forward.edges, ...backwardEdgesReversed],
totalWeight: forward.weight + backward.weight,
length: fullPath.length - 1
}
}
backwardNext.push(nodeId)
}
}
forwardQueue.splice(0, forwardQueue.length, ...forwardNext)
backwardQueue.splice(0, backwardQueue.length, ...backwardNext)
depth++
}
return null
}
/**
* Multi-hop traversal (e.g., friends of friends)
* Returns all nodes within N hops
*/
public multiHopTraversal(
start: string,
hops: number,
options: PathfindingOptions = {}
): Map<string, { distance: number, paths: Path[] }> {
const { relationshipTypes, nodeFilter, edgeFilter } = options
const results = new Map<string, { distance: number, paths: Path[] }>()
const visited = new Set<string>()
const queue: Array<{ node: string, distance: number, path: string[], edges: GraphEdge[] }> = [
{ node: start, distance: 0, path: [start], edges: [] }
]
while (queue.length > 0) {
const { node, distance, path, edges } = queue.shift()!
if (distance > hops) continue
// Record this node
if (!results.has(node)) {
results.set(node, { distance, paths: [] })
}
results.get(node)!.paths.push({
nodes: path,
edges,
totalWeight: edges.reduce((sum, e) => sum + e.weight, 0),
length: path.length - 1
})
if (distance === hops) continue
// Explore neighbors
const neighbors = this.adjacencyList.get(node)
if (neighbors) {
for (const [neighbor, edgeList] of neighbors) {
// Apply node filter
if (nodeFilter) {
const neighborNode = this.nodes.get(neighbor)
if (neighborNode && !nodeFilter(neighborNode)) continue
}
for (const edge of edgeList) {
// Apply filters
if (relationshipTypes && !relationshipTypes.includes(edge.type)) continue
if (edgeFilter && !edgeFilter(edge)) continue
queue.push({
node: neighbor,
distance: distance + 1,
path: [...path, neighbor],
edges: [...edges, edge]
})
}
}
}
}
return results
}
/**
* Find connected components using DFS
*/
public connectedComponents(): Array<Set<string>> {
const visited = new Set<string>()
const components: Array<Set<string>> = []
const dfs = (node: string, component: Set<string>): void => {
visited.add(node)
component.add(node)
const neighbors = this.adjacencyList.get(node)
if (neighbors) {
for (const neighbor of neighbors.keys()) {
if (!visited.has(neighbor)) {
dfs(neighbor, component)
}
}
}
}
for (const node of this.adjacencyList.keys()) {
if (!visited.has(node)) {
const component = new Set<string>()
dfs(node, component)
components.push(component)
}
}
return components
}
/**
* Calculate PageRank for all nodes
* Useful for ranking importance in the graph
*/
public pageRank(iterations: number = 100, damping: number = 0.85): Map<string, number> {
const nodes = Array.from(this.adjacencyList.keys())
const n = nodes.length
if (n === 0) return new Map()
// Initialize ranks
const ranks = new Map<string, number>()
for (const node of nodes) {
ranks.set(node, 1 / n)
}
// Calculate outgoing edge counts
const outDegree = new Map<string, number>()
for (const [node, neighbors] of this.adjacencyList) {
let count = 0
for (const edges of neighbors.values()) {
count += edges.length
}
outDegree.set(node, count)
}
// Iterate PageRank algorithm
for (let i = 0; i < iterations; i++) {
const newRanks = new Map<string, number>()
for (const node of nodes) {
let rank = (1 - damping) / n
// Sum contributions from incoming edges
for (const [source, neighbors] of this.adjacencyList) {
if (neighbors.has(node)) {
const sourceRank = ranks.get(source) ?? 0
const sourceOutDegree = outDegree.get(source) ?? 1
rank += damping * (sourceRank / sourceOutDegree)
}
}
newRanks.set(node, rank)
}
// Update ranks
for (const [node, rank] of newRanks) {
ranks.set(node, rank)
}
}
return ranks
}
/**
* Clear the graph
*/
public clear(): void {
this.adjacencyList.clear()
this.nodes.clear()
}
}

354
src/import/EntityDeduplicator.ts
View file

@ -1,354 +0,0 @@
/**
* Entity Deduplicator
*
* Finds and merges duplicate entities across imports using:
* - Embedding-based similarity matching
* - Type-aware comparison
* - Confidence-weighted merging
* - Provenance tracking
*
* NO MOCKS - Production-ready implementation
*/
import { Brainy } from '../brainy.js'
import { NounType } from '../types/graphTypes.js'
export interface EntityCandidate {
id?: string
name: string
type: NounType
description: string
confidence: number
metadata: Record<string, any>
}
export interface DuplicateMatch {
existingId: string
existingName: string
similarity: number
shouldMerge: boolean
reason: string
}
export interface EntityDeduplicationOptions {
/** Similarity threshold for considering entities as duplicates (0-1) */
similarityThreshold?: number
/** Only match entities of the same type */
strictTypeMatching?: boolean
/** Enable fuzzy name matching */
enableFuzzyMatching?: boolean
/** Minimum confidence to consider for merging */
minConfidence?: number
}
export interface MergeResult {
mergedEntityId: string
wasMerged: boolean
mergedWith?: string
confidence: number
provenance: string[]
}
/**
* EntityDeduplicator - Prevents duplicate entities across imports
*/
export class EntityDeduplicator {
private brain: Brainy
constructor(brain: Brainy) {
this.brain = brain
}
/**
* Find duplicate entities in the knowledge graph
*/
async findDuplicates(
candidate: EntityCandidate,
options: EntityDeduplicationOptions = {}
): Promise<DuplicateMatch | null> {
const opts = {
similarityThreshold: options.similarityThreshold || 0.85,
strictTypeMatching: options.strictTypeMatching !== false,
enableFuzzyMatching: options.enableFuzzyMatching !== false,
minConfidence: options.minConfidence || 0.6
}
// Skip low-confidence candidates
if (candidate.confidence < opts.minConfidence) {
return null
}
// Search for similar entities by name and description
const searchText = `${candidate.name} ${candidate.description}`.trim()
try {
const results = await this.brain.find({
query: searchText,
limit: 5,
where: opts.strictTypeMatching ? { type: candidate.type } : undefined
})
// Check each result for potential duplicates
for (const result of results) {
const similarity = result.score || 0
const existingName = result.entity.metadata?.name || result.id
const existingType = result.entity.metadata?.type || result.entity.metadata?.nounType || result.entity.type
// Skip if below similarity threshold
if (similarity < opts.similarityThreshold) {
continue
}
// Type matching check
if (opts.strictTypeMatching && existingType !== candidate.type) {
continue
}
// Exact name match (case-insensitive)
if (this.normalizeString(candidate.name) === this.normalizeString(existingName)) {
return {
existingId: result.id,
existingName,
similarity: 1.0,
shouldMerge: true,
reason: 'Exact name match'
}
}
// High similarity match
if (similarity >= opts.similarityThreshold) {
// Additional validation for fuzzy matching
if (opts.enableFuzzyMatching && this.areSimilarNames(candidate.name, existingName)) {
return {
existingId: result.id,
existingName,
similarity,
shouldMerge: true,
reason: `High similarity (${(similarity * 100).toFixed(1)}%)`
}
}
}
}
} catch (error) {
// If search fails, assume no duplicates
return null
}
return null
}
/**
* Merge entity data with existing entity
*/
async mergeEntity(
existingId: string,
candidate: EntityCandidate,
importSource: string
): Promise<MergeResult> {
try {
// Get existing entity
const existing = await this.brain.get(existingId)
if (!existing) {
throw new Error(`Entity ${existingId} not found`)
}
// Update confidence (weighted average) — `confidence` is a reserved
// top-level field, so it travels via the dedicated update() param, not
// the metadata bag.
const mergedConfidence = this.mergeConfidence(
existing.confidence ?? 0.5,
candidate.confidence
)
// Merge metadata (custom fields only — reserved fields are top-level)
const mergedMetadata = {
...existing.metadata,
// Track provenance
imports: [
...(existing.metadata?.imports || []),
importSource
],
// Merge VFS paths
vfsPaths: [
...(existing.metadata?.vfsPaths || [existing.metadata?.vfsPath]).filter(Boolean),
candidate.metadata?.vfsPath
].filter(Boolean),
// Merge other metadata
...this.mergeMetadataFields(existing.metadata, candidate.metadata),
// Track last update
lastUpdated: Date.now(),
mergeCount: (existing.metadata?.mergeCount || 0) + 1
}
// Update entity
await this.brain.update({
id: existingId,
confidence: mergedConfidence,
metadata: mergedMetadata,
merge: true
})
return {
mergedEntityId: existingId,
wasMerged: true,
mergedWith: existing.metadata?.name || existingId,
confidence: mergedConfidence,
provenance: mergedMetadata.imports
}
} catch (error) {
throw new Error(`Failed to merge entity: ${error instanceof Error ? error.message : String(error)}`)
}
}
/**
* Create or merge entity with deduplication
*/
async createOrMerge(
candidate: EntityCandidate,
importSource: string,
options: EntityDeduplicationOptions = {}
): Promise<MergeResult> {
// Check for duplicates
const duplicate = await this.findDuplicates(candidate, options)
if (duplicate && duplicate.shouldMerge) {
// Merge with existing entity
return await this.mergeEntity(duplicate.existingId, candidate, importSource)
}
// No duplicate found, create new entity. Preserve any subtype the candidate
// carried (set by the extractor or upstream importer), else fall back to
// `'imported'` so enforcement doesn't fire (added 7.30.1).
// `confidence` is a reserved top-level field (dedicated add() param);
// creation time is system-managed — neither belongs in the metadata bag.
const entityId = await this.brain.add({
data: candidate.description || candidate.name,
type: candidate.type,
subtype:
(candidate as EntityCandidate & { subtype?: string }).subtype ??
'imported',
confidence: candidate.confidence,
metadata: {
...candidate.metadata,
name: candidate.name,
imports: [importSource],
vfsPaths: [candidate.metadata?.vfsPath].filter(Boolean),
mergeCount: 0
}
})
// Update candidate with new ID
candidate.id = entityId
return {
mergedEntityId: entityId,
wasMerged: false,
confidence: candidate.confidence,
provenance: [importSource]
}
}
/**
* Normalize string for comparison
*/
private normalizeString(str: string): string {
return str
.toLowerCase()
.trim()
.replace(/[^a-z0-9]/g, '')
}
/**
* Check if two names are similar (fuzzy matching)
*/
private areSimilarNames(name1: string, name2: string): boolean {
const n1 = this.normalizeString(name1)
const n2 = this.normalizeString(name2)
// Exact match
if (n1 === n2) return true
// Length difference check
const lengthDiff = Math.abs(n1.length - n2.length)
if (lengthDiff > 3) return false
// Levenshtein distance
const distance = this.levenshteinDistance(n1, n2)
const maxLength = Math.max(n1.length, n2.length)
const similarity = 1 - (distance / maxLength)
return similarity >= 0.85
}
/**
* Calculate Levenshtein distance between two strings
*/
private levenshteinDistance(str1: string, str2: string): number {
const m = str1.length
const n = str2.length
const dp: number[][] = Array(m + 1).fill(null).map(() => Array(n + 1).fill(0))
for (let i = 0; i <= m; i++) dp[i][0] = i
for (let j = 0; j <= n; j++) dp[0][j] = j
for (let i = 1; i <= m; i++) {
for (let j = 1; j <= n; j++) {
if (str1[i - 1] === str2[j - 1]) {
dp[i][j] = dp[i - 1][j - 1]
} else {
dp[i][j] = Math.min(
dp[i - 1][j] + 1, // deletion
dp[i][j - 1] + 1, // insertion
dp[i - 1][j - 1] + 1 // substitution
)
}
}
}
return dp[m][n]
}
/**
* Merge confidence scores (weighted average favoring higher confidence)
*/
private mergeConfidence(existing: number, incoming: number): number {
// Weight higher confidence more heavily
const weights = existing > incoming ? [0.6, 0.4] : [0.4, 0.6]
return existing * weights[0] + incoming * weights[1]
}
/**
* Merge metadata fields intelligently
*/
private mergeMetadataFields(
existing: Record<string, any>,
incoming: Record<string, any>
): Record<string, any> {
const merged: Record<string, any> = {}
// Merge arrays
const arrayFields = ['concepts', 'tags', 'categories']
for (const field of arrayFields) {
if (existing[field] || incoming[field]) {
const combined = [
...(existing[field] || []),
...(incoming[field] || [])
]
// Deduplicate
merged[field] = [...new Set(combined)]
}
}
// Prefer longer descriptions
if (existing.description || incoming.description) {
merged.description = (existing.description || '').length > (incoming.description || '').length
? existing.description
: incoming.description
}
return merged
}
}

269
src/import/InstancePool.ts
View file

@ -1,269 +0,0 @@
/**
* InstancePool - Shared instance management for memory efficiency
*
* Production-grade instance pooling to prevent memory leaks during imports.
* Critical for scaling to billions of entities.
*
* Problem: Creating new NLP/Extractor instances in loops → memory leak
* Solution: Reuse shared instances across entire import session
*
* Memory savings:
* - Without pooling: 100K rows × 50MB per instance = 5TB RAM (OOM!)
* - With pooling: 50MB total (shared across all rows)
*/
import { Brainy } from '../brainy.js'
import { NaturalLanguageProcessor } from '../neural/naturalLanguageProcessor.js'
import { NeuralEntityExtractor } from '../neural/entityExtractor.js'
/**
* InstancePool - Manages shared instances for memory efficiency
*
* Lifecycle:
* 1. Create pool at import start
* 2. Reuse instances across all rows
* 3. Pool is garbage collected when import completes
*
* Thread safety: Not thread-safe (single import session per pool)
*/
export class InstancePool {
private brain: Brainy
// Shared instances (created lazily)
private nlpInstance: NaturalLanguageProcessor | null = null
private extractorInstance: NeuralEntityExtractor | null = null
// Initialization state
private nlpInitialized = false
private initializationPromise: Promise<void> | null = null
// Statistics
private stats = {
nlpReuses: 0,
extractorReuses: 0,
creationTime: 0
}
constructor(brain: Brainy) {
this.brain = brain
}
/**
* Get shared NaturalLanguageProcessor instance
*
* Lazy initialization - created on first access
* All subsequent calls return same instance
*
* @returns Shared NLP instance
*/
async getNLP(): Promise<NaturalLanguageProcessor> {
if (!this.nlpInstance) {
const startTime = Date.now()
this.nlpInstance = new NaturalLanguageProcessor(this.brain)
this.stats.creationTime += Date.now() - startTime
}
// Ensure initialized before returning
if (!this.nlpInitialized) {
await this.ensureNLPInitialized()
}
this.stats.nlpReuses++
return this.nlpInstance
}
/**
* Get shared NeuralEntityExtractor instance
*
* Lazy initialization - created on first access
* All subsequent calls return same instance
*
* @returns Shared extractor instance
*/
getExtractor(): NeuralEntityExtractor {
if (!this.extractorInstance) {
const startTime = Date.now()
this.extractorInstance = new NeuralEntityExtractor(this.brain)
this.stats.creationTime += Date.now() - startTime
}
this.stats.extractorReuses++
return this.extractorInstance
}
/**
* Get shared NLP instance (synchronous, may return uninitialized)
*
* Use when you need NLP synchronously and will handle initialization yourself.
* Prefer getNLP() for async code.
*
* @returns Shared NLP instance (possibly uninitialized)
*/
getNLPSync(): NaturalLanguageProcessor {
if (!this.nlpInstance) {
this.nlpInstance = new NaturalLanguageProcessor(this.brain)
}
this.stats.nlpReuses++
return this.nlpInstance
}
/**
* Initialize all instances upfront
*
* Call at start of import to avoid lazy initialization overhead
* during processing. Improves predictability and first-row performance.
*
* @returns Promise that resolves when all instances are ready
*/
async init(): Promise<void> {
// Prevent duplicate initialization
if (this.initializationPromise) {
return this.initializationPromise
}
this.initializationPromise = this.initializeInternal()
return this.initializationPromise
}
/**
* Internal initialization implementation
*/
private async initializeInternal(): Promise<void> {
const startTime = Date.now()
// Create instances
if (!this.nlpInstance) {
this.nlpInstance = new NaturalLanguageProcessor(this.brain)
}
if (!this.extractorInstance) {
this.extractorInstance = new NeuralEntityExtractor(this.brain)
}
// Initialize NLP (loads pattern library)
await this.ensureNLPInitialized()
this.stats.creationTime = Date.now() - startTime
}
/**
* Ensure NLP is initialized (loads 220 patterns)
*
* Handles concurrent initialization requests safely
*/
private async ensureNLPInitialized(): Promise<void> {
if (this.nlpInitialized) {
return
}
if (!this.nlpInstance) {
throw new Error('NLP instance not created yet')
}
await this.nlpInstance.init()
this.nlpInitialized = true
}
/**
* Check if instances are initialized
*
* @returns True if NLP is initialized and ready to use
*/
isInitialized(): boolean {
return this.nlpInitialized && this.nlpInstance !== null
}
/**
* Get pool statistics
*
* Useful for performance monitoring and memory leak detection
*
* @returns Statistics about instance reuse
*/
getStats() {
return {
...this.stats,
nlpCreated: this.nlpInstance !== null,
extractorCreated: this.extractorInstance !== null,
initialized: this.isInitialized(),
// Memory savings estimate
memorySaved: this.calculateMemorySaved()
}
}
/**
* Calculate estimated memory saved by pooling
*
* Assumes ~50MB per NLP instance, ~10MB per extractor instance
*
* @returns Estimated memory saved in bytes
*/
private calculateMemorySaved(): number {
const nlpSize = 50 * 1024 * 1024 // 50MB per instance
const extractorSize = 10 * 1024 * 1024 // 10MB per instance
// Without pooling: size × reuses
// With pooling: size × 1
// Saved: size × (reuses - 1)
const nlpSaved = nlpSize * Math.max(0, this.stats.nlpReuses - 1)
const extractorSaved = extractorSize * Math.max(0, this.stats.extractorReuses - 1)
return nlpSaved + extractorSaved
}
/**
* Reset statistics (useful for testing)
*/
resetStats(): void {
this.stats = {
nlpReuses: 0,
extractorReuses: 0,
creationTime: 0
}
}
/**
* Get string representation (for debugging)
*/
toString(): string {
const stats = this.getStats()
return `InstancePool(nlp=${stats.nlpCreated}, extractor=${stats.extractorCreated}, initialized=${stats.initialized}, nlpReuses=${stats.nlpReuses}, extractorReuses=${stats.extractorReuses})`
}
/**
* Cleanup method (for explicit resource management)
*
* Note: Usually not needed - pool is garbage collected when import completes.
* Use only if you need explicit cleanup for some reason.
*/
cleanup(): void {
// Clear references to allow garbage collection
this.nlpInstance = null
this.extractorInstance = null
this.nlpInitialized = false
this.initializationPromise = null
}
}
/**
* Create a new instance pool
*
* Convenience factory function
*
* @param brain Brainy instance
* @param autoInit Whether to initialize instances immediately
* @returns Instance pool
*/
export async function createInstancePool(
brain: Brainy,
autoInit = true
): Promise<InstancePool> {
const pool = new InstancePool(brain)
if (autoInit) {
await pool.init()
}
return pool
}

38
src/import/index.ts
View file

@ -1,38 +0,0 @@
/**
* Unified Import System
*
* Single entry point for importing any file format into Brainy with:
* - Auto-detection of formats
* - Dual storage (VFS + Knowledge Graph)
* - Shared entities across imports (deduplication)
* - Simple, powerful API
*/
export { ImportCoordinator } from './ImportCoordinator.js'
export { FormatDetector, SupportedFormat, DetectionResult } from './FormatDetector.js'
export { EntityDeduplicator } from './EntityDeduplicator.js'
export { BackgroundDeduplicator } from './BackgroundDeduplicator.js'
export { ImportHistory } from './ImportHistory.js'
export type {
ImportSource,
ImportOptions,
ImportProgress,
ImportResult
} from './ImportCoordinator.js'
export type {
EntityCandidate,
DuplicateMatch,
EntityDeduplicationOptions,
MergeResult
} from './EntityDeduplicator.js'
export type {
DeduplicationStats
} from './BackgroundDeduplicator.js'
export type {
ImportHistoryEntry,
RollbackResult
} from './ImportHistory.js'

789
src/importers/SmartImportOrchestrator.ts
View file

@ -1,789 +0,0 @@
/**
* Smart Import Orchestrator
*
* Coordinates the entire smart import pipeline:
* 1. Extract entities/relationships using SmartExcelImporter
* 2. Create entities and relationships in Brainy
* 3. Organize into VFS structure using VFSStructureGenerator
*
* NO MOCKS - Production-ready implementation
*/
import { Brainy } from '../brainy.js'
import { VirtualFileSystem } from '../vfs/VirtualFileSystem.js'
import { NounType, VerbType } from '../types/graphTypes.js'
import { splitNounMetadataRecord } from '../types/reservedFields.js'
import { SmartExcelImporter, SmartExcelOptions, SmartExcelResult } from './SmartExcelImporter.js'
import { SmartPDFImporter, SmartPDFOptions, SmartPDFResult } from './SmartPDFImporter.js'
import { SmartCSVImporter, SmartCSVOptions, SmartCSVResult } from './SmartCSVImporter.js'
import { SmartJSONImporter, SmartJSONOptions, SmartJSONResult } from './SmartJSONImporter.js'
import { SmartMarkdownImporter, SmartMarkdownOptions, SmartMarkdownResult } from './SmartMarkdownImporter.js'
import { VFSStructureGenerator, VFSStructureOptions } from './VFSStructureGenerator.js'
export interface SmartImportOptions extends SmartExcelOptions {
/** Create VFS structure */
createVFSStructure?: boolean
/** VFS root path */
vfsRootPath?: string
/** VFS grouping strategy */
vfsGroupBy?: 'type' | 'sheet' | 'flat' | 'custom'
/** Create entities in Brainy */
createEntities?: boolean
/** Create relationships in Brainy */
createRelationships?: boolean
/** Source filename */
filename?: string
/**
* Default subtype tag for entities + relationships this importer creates when
* the extractor doesn't set one. See `ValidImportOptions.defaultSubtype` —
* same semantics, same precedence (extractor > caller default > `'imported'`).
* Added 7.30.1.
*/
defaultSubtype?: string
}
export interface SmartImportProgress {
phase: 'parsing' | 'extracting' | 'creating' | 'relationships' | 'organizing' | 'complete'
message: string
processed: number
total: number
entities: number
relationships: number
}
export interface SmartImportResult {
success: boolean
/** Extraction results */
extraction: SmartExcelResult
/** Created entity IDs */
entityIds: string[]
/** Created relationship IDs */
relationshipIds: string[]
/** VFS structure created */
vfsStructure?: {
rootPath: string
directories: string[]
files: number
}
/** Overall statistics */
stats: {
rowsProcessed: number
entitiesCreated: number
relationshipsCreated: number
filesCreated: number
totalTime: number
}
/** Any errors encountered */
errors: string[]
}
/**
* SmartImportOrchestrator - Main entry point for smart imports
*/
export class SmartImportOrchestrator {
private brain: Brainy
private excelImporter: SmartExcelImporter
private pdfImporter: SmartPDFImporter
private csvImporter: SmartCSVImporter
private jsonImporter: SmartJSONImporter
private markdownImporter: SmartMarkdownImporter
private vfsGenerator: VFSStructureGenerator
constructor(brain: Brainy) {
this.brain = brain
this.excelImporter = new SmartExcelImporter(brain)
this.pdfImporter = new SmartPDFImporter(brain)
this.csvImporter = new SmartCSVImporter(brain)
this.jsonImporter = new SmartJSONImporter(brain)
this.markdownImporter = new SmartMarkdownImporter(brain)
this.vfsGenerator = new VFSStructureGenerator(brain)
}
/**
* Initialize the orchestrator
*/
async init(): Promise<void> {
await this.excelImporter.init()
await this.pdfImporter.init()
await this.csvImporter.init()
await this.jsonImporter.init()
await this.markdownImporter.init()
await this.vfsGenerator.init()
}
/**
* Import Excel file with full pipeline
*/
async importExcel(
buffer: Buffer,
options: SmartImportOptions = {},
onProgress?: (progress: SmartImportProgress) => void
): Promise<SmartImportResult> {
const startTime = Date.now()
const result: SmartImportResult = {
success: false,
// Typed boundary: populated in the extraction phase below. If extraction
// throws, the error path returns with this still null (pre-existing
// contract — consumers check `success`/`errors` before reading it).
extraction: null as unknown as SmartExcelResult,
entityIds: [],
relationshipIds: [],
stats: {
rowsProcessed: 0,
entitiesCreated: 0,
relationshipsCreated: 0,
filesCreated: 0,
totalTime: 0
},
errors: []
}
try {
// Phase 1: Extract entities and relationships
onProgress?.({
phase: 'extracting',
message: 'Extracting entities and relationships...',
processed: 0,
total: 0,
entities: 0,
relationships: 0
})
result.extraction = await this.excelImporter.extract(buffer, {
...options,
onProgress: (stats) => {
onProgress?.({
phase: 'extracting',
message: `Processing row ${stats.processed}/${stats.total}...`,
processed: stats.processed,
total: stats.total,
entities: stats.entities,
relationships: stats.relationships
})
}
})
result.stats.rowsProcessed = result.extraction.rowsProcessed
// Phase 2: Create entities in Brainy
if (options.createEntities !== false) {
onProgress?.({
phase: 'creating',
message: 'Creating entities in knowledge graph...',
processed: 0,
total: result.extraction.rows.length,
entities: 0,
relationships: 0
})
for (let i = 0; i < result.extraction.rows.length; i++) {
const extracted = result.extraction.rows[i]
try {
// Create main entity. Subtype precedence: extractor-set → caller default
// → Brainy default `'imported'` (added 7.30.1).
const entityId = await this.brain.add({
data: extracted.entity.description,
type: extracted.entity.type,
subtype:
(extracted.entity as typeof extracted.entity & { subtype?: string })
.subtype ?? options.defaultSubtype ?? 'imported',
confidence: extracted.entity.confidence, // reserved field — dedicated param, not metadata
metadata: {
// Strip reserved keys an extractor may have smuggled into the bag
// (8.0 reservedFieldPolicy defaults to 'throw').
...splitNounMetadataRecord(extracted.entity.metadata).custom,
name: extracted.entity.name,
importedFrom: 'smart-import'
}
})
result.entityIds.push(entityId)
result.stats.entitiesCreated++
// Update entity ID in extraction result
extracted.entity.id = entityId
onProgress?.({
phase: 'creating',
message: `Created entity: ${extracted.entity.name}`,
processed: i + 1,
total: result.extraction.rows.length,
entities: result.entityIds.length,
relationships: result.relationshipIds.length
})
} catch (error: any) {
result.errors.push(`Failed to create entity ${extracted.entity.name}: ${error.message}`)
}
}
}
// Phase 3: Create relationships
if (options.createRelationships !== false && options.createEntities !== false) {
onProgress?.({
phase: 'creating',
message: 'Preparing relationships...',
processed: 0,
total: result.extraction.rows.length,
entities: result.entityIds.length,
relationships: 0
})
// Build entity name -> ID map
const entityMap = new Map<string, string>()
for (const extracted of result.extraction.rows) {
entityMap.set(extracted.entity.name.toLowerCase(), extracted.entity.id)
}
// Collect all relationship parameters
const relationshipParams: Array<{from: string; to: string; type: VerbType; subtype?: string; confidence?: number; metadata?: any}> = []
for (const extracted of result.extraction.rows) {
for (const rel of extracted.relationships) {
try {
// Find target entity ID
let toEntityId: string | undefined
// Try to find by name in our extracted entities
for (const otherExtracted of result.extraction.rows) {
if (rel.to.toLowerCase().includes(otherExtracted.entity.name.toLowerCase()) ||
otherExtracted.entity.name.toLowerCase().includes(rel.to.toLowerCase())) {
toEntityId = otherExtracted.entity.id
break
}
}
// If not found, create a placeholder entity. `import-placeholder` marks
// these as synthetic targets so consumers can distinguish them from real
// imports and downstream dedup can consolidate (added 7.30.1).
if (!toEntityId) {
toEntityId = await this.brain.add({
data: rel.to,
type: NounType.Thing,
subtype: 'import-placeholder',
metadata: {
name: rel.to,
placeholder: true,
extractedFrom: extracted.entity.name
}
})
result.entityIds.push(toEntityId)
}
// Collect relationship parameter. Subtype precedence: extractor-set rel
// subtype → caller default → Brainy default `'imported'` (added 7.30.1).
relationshipParams.push({
from: extracted.entity.id,
to: toEntityId,
type: rel.type,
subtype:
(rel as typeof rel & { subtype?: string }).subtype ??
options.defaultSubtype ?? 'imported',
confidence: rel.confidence, // reserved field — dedicated param, not metadata
metadata: {
evidence: rel.evidence
}
})
} catch (error: any) {
result.errors.push(`Failed to prepare relationship: ${error.message}`)
}
}
}
// Batch create all relationships with progress
if (relationshipParams.length > 0) {
onProgress?.({
phase: 'relationships',
message: 'Building relationships...',
processed: 0,
total: relationshipParams.length,
entities: result.entityIds.length,
relationships: 0
})
try {
const relationshipIds = await this.brain.relateMany({
items: relationshipParams,
parallel: true,
chunkSize: 100,
continueOnError: true,
onProgress: (done, total) => {
onProgress?.({
phase: 'relationships',
message: `Building relationships: ${done}/${total}`,
processed: done,
total: total,
entities: result.entityIds.length,
relationships: done
})
}
})
result.relationshipIds = relationshipIds
result.stats.relationshipsCreated = relationshipIds.length
} catch (error: any) {
result.errors.push(`Failed to create relationships: ${error.message}`)
}
}
}
// Phase 4: Create VFS structure
if (options.createVFSStructure !== false) {
onProgress?.({
phase: 'organizing',
message: 'Organizing into file structure...',
processed: 0,
total: result.extraction.rows.length,
entities: result.entityIds.length,
relationships: result.relationshipIds.length
})
const vfsOptions: VFSStructureOptions = {
rootPath: options.vfsRootPath || '/imports/' + (options.filename || 'import'),
groupBy: options.vfsGroupBy || 'type',
preserveSource: true,
sourceBuffer: buffer,
sourceFilename: options.filename || 'import.xlsx',
createRelationshipFile: true,
createMetadataFile: true
}
const vfsResult = await this.vfsGenerator.generate(result.extraction, vfsOptions)
result.vfsStructure = {
rootPath: vfsResult.rootPath,
directories: vfsResult.directories,
files: vfsResult.files.length
}
result.stats.filesCreated = vfsResult.files.length
}
// Complete
result.success = result.errors.length === 0
result.stats.totalTime = Date.now() - startTime
onProgress?.({
phase: 'complete',
message: `Import complete: ${result.stats.entitiesCreated} entities, ${result.stats.relationshipsCreated} relationships`,
processed: result.extraction.rows.length,
total: result.extraction.rows.length,
entities: result.stats.entitiesCreated,
relationships: result.stats.relationshipsCreated
})
} catch (error: any) {
result.errors.push(`Import failed: ${error.message}`)
result.success = false
}
return result
}
/**
* Import PDF file with full pipeline
*/
async importPDF(
buffer: Buffer,
options: SmartImportOptions & SmartPDFOptions = {},
onProgress?: (progress: SmartImportProgress) => void
): Promise<SmartImportResult> {
const startTime = Date.now()
const result: SmartImportResult = {
success: false,
// Typed boundary: populated after extraction (see importExcel).
extraction: null as unknown as SmartExcelResult,
entityIds: [],
relationshipIds: [],
stats: {
rowsProcessed: 0,
entitiesCreated: 0,
relationshipsCreated: 0,
filesCreated: 0,
totalTime: 0
},
errors: []
}
try {
// Phase 1: Extract from PDF
onProgress?.({ phase: 'extracting', message: 'Extracting from PDF...', processed: 0, total: 0, entities: 0, relationships: 0 })
const pdfResult = await this.pdfImporter.extract(buffer, options)
// Convert PDF result to Excel-like format for processing
result.extraction = this.convertPDFToExcelFormat(pdfResult)
result.stats.rowsProcessed = pdfResult.sectionsProcessed
// Phase 2 & 3: Create entities and relationships
await this.createEntitiesAndRelationships(result, options, onProgress)
// Phase 4: Create VFS structure
if (options.createVFSStructure !== false) {
const vfsOptions: VFSStructureOptions = {
rootPath: options.vfsRootPath || '/imports/' + (options.filename || 'import'),
groupBy: options.vfsGroupBy || 'type',
preserveSource: true,
sourceBuffer: buffer,
sourceFilename: options.filename || 'import.pdf',
createRelationshipFile: true,
createMetadataFile: true
}
const vfsResult = await this.vfsGenerator.generate(result.extraction, vfsOptions)
result.vfsStructure = { rootPath: vfsResult.rootPath, directories: vfsResult.directories, files: vfsResult.files.length }
result.stats.filesCreated = vfsResult.files.length
}
result.success = result.errors.length === 0
result.stats.totalTime = Date.now() - startTime
onProgress?.({ phase: 'complete', message: `Import complete: ${result.stats.entitiesCreated} entities, ${result.stats.relationshipsCreated} relationships`, processed: result.stats.rowsProcessed, total: result.stats.rowsProcessed, entities: result.stats.entitiesCreated, relationships: result.stats.relationshipsCreated })
} catch (error: any) {
result.errors.push(`PDF import failed: ${error.message}`)
result.success = false
}
return result
}
/**
* Import CSV file with full pipeline
*/
async importCSV(
buffer: Buffer,
options: SmartImportOptions & SmartCSVOptions = {},
onProgress?: (progress: SmartImportProgress) => void
): Promise<SmartImportResult> {
// CSV is very similar to Excel, can reuse importExcel logic
return this.importExcel(buffer, options, onProgress)
}
/**
* Import JSON data with full pipeline
*/
async importJSON(
data: any,
options: SmartImportOptions & SmartJSONOptions = {},
onProgress?: (progress: SmartImportProgress) => void
): Promise<SmartImportResult> {
const startTime = Date.now()
const result: SmartImportResult = {
success: false,
// Typed boundary: populated after extraction (see importExcel).
extraction: null as unknown as SmartExcelResult,
entityIds: [],
relationshipIds: [],
stats: {
rowsProcessed: 0,
entitiesCreated: 0,
relationshipsCreated: 0,
filesCreated: 0,
totalTime: 0
},
errors: []
}
try {
onProgress?.({ phase: 'extracting', message: 'Extracting from JSON...', processed: 0, total: 0, entities: 0, relationships: 0 })
const jsonResult = await this.jsonImporter.extract(data, options)
result.extraction = this.convertJSONToExcelFormat(jsonResult)
result.stats.rowsProcessed = jsonResult.nodesProcessed
await this.createEntitiesAndRelationships(result, options, onProgress)
if (options.createVFSStructure !== false) {
const sourceBuffer = Buffer.from(typeof data === 'string' ? data : JSON.stringify(data, null, 2))
const vfsOptions: VFSStructureOptions = {
rootPath: options.vfsRootPath || '/imports/' + (options.filename || 'import'),
groupBy: options.vfsGroupBy || 'type',
preserveSource: true,
sourceBuffer,
sourceFilename: options.filename || 'import.json',
createRelationshipFile: true,
createMetadataFile: true
}
const vfsResult = await this.vfsGenerator.generate(result.extraction, vfsOptions)
result.vfsStructure = { rootPath: vfsResult.rootPath, directories: vfsResult.directories, files: vfsResult.files.length }
result.stats.filesCreated = vfsResult.files.length
}
result.success = result.errors.length === 0
result.stats.totalTime = Date.now() - startTime
onProgress?.({ phase: 'complete', message: `Import complete: ${result.stats.entitiesCreated} entities, ${result.stats.relationshipsCreated} relationships`, processed: result.stats.rowsProcessed, total: result.stats.rowsProcessed, entities: result.stats.entitiesCreated, relationships: result.stats.relationshipsCreated })
} catch (error: any) {
result.errors.push(`JSON import failed: ${error.message}`)
result.success = false
}
return result
}
/**
* Import Markdown content with full pipeline
*/
async importMarkdown(
markdown: string,
options: SmartImportOptions & SmartMarkdownOptions = {},
onProgress?: (progress: SmartImportProgress) => void
): Promise<SmartImportResult> {
const startTime = Date.now()
const result: SmartImportResult = {
success: false,
// Typed boundary: populated after extraction (see importExcel).
extraction: null as unknown as SmartExcelResult,
entityIds: [],
relationshipIds: [],
stats: {
rowsProcessed: 0,
entitiesCreated: 0,
relationshipsCreated: 0,
filesCreated: 0,
totalTime: 0
},
errors: []
}
try {
onProgress?.({ phase: 'extracting', message: 'Extracting from Markdown...', processed: 0, total: 0, entities: 0, relationships: 0 })
const mdResult = await this.markdownImporter.extract(markdown, options)
result.extraction = this.convertMarkdownToExcelFormat(mdResult)
result.stats.rowsProcessed = mdResult.sectionsProcessed
await this.createEntitiesAndRelationships(result, options, onProgress)
if (options.createVFSStructure !== false) {
const sourceBuffer = Buffer.from(markdown, 'utf-8')
const vfsOptions: VFSStructureOptions = {
rootPath: options.vfsRootPath || '/imports/' + (options.filename || 'import'),
groupBy: options.vfsGroupBy || 'type',
preserveSource: true,
sourceBuffer,
sourceFilename: options.filename || 'import.md',
createRelationshipFile: true,
createMetadataFile: true
}
const vfsResult = await this.vfsGenerator.generate(result.extraction, vfsOptions)
result.vfsStructure = { rootPath: vfsResult.rootPath, directories: vfsResult.directories, files: vfsResult.files.length }
result.stats.filesCreated = vfsResult.files.length
}
result.success = result.errors.length === 0
result.stats.totalTime = Date.now() - startTime
onProgress?.({ phase: 'complete', message: `Import complete: ${result.stats.entitiesCreated} entities, ${result.stats.relationshipsCreated} relationships`, processed: result.stats.rowsProcessed, total: result.stats.rowsProcessed, entities: result.stats.entitiesCreated, relationships: result.stats.relationshipsCreated })
} catch (error: any) {
result.errors.push(`Markdown import failed: ${error.message}`)
result.success = false
}
return result
}
/**
* Helper: Create entities and relationships from extraction result
*/
private async createEntitiesAndRelationships(
result: SmartImportResult,
options: SmartImportOptions,
onProgress?: (progress: SmartImportProgress) => void
): Promise<void> {
if (options.createEntities !== false) {
onProgress?.({ phase: 'creating', message: 'Creating entities in knowledge graph...', processed: 0, total: result.extraction.rows.length, entities: 0, relationships: 0 })
for (let i = 0; i < result.extraction.rows.length; i++) {
const extracted = result.extraction.rows[i]
try {
// Subtype precedence: extractor → caller default → `'imported'` (7.30.1).
const entityId = await this.brain.add({
data: extracted.entity.description,
type: extracted.entity.type,
subtype:
(extracted.entity as typeof extracted.entity & { subtype?: string })
.subtype ?? options.defaultSubtype ?? 'imported',
confidence: extracted.entity.confidence, // reserved field — dedicated param, not metadata
metadata: { ...splitNounMetadataRecord(extracted.entity.metadata).custom, name: extracted.entity.name, importedFrom: 'smart-import' }
})
result.entityIds.push(entityId)
result.stats.entitiesCreated++
extracted.entity.id = entityId
} catch (error: any) {
result.errors.push(`Failed to create entity ${extracted.entity.name}: ${error.message}`)
}
}
}
if (options.createRelationships !== false && options.createEntities !== false) {
onProgress?.({ phase: 'creating', message: 'Preparing relationships...', processed: 0, total: result.extraction.rows.length, entities: result.entityIds.length, relationships: 0 })
// Collect all relationship parameters
const relationshipParams: Array<{from: string; to: string; type: VerbType; subtype?: string; confidence?: number; metadata?: any}> = []
for (const extracted of result.extraction.rows) {
for (const rel of extracted.relationships) {
try {
let toEntityId: string | undefined
for (const otherExtracted of result.extraction.rows) {
if (rel.to.toLowerCase().includes(otherExtracted.entity.name.toLowerCase()) || otherExtracted.entity.name.toLowerCase().includes(rel.to.toLowerCase())) {
toEntityId = otherExtracted.entity.id
break
}
}
if (!toEntityId) {
// Subtype `import-placeholder` marks synthetic targets (7.30.1).
toEntityId = await this.brain.add({ data: rel.to, type: NounType.Thing, subtype: 'import-placeholder', metadata: { name: rel.to, placeholder: true, extractedFrom: extracted.entity.name } })
result.entityIds.push(toEntityId)
}
// Relationship subtype precedence: extractor → caller default → `'imported'` (7.30.1).
// `confidence` is a reserved top-level field — dedicated relate() param, not metadata
relationshipParams.push({ from: extracted.entity.id, to: toEntityId, type: rel.type, subtype: (rel as typeof rel & { subtype?: string }).subtype ?? options.defaultSubtype ?? 'imported', confidence: rel.confidence, metadata: { evidence: rel.evidence } })
} catch (error: any) {
result.errors.push(`Failed to prepare relationship: ${error.message}`)
}
}
}
// Batch create all relationships with progress
if (relationshipParams.length > 0) {
onProgress?.({ phase: 'relationships', message: 'Building relationships...', processed: 0, total: relationshipParams.length, entities: result.entityIds.length, relationships: 0 })
try {
const relationshipIds = await this.brain.relateMany({
items: relationshipParams,
parallel: true,
chunkSize: 100,
continueOnError: true,
onProgress: (done, total) => {
onProgress?.({ phase: 'relationships', message: `Building relationships: ${done}/${total}`, processed: done, total: total, entities: result.entityIds.length, relationships: done })
}
})
result.relationshipIds = relationshipIds
result.stats.relationshipsCreated = relationshipIds.length
} catch (error: any) {
result.errors.push(`Failed to create relationships: ${error.message}`)
}
}
}
}
/**
* Helper: Convert PDF result to Excel-like format
*/
private convertPDFToExcelFormat(pdfResult: SmartPDFResult): Omit<SmartExcelResult, 'rows'> & { rows: any[] } {
const rows = pdfResult.sections.flatMap(section =>
section.entities.map(entity => ({
entity,
relatedEntities: [],
relationships: section.relationships.filter(r => r.from === entity.id),
concepts: section.concepts
}))
)
return {
rowsProcessed: pdfResult.sectionsProcessed,
entitiesExtracted: pdfResult.entitiesExtracted,
relationshipsInferred: pdfResult.relationshipsInferred,
rows,
entityMap: pdfResult.entityMap,
processingTime: pdfResult.processingTime,
stats: pdfResult.stats
}
}
/**
* Helper: Convert JSON result to Excel-like format
*/
private convertJSONToExcelFormat(jsonResult: SmartJSONResult): Omit<SmartExcelResult, 'rows'> & { rows: any[] } {
const rows = jsonResult.entities.map(entity => ({
entity,
relatedEntities: [],
relationships: jsonResult.relationships.filter(r => r.from === entity.id),
concepts: entity.metadata.concepts || []
}))
return {
rowsProcessed: jsonResult.nodesProcessed,
entitiesExtracted: jsonResult.entitiesExtracted,
relationshipsInferred: jsonResult.relationshipsInferred,
rows,
entityMap: jsonResult.entityMap,
processingTime: jsonResult.processingTime,
stats: jsonResult.stats
}
}
/**
* Helper: Convert Markdown result to Excel-like format
*/
private convertMarkdownToExcelFormat(mdResult: SmartMarkdownResult): Omit<SmartExcelResult, 'rows'> & { rows: any[] } {
const rows = mdResult.sections.flatMap(section =>
section.entities.map(entity => ({
entity,
relatedEntities: [],
relationships: section.relationships.filter(r => r.from === entity.id),
concepts: section.concepts
}))
)
return {
rowsProcessed: mdResult.sectionsProcessed,
entitiesExtracted: mdResult.entitiesExtracted,
relationshipsInferred: mdResult.relationshipsInferred,
rows,
entityMap: mdResult.entityMap,
processingTime: mdResult.processingTime,
stats: mdResult.stats
}
}
/**
* Get import statistics
*/
async getImportStatistics(vfsRootPath: string): Promise<{
entitiesInGraph: number
relationshipsInGraph: number
filesInVFS: number
lastImport?: Date
}> {
// Read metadata file
const vfs = new VirtualFileSystem(this.brain)
await vfs.init()
const metadataPath = `${vfsRootPath}/_metadata.json`
try {
const metadataBuffer = await vfs.readFile(metadataPath)
const metadata = JSON.parse(metadataBuffer.toString('utf-8'))
return {
entitiesInGraph: metadata.import.stats.entitiesExtracted,
relationshipsInGraph: metadata.import.stats.relationshipsInferred,
filesInVFS: metadata.structure.fileCount,
lastImport: new Date(metadata.import.timestamp)
}
} catch (error) {
return {
entitiesInGraph: 0,
relationshipsInGraph: 0,
filesInVFS: 0
}
}
}
}

69
src/importers/index.ts
View file

@ -1,69 +0,0 @@
/**
* Smart Import System
*
* Production-ready entity and relationship extraction from multiple formats:
* - Excel (.xlsx)
* - PDF (.pdf)
* - CSV (.csv)
* - JSON (.json)
* - Markdown (.md)
*
* Uses brainy's built-in NeuralEntityExtractor and NaturalLanguageProcessor
*
* NO MOCKS - Real working implementation
*/
// Excel Importer
export { SmartExcelImporter } from './SmartExcelImporter.js'
export type {
SmartExcelOptions,
ExtractedRow,
SmartExcelResult
} from './SmartExcelImporter.js'
// PDF Importer
export { SmartPDFImporter } from './SmartPDFImporter.js'
export type {
SmartPDFOptions,
ExtractedSection,
SmartPDFResult
} from './SmartPDFImporter.js'
// CSV Importer
export { SmartCSVImporter } from './SmartCSVImporter.js'
export type {
SmartCSVOptions,
SmartCSVResult
} from './SmartCSVImporter.js'
// JSON Importer
export { SmartJSONImporter } from './SmartJSONImporter.js'
export type {
SmartJSONOptions,
ExtractedJSONEntity,
ExtractedJSONRelationship,
SmartJSONResult
} from './SmartJSONImporter.js'
// Markdown Importer
export { SmartMarkdownImporter } from './SmartMarkdownImporter.js'
export type {
SmartMarkdownOptions,
MarkdownSection,
SmartMarkdownResult
} from './SmartMarkdownImporter.js'
// VFS Structure Generator
export { VFSStructureGenerator } from './VFSStructureGenerator.js'
export type {
VFSStructureOptions,
VFSStructureResult
} from './VFSStructureGenerator.js'
// Orchestrator (Main entry point)
export { SmartImportOrchestrator } from './SmartImportOrchestrator.js'
export type {
SmartImportOptions,
SmartImportProgress,
SmartImportResult
} from './SmartImportOrchestrator.js'

38
src/indexes/columnStore/index.ts
View file

@ -1,38 +0,0 @@
/**
* @module columnStore
* @description Unified column store for filtering, sorting, range queries,
* and text search on any field type with exact precision at billion scale.
*
* Replaces MetadataIndex's sparse chunk/bloom filter/bucketing internals
* with per-field sorted columns. Design lineage: Lucene doc values + roaring
* bitmap acceleration.
*/
export { ColumnStore } from './ColumnStore.js'
export type { ColumnStoreConfig } from './ColumnStore.js'
export { ColumnTailBuffer } from './ColumnTailBuffer.js'
export { ColumnManifest } from './ColumnManifest.js'
export { ColumnSegmentCursor, TailBufferCursor } from './ColumnSegmentCursor.js'
export {
writeSegmentToBuffer,
readSegmentFromBuffer,
writeHeader,
readHeader,
crc32
} from './ColumnSegmentFormat.js'
export {
ValueType,
CIDX_MAGIC,
CIDX_VERSION,
HEADER_SIZE,
FOOTER_SIZE,
DEFAULT_FLUSH_THRESHOLD,
FLAG_MULTI_VALUE
} from './types.js'
export type {
ColumnStoreProvider,
SegmentHeader,
SegmentFooter,
SegmentMeta,
ManifestData
} from './types.js'

363
src/mcp/brainyMCPBroadcast.ts
View file

@ -1,363 +0,0 @@
/**
* BrainyMCPBroadcast
*
* Enhanced MCP service with real-time WebSocket broadcasting capabilities
* for multi-agent coordination (Jarvis ↔ Picasso communication)
*
* Features:
* - WebSocket server for real-time push notifications
* - Subscription management for multiple Claude instances
* - Message broadcasting to all connected agents
* - Works both locally and with cloud deployment
*/
import { WebSocketServer, WebSocket } from 'ws'
import { createServer, IncomingMessage } from 'node:http'
import { BrainyMCPService } from './brainyMCPService.js'
import { BrainyInterface } from '../types/brainyInterface.js'
import { MCPServiceOptions } from '../types/mcpTypes.js'
import { v4 as uuidv4 } from '../universal/uuid.js'
interface BroadcastMessage {
id: string
from: string
to?: string | string[]
type: 'message' | 'notification' | 'sync' | 'heartbeat' | 'identify'
event?: string
data: any
timestamp: number
}
interface ConnectedAgent {
id: string
name: string
role: string
socket: WebSocket
lastSeen: number
}
export class BrainyMCPBroadcast extends BrainyMCPService {
private wsServer?: WebSocketServer
private httpServer?: any
private agents: Map<string, ConnectedAgent> = new Map()
private messageHistory: BroadcastMessage[] = []
private maxHistorySize = 100
constructor(
brainyData: BrainyInterface,
options: MCPServiceOptions & {
broadcastPort?: number
cloudUrl?: string
} = {}
) {
super(brainyData, options)
}
/**
* Start the WebSocket broadcast server
* @param port Port to listen on (default: 8765)
* @param isCloud Whether this is a cloud deployment
*/
async startBroadcastServer(port = 8765, isCloud = false): Promise<void> {
return new Promise((resolve, reject) => {
try {
// Create HTTP server
this.httpServer = createServer((req, res) => {
// Health check endpoint
if (req.url === '/health') {
res.writeHead(200, { 'Content-Type': 'application/json' })
res.end(JSON.stringify({
status: 'healthy',
agents: Array.from(this.agents.values()).map(a => ({
id: a.id,
name: a.name,
role: a.role,
connected: true
})),
uptime: process.uptime()
}))
} else {
res.writeHead(404)
res.end('Not found')
}
})
// Create WebSocket server
this.wsServer = new WebSocketServer({
server: this.httpServer,
perMessageDeflate: false // Better performance
})
this.wsServer.on('connection', (socket, request) => {
this.handleNewConnection(socket, request)
})
// Start listening
this.httpServer.listen(port, () => {
console.log(`🧠 Brain Jar Broadcast Server running on ${isCloud ? 'cloud' : 'local'} port ${port}`)
console.log(`📡 WebSocket: ws://localhost:${port}`)
console.log(`🔍 Health: http://localhost:${port}/health`)
resolve()
})
// Heartbeat to keep connections alive
setInterval(() => {
this.agents.forEach((agent) => {
if (Date.now() - agent.lastSeen > 30000) {
// Remove inactive agents
this.removeAgent(agent.id)
} else {
// Send heartbeat
this.sendToAgent(agent.id, {
id: uuidv4(),
from: 'server',
type: 'heartbeat',
data: { timestamp: Date.now() },
timestamp: Date.now()
})
}
})
}, 15000)
} catch (error) {
reject(error)
}
})
}
/**
* Handle new WebSocket connection
*/
private handleNewConnection(socket: WebSocket, request: IncomingMessage) {
const agentId = uuidv4()
// Send welcome message
socket.send(JSON.stringify({
id: uuidv4(),
from: 'server',
type: 'notification',
event: 'welcome',
data: {
agentId,
message: 'Connected to Brain Jar Broadcast Server',
agents: Array.from(this.agents.values()).map(a => ({
id: a.id,
name: a.name,
role: a.role
}))
},
timestamp: Date.now()
}))
// Handle messages from this agent
socket.on('message', (data) => {
try {
const message = JSON.parse(data.toString())
this.handleAgentMessage(agentId, message)
} catch (error) {
console.error('Invalid message from agent:', error)
}
})
// Handle disconnection
socket.on('close', () => {
this.removeAgent(agentId)
})
// Handle errors
socket.on('error', (error) => {
console.error(`Agent ${agentId} error:`, error)
})
// Store temporary connection until identified
this.agents.set(agentId, {
id: agentId,
name: 'Unknown',
role: 'Unknown',
socket,
lastSeen: Date.now()
})
}
/**
* Handle message from an agent
*/
private handleAgentMessage(agentId: string, message: any) {
const agent = this.agents.get(agentId)
if (!agent) return
// Update last seen
agent.lastSeen = Date.now()
// Handle identification
if (message.type === 'identify') {
agent.name = message.name || agent.name
agent.role = message.role || agent.role
// Notify all agents about new member
this.broadcast({
id: uuidv4(),
from: 'server',
type: 'notification',
event: 'agent_joined',
data: {
agent: {
id: agent.id,
name: agent.name,
role: agent.role
}
},
timestamp: Date.now()
}, agentId) // Exclude the joining agent
// Send recent history to new agent
if (this.messageHistory.length > 0) {
this.sendToAgent(agentId, {
id: uuidv4(),
from: 'server',
type: 'sync',
data: {
history: this.messageHistory.slice(-20) // Last 20 messages
},
timestamp: Date.now()
})
}
return
}
// Create broadcast message
const broadcastMsg: BroadcastMessage = {
id: message.id || uuidv4(),
from: agent.name,
to: message.to,
type: message.type || 'message',
event: message.event,
data: message.data,
timestamp: Date.now()
}
// Store in history
this.addToHistory(broadcastMsg)
// Broadcast based on recipient
if (message.to) {
// Send to specific agent(s)
const recipients = Array.isArray(message.to) ? message.to : [message.to]
recipients.forEach((recipientName: string) => {
const recipient = Array.from(this.agents.values()).find(
a => a.name === recipientName
)
if (recipient) {
this.sendToAgent(recipient.id, broadcastMsg)
}
})
} else {
// Broadcast to all agents except sender
this.broadcast(broadcastMsg, agentId)
}
}
/**
* Broadcast message to all connected agents
*/
broadcast(message: BroadcastMessage, excludeId?: string) {
const messageStr = JSON.stringify(message)
this.agents.forEach((agent) => {
if (agent.id !== excludeId && agent.socket.readyState === WebSocket.OPEN) {
agent.socket.send(messageStr)
}
})
}
/**
* Send message to specific agent
*/
private sendToAgent(agentId: string, message: BroadcastMessage) {
const agent = this.agents.get(agentId)
if (agent && agent.socket.readyState === WebSocket.OPEN) {
agent.socket.send(JSON.stringify(message))
}
}
/**
* Remove agent from connected list
*/
private removeAgent(agentId: string) {
const agent = this.agents.get(agentId)
if (agent) {
// Notify others about disconnection
this.broadcast({
id: uuidv4(),
from: 'server',
type: 'notification',
event: 'agent_left',
data: {
agent: {
id: agent.id,
name: agent.name,
role: agent.role
}
},
timestamp: Date.now()
})
this.agents.delete(agentId)
}
}
/**
* Add message to history
*/
private addToHistory(message: BroadcastMessage) {
this.messageHistory.push(message)
// Trim history if too large
if (this.messageHistory.length > this.maxHistorySize) {
this.messageHistory = this.messageHistory.slice(-this.maxHistorySize)
}
}
/**
* Stop the broadcast server
*/
async stopBroadcastServer(): Promise<void> {
// Close all agent connections
this.agents.forEach(agent => {
agent.socket.close(1000, 'Server shutting down')
})
this.agents.clear()
// Close WebSocket server
if (this.wsServer) {
this.wsServer.close()
}
// Close HTTP server
if (this.httpServer) {
this.httpServer.close()
}
}
/**
* Get connected agents
*/
getConnectedAgents(): Array<{ id: string; name: string; role: string }> {
return Array.from(this.agents.values()).map(a => ({
id: a.id,
name: a.name,
role: a.role
}))
}
/**
* Get message history
*/
getMessageHistory(): BroadcastMessage[] {
return [...this.messageHistory]
}
}
// Export for both environments
export default BrainyMCPBroadcast

322
src/mcp/brainyMCPClient.ts
View file

@ -1,322 +0,0 @@
/**
* BrainyMCPClient
*
* Client for connecting Claude instances to the Brain Jar Broadcast Server
* Utilizes Brainy for persistent memory and vector search capabilities
*/
import WebSocket from 'ws'
import { Brainy } from '../brainy.js'
import { NounType } from '../types/graphTypes.js'
import { v4 as uuidv4 } from '../universal/uuid.js'
interface ClientOptions {
name: string // e.g., 'Jarvis' or 'Picasso'
role: string // e.g., 'Backend Systems' or 'Frontend Design'
serverUrl?: string // Default: ws://localhost:8765
autoReconnect?: boolean
useBrainyMemory?: boolean // Store messages in Brainy for persistence
}
interface Message {
id: string
from: string
to?: string | string[]
type: 'message' | 'notification' | 'sync' | 'heartbeat' | 'identify'
event?: string
data: any
timestamp: number
}
export class BrainyMCPClient {
private socket?: WebSocket
private options: Required<ClientOptions>
private brainy?: Brainy
private messageHandlers: Map<string, (message: Message) => void> = new Map()
private reconnectTimeout?: NodeJS.Timeout
private isConnected = false
constructor(options: ClientOptions) {
this.options = {
serverUrl: 'ws://localhost:8765',
autoReconnect: true,
useBrainyMemory: true,
...options
}
}
/**
* Initialize Brainy for persistent memory
*/
private async initBrainy() {
if (this.options.useBrainyMemory && !this.brainy) {
this.brainy = new Brainy({
storage: {
requestPersistentStorage: true
}
})
await this.brainy.init()
console.log(`🧠 Brainy memory initialized for ${this.options.name}`)
}
}
/**
* Connect to the broadcast server
*/
async connect(): Promise<void> {
// Initialize Brainy first
await this.initBrainy()
return new Promise((resolve, reject) => {
try {
this.socket = new WebSocket(this.options.serverUrl)
this.socket.on('open', () => {
console.log(`✅ ${this.options.name} connected to Brain Jar Broadcast`)
this.isConnected = true
// Identify ourselves
this.send({
type: 'identify',
data: {
name: this.options.name,
role: this.options.role
}
})
resolve()
})
this.socket.on('message', async (data) => {
try {
const message = JSON.parse(data.toString()) as Message
await this.handleMessage(message)
} catch (error) {
console.error('Error parsing message:', error)
}
})
this.socket.on('close', () => {
console.log(`❌ ${this.options.name} disconnected from Brain Jar`)
this.isConnected = false
if (this.options.autoReconnect) {
this.scheduleReconnect()
}
})
this.socket.on('error', (error) => {
console.error(`Connection error for ${this.options.name}:`, error)
reject(error)
})
} catch (error) {
reject(error)
}
})
}
/**
* Handle incoming message
*/
private async handleMessage(message: Message) {
// Store in Brainy for persistent memory. Subtype `'mcp-message'` marks
// these as MCP-protocol messages so consumers can filter / count them via
// `find({ type: NounType.Message, subtype: 'mcp-message' })` and so
// enforcement consumers registering a vocabulary on NounType.Message don't
// reject MCP traffic (added 7.30.1; also fixes the pre-existing missing
// `data` field by aliasing from the prior `text` field).
if (this.brainy && message.type === 'message') {
try {
await this.brainy.add({
data: `${message.from}: ${JSON.stringify(message.data)}`,
type: NounType.Message,
subtype: 'mcp-message',
metadata: {
messageId: message.id,
from: message.from,
to: message.to,
timestamp: message.timestamp,
messageType: message.type,
event: message.event
}
})
} catch (error) {
console.error('Error storing message in Brainy:', error)
}
}
// Handle sync messages (receive history)
if (message.type === 'sync' && message.data.history) {
console.log(`📜 ${this.options.name} received ${message.data.history.length} historical messages`)
// Store history in Brainy with the same subtype as live messages.
if (this.brainy) {
for (const histMsg of message.data.history) {
await this.brainy.add({
data: `${histMsg.from}: ${JSON.stringify(histMsg.data)}`,
type: NounType.Message,
subtype: 'mcp-message',
metadata: {
...histMsg
}
})
}
}
}
// Call registered handlers
const handler = this.messageHandlers.get(message.type)
if (handler) {
handler(message)
}
// Call universal handler
const universalHandler = this.messageHandlers.get('*')
if (universalHandler) {
universalHandler(message)
}
}
/**
* Send a message
*/
send(message: Partial<Message>) {
if (!this.socket || this.socket.readyState !== WebSocket.OPEN) {
console.error(`${this.options.name} is not connected`)
return
}
const fullMessage: Message = {
id: message.id || uuidv4(),
from: this.options.name,
type: message.type || 'message',
data: message.data || {},
timestamp: Date.now(),
...message
}
this.socket.send(JSON.stringify(fullMessage))
}
/**
* Send a message to specific agent(s)
*/
sendTo(recipient: string | string[], data: any) {
this.send({
to: recipient,
type: 'message',
data
})
}
/**
* Broadcast to all agents
*/
broadcast(data: any) {
this.send({
type: 'message',
data
})
}
/**
* Register a message handler
*/
on(type: string, handler: (message: Message) => void) {
this.messageHandlers.set(type, handler)
}
/**
* Remove a message handler
*/
off(type: string) {
this.messageHandlers.delete(type)
}
/**
* Search historical messages using Brainy's vector search
*/
async searchMemory(query: string, limit = 10): Promise<any[]> {
if (!this.brainy) {
console.warn('Brainy memory not initialized')
return []
}
const results = await this.brainy.find({ query, limit })
return results.map(r => ({
...r.metadata,
relevance: r.score
}))
}
/**
* Get recent messages from Brainy memory
*/
async getRecentMessages(limit = 20): Promise<any[]> {
if (!this.brainy) {
console.warn('Brainy memory not initialized')
return []
}
// Search for recent activity
const results = await this.brainy.find({ query: 'recent messages communication', limit })
return results
.map(r => r.metadata)
.sort((a: any, b: any) => b.timestamp - a.timestamp)
}
/**
* Schedule reconnection attempt
*/
private scheduleReconnect() {
if (this.reconnectTimeout) {
clearTimeout(this.reconnectTimeout)
}
this.reconnectTimeout = setTimeout(() => {
console.log(`🔄 ${this.options.name} attempting to reconnect...`)
this.connect().catch(error => {
console.error('Reconnection failed:', error)
this.scheduleReconnect()
})
}, 5000)
}
/**
* Disconnect from server
*/
disconnect() {
if (this.reconnectTimeout) {
clearTimeout(this.reconnectTimeout)
}
if (this.socket) {
this.socket.close(1000, 'Client disconnecting')
this.socket = undefined
}
this.isConnected = false
}
/**
* Check if connected
*/
getIsConnected(): boolean {
return this.isConnected
}
/**
* Get agent info
*/
getAgentInfo() {
return {
name: this.options.name,
role: this.options.role,
connected: this.isConnected
}
}
}
// Export for both environments
export default BrainyMCPClient

200
src/neural/naturalLanguageProcessorStatic.ts
View file

@ -1,200 +0,0 @@
/**
* 🧠 Natural Language Query Processor - STATIC VERSION
* No runtime initialization, no memory leaks, patterns pre-built at compile time
*
* Uses static pattern matching with 220 pre-built patterns
*/
import { Vector } from '../coreTypes.js'
import { TripleQuery } from '../triple/TripleIntelligence.js'
import { patternMatchQuery, PATTERN_STATS } from './staticPatternMatcher.js'
export interface NaturalQueryIntent {
type: 'vector' | 'field' | 'graph' | 'combined'
confidence: number
extractedTerms: {
entities?: string[]
fields?: string[]
relationships?: string[]
modifiers?: string[]
}
}
export class NaturalLanguageProcessor {
private queryHistory: Array<{ query: string; result: TripleQuery; success: boolean }>
constructor() {
this.queryHistory = []
// Patterns are static - no initialization needed!
}
/**
* No initialization needed - patterns are pre-built!
*/
async init(): Promise<void> {
// Nothing to do - patterns are compiled into the code
return Promise.resolve()
}
/**
* Process natural language query into structured Triple Intelligence query
* @param naturalQuery The natural language query string
* @param queryEmbedding Pre-computed embedding from Brainy (passed in to avoid circular dependency)
*/
async processNaturalQuery(naturalQuery: string, queryEmbedding?: Vector): Promise<TripleQuery> {
// Use static pattern matcher (no async, no memory allocation!)
const structuredQuery = patternMatchQuery(naturalQuery, queryEmbedding)
// Step 3: Enhance with intent analysis if needed
if (!structuredQuery.where && !structuredQuery.connected) {
const intent = await this.analyzeIntent(naturalQuery)
// Add metadata based on intent
if (intent.type === 'field' && intent.extractedTerms.fields) {
structuredQuery.where = this.buildFieldConstraints(intent.extractedTerms.fields)
}
}
// Track for learning (but don't create new Brainy!)
this.queryHistory.push({
query: naturalQuery,
result: structuredQuery,
success: false // Will be updated based on user interaction
})
// Keep history limited to prevent memory growth
if (this.queryHistory.length > 100) {
this.queryHistory.shift()
}
return structuredQuery
}
/**
* Analyze query intent using keywords
*/
private async analyzeIntent(query: string): Promise<NaturalQueryIntent> {
const lowerQuery = query.toLowerCase()
// Check for field-specific keywords
const fieldKeywords = ['where', 'filter', 'with', 'has', 'contains', 'equals', 'greater', 'less', 'between']
const hasFieldIntent = fieldKeywords.some(kw => lowerQuery.includes(kw))
// Check for graph keywords
const graphKeywords = ['related', 'connected', 'linked', 'associated', 'references']
const hasGraphIntent = graphKeywords.some(kw => lowerQuery.includes(kw))
// Determine type
let type: NaturalQueryIntent['type'] = 'vector'
if (hasFieldIntent && hasGraphIntent) {
type = 'combined'
} else if (hasFieldIntent) {
type = 'field'
} else if (hasGraphIntent) {
type = 'graph'
}
return {
type,
confidence: 0.8,
extractedTerms: {
fields: hasFieldIntent ? this.extractFieldTerms(query) : undefined,
relationships: hasGraphIntent ? this.extractRelationshipTerms(query) : undefined
}
}
}
/**
* Extract field terms from query
*/
private extractFieldTerms(query: string): string[] {
const terms: string[] = []
// Simple extraction of potential field names
const words = query.split(/\s+/)
const fieldIndicators = ['year', 'date', 'author', 'type', 'category', 'status', 'price']
for (const word of words) {
if (fieldIndicators.includes(word.toLowerCase())) {
terms.push(word.toLowerCase())
}
}
return terms
}
/**
* Extract relationship terms
*/
private extractRelationshipTerms(query: string): string[] {
const terms: string[] = []
const relationshipWords = ['related', 'connected', 'linked', 'references', 'cites']
const words = query.toLowerCase().split(/\s+/)
for (const word of words) {
if (relationshipWords.includes(word)) {
terms.push(word)
}
}
return terms
}
/**
* Build field constraints from extracted terms
*/
private buildFieldConstraints(fields: string[]): Record<string, any> {
const constraints: Record<string, any> = {}
// Simple mapping for common fields
for (const field of fields) {
// This would be enhanced with actual value extraction
constraints[field] = { exists: true }
}
return constraints
}
/**
* Find similar queries from history (without using Brainy)
* NOTE: Currently unused - reserved for future query caching optimization
*/
private findSimilarQueries(embedding: Vector): Array<{
query: string
result: TripleQuery
similarity: number
}> {
// Not implemented - not required for core functionality
// Would implement cosine similarity against queryHistory if needed
return []
}
/**
* Adapt a previous query for new input
*/
private adaptQuery(newQuery: string, previousResult: TripleQuery): TripleQuery {
return previousResult
}
/**
* Extract entities from query
*/
private async extractEntities(query: string): Promise<string[]> {
// Could use the Entity Registry here if available
return []
}
/**
* Build query from components
*/
private buildQuery(
query: string,
intent: NaturalQueryIntent,
entities: string[]
): TripleQuery {
return {
like: query,
limit: 10
}
}
}

633
src/neural/neuralImportAugmentation.ts
View file

@ -1,633 +0,0 @@
/**
* Neural Import - AI-Powered Data Understanding
*
* Standalone implementation for intelligent data processing.
*/
import { NounType, VerbType } from '../types/graphTypes.js'
import * as fs from '../universal/fs.js'
import * as path from '../universal/path.js'
import { prodLog } from '../utils/logger.js'
// Neural Import Analysis Types
export interface NeuralAnalysisResult {
detectedEntities: DetectedEntity[]
detectedRelationships: DetectedRelationship[]
confidence: number
insights: NeuralInsight[]
}
export interface DetectedEntity {
originalData: any
nounType: string
confidence: number
suggestedId: string
reasoning: string
alternativeTypes: Array<{ type: string, confidence: number }>
}
export interface DetectedRelationship {
sourceId: string
targetId: string
verbType: string
confidence: number
weight: number
reasoning: string
context: string
metadata?: Record<string, any>
}
export interface NeuralInsight {
type: 'hierarchy' | 'cluster' | 'pattern' | 'anomaly' | 'opportunity'
description: string
confidence: number
affectedEntities: string[]
recommendation?: string
}
export interface NeuralImportConfig {
confidenceThreshold: number
enableWeights: boolean
skipDuplicates: boolean
categoryFilter?: string[]
dataType?: string
}
/**
* Neural Import Augmentation - Unified Implementation
* Processes data with AI before storage operations
*/
export class NeuralImportAugmentation {
readonly name = 'neural-import'
private operations = ['add', 'addNoun', 'addVerb', 'all']
protected config: NeuralImportConfig
private analysisCache = new Map<string, NeuralAnalysisResult>()
private context?: { brain: any }
constructor(config: Partial<NeuralImportConfig> = {}) {
this.config = {
confidenceThreshold: 0.7,
enableWeights: true,
skipDuplicates: true,
dataType: 'json',
...config
}
}
async init(): Promise<void> {
// No external dependencies to initialize
}
private log(message: string, _level?: string): void {
// Silent by default
}
/**
* Execute augmentation - process data with AI before storage
*/
async execute<T = any>(
operation: string,
params: any,
next: () => Promise<T>
): Promise<T> {
// Only process on add operations
if (!this.operations.includes(operation)) {
return next()
}
try {
// Extract data from params based on operation
const rawData = this.extractRawData(operation, params)
if (!rawData) {
return next()
}
// Perform neural analysis
const analysis = await this.performNeuralAnalysis(rawData, this.config)
// Enhance params with neural insights
if (params.metadata) {
params.metadata._neuralProcessed = true
params.metadata._neuralConfidence = analysis.confidence
params.metadata._detectedEntities = analysis.detectedEntities.length
params.metadata._detectedRelationships = analysis.detectedRelationships.length
params.metadata._neuralInsights = analysis.insights
} else if (typeof params === 'object') {
params.metadata = {
_neuralProcessed: true,
_neuralConfidence: analysis.confidence,
_detectedEntities: analysis.detectedEntities.length,
_detectedRelationships: analysis.detectedRelationships.length,
_neuralInsights: analysis.insights
}
}
// Store neural analysis for later retrieval
await this.storeNeuralAnalysis(analysis)
// If we detected entities/relationships, potentially add them
if (this.context?.brain && analysis.detectedEntities.length > 0) {
// This could automatically create entities/relationships
// But for now, just enhance the metadata
this.log(`Detected ${analysis.detectedEntities.length} entities and ${analysis.detectedRelationships.length} relationships`)
}
// Continue with enhanced data
return next()
} catch (error) {
this.log(`Neural analysis failed: ${error}`, 'warn')
// Continue without neural processing
return next()
}
}
/**
* Extract raw data from operation params
*/
private extractRawData(operation: string, params: any): any {
switch (operation) {
case 'add':
return params.content || params.data || params
case 'addNoun':
return params.noun || params.data || params
case 'addVerb':
return params.verb || params
case 'addBatch':
return params.items || params.batch || params
default:
return null
}
}
/**
* Get the full neural analysis result (for external use)
*/
async getNeuralAnalysis(rawData: Buffer | string, dataType?: string): Promise<NeuralAnalysisResult> {
const parsedData = await this.parseRawData(rawData, dataType || this.config.dataType || 'json')
return await this.performNeuralAnalysis(parsedData, this.config)
}
/**
* Parse raw data based on type
*/
private async parseRawData(rawData: Buffer | string, dataType: string): Promise<any[]> {
const content = typeof rawData === 'string' ? rawData : rawData.toString('utf8')
switch (dataType.toLowerCase()) {
case 'json':
try {
const jsonData = JSON.parse(content)
return Array.isArray(jsonData) ? jsonData : [jsonData]
} catch {
// If JSON parse fails, treat as text
return [{ text: content }]
}
case 'csv':
return this.parseCSV(content)
case 'yaml':
case 'yml':
return this.parseYAML(content)
case 'txt':
case 'text':
// Split text into sentences/paragraphs for analysis
return content.split(/\n+/).filter(line => line.trim()).map(line => ({ text: line }))
default:
// Unknown type, treat as text
return [{ text: content }]
}
}
/**
* Parse CSV data - handles quoted values, escaped quotes, and edge cases
*/
private parseCSV(content: string): any[] {
const lines = content.split('\n')
if (lines.length === 0) return []
// Parse a CSV line handling quotes
const parseLine = (line: string): string[] => {
const result: string[] = []
let current = ''
let inQuotes = false
let i = 0
while (i < line.length) {
const char = line[i]
const nextChar = line[i + 1]
if (char === '"') {
if (inQuotes && nextChar === '"') {
// Escaped quote
current += '"'
i += 2
} else {
// Toggle quote mode
inQuotes = !inQuotes
i++
}
} else if (char === ',' && !inQuotes) {
// Field separator
result.push(current.trim())
current = ''
i++
} else {
current += char
i++
}
}
// Add last field
result.push(current.trim())
return result
}
// Parse headers
const headers = parseLine(lines[0])
const data = []
// Parse data rows
for (let i = 1; i < lines.length; i++) {
const line = lines[i].trim()
if (!line) continue // Skip empty lines
const values = parseLine(line)
const row: any = {}
headers.forEach((header, index) => {
const value = values[index] || ''
// Try to parse numbers
const num = Number(value)
row[header] = !isNaN(num) && value !== '' ? num : value
})
data.push(row)
}
return data
}
/**
* Parse YAML data
*/
private parseYAML(content: string): any[] {
try {
// Simple YAML parser for basic structures
// For full YAML support, we'd use js-yaml library
const lines = content.split('\n')
const result: any[] = []
let currentObject: any = null
let currentIndent = 0
for (const line of lines) {
const trimmed = line.trim()
if (!trimmed || trimmed.startsWith('#')) continue // Skip empty lines and comments
// Calculate indentation
const indent = line.length - line.trimStart().length
// Check for array item
if (trimmed.startsWith('- ')) {
const value = trimmed.substring(2).trim()
if (indent === 0) {
// Top-level array item
if (value.includes(':')) {
// Object in array
currentObject = {}
result.push(currentObject)
const [key, val] = value.split(':').map(s => s.trim())
currentObject[key] = this.parseYAMLValue(val)
} else {
result.push(this.parseYAMLValue(value))
}
} else if (currentObject) {
// Nested array
const lastKey = Object.keys(currentObject).pop()
if (lastKey) {
if (!Array.isArray(currentObject[lastKey])) {
currentObject[lastKey] = []
}
currentObject[lastKey].push(this.parseYAMLValue(value))
}
}
} else if (trimmed.includes(':')) {
// Key-value pair
const colonIndex = trimmed.indexOf(':')
const key = trimmed.substring(0, colonIndex).trim()
const value = trimmed.substring(colonIndex + 1).trim()
if (indent === 0) {
// Top-level object
if (!currentObject) {
currentObject = {}
result.push(currentObject)
}
currentObject[key] = this.parseYAMLValue(value)
currentIndent = 0
} else if (currentObject) {
// Nested object
if (indent > currentIndent && !value) {
// Start of nested object
const lastKey = Object.keys(currentObject).pop()
if (lastKey) {
currentObject[lastKey] = { [key]: '' }
}
} else {
currentObject[key] = this.parseYAMLValue(value)
}
currentIndent = indent
}
}
}
// If we built a single object and not an array, wrap it
if (result.length === 0 && currentObject) {
result.push(currentObject)
}
return result.length > 0 ? result : [{ text: content }]
} catch (error) {
prodLog.warn('YAML parsing failed, treating as text:', error)
return [{ text: content }]
}
}
/**
* Parse a YAML value (handle strings, numbers, booleans, null)
*/
private parseYAMLValue(value: string): any {
if (!value || value === '~' || value === 'null') return null
if (value === 'true') return true
if (value === 'false') return false
// Remove quotes if present
if ((value.startsWith('"') && value.endsWith('"')) ||
(value.startsWith("'") && value.endsWith("'"))) {
return value.slice(1, -1)
}
// Try to parse as number
const num = Number(value)
if (!isNaN(num) && value !== '') return num
return value
}
/**
* Perform neural analysis on parsed data
*/
private async performNeuralAnalysis(data: any[], config?: any): Promise<NeuralAnalysisResult> {
const detectedEntities: DetectedEntity[] = []
const detectedRelationships: DetectedRelationship[] = []
const insights: NeuralInsight[] = []
// Simple entity detection (in real implementation, would use ML)
for (const item of data) {
if (typeof item === 'object') {
// Detect entities from object properties
const entityId = item.id || item.name || item.title || `entity_${Date.now()}_${Math.random()}`
detectedEntities.push({
originalData: item,
nounType: await this.inferNounType(item),
confidence: 0.85,
suggestedId: String(entityId),
reasoning: 'Detected from structured data',
alternativeTypes: []
})
// Detect relationships from references
await this.detectRelationships(item, entityId, detectedRelationships)
}
}
// Generate insights
if (detectedEntities.length > 10) {
insights.push({
type: 'pattern',
description: `Large dataset with ${detectedEntities.length} entities detected`,
confidence: 0.9,
affectedEntities: detectedEntities.slice(0, 5).map(e => e.suggestedId),
recommendation: 'Consider batch processing for optimal performance'
})
}
// Look for clusters
const typeGroups = this.groupByType(detectedEntities)
if (Object.keys(typeGroups).length > 1) {
insights.push({
type: 'cluster',
description: `Multiple entity types detected: ${Object.keys(typeGroups).join(', ')}`,
confidence: 0.8,
affectedEntities: [],
recommendation: 'Data contains diverse entity types suitable for graph analysis'
})
}
return {
detectedEntities,
detectedRelationships,
confidence: detectedEntities.length > 0 ? 0.85 : 0.5,
insights
}
}
/**
* Infer noun type from object structure using field heuristics
*/
private async inferNounType(obj: any): Promise<string> {
if (typeof obj !== 'object' || obj === null) return NounType.Thing
// Check for explicit type field
if (obj.type && typeof obj.type === 'string') {
const normalized = obj.type.charAt(0).toUpperCase() + obj.type.slice(1)
if (Object.values(NounType).includes(normalized as NounType)) {
return normalized as NounType
}
}
if (obj.email || obj.firstName || obj.lastName || obj.username) return NounType.Person
if (obj.companyName || obj.organizationId || obj.employees) return NounType.Organization
if (obj.latitude || obj.longitude || obj.address || obj.city) return NounType.Location
if ((obj.content && (obj.title || obj.author)) || obj.pages) return NounType.Document
if (obj.startTime || obj.endTime || obj.date || obj.attendees) return NounType.Event
if (obj.price || obj.sku || obj.productId) return NounType.Product
if ((obj.status && obj.assignee) || obj.priority) return NounType.Task
if (Array.isArray(obj.data) || obj.rows || obj.columns) return NounType.Dataset
return NounType.Thing
}
/**
* Detect relationships from object references
*/
private async detectRelationships(obj: any, sourceId: string, relationships: DetectedRelationship[]): Promise<void> {
// Look for reference patterns
for (const [key, value] of Object.entries(obj)) {
if (key.endsWith('Id') || key.endsWith('_id') || key === 'parentId' || key === 'userId') {
relationships.push({
sourceId,
targetId: String(value),
verbType: await this.inferVerbType(key, obj, { id: value }),
confidence: 0.75,
weight: 1,
reasoning: `Reference detected in field: ${key}`,
context: key
})
}
// Array of IDs
if (Array.isArray(value) && value.length > 0 && typeof value[0] === 'string') {
if (key.endsWith('Ids') || key.endsWith('_ids')) {
for (const targetId of value) {
relationships.push({
sourceId,
targetId: String(targetId),
verbType: await this.inferVerbType(key, obj, { id: targetId }),
confidence: 0.7,
weight: 1,
reasoning: `Array reference in field: ${key}`,
context: key
})
}
}
}
}
}
/**
* Infer verb type from field name using common patterns
*/
private async inferVerbType(fieldName: string, _sourceObj?: any, _targetObj?: any): Promise<string> {
const field = fieldName.toLowerCase()
if (field.includes('parent') || field.includes('child') || field.includes('contain')) {
return VerbType.Contains
}
if (field.includes('owner') || field.includes('created') || field.includes('author')) {
return VerbType.Creates
}
if (field.includes('member') || field.includes('belong')) {
return VerbType.MemberOf
}
if (field.includes('depend') || field.includes('require')) {
return VerbType.DependsOn
}
if (field.includes('ref') || field.includes('link') || field.includes('source')) {
return VerbType.References
}
return VerbType.RelatedTo
}
/**
* Group entities by type
*/
private groupByType(entities: DetectedEntity[]): Record<string, DetectedEntity[]> {
const groups: Record<string, DetectedEntity[]> = {}
for (const entity of entities) {
if (!groups[entity.nounType]) {
groups[entity.nounType] = []
}
groups[entity.nounType].push(entity)
}
return groups
}
/**
* Store neural analysis results
*/
private async storeNeuralAnalysis(analysis: NeuralAnalysisResult): Promise<void> {
// Cache the analysis for potential later use
const key = `analysis_${Date.now()}`
this.analysisCache.set(key, analysis)
// Limit cache size
if (this.analysisCache.size > 100) {
const firstKey = this.analysisCache.keys().next().value
if (firstKey) {
this.analysisCache.delete(firstKey)
}
}
}
/**
* Helper to get data type from file path
*/
private getDataTypeFromPath(filePath: string): string {
const ext = path.extname(filePath).toLowerCase()
switch (ext) {
case '.json': return 'json'
case '.csv': return 'csv'
case '.txt': return 'text'
case '.yaml':
case '.yml': return 'yaml'
default: return 'text'
}
}
/**
* PUBLIC API: Process raw data (for external use, like Synapses)
* This maintains compatibility with code that wants to use Neural Import directly
*/
async processRawData(
rawData: Buffer | string,
dataType: string,
options?: Record<string, unknown>
): Promise<{
success: boolean
data: {
nouns: string[]
verbs: string[]
confidence?: number
insights?: Array<{
type: string
description: string
confidence: number
}>
metadata?: Record<string, unknown>
}
error?: string
}> {
try {
const analysis = await this.getNeuralAnalysis(rawData, dataType)
// Convert to legacy format for compatibility
const nouns = analysis.detectedEntities.map(e => e.suggestedId)
const verbs = analysis.detectedRelationships.map(r =>
`${r.sourceId}->${r.verbType}->${r.targetId}`
)
return {
success: true,
data: {
nouns,
verbs,
confidence: analysis.confidence,
insights: analysis.insights.map(i => ({
type: i.type,
description: i.description,
confidence: i.confidence
})),
metadata: {
detectedEntities: analysis.detectedEntities.length,
detectedRelationships: analysis.detectedRelationships.length,
timestamp: new Date().toISOString()
}
}
}
} catch (error) {
return {
success: false,
data: { nouns: [], verbs: [] },
error: error instanceof Error ? error.message : 'Neural analysis failed'
}
}
}
}

479
src/neural/presets.ts
View file

@ -1,479 +0,0 @@
/**
* Smart Import Presets - Zero-Configuration Auto-Detection
*
* Automatically selects optimal import strategy based on:
* - File type (Excel, CSV, PDF, Markdown, JSON)
* - File size and row count
* - Column structure (explicit relationships vs narrative)
* - Available memory and performance requirements
*
* Production-ready: Handles billions of entities with optimal performance
*/
import { NounType, VerbType } from '../types/graphTypes.js'
/**
* Signal types used for entity classification
*/
export type SignalType = 'embedding' | 'exact' | 'pattern' | 'context'
/**
* Strategy types used for relationship extraction
*/
export type StrategyType = 'explicit' | 'pattern' | 'embedding'
/**
* Import context for preset auto-detection
*/
export interface ImportContext {
fileType?: 'excel' | 'csv' | 'json' | 'pdf' | 'markdown' | 'unknown'
fileSize?: number // bytes
rowCount?: number
hasExplicitColumns?: boolean // Has "Related Terms" or similar columns
hasNarrativeContent?: boolean // Has long-form text/descriptions
avgDefinitionLength?: number // Average length of definitions
memoryAvailable?: number // bytes
}
/**
* Signal configuration with weights
*/
export interface SignalConfig {
enabled: SignalType[]
weights: Record<SignalType, number>
timeout: number // milliseconds
}
/**
* Strategy configuration with priorities
*/
export interface StrategyConfig {
enabled: StrategyType[]
timeout: number // milliseconds
earlyTermination: boolean
minConfidence: number
}
/**
* Complete preset configuration
*/
export interface PresetConfig {
name: string
description: string
signals: SignalConfig
strategies: StrategyConfig
streaming: boolean
batchSize: number
}
/**
* Fast Preset - For large imports (>10K rows)
*
* Optimized for speed over accuracy:
* - Only exact match and pattern signals
* - Only explicit strategy (O(1) lookups)
* - Streaming enabled for memory efficiency
* - Early termination on first high-confidence match
*
* Use case: Bulk imports, data migrations
* Performance: ~10ms per row
* Accuracy: ~85%
*/
export const FAST_PRESET: PresetConfig = {
name: 'fast',
description: 'Fast bulk import for large datasets',
signals: {
enabled: ['exact', 'pattern'],
weights: {
exact: 0.70,
pattern: 0.30,
embedding: 0,
context: 0
},
timeout: 50
},
strategies: {
enabled: ['explicit'],
timeout: 100,
earlyTermination: true,
minConfidence: 0.70
},
streaming: true,
batchSize: 1000
}
/**
* Balanced Preset - Default for most imports
*
* Good balance of speed and accuracy:
* - All signals except context (embedding, exact, pattern)
* - All strategies with smart ordering
* - Moderate timeouts
* - Early termination after high-confidence matches
*
* Use case: Standard imports, general glossaries
* Performance: ~30ms per row
* Accuracy: ~92%
*/
export const BALANCED_PRESET: PresetConfig = {
name: 'balanced',
description: 'Balanced speed and accuracy for most imports',
signals: {
enabled: ['exact', 'embedding', 'pattern'],
weights: {
exact: 0.40,
embedding: 0.35,
pattern: 0.25,
context: 0
},
timeout: 100
},
strategies: {
enabled: ['explicit', 'pattern', 'embedding'],
timeout: 200,
earlyTermination: true,
minConfidence: 0.65
},
streaming: false,
batchSize: 500
}
/**
* Accurate Preset - For small, critical imports
*
* Optimized for accuracy over speed:
* - All signals including context
* - All strategies, no early termination
* - Longer timeouts for thorough analysis
* - Lower confidence threshold (accept more matches)
*
* Use case: Knowledge bases, critical taxonomies
* Performance: ~100ms per row
* Accuracy: ~97%
*/
export const ACCURATE_PRESET: PresetConfig = {
name: 'accurate',
description: 'Maximum accuracy for critical imports',
signals: {
enabled: ['exact', 'embedding', 'pattern', 'context'],
weights: {
exact: 0.40,
embedding: 0.35,
pattern: 0.20,
context: 0.05
},
timeout: 500
},
strategies: {
enabled: ['explicit', 'pattern', 'embedding'],
timeout: 1000,
earlyTermination: false,
minConfidence: 0.50
},
streaming: false,
batchSize: 100
}
/**
* Explicit Preset - For glossaries with relationship columns
*
* Optimized for structured data with explicit relationships:
* - Only exact match signals (no AI needed)
* - Only explicit and pattern strategies
* - Fast, deterministic results
* - Perfect for Excel/CSV with "Related Terms" columns
*
* Use case: structured taxonomies and glossaries from spreadsheet sources
* Performance: ~5ms per row
* Accuracy: ~99% (high confidence)
*/
export const EXPLICIT_PRESET: PresetConfig = {
name: 'explicit',
description: 'For glossaries with explicit relationship columns',
signals: {
enabled: ['exact', 'pattern'],
weights: {
exact: 0.70,
pattern: 0.30,
embedding: 0,
context: 0
},
timeout: 50
},
strategies: {
enabled: ['explicit', 'pattern'],
timeout: 100,
earlyTermination: true,
minConfidence: 0.80
},
streaming: false,
batchSize: 500
}
/**
* Pattern Preset - For documents with narrative content
*
* Optimized for unstructured text with rich patterns:
* - Embedding and pattern signals (semantic understanding)
* - Pattern and embedding strategies
* - Good for PDFs, articles, documentation
*
* Use case: PDF imports, markdown docs, articles
* Performance: ~50ms per row
* Accuracy: ~90%
*/
export const PATTERN_PRESET: PresetConfig = {
name: 'pattern',
description: 'For documents with narrative content',
signals: {
enabled: ['embedding', 'pattern', 'context'],
weights: {
embedding: 0.50,
pattern: 0.40,
context: 0.10,
exact: 0
},
timeout: 200
},
strategies: {
enabled: ['pattern', 'embedding'],
timeout: 300,
earlyTermination: false,
minConfidence: 0.60
},
streaming: false,
batchSize: 200
}
/**
* All available presets
*/
export const PRESETS: Record<string, PresetConfig> = {
fast: FAST_PRESET,
balanced: BALANCED_PRESET,
accurate: ACCURATE_PRESET,
explicit: EXPLICIT_PRESET,
pattern: PATTERN_PRESET
}
/**
* Auto-detect optimal preset based on import context
*
* Decision tree:
* 1. Large dataset (>10K rows or >10MB) → fast
* 2. Small dataset (<100 rows) → accurate
* 3. Excel/CSV with explicit columns → explicit
* 4. PDF/Markdown with long content → pattern
* 5. Default → balanced
*
* @param context Import context (file type, size, structure)
* @returns Optimal preset configuration
*/
export function autoDetectPreset(context: ImportContext = {}): PresetConfig {
const {
fileType = 'unknown',
fileSize = 0,
rowCount = 0,
hasExplicitColumns = false,
hasNarrativeContent = false,
avgDefinitionLength = 0
} = context
// Rule 1: Large imports → fast preset (prioritize speed)
if (rowCount > 10000 || fileSize > 10_000_000) {
return FAST_PRESET
}
// Rule 2: Small critical imports → accurate preset (prioritize accuracy)
if (rowCount > 0 && rowCount < 100) {
return ACCURATE_PRESET
}
// Rule 3: Structured data with explicit relationships → explicit preset
// (Handles spreadsheet imports where relationships are encoded in columns.)
if (hasExplicitColumns && (fileType === 'excel' || fileType === 'csv')) {
return EXPLICIT_PRESET
}
// Rule 4: Narrative content → pattern preset
// Good for PDFs, articles, documentation
if (
hasNarrativeContent ||
fileType === 'pdf' ||
fileType === 'markdown' ||
avgDefinitionLength > 500
) {
return PATTERN_PRESET
}
// Rule 5: JSON data → balanced preset
if (fileType === 'json') {
return BALANCED_PRESET
}
// Default: balanced preset
return BALANCED_PRESET
}
/**
* Get preset by name
*
* @param name Preset name (fast, balanced, accurate, explicit, pattern)
* @returns Preset configuration
* @throws Error if preset not found
*/
export function getPreset(name: string): PresetConfig {
const preset = PRESETS[name.toLowerCase()]
if (!preset) {
throw new Error(`Unknown preset: ${name}. Available: ${Object.keys(PRESETS).join(', ')}`)
}
return preset
}
/**
* Get all available preset names
*
* @returns Array of preset names
*/
export function getPresetNames(): string[] {
return Object.keys(PRESETS)
}
/**
* Explain why a preset was selected
*
* @param context Import context
* @returns Human-readable explanation
*/
export function explainPresetChoice(context: ImportContext = {}): string {
const {
fileType = 'unknown',
fileSize = 0,
rowCount = 0,
hasExplicitColumns = false,
hasNarrativeContent = false,
avgDefinitionLength = 0
} = context
if (rowCount > 10000 || fileSize > 10_000_000) {
return `Large dataset (${rowCount} rows, ${(fileSize / 1_000_000).toFixed(1)}MB) → fast preset for optimal performance`
}
if (rowCount > 0 && rowCount < 100) {
return `Small critical dataset (${rowCount} rows) → accurate preset for maximum accuracy`
}
if (hasExplicitColumns && (fileType === 'excel' || fileType === 'csv')) {
return `${fileType.toUpperCase()} with explicit relationship columns → explicit preset for deterministic results`
}
if (hasNarrativeContent || fileType === 'pdf' || fileType === 'markdown') {
return `Narrative content (${fileType}) → pattern preset for semantic understanding`
}
if (fileType === 'json') {
return `JSON data → balanced preset for structured imports`
}
return `Standard import → balanced preset (default)`
}
/**
* Create custom preset by merging with base preset
*
* @param baseName Base preset name
* @param overrides Custom overrides
* @returns Custom preset configuration
*/
export function createCustomPreset(
baseName: string,
overrides: Partial<PresetConfig>
): PresetConfig {
const base = getPreset(baseName)
return {
...base,
...overrides,
signals: {
...base.signals,
...(overrides.signals || {})
},
strategies: {
...base.strategies,
...(overrides.strategies || {})
}
}
}
/**
* Validate preset configuration
*
* @param preset Preset to validate
* @returns True if valid, throws error otherwise
*/
export function validatePreset(preset: PresetConfig): boolean {
// Validate signals
if (preset.signals.enabled.length === 0) {
throw new Error('Preset must have at least one enabled signal')
}
// Validate strategies
if (preset.strategies.enabled.length === 0) {
throw new Error('Preset must have at least one enabled strategy')
}
// Validate weights sum to ~1.0
const enabledSignals = preset.signals.enabled
const totalWeight = enabledSignals.reduce(
(sum, signal) => sum + preset.signals.weights[signal],
0
)
if (Math.abs(totalWeight - 1.0) > 0.01) {
throw new Error(
`Signal weights must sum to 1.0, got ${totalWeight.toFixed(2)}`
)
}
// Validate timeouts
if (preset.signals.timeout <= 0 || preset.strategies.timeout <= 0) {
throw new Error('Timeouts must be positive')
}
// Validate batch size
if (preset.batchSize <= 0) {
throw new Error('Batch size must be positive')
}
return true
}
/**
* Format preset for display
*
* @param preset Preset configuration
* @returns Human-readable preset summary
*/
export function formatPreset(preset: PresetConfig): string {
const lines = [
`Preset: ${preset.name}`,
`Description: ${preset.description}`,
'',
'Signals:',
...preset.signals.enabled.map(
(s) => ` - ${s}: ${(preset.signals.weights[s] * 100).toFixed(0)}%`
),
` Timeout: ${preset.signals.timeout}ms`,
'',
'Strategies:',
...preset.strategies.enabled.map((s) => ` - ${s}`),
` Timeout: ${preset.strategies.timeout}ms`,
` Early termination: ${preset.strategies.earlyTermination}`,
` Min confidence: ${preset.strategies.minConfidence}`,
'',
`Streaming: ${preset.streaming}`,
`Batch size: ${preset.batchSize}`
]
return lines.join('\n')
}

309
src/neural/relationshipConfidence.ts
View file

@ -1,309 +0,0 @@
/**
* Relationship Confidence Scoring
*
* Scores the confidence of detected relationships based on multiple factors:
* - Entity proximity in text
* - Entity confidence scores
* - Pattern matches
* - Structural analysis
*/
import { ExtractedEntity } from './entityExtractor.js'
import { VerbType } from '../types/graphTypes.js'
import { RelationEvidence } from '../types/brainy.types.js'
/**
* Detected relationship with confidence
*/
export interface DetectedRelationship {
sourceEntity: ExtractedEntity
targetEntity: ExtractedEntity
verbType: VerbType
confidence: number
evidence: RelationEvidence
}
/**
* Configuration for relationship detection
*/
export interface RelationshipDetectionConfig {
minConfidence?: number // Minimum confidence to return (default: 0.5)
maxDistance?: number // Maximum token distance between entities (default: 50)
useProximityBoost?: boolean // Boost score based on proximity (default: true)
usePatternMatching?: boolean // Use verb pattern matching (default: true)
useStructuralAnalysis?: boolean // Analyze sentence structure (default: true)
}
/**
* Relationship confidence scorer
*/
export class RelationshipConfidenceScorer {
private config: Required<RelationshipDetectionConfig>
constructor(config: RelationshipDetectionConfig = {}) {
this.config = {
minConfidence: config.minConfidence || 0.5,
maxDistance: config.maxDistance || 50,
useProximityBoost: config.useProximityBoost !== false,
usePatternMatching: config.usePatternMatching !== false,
useStructuralAnalysis: config.useStructuralAnalysis !== false
}
}
/**
* Score a potential relationship between two entities
*/
scoreRelationship(
source: ExtractedEntity,
target: ExtractedEntity,
verbType: VerbType,
context: string
): { confidence: number, evidence: RelationEvidence } {
let confidence = 0.5 // Base confidence
// Evidence tracking
const reasoningParts: string[] = []
// Factor 1: Proximity boost (closer entities = higher confidence)
if (this.config.useProximityBoost) {
const proximityBoost = this.calculateProximityBoost(source, target)
confidence += proximityBoost
if (proximityBoost > 0) {
reasoningParts.push(
`Entities are close together (boost: +${proximityBoost.toFixed(2)})`
)
}
}
// Factor 2: Entity confidence boost
const entityConfidence = (source.confidence + target.confidence) / 2
const entityBoost = (entityConfidence - 0.5) * 0.2 // Scale to 0-0.2
confidence *= (1 + entityBoost)
if (entityBoost > 0) {
reasoningParts.push(
`High entity confidence (boost: ${entityBoost.toFixed(2)})`
)
}
// Factor 3: Pattern match boost
if (this.config.usePatternMatching) {
const patternBoost = this.checkVerbPattern(source, target, verbType, context)
confidence += patternBoost
if (patternBoost > 0) {
reasoningParts.push(
`Matches relationship pattern (boost: +${patternBoost.toFixed(2)})`
)
}
}
// Factor 4: Structural boost (same sentence, clause, etc.)
if (this.config.useStructuralAnalysis) {
const structuralBoost = this.analyzeStructure(source, target, context)
confidence += structuralBoost
if (structuralBoost > 0) {
reasoningParts.push(
`Structural relationship (boost: +${structuralBoost.toFixed(2)})`
)
}
}
// Cap confidence at 1.0
confidence = Math.min(confidence, 1.0)
// Extract source text evidence
const start = Math.min(source.position.start, target.position.start)
const end = Math.max(source.position.end, target.position.end)
const evidence: RelationEvidence = {
sourceText: context.substring(start, end),
position: { start, end },
method: 'neural',
reasoning: reasoningParts.join('; ')
}
return { confidence, evidence }
}
/**
* Calculate proximity boost based on distance between entities
*/
private calculateProximityBoost(
source: ExtractedEntity,
target: ExtractedEntity
): number {
const distance = Math.abs(source.position.start - target.position.start)
if (distance === 0) return 0 // Same position, not meaningful
// Very close (< 20 chars): +0.2
if (distance < 20) return 0.2
// Close (< 50 chars): +0.1
if (distance < 50) return 0.1
// Medium (< 100 chars): +0.05
if (distance < 100) return 0.05
// Far (> 100 chars): no boost
return 0
}
/**
* Check if entities match a verb pattern
*/
private checkVerbPattern(
source: ExtractedEntity,
target: ExtractedEntity,
verbType: VerbType,
context: string
): number {
const contextBetween = this.getContextBetween(source, target, context)
const contextLower = contextBetween.toLowerCase()
// Verb-specific patterns
const patterns: Record<string, string[]> = {
[VerbType.Creates]: ['creates', 'made', 'built', 'developed', 'produces'],
[VerbType.Owns]: ['owns', 'belongs to', 'possessed by', 'has'],
[VerbType.Contains]: ['contains', 'includes', 'has', 'holds'],
[VerbType.Requires]: ['requires', 'needs', 'depends on', 'relies on'],
[VerbType.Uses]: ['uses', 'utilizes', 'employs', 'applies'],
[VerbType.ReportsTo]: ['manages', 'oversees', 'supervises', 'controls'],
[VerbType.Causes]: ['influences', 'affects', 'impacts', 'shapes', 'causes'],
[VerbType.DependsOn]: ['depends on', 'relies on', 'based on'],
[VerbType.Modifies]: ['modifies', 'changes', 'alters', 'updates'],
[VerbType.References]: ['references', 'cites', 'mentions', 'refers to']
}
const verbPatterns = patterns[verbType] || []
for (const pattern of verbPatterns) {
if (contextLower.includes(pattern)) {
return 0.2 // Strong pattern match
}
}
return 0 // No pattern match
}
/**
* Analyze structural relationship
*/
private analyzeStructure(
source: ExtractedEntity,
target: ExtractedEntity,
context: string
): number {
const contextBetween = this.getContextBetween(source, target, context)
// Same sentence (no sentence-ending punctuation between them)
if (!contextBetween.match(/[.!?]/)) {
return 0.1
}
// Same paragraph (single newline between them)
if (!contextBetween.match(/\n\n/)) {
return 0.05
}
return 0
}
/**
* Get context text between two entities
*/
private getContextBetween(
source: ExtractedEntity,
target: ExtractedEntity,
context: string
): string {
const start = Math.min(source.position.end, target.position.end)
const end = Math.max(source.position.start, target.position.start)
if (start >= end) return ''
return context.substring(start, end)
}
/**
* Detect relationships between a list of entities
*/
detectRelationships(
entities: ExtractedEntity[],
context: string,
verbHints?: VerbType[]
): DetectedRelationship[] {
const relationships: DetectedRelationship[] = []
const verbs = verbHints || [
VerbType.Creates,
VerbType.Uses,
VerbType.Contains,
VerbType.Requires,
VerbType.RelatedTo
]
// Check all entity pairs
for (let i = 0; i < entities.length; i++) {
for (let j = i + 1; j < entities.length; j++) {
const source = entities[i]
const target = entities[j]
// Check distance
const distance = Math.abs(source.position.start - target.position.start)
if (distance > this.config.maxDistance) {
continue // Too far apart
}
// Try each verb type
for (const verbType of verbs) {
const { confidence, evidence } = this.scoreRelationship(
source,
target,
verbType,
context
)
if (confidence >= this.config.minConfidence) {
relationships.push({
sourceEntity: source,
targetEntity: target,
verbType,
confidence,
evidence
})
}
}
}
}
// Sort by confidence (highest first)
relationships.sort((a, b) => b.confidence - a.confidence)
return relationships
}
}
/**
* Convenience function to score a single relationship
*/
export function scoreRelationshipConfidence(
source: ExtractedEntity,
target: ExtractedEntity,
verbType: VerbType,
context: string,
config?: RelationshipDetectionConfig
): { confidence: number, evidence: RelationEvidence } {
const scorer = new RelationshipConfidenceScorer(config)
return scorer.scoreRelationship(source, target, verbType, context)
}
/**
* Convenience function to detect all relationships in text
*/
export function detectRelationshipsWithConfidence(
entities: ExtractedEntity[],
context: string,
config?: RelationshipDetectionConfig
): DetectedRelationship[] {
const scorer = new RelationshipConfidenceScorer(config)
return scorer.detectRelationships(entities, context)
}

188
src/neural/staticPatternMatcher.ts
View file

@ -1,188 +0,0 @@
/**
* Static Pattern Matcher - NO runtime initialization, NO Brainy needed
*
* All patterns and embeddings are pre-computed at build time
* This is pure pattern matching with zero dependencies
*/
import { EMBEDDED_PATTERNS, getPatternEmbeddings } from './embeddedPatterns.js'
import type { Vector } from '../coreTypes.js'
import type { TripleQuery } from '../triple/TripleIntelligence.js'
// Pre-load patterns and embeddings at module load time (happens once)
const patterns = new Map(EMBEDDED_PATTERNS.map(p => [p.id, p]))
const patternEmbeddings = getPatternEmbeddings()
/**
* Cosine similarity between two vectors.
* Accepts any number-indexed sequence so pre-computed Float32Array pattern
* embeddings can be compared against number[] query vectors without copying.
*/
function cosineSimilarity(a: ArrayLike<number>, b: ArrayLike<number>): number {
if (!a || !b || a.length !== b.length) return 0
let dotProduct = 0
let normA = 0
let normB = 0
for (let i = 0; i < a.length; i++) {
dotProduct += a[i] * b[i]
normA += a[i] * a[i]
normB += b[i] * b[i]
}
const denominator = Math.sqrt(normA) * Math.sqrt(normB)
return denominator === 0 ? 0 : dotProduct / denominator
}
/**
* Extract slots from matched pattern
*/
function extractSlots(query: string, pattern: string): Record<string, string> | null {
try {
const regex = new RegExp(pattern, 'i')
const match = query.match(regex)
if (!match) return null
const slots: Record<string, string> = {}
for (let i = 1; i < match.length; i++) {
if (match[i]) {
slots[`$${i}`] = match[i]
}
}
return Object.keys(slots).length > 0 ? slots : null
} catch {
return null
}
}
/**
* Apply template with extracted slots
*/
function applyTemplate(template: any, slots: Record<string, string>): any {
if (!template || !slots) return template
const result = JSON.parse(JSON.stringify(template))
const applySlots = (obj: any): any => {
if (typeof obj === 'string') {
return obj.replace(/\$\{(\d+)\}/g, (_, num) => slots[`$${num}`] || '')
}
if (Array.isArray(obj)) {
return obj.map(applySlots)
}
if (typeof obj === 'object' && obj !== null) {
const newObj: any = {}
for (const [key, value] of Object.entries(obj)) {
newObj[key] = applySlots(value)
}
return newObj
}
return obj
}
return applySlots(result)
}
/**
* Match query against all patterns using embeddings
*/
export function findBestPatterns(
queryEmbedding: Vector,
k: number = 3
): Array<{ pattern: typeof EMBEDDED_PATTERNS[0]; similarity: number }> {
const matches: Array<{ pattern: typeof EMBEDDED_PATTERNS[0]; similarity: number }> = []
for (const pattern of EMBEDDED_PATTERNS) {
const patternEmbedding = patternEmbeddings.get(pattern.id)
if (!patternEmbedding) continue
// Pass Float32Array directly, no need for Array.from()!
const similarity = cosineSimilarity(queryEmbedding, patternEmbedding)
if (similarity > 0.5) { // Threshold for relevance
matches.push({ pattern, similarity })
}
}
// Sort by similarity and return top k
return matches
.sort((a, b) => b.similarity - a.similarity)
.slice(0, k)
}
/**
* Match query against patterns using regex
*/
export function matchPatternByRegex(query: string): {
pattern: typeof EMBEDDED_PATTERNS[0]
slots: Record<string, string>
query: TripleQuery
} | null {
// Try direct regex matching first (fastest)
for (const pattern of EMBEDDED_PATTERNS) {
const slots = extractSlots(query, pattern.pattern)
if (slots) {
const templatedQuery = applyTemplate(pattern.template, slots)
return {
pattern,
slots,
query: templatedQuery
}
}
}
return null
}
/**
* Convert natural language to structured query using STATIC patterns
* NO initialization needed, NO Brainy required
*/
export function patternMatchQuery(
query: string,
queryEmbedding?: Vector
): TripleQuery {
// ALWAYS use vector similarity when we have embeddings (which we always do!)
if (queryEmbedding && queryEmbedding.length === 384) {
const bestPatterns = findBestPatterns(queryEmbedding, 5) // Get top 5 matches
// Try to extract slots from best matching patterns
for (const { pattern, similarity } of bestPatterns) {
// Only try patterns with good similarity
if (similarity < 0.7) break
const slots = extractSlots(query, pattern.pattern)
if (slots) {
// Found a good match with extractable slots!
const result = applyTemplate(pattern.template, slots)
console.log('[NLP] Applied template with slots:', JSON.stringify(result))
return result
}
}
// If no slots extracted but we have a good match, use the template as-is
if (bestPatterns.length > 0 && bestPatterns[0].similarity > 0.75) {
console.log('[NLP] Returning template as-is:', JSON.stringify(bestPatterns[0].pattern.template))
return bestPatterns[0].pattern.template
}
}
// Fallback: simple vector search (should rarely happen)
console.log('[NLP] Fallback - returning simple query')
return {
like: query,
limit: 10
}
}
// Export pattern statistics for monitoring
export const PATTERN_STATS = {
totalPatterns: EMBEDDED_PATTERNS.length,
categories: [...new Set(EMBEDDED_PATTERNS.map(p => p.category))],
domains: [...new Set(EMBEDDED_PATTERNS.filter(p => p.domain).map(p => p.domain!))],
hasEmbeddings: patternEmbeddings.size > 0
}

1257
src/storage/cacheManager.ts
View file

File diff suppressed because it is too large Load diff

34
src/transaction/index.ts
View file

@ -1,34 +0,0 @@
/**
* Transaction System
*
* Provides atomicity for Brainy operations.
* All operations succeed or all rollback - no partial failures.
*
* @module transaction
*/
export * from './types.js'
export * from './errors.js'
export { Transaction } from './Transaction.js'
export { TransactionManager, type TransactionStats } from './TransactionManager.js'
// Re-export for convenience
export type {
Operation,
RollbackAction,
TransactionState,
TransactionContext,
TransactionFunction,
TransactionResult,
TransactionOptions
} from './types.js'
export {
TransactionError,
TransactionExecutionError,
TransactionRollbackError,
InvalidTransactionStateError,
TransactionTimeoutError
} from './errors.js'
export { RevisionConflictError } from './RevisionConflictError.js'

326
src/types/apiTypes.ts
View file

@ -1,326 +0,0 @@
/**
* Consistent API Types for Brainy
*
* These types provide a uniform interface for all public methods,
* using object parameters for consistency and extensibility.
*/
import type { Vector } from '../coreTypes.js'
import type { NounType, VerbType } from './graphTypes.js'
// ============= NOUN OPERATIONS =============
/**
* Parameters for adding a noun
*/
export interface AddNounParams {
data: any | Vector // Content or pre-computed vector
type: NounType | string // Noun type (required)
metadata?: any // Optional metadata
id?: string // Optional custom ID
service?: string // Optional service identifier
}
/**
* Parameters for updating a noun
*/
export interface UpdateNounParams {
id: string // Noun ID to update
data?: any // New data
metadata?: any // New metadata
type?: NounType | string // New type
}
/**
* Parameters for getting nouns
*/
export interface GetNounsParams {
ids?: string[] // Specific IDs to fetch
type?: NounType | string | string[] // Filter by type(s)
limit?: number // Maximum results
offset?: number // Pagination offset
cursor?: string // Pagination cursor
filter?: Record<string, any> // Metadata filters
service?: string // Service filter
}
// ============= VERB OPERATIONS =============
/**
* Parameters for adding a verb (relationship)
*/
export interface AddVerbParams {
source: string // Source noun ID
target: string // Target noun ID
type: VerbType | string // Verb type (required)
weight?: number // Relationship weight (0-1)
metadata?: any // Optional metadata
service?: string // Optional service identifier
}
/**
* Parameters for getting verbs
*/
export interface GetVerbsParams {
source?: string // Filter by source
target?: string // Filter by target
type?: VerbType | string | string[] // Filter by type(s)
limit?: number // Maximum results
offset?: number // Pagination offset
cursor?: string // Pagination cursor
filter?: Record<string, any> // Metadata filters
service?: string // Service filter
}
// ============= SEARCH OPERATIONS =============
/**
* Unified search parameters
*/
export interface SearchParams {
query: string | Vector // Text query or vector
limit?: number // Maximum results (default: 10)
threshold?: number // Similarity threshold (0-1)
filter?: {
type?: NounType | string | string[] // Filter by noun type(s)
metadata?: Record<string, any> // Metadata filters
service?: string // Service filter
}
includeMetadata?: boolean // Include metadata in results
includeVectors?: boolean // Include vectors in results
}
/**
* Parameters for similarity search
*/
export interface SimilarityParams {
id?: string // Find similar to this ID
data?: any | Vector // Or find similar to this data
limit?: number // Maximum results (default: 10)
threshold?: number // Similarity threshold (0-1)
filter?: {
type?: NounType | string | string[]
metadata?: Record<string, any>
service?: string
}
}
/**
* Parameters for related items search
*/
export interface RelatedParams {
id: string // Starting noun ID
depth?: number // Traversal depth (default: 1)
limit?: number // Max results per level
types?: VerbType[] | string[] // Relationship types to follow
direction?: 'outgoing' | 'incoming' | 'both'
}
// ============= BATCH OPERATIONS =============
/**
* Parameters for batch noun operations
*/
export interface BatchNounsParams {
items: AddNounParams[] // Array of nouns to add
parallel?: boolean // Process in parallel
chunkSize?: number // Batch size for processing
onProgress?: (completed: number, total: number) => void
}
/**
* Parameters for batch verb operations
*/
export interface BatchVerbsParams {
items: AddVerbParams[] // Array of verbs to add
parallel?: boolean // Process in parallel
chunkSize?: number // Batch size for processing
onProgress?: (completed: number, total: number) => void
}
// ============= STATISTICS & METADATA =============
/**
* Parameters for statistics queries
*/
export interface StatisticsParams {
detailed?: boolean // Include detailed breakdown
includeAugmentations?: boolean // Include augmentation stats
includeMemory?: boolean // Include memory usage
service?: string // Filter by service
}
/**
* Parameters for metadata operations
*/
export interface MetadataParams {
id: string // Entity ID
metadata: any // Metadata to set/update
merge?: boolean // Merge with existing (vs replace)
}
// ============= CONFIGURATION =============
/**
* Dynamic configuration update parameters
*/
export interface ConfigUpdateParams {
embeddings?: {
model?: string
precision?: 'q8'
cache?: boolean
}
augmentations?: {
[name: string]: boolean | Record<string, any>
}
storage?: {
type?: string
config?: any
}
performance?: {
batchSize?: number
maxConcurrency?: number
cacheSize?: number
}
}
// ============= TRIPLE INTELLIGENCE API =============
/**
* API for Triple Intelligence Engine to access Brainy internals
* This provides type-safe access without unchecked casts
*/
export interface TripleIntelligenceAPI {
// Vector operations
vectorSearch(vector: Vector | string, limit: number): Promise<Array<{id: string, score: number, entity?: any}>>
// Graph operations
graphTraversal(options: {
start: string | string[]
type?: string | string[]
direction?: 'in' | 'out' | 'both'
maxDepth?: number
}): Promise<Array<{id: string, score: number, depth: number}>>
// Metadata operations
metadataQuery(where: Record<string, any>): Promise<Set<string>>
getEntity(id: string): Promise<any>
// Storage operations
getVerbsBySource(sourceId: string): Promise<any[]>
getVerbsByTarget(targetId: string): Promise<any[]>
// Statistics
getStatistics(): Promise<{
totalCount: number
fieldStats: Record<string, {
min: number
max: number
cardinality: number
type: string
}>
}>
// Index access
getAllNouns(): Map<string, any>
hasMetadataIndex(): boolean
}
// ============= RESULTS =============
/**
* Unified search result
*/
export interface SearchResult<T = any> {
id: string
score: number // Similarity score (0-1)
data?: T // Original data
metadata?: any // Metadata if requested
vector?: Vector // Vector if requested
type?: string // Noun type
distance?: number // Raw distance metric
}
/**
* Paginated result wrapper
*/
export interface PaginatedResult<T> {
items: T[]
total?: number
hasMore: boolean
nextCursor?: string
previousCursor?: string
}
/**
* Batch operation result
*/
export interface BatchResult {
successful: string[] // Successfully processed IDs
failed: Array<{
index: number
error: string
item?: any
}>
total: number
duration: number // Total time in ms
}
/**
* Statistics result
*/
export interface StatisticsResult {
nouns: {
total: number
byType: Record<string, number>
}
verbs: {
total: number
byType: Record<string, number>
}
storage: {
used: number
type: string
}
performance?: {
avgLatency: number
throughput: number
cacheHitRate?: number
}
augmentations?: Record<string, any>
memory?: {
used: number
limit: number
}
}
// ============= ERRORS =============
/**
* Structured error for API operations
*/
export class BrainyAPIError extends Error {
constructor(
message: string,
public code: string,
public statusCode: number = 400,
public details?: any
) {
super(message)
this.name = 'BrainyAPIError'
}
}
// Error codes
export const ErrorCodes = {
INVALID_TYPE: 'INVALID_TYPE',
NOT_FOUND: 'NOT_FOUND',
DUPLICATE_ID: 'DUPLICATE_ID',
INVALID_VECTOR: 'INVALID_VECTOR',
STORAGE_ERROR: 'STORAGE_ERROR',
EMBEDDING_ERROR: 'EMBEDDING_ERROR',
AUGMENTATION_ERROR: 'AUGMENTATION_ERROR',
VALIDATION_ERROR: 'VALIDATION_ERROR',
QUOTA_EXCEEDED: 'QUOTA_EXCEEDED',
UNAUTHORIZED: 'UNAUTHORIZED'
} as const

24
src/types/fileSystemTypes.ts
View file

@ -1,24 +0,0 @@
/**
* Type declarations for the File System Access API
* Extends the FileSystemDirectoryHandle interface to include the [Symbol.asyncIterator] method
* and FileSystemHandle to include getFile() method for TypeScript compatibility
*/
// Extend the FileSystemDirectoryHandle interface
interface FileSystemDirectoryHandle {
[Symbol.asyncIterator](): AsyncIterableIterator<[string, FileSystemHandle]>;
keys(): AsyncIterableIterator<string>;
entries(): AsyncIterableIterator<[string, FileSystemHandle]>;
}
// Extend the FileSystemHandle interface to include getFile method
// This is needed because TypeScript doesn't recognize that a FileSystemHandle
// can be a FileSystemFileHandle which has the getFile method
interface FileSystemHandle {
getFile?(): Promise<File>;
}
// Export something to make this a module
export const fileSystemTypesLoaded = true

288
src/types/progress.types.ts
View file

@ -1,288 +0,0 @@
/**
* Standardized Progress Reporting
*
* Provides unified progress tracking across all long-running operations
* in Brainy (imports, clustering, large searches, etc.)
*/
/**
* Progress status states
*/
export type ProgressStatus = 'pending' | 'running' | 'completed' | 'failed' | 'cancelled'
/**
* Standardized progress report
*/
export interface BrainyProgress<T = any> {
// Core status
status: ProgressStatus
// Progress percentage (0-100)
progress: number
// Human-readable message
message: string
// Detailed metadata
metadata: {
itemsProcessed: number
itemsTotal: number
currentItem?: string
estimatedTimeRemaining?: number // milliseconds
startedAt: number
completedAt?: number
throughput?: number // items per second
}
// Result when completed
result?: T
// Error when failed
error?: Error
}
/**
* Progress tracker with automatic time estimation
*/
export class ProgressTracker<T = any> {
private status: ProgressStatus = 'pending'
private processed = 0
private total: number
private startedAt?: number
private completedAt?: number
private currentItem?: string
private result?: T
private error?: Error
private processingTimes: number[] = [] // Track last N processing times for estimation
constructor(total: number) {
if (total < 0) {
throw new Error('Total must be non-negative')
}
this.total = total
}
/**
* Factory method for creating progress trackers
*/
static create<T>(total: number): ProgressTracker<T> {
return new ProgressTracker<T>(total)
}
/**
* Start tracking progress
*/
start(): BrainyProgress<T> {
this.status = 'running'
this.startedAt = Date.now()
return this.current()
}
/**
* Update progress
*/
update(processed: number, currentItem?: string): BrainyProgress<T> {
if (processed < 0) {
throw new Error('Processed count must be non-negative')
}
if (processed > this.total) {
throw new Error(`Processed count (${processed}) exceeds total (${this.total})`)
}
const previousProcessed = this.processed
this.processed = processed
this.currentItem = currentItem
// Track processing time for estimation
if (this.startedAt && previousProcessed < processed) {
const itemsProcessed = processed - previousProcessed
const timeTaken = Date.now() - this.startedAt
const avgTimePerItem = timeTaken / processed
this.processingTimes.push(avgTimePerItem)
// Keep only last 100 measurements for rolling average
if (this.processingTimes.length > 100) {
this.processingTimes.shift()
}
}
return this.current()
}
/**
* Increment progress by 1
*/
increment(currentItem?: string): BrainyProgress<T> {
return this.update(this.processed + 1, currentItem)
}
/**
* Mark as completed
*/
complete(result: T): BrainyProgress<T> {
this.status = 'completed'
this.completedAt = Date.now()
this.processed = this.total
this.result = result
return this.current()
}
/**
* Mark as failed
*/
fail(error: Error): BrainyProgress<T> {
this.status = 'failed'
this.completedAt = Date.now()
this.error = error
return this.current()
}
/**
* Mark as cancelled
*/
cancel(): BrainyProgress<T> {
this.status = 'cancelled'
this.completedAt = Date.now()
return this.current()
}
/**
* Get current progress state
*/
current(): BrainyProgress<T> {
const progress = this.total > 0 ? Math.round((this.processed / this.total) * 100) : 0
// Generate message based on status
let message: string
switch (this.status) {
case 'pending':
message = `Ready to process ${this.total} items`
break
case 'running':
message = this.currentItem
? `Processing: ${this.currentItem} (${this.processed}/${this.total})`
: `Processing ${this.processed}/${this.total} items`
break
case 'completed':
message = `Completed ${this.total} items`
break
case 'failed':
message = `Failed after ${this.processed} items: ${this.error?.message || 'Unknown error'}`
break
case 'cancelled':
message = `Cancelled after ${this.processed} items`
break
}
return {
status: this.status,
progress,
message,
metadata: {
itemsProcessed: this.processed,
itemsTotal: this.total,
currentItem: this.currentItem,
estimatedTimeRemaining: this.estimateTimeRemaining(),
startedAt: this.startedAt || Date.now(),
completedAt: this.completedAt,
throughput: this.calculateThroughput()
},
result: this.result,
error: this.error
}
}
/**
* Estimate time remaining based on processing history
*/
private estimateTimeRemaining(): number | undefined {
if (this.status !== 'running' || !this.startedAt || this.processed === 0) {
return undefined
}
const remaining = this.total - this.processed
if (remaining === 0) {
return 0
}
// Use rolling average if we have enough samples
if (this.processingTimes.length > 0) {
const avgTimePerItem = this.processingTimes.reduce((a, b) => a + b, 0) / this.processingTimes.length
return Math.round(avgTimePerItem * remaining)
}
// Fallback to simple calculation
const elapsed = Date.now() - this.startedAt
const avgTimePerItem = elapsed / this.processed
return Math.round(avgTimePerItem * remaining)
}
/**
* Calculate current throughput (items/second)
*/
private calculateThroughput(): number | undefined {
if (!this.startedAt || this.processed === 0) {
return undefined
}
const elapsed = Date.now() - this.startedAt
const seconds = elapsed / 1000
return seconds > 0 ? Math.round((this.processed / seconds) * 100) / 100 : undefined
}
/**
* Get progress statistics
*/
getStats() {
const elapsed = this.startedAt ? Date.now() - this.startedAt : 0
return {
status: this.status,
processed: this.processed,
total: this.total,
remaining: this.total - this.processed,
progress: this.total > 0 ? this.processed / this.total : 0,
elapsed,
estimatedTotal: elapsed > 0 && this.processed > 0
? Math.round((elapsed / this.processed) * this.total)
: undefined,
throughput: this.calculateThroughput()
}
}
}
/**
* Helper to format time duration
*/
export function formatDuration(ms: number): string {
const seconds = Math.floor(ms / 1000)
const minutes = Math.floor(seconds / 60)
const hours = Math.floor(minutes / 60)
if (hours > 0) {
return `${hours}h ${minutes % 60}m`
} else if (minutes > 0) {
return `${minutes}m ${seconds % 60}s`
} else {
return `${seconds}s`
}
}
/**
* Helper to format progress percentage
*/
export function formatProgress(progress: BrainyProgress): string {
const { status, progress: pct, metadata } = progress
const remaining = metadata.estimatedTimeRemaining
let str = `[${status.toUpperCase()}] ${pct}% (${metadata.itemsProcessed}/${metadata.itemsTotal})`
if (metadata.throughput) {
str += ` - ${metadata.throughput} items/s`
}
if (remaining && remaining > 0) {
str += ` - ${formatDuration(remaining)} remaining`
}
return str
}

174
src/types/typeMigration.ts
View file

@ -1,174 +0,0 @@
/**
* Type Migration Utilities for Stage 3 Taxonomy
*
* Provides migration helpers for code using removed types from v5.x
*
* ## Removed Types
*
* ### Nouns (2 removed):
* - `user` → merged into `person`
* - `topic` → merged into `concept`
*
* ### Verbs (4 removed):
* - `succeeds` → use inverse of `precedes`
* - `belongsTo` → use inverse of `owns`
* - `createdBy` → use inverse of `creates`
* - `supervises` → use inverse of `reportsTo`
*/
import { NounType, VerbType } from './graphTypes.js'
/**
* Migration mapping for removed noun types
*/
export const REMOVED_NOUN_TYPES = {
user: NounType.Person,
topic: NounType.Concept
} as const
/**
* Migration mapping for removed verb types
* Note: Some verbs should use inverse relationships in Stage 3
*/
export const REMOVED_VERB_TYPES = {
succeeds: VerbType.Precedes, // Use with inverted source/target
belongsTo: VerbType.Owns, // Use with inverted source/target
createdBy: VerbType.Creates, // Use with inverted source/target
supervises: VerbType.ReportsTo // Use with inverted source/target
} as const
/**
* Check if a type was removed in Stage 3
*/
export function isRemovedNounType(type: string): type is keyof typeof REMOVED_NOUN_TYPES {
return type in REMOVED_NOUN_TYPES
}
/**
* Check if a verb type was removed in Stage 3
*/
export function isRemovedVerbType(type: string): type is keyof typeof REMOVED_VERB_TYPES {
return type in REMOVED_VERB_TYPES
}
/**
* Migrate a noun type (Stage 3)
* Returns the migrated type or the original if no migration needed
*/
export function migrateNounType(type: string): NounType {
if (isRemovedNounType(type)) {
console.warn(`⚠️ NounType "${type}" was removed in v6.0. Migrating to "${REMOVED_NOUN_TYPES[type]}"`)
return REMOVED_NOUN_TYPES[type]
}
return type as NounType
}
/**
* Migrate a verb type (Stage 3)
* Returns the migrated type or the original if no migration needed
*
* WARNING: Some verbs require inverting source/target relationships!
* See VERB_REQUIRES_INVERSION for details.
*/
export function migrateVerbType(type: string): VerbType {
if (isRemovedVerbType(type)) {
console.warn(`⚠️ VerbType "${type}" was removed in v6.0. Migrating to "${REMOVED_VERB_TYPES[type]}" (may require source/target inversion)`)
return REMOVED_VERB_TYPES[type]
}
return type as VerbType
}
/**
* Verbs that require inverting source/target when migrating
*
* Example:
* - Old: `A createdBy B` → New: `B creates A`
* - Old: `A belongsTo B` → New: `B owns A`
* - Old: `A supervises B` → New: `B reportsTo A`
* - Old: `A succeeds B` → New: `B precedes A`
*/
export const VERB_REQUIRES_INVERSION = new Set([
'succeeds',
'belongsTo',
'createdBy',
'supervises'
])
/**
* Check if a verb type requires inverting source/target during migration
*/
export function requiresInversion(oldVerbType: string): boolean {
return VERB_REQUIRES_INVERSION.has(oldVerbType)
}
/**
* Migrate a relationship, handling source/target inversion if needed
*
* @returns Object with migrated verb and potentially inverted source/target
*/
export function migrateRelationship(params: {
verb: string
source: string
target: string
}): {
verb: VerbType
source: string
target: string
inverted: boolean
} {
const verb = migrateVerbType(params.verb)
const inverted = requiresInversion(params.verb)
if (inverted) {
return {
verb,
source: params.target, // Swap source and target
target: params.source,
inverted: true
}
}
return {
verb,
source: params.source,
target: params.target,
inverted: false
}
}
/**
* Stage 3 Type Compatibility Check
* Helps developers identify code that needs updating
*/
export function checkTypeCompatibility(nounTypes: string[], verbTypes: string[]): {
valid: boolean
removedNouns: string[]
removedVerbs: string[]
warnings: string[]
} {
const removedNouns = nounTypes.filter(isRemovedNounType)
const removedVerbs = verbTypes.filter(isRemovedVerbType)
const warnings: string[] = []
if (removedNouns.length > 0) {
warnings.push(
`Found ${removedNouns.length} removed noun type(s): ${removedNouns.join(', ')}. ` +
`These were merged in Stage 3. Use Person instead of User, Concept instead of Topic.`
)
}
if (removedVerbs.length > 0) {
warnings.push(
`Found ${removedVerbs.length} removed verb type(s): ${removedVerbs.join(', ')}. ` +
`These require using inverse relationships in Stage 3. ` +
`Example: "A createdBy B" becomes "B creates A".`
)
}
return {
valid: removedNouns.length === 0 && removedVerbs.length === 0,
removedNouns,
removedVerbs,
warnings
}
}

39
src/unified.ts
View file

@ -1,39 +0,0 @@
/**
* @module unified
* @description Unified entry point for Brainy. Re-exports the public surface
* from `index.js` and surfaces a tiny runtime-environment object the rest of
* the library can read.
*
* 8.0 supports Node-like runtimes only (Node.js, Bun, Deno); the browser
* detection helpers and Worker Thread plumbing are gone.
*/
import './setup.js'
import { isNode } from './utils/environment.js'
export const environment = {
get isNode() {
return isNode()
}
}
declare global {
/**
* Runtime-environment marker published by the unified entry point so
* embedders and diagnostics can detect the active Brainy environment.
* Ambient `var` is required — `let`/`const` in `declare global` do not
* attach to `globalThis`.
*/
var __ENV__: typeof environment | undefined
}
if (typeof globalThis !== 'undefined') {
globalThis.__ENV__ = environment
}
console.log(
`Brainy running on ${environment.isNode ? 'Node-like runtime' : 'unknown runtime'}`
)
export * from './index.js'

159
src/universal/crypto.ts
View file

@ -1,159 +0,0 @@
/**
* Universal Crypto implementation
* Framework-friendly: Trusts that frameworks provide crypto polyfills
* Works in all environments: Browser (via framework), Node.js, Serverless
*/
import { isNode } from '../utils/environment.js'
let nodeCrypto: any = null
// Dynamic import for Node.js crypto (only in Node.js environment)
if (isNode()) {
try {
// Use node: protocol to prevent bundler polyfilling (requires Node 22+)
nodeCrypto = await import('node:crypto')
} catch {
// Ignore import errors in non-Node environments
}
}
/**
* Generate random bytes
* Framework-friendly: Assumes crypto API is available via framework polyfills
*/
export function randomBytes(size: number): Uint8Array {
if (typeof crypto !== 'undefined') {
// Use Web Crypto API (available in browsers via framework polyfills and modern Node.js)
const array = new Uint8Array(size)
crypto.getRandomValues(array)
return array
} else if (nodeCrypto) {
// Use Node.js crypto
return new Uint8Array(nodeCrypto.randomBytes(size))
} else {
throw new Error('Crypto API not available. Framework bundlers should provide crypto polyfills.')
}
}
/**
* Generate random UUID
* Framework-friendly: Assumes crypto.randomUUID is available via framework polyfills
*/
export function randomUUID(): string {
if (typeof crypto !== 'undefined' && crypto.randomUUID) {
return crypto.randomUUID()
} else if (nodeCrypto && nodeCrypto.randomUUID) {
return nodeCrypto.randomUUID()
} else {
throw new Error('crypto.randomUUID not available. Framework bundlers should provide crypto polyfills.')
}
}
/**
* Create hash (simplified interface)
* Framework-friendly: Relies on Node.js crypto or framework-provided implementations
*/
export function createHash(algorithm: string): {
update: (data: string | Uint8Array) => any
digest: (encoding: string) => string
} {
if (nodeCrypto && nodeCrypto.createHash) {
return nodeCrypto.createHash(algorithm)
} else {
throw new Error(`createHash not available. For browser environments, frameworks should provide crypto polyfills or use Web Crypto API directly.`)
}
}
/**
* Create HMAC
* Framework-friendly: Relies on Node.js crypto or framework-provided implementations
*/
export function createHmac(algorithm: string, key: string | Uint8Array): {
update: (data: string | Uint8Array) => any
digest: (encoding: string) => string
} {
if (nodeCrypto && nodeCrypto.createHmac) {
return nodeCrypto.createHmac(algorithm, key)
} else {
throw new Error(`createHmac not available. For browser environments, frameworks should provide crypto polyfills or use Web Crypto API directly.`)
}
}
/**
* PBKDF2 synchronous
* Framework-friendly: Relies on Node.js crypto or framework-provided implementations
*/
export function pbkdf2Sync(password: string | Uint8Array, salt: string | Uint8Array, iterations: number, keylen: number, digest: string): Uint8Array {
if (nodeCrypto && nodeCrypto.pbkdf2Sync) {
return new Uint8Array(nodeCrypto.pbkdf2Sync(password, salt, iterations, keylen, digest))
} else {
throw new Error(`pbkdf2Sync not available. For browser environments, frameworks should provide crypto polyfills or use Web Crypto API directly.`)
}
}
/**
* Scrypt synchronous
* Framework-friendly: Relies on Node.js crypto or framework-provided implementations
*/
export function scryptSync(password: string | Uint8Array, salt: string | Uint8Array, keylen: number, options?: any): Uint8Array {
if (nodeCrypto && nodeCrypto.scryptSync) {
return new Uint8Array(nodeCrypto.scryptSync(password, salt, keylen, options))
} else {
throw new Error(`scryptSync not available. For browser environments, frameworks should provide crypto polyfills or use Web Crypto API directly.`)
}
}
/**
* Create cipher
* Framework-friendly: Relies on Node.js crypto or framework-provided implementations
*/
export function createCipheriv(algorithm: string, key: Uint8Array, iv: Uint8Array): {
update: (data: string, inputEncoding?: string, outputEncoding?: string) => string
final: (outputEncoding?: string) => string
} {
if (nodeCrypto && nodeCrypto.createCipheriv) {
return nodeCrypto.createCipheriv(algorithm, key, iv)
} else {
throw new Error(`createCipheriv not available. For browser environments, frameworks should provide crypto polyfills or use Web Crypto API directly.`)
}
}
/**
* Create decipher
* Framework-friendly: Relies on Node.js crypto or framework-provided implementations
*/
export function createDecipheriv(algorithm: string, key: Uint8Array, iv: Uint8Array): {
update: (data: string, inputEncoding?: string, outputEncoding?: string) => string
final: (outputEncoding?: string) => string
} {
if (nodeCrypto && nodeCrypto.createDecipheriv) {
return nodeCrypto.createDecipheriv(algorithm, key, iv)
} else {
throw new Error(`createDecipheriv not available. For browser environments, frameworks should provide crypto polyfills or use Web Crypto API directly.`)
}
}
/**
* Timing safe equal
* Framework-friendly: Relies on Node.js crypto or framework-provided implementations
*/
export function timingSafeEqual(a: Uint8Array, b: Uint8Array): boolean {
if (nodeCrypto && nodeCrypto.timingSafeEqual) {
return nodeCrypto.timingSafeEqual(a, b)
} else {
throw new Error(`timingSafeEqual not available. For browser environments, frameworks should provide crypto polyfills or use Web Crypto API directly.`)
}
}
export default {
randomBytes,
randomUUID,
createHash,
createHmac,
pbkdf2Sync,
scryptSync,
createCipheriv,
createDecipheriv,
timingSafeEqual
}

62
src/utils/BoundedRegistry.ts
View file

@ -1,62 +0,0 @@
/**
* Bounded Registry with LRU eviction
* Prevents unbounded memory growth in production
*/
export class BoundedRegistry<T> {
private items = new Map<T, number>() // item -> last accessed timestamp
private readonly maxSize: number
constructor(maxSize: number = 10000) {
this.maxSize = maxSize
}
/**
* Add item to registry, evicting oldest if at capacity
*/
add(item: T): void {
// Update timestamp if already exists
if (this.items.has(item)) {
this.items.delete(item) // Remove to re-add at end
this.items.set(item, Date.now())
return
}
// Evict oldest if at capacity
if (this.items.size >= this.maxSize) {
const oldest = this.items.entries().next().value
if (oldest) {
this.items.delete(oldest[0])
}
}
this.items.set(item, Date.now())
}
/**
* Check if item exists
*/
has(item: T): boolean {
return this.items.has(item)
}
/**
* Get all items
*/
getAll(): T[] {
return Array.from(this.items.keys())
}
/**
* Get size
*/
get size(): number {
return this.items.size
}
/**
* Clear all items
*/
clear(): void {
this.items.clear()
}
}

47
src/utils/crypto.ts
View file

@ -1,47 +0,0 @@
/**
* Cross-platform crypto utilities
* Provides hashing functions that work in both Node.js and browser environments
*/
/**
* Simple string hash function that works in all environments
* Uses djb2 algorithm - fast and good distribution
* @param str - String to hash
* @returns Positive integer hash
*/
export function hashString(str: string): number {
let hash = 5381
for (let i = 0; i < str.length; i++) {
const char = str.charCodeAt(i)
hash = ((hash << 5) + hash) + char // hash * 33 + char
}
// Ensure positive number
return Math.abs(hash)
}
/**
* Alternative: FNV-1a hash algorithm
* Good distribution and fast
* @param str - String to hash
* @returns Positive integer hash
*/
export function fnv1aHash(str: string): number {
let hash = 2166136261
for (let i = 0; i < str.length; i++) {
hash ^= str.charCodeAt(i)
hash = (hash * 16777619) >>> 0
}
return hash
}
/**
* Generate a deterministic hash for partitioning
* Uses the most appropriate algorithm for the environment
* @param input - Input string to hash
* @returns Positive integer hash suitable for modulo operations
*/
export function getPartitionHash(input: string): number {
// Use djb2 by default as it's fast and has good distribution
// This ensures consistent partitioning across all environments
return hashString(input)
}

106
src/utils/deletedItemsIndex.ts
View file

@ -1,106 +0,0 @@
/**
* Dedicated index for tracking soft-deleted items
* This is MUCH more efficient than checking every item in the database
*
* Performance characteristics:
* - Add deleted item: O(1)
* - Remove deleted item: O(1)
* - Check if deleted: O(1)
* - Get all deleted: O(d) where d = number of deleted items << total items
*/
export class DeletedItemsIndex {
private deletedIds: Set<string> = new Set()
private deletedCount: number = 0
/**
* Mark an item as deleted
*/
markDeleted(id: string): void {
if (!this.deletedIds.has(id)) {
this.deletedIds.add(id)
this.deletedCount++
}
}
/**
* Mark an item as not deleted (restored)
*/
markRestored(id: string): void {
if (this.deletedIds.delete(id)) {
this.deletedCount--
}
}
/**
* Check if an item is deleted - O(1)
*/
isDeleted(id: string): boolean {
return this.deletedIds.has(id)
}
/**
* Get all deleted item IDs - O(d)
*/
getAllDeleted(): string[] {
return Array.from(this.deletedIds)
}
/**
* Filter out deleted items from results - O(k) where k = result count
*/
filterDeleted<T extends { id?: string }>(items: T[]): T[] {
if (this.deletedCount === 0) {
// Fast path - no deleted items
return items
}
return items.filter(item => {
const id = item.id
return id ? !this.deletedIds.has(id) : true
})
}
/**
* Get statistics
*/
getStats() {
return {
deletedCount: this.deletedCount,
memoryUsage: this.deletedCount * 100 // Rough estimate: 100 bytes per ID
}
}
/**
* Clear all deleted items (for testing)
*/
clear(): void {
this.deletedIds.clear()
this.deletedCount = 0
}
/**
* Serialize for persistence
*/
serialize(): string {
return JSON.stringify(Array.from(this.deletedIds))
}
/**
* Deserialize from persistence
*/
deserialize(data: string): void {
try {
const ids = JSON.parse(data)
this.deletedIds = new Set(ids)
this.deletedCount = this.deletedIds.size
} catch (e) {
console.warn('Failed to deserialize deleted items index')
}
}
}
/**
* Global singleton for deleted items tracking
*/
export const deletedItemsIndex = new DeletedItemsIndex()

88
src/utils/ensureDeleted.ts
View file

@ -1,88 +0,0 @@
/**
* Utility to ensure all metadata has the deleted field set properly
* This is CRITICAL for O(1) soft delete filtering performance
*
* Uses _brainy namespace to avoid conflicts with user metadata
*/
const BRAINY_NAMESPACE = '_brainy'
/**
* Ensure metadata has internal Brainy fields set
* @param metadata The metadata object (could be null/undefined)
* @param preserveExisting If true, preserve existing deleted value
* @returns Metadata with internal fields guaranteed
*/
export function ensureDeletedField(metadata: any, preserveExisting: boolean = true): any {
// Handle null/undefined metadata
if (!metadata) {
return {
[BRAINY_NAMESPACE]: {
deleted: false,
version: 1
}
}
}
// Clone to avoid mutation
const result = { ...metadata }
// Ensure _brainy namespace exists
if (!result[BRAINY_NAMESPACE]) {
result[BRAINY_NAMESPACE] = {}
}
// Set deleted field if not present
if (!('deleted' in result[BRAINY_NAMESPACE])) {
result[BRAINY_NAMESPACE].deleted = false
} else if (!preserveExisting) {
// Force to false if not preserving
result[BRAINY_NAMESPACE].deleted = false
}
return result
}
/**
* Mark an item as soft deleted
* @param metadata The metadata object
* @returns Metadata with _brainy.deleted=true
*/
export function markAsDeleted(metadata: any): any {
const result = ensureDeletedField(metadata)
result[BRAINY_NAMESPACE].deleted = true
return result
}
/**
* Mark an item as restored (not deleted)
* @param metadata The metadata object
* @returns Metadata with _brainy.deleted=false
*/
export function markAsRestored(metadata: any): any {
const result = ensureDeletedField(metadata)
result[BRAINY_NAMESPACE].deleted = false
return result
}
/**
* Check if an item is deleted
* @param metadata The metadata object
* @returns true if deleted, false otherwise (including if field missing)
*/
export function isDeleted(metadata: any): boolean {
return metadata?.[BRAINY_NAMESPACE]?.deleted === true
}
/**
* Check if an item is active (not deleted)
* @param metadata The metadata object
* @returns true if not deleted (default), false if deleted
*/
export function isActive(metadata: any): boolean {
// If no deleted field or deleted=false, item is active
return !isDeleted(metadata)
}
// Export the namespace constant for use in queries
export const BRAINY_DELETED_FIELD = `${BRAINY_NAMESPACE}.deleted`

255
src/utils/metadataNamespace.ts
View file

@ -1,255 +0,0 @@
/**
* Clean Metadata Architecture for Brainy 2.2
* No backward compatibility - doing it RIGHT from the start!
*/
// Namespace constants
export const BRAINY_NS = '_brainy' as const
export const AUG_NS = '_augmentations' as const
export const AUDIT_NS = '_audit' as const
// Field paths for O(1) indexing
export const DELETED_FIELD = `${BRAINY_NS}.deleted` as const
export const INDEXED_FIELD = `${BRAINY_NS}.indexed` as const
export const VERSION_FIELD = `${BRAINY_NS}.version` as const
/**
* Internal Brainy metadata structure
* These fields are ALWAYS present and indexed for O(1) access
*/
export interface BrainyInternalMetadata {
deleted: boolean // ALWAYS boolean, enables O(1) soft delete
indexed: boolean // Whether in search index
version: number // Schema version
created: number // Unix timestamp
updated: number // Unix timestamp
// Optional internal fields
domain?: string // Domain classification
priority?: number // Query priority hint
ttl?: number // Time to live
}
/**
* Complete metadata structure with namespaces
*/
export interface NamespacedMetadata<T = any> {
// User metadata - any fields they want
[key: string]: any
// Internal metadata - our fields
[BRAINY_NS]: BrainyInternalMetadata
// Augmentation metadata - isolated per augmentation
[AUG_NS]?: {
[augmentationName: string]: any
}
// Audit trail - optional
[AUDIT_NS]?: Array<{
timestamp: number
augmentation: string
field: string
oldValue: any
newValue: any
}>
}
/**
* Create properly namespaced metadata
* This is called for EVERY noun/verb creation
*/
export function createNamespacedMetadata<T = any>(
userMetadata?: T
): NamespacedMetadata<T> {
const now = Date.now()
// Start with user metadata or empty object
const result: any = userMetadata ? { ...userMetadata } : {}
// ALWAYS add internal namespace with required fields
result[BRAINY_NS] = {
deleted: false, // CRITICAL: Always false for new items
indexed: true, // New items are indexed
version: 1, // Current schema version
created: now,
updated: now
}
return result
}
/**
* Update metadata while preserving namespaces
*/
export function updateNamespacedMetadata<T = any>(
existing: NamespacedMetadata<T>,
updates: Partial<T>
): NamespacedMetadata<T> {
const now = Date.now()
// Merge user fields
const result: any = {
...existing,
...updates
}
// Preserve internal namespace but update timestamp
result[BRAINY_NS] = {
...existing[BRAINY_NS],
updated: now
}
// Preserve augmentation namespace
if (existing[AUG_NS]) {
result[AUG_NS] = existing[AUG_NS]
}
// Preserve audit trail
if (existing[AUDIT_NS]) {
result[AUDIT_NS] = existing[AUDIT_NS]
}
return result
}
/**
* Soft delete a noun (O(1) operation)
*/
export function markDeleted<T = any>(
metadata: NamespacedMetadata<T>
): NamespacedMetadata<T> {
return {
...metadata,
[BRAINY_NS]: {
...metadata[BRAINY_NS],
deleted: true,
updated: Date.now()
}
}
}
/**
* Restore a soft-deleted noun (O(1) operation)
*/
export function markRestored<T = any>(
metadata: NamespacedMetadata<T>
): NamespacedMetadata<T> {
return {
...metadata,
[BRAINY_NS]: {
...metadata[BRAINY_NS],
deleted: false,
updated: Date.now()
}
}
}
/**
* Check if a noun is deleted (O(1) check)
*/
export function isDeleted<T = any>(
metadata: NamespacedMetadata<T>
): boolean {
return metadata[BRAINY_NS]?.deleted === true
}
/**
* Get user metadata without internal fields
* Used by augmentations to get clean user data
*/
export function getUserMetadata<T = any>(
metadata: NamespacedMetadata<T>
): T {
const { [BRAINY_NS]: _, [AUG_NS]: __, [AUDIT_NS]: ___, ...userMeta } = metadata
return userMeta as T
}
/**
* Set augmentation data in isolated namespace
*/
export function setAugmentationData<T = any>(
metadata: NamespacedMetadata<T>,
augmentationName: string,
data: any
): NamespacedMetadata<T> {
const result = { ...metadata }
if (!result[AUG_NS]) {
result[AUG_NS] = {}
}
result[AUG_NS][augmentationName] = data
return result
}
/**
* Add audit entry for tracking
*/
export function addAuditEntry<T = any>(
metadata: NamespacedMetadata<T>,
entry: {
augmentation: string
field: string
oldValue: any
newValue: any
}
): NamespacedMetadata<T> {
const result = { ...metadata }
if (!result[AUDIT_NS]) {
result[AUDIT_NS] = []
}
result[AUDIT_NS].push({
...entry,
timestamp: Date.now()
})
return result
}
/**
* INDEXING EXPLANATION:
*
* The MetadataIndex flattens nested objects into dot-notation keys:
*
* Input metadata:
* {
* name: "Django",
* _brainy: {
* deleted: false,
* indexed: true
* }
* }
*
* Creates index entries:
* - "name" -> "django" -> Set([id1, id2...])
* - "_brainy.deleted" -> "false" -> Set([id1, id2...]) // O(1) lookup!
* - "_brainy.indexed" -> "true" -> Set([id1, id2...])
*
* Query: { "_brainy.deleted": false }
* Lookup: index["_brainy.deleted"]["false"] -> Set of IDs in O(1)
*
* This is why namespacing doesn't hurt performance - it's all flattened!
*/
/**
* Fields that should ALWAYS be indexed for O(1) access
*/
export const ALWAYS_INDEXED_FIELDS = [
DELETED_FIELD, // For soft delete filtering
INDEXED_FIELD, // For index management
VERSION_FIELD // For schema versioning
]
/**
* Fields that should use sorted index for O(log n) range queries
*/
export const SORTED_INDEX_FIELDS = [
`${BRAINY_NS}.created`,
`${BRAINY_NS}.updated`,
`${BRAINY_NS}.priority`,
`${BRAINY_NS}.ttl`
]

545
src/utils/structuredLogger.ts
View file

@ -1,545 +0,0 @@
/**
* Enhanced Structured Logging System for Brainy
* Provides production-ready logging with structured output, context preservation,
* performance tracking, and multiple transport support
*/
import { performance } from 'perf_hooks'
import { randomUUID } from '../universal/crypto.js'
export enum LogLevel {
SILENT = -1,
FATAL = 0,
ERROR = 1,
WARN = 2,
INFO = 3,
DEBUG = 4,
TRACE = 5
}
export interface LogContext {
requestId?: string
userId?: string
operation?: string
entityId?: string
entityType?: string
[key: string]: any
}
export interface LogEntry {
timestamp: string
level: string
levelNumeric: number
module: string
message: string
context?: LogContext
data?: any
error?: {
name: string
message: string
stack?: string
code?: string
}
performance?: {
duration?: number
memory?: {
used: number
total: number
}
}
host?: string
pid: number
version?: string
}
export interface LogTransport {
name: string
log(entry: LogEntry): void | Promise<void>
flush?(): Promise<void>
}
export interface StructuredLoggerConfig {
level: LogLevel
modules?: Record<string, LogLevel>
format: 'json' | 'pretty' | 'simple'
transports: LogTransport[]
context?: LogContext
includeHost?: boolean
includeMemory?: boolean
bufferSize?: number
flushInterval?: number
version?: string
}
class ConsoleTransport implements LogTransport {
name = 'console'
private format: 'json' | 'pretty' | 'simple'
constructor(format: 'json' | 'pretty' | 'simple' = 'json') {
this.format = format
}
log(entry: LogEntry): void {
const method = this.getConsoleMethod(entry.levelNumeric)
if (this.format === 'json') {
method(JSON.stringify(entry))
} else if (this.format === 'pretty') {
const color = this.getColor(entry.levelNumeric)
const prefix = `${entry.timestamp} ${color}[${entry.level}]\\x1b[0m [${entry.module}]`
const message = entry.message
if (entry.error) {
method(`${prefix} ${message}`, entry.error)
} else if (entry.data) {
method(`${prefix} ${message}`, entry.data)
} else {
method(`${prefix} ${message}`)
}
} else {
// Simple format
method(`[${entry.level}] ${entry.message}`)
}
}
private getConsoleMethod(level: number): (...args: any[]) => void {
switch (level) {
case LogLevel.FATAL:
case LogLevel.ERROR:
return console.error
case LogLevel.WARN:
return console.warn
case LogLevel.INFO:
return console.info
default:
return console.log
}
}
private getColor(level: number): string {
switch (level) {
case LogLevel.FATAL:
return '\\x1b[35m' // Magenta
case LogLevel.ERROR:
return '\\x1b[31m' // Red
case LogLevel.WARN:
return '\\x1b[33m' // Yellow
case LogLevel.INFO:
return '\\x1b[36m' // Cyan
case LogLevel.DEBUG:
return '\\x1b[32m' // Green
case LogLevel.TRACE:
return '\\x1b[90m' // Gray
default:
return '\\x1b[0m' // Reset
}
}
}
class BufferedTransport implements LogTransport {
name = 'buffered'
private buffer: LogEntry[] = []
private innerTransport: LogTransport
private bufferSize: number
private flushTimer?: NodeJS.Timeout
constructor(innerTransport: LogTransport, bufferSize: number = 100, flushInterval: number = 5000) {
this.innerTransport = innerTransport
this.bufferSize = bufferSize
if (flushInterval > 0) {
this.flushTimer = setInterval(() => this.flush(), flushInterval)
}
}
log(entry: LogEntry): void {
this.buffer.push(entry)
if (this.buffer.length >= this.bufferSize) {
this.flush()
}
}
async flush(): Promise<void> {
const entries = this.buffer.splice(0)
for (const entry of entries) {
await this.innerTransport.log(entry)
}
if (this.innerTransport.flush) {
await this.innerTransport.flush()
}
}
destroy(): void {
if (this.flushTimer) {
clearInterval(this.flushTimer)
}
this.flush()
}
}
export class StructuredLogger {
private static instance: StructuredLogger
private config: StructuredLoggerConfig
private defaultContext: LogContext = {}
private performanceMarks = new Map<string, number>()
private constructor() {
const isDevelopment = process.env.NODE_ENV !== 'production'
const format = isDevelopment ? 'pretty' : 'json'
this.config = {
level: isDevelopment ? LogLevel.DEBUG : LogLevel.INFO,
format,
transports: [new ConsoleTransport(format)],
includeHost: !isDevelopment,
includeMemory: false,
bufferSize: 100,
flushInterval: 5000,
version: process.env.npm_package_version
}
// Load from environment
this.loadEnvironmentConfig()
}
private loadEnvironmentConfig(): void {
const envLevel = process.env.BRAINY_LOG_LEVEL
if (envLevel) {
const level = LogLevel[envLevel.toUpperCase() as keyof typeof LogLevel]
if (level !== undefined) {
this.config.level = level
}
}
const envFormat = process.env.BRAINY_LOG_FORMAT
if (envFormat && ['json', 'pretty', 'simple'].includes(envFormat)) {
this.config.format = envFormat as 'json' | 'pretty' | 'simple'
}
const moduleConfig = process.env.BRAINY_MODULE_LOG_LEVELS
if (moduleConfig) {
try {
this.config.modules = JSON.parse(moduleConfig)
} catch {
// Ignore parse errors
}
}
}
static getInstance(): StructuredLogger {
if (!StructuredLogger.instance) {
StructuredLogger.instance = new StructuredLogger()
}
return StructuredLogger.instance
}
configure(config: Partial<StructuredLoggerConfig>): void {
this.config = { ...this.config, ...config }
}
setContext(context: LogContext): void {
this.defaultContext = { ...this.defaultContext, ...context }
}
clearContext(): void {
this.defaultContext = {}
}
withContext(context: LogContext): StructuredLogger {
const contextualLogger = Object.create(this)
contextualLogger.defaultContext = { ...this.defaultContext, ...context }
return contextualLogger
}
startTimer(label: string): void {
this.performanceMarks.set(label, performance.now())
}
endTimer(label: string): number | undefined {
const start = this.performanceMarks.get(label)
if (start === undefined) return undefined
const duration = performance.now() - start
this.performanceMarks.delete(label)
return duration
}
private shouldLog(level: LogLevel, module: string): boolean {
if (this.config.modules?.[module] !== undefined) {
return level <= this.config.modules[module]
}
return level <= this.config.level
}
private createLogEntry(
level: LogLevel,
module: string,
message: string,
context?: LogContext,
data?: any,
error?: Error
): LogEntry {
const entry: LogEntry = {
timestamp: new Date().toISOString(),
level: LogLevel[level],
levelNumeric: level,
module,
message,
pid: process.pid,
version: this.config.version
}
// Merge contexts
const mergedContext = { ...this.defaultContext, ...context }
if (Object.keys(mergedContext).length > 0) {
entry.context = mergedContext
}
if (data !== undefined) {
entry.data = data
}
if (error) {
entry.error = {
name: error.name,
message: error.message,
stack: error.stack,
code: (error as Error & { code?: string }).code
}
}
if (this.config.includeHost) {
try {
const os = require('node:os')
entry.host = os.hostname()
} catch {
entry.host = 'unknown'
}
}
if (this.config.includeMemory && typeof process !== 'undefined' && process.memoryUsage) {
const mem = process.memoryUsage()
entry.performance = {
memory: {
used: Math.round(mem.heapUsed / 1024 / 1024),
total: Math.round(mem.heapTotal / 1024 / 1024)
}
}
}
return entry
}
private log(
level: LogLevel,
module: string,
message: string,
contextOrData?: LogContext | any,
data?: any
): void {
if (!this.shouldLog(level, module)) {
return
}
// Handle overloaded parameters
let context: LogContext | undefined
let logData: any
if (contextOrData && typeof contextOrData === 'object' && !Array.isArray(contextOrData)) {
// Check if it looks like a context object
const hasContextKeys = ['requestId', 'userId', 'operation', 'entityId', 'entityType']
.some(key => key in contextOrData)
if (hasContextKeys) {
context = contextOrData
logData = data
} else {
logData = contextOrData
}
} else {
logData = contextOrData
}
// Extract error if present
let error: Error | undefined
if (logData instanceof Error) {
error = logData
logData = undefined
} else if (logData?.error instanceof Error) {
error = logData.error
delete logData.error
}
const entry = this.createLogEntry(level, module, message, context, logData, error)
// Send to all transports
for (const transport of this.config.transports) {
try {
transport.log(entry)
} catch (err) {
// Fallback to console.error if transport fails
console.error('Logger transport error:', err)
}
}
}
fatal(module: string, message: string, contextOrData?: LogContext | any, data?: any): void {
this.log(LogLevel.FATAL, module, message, contextOrData, data)
}
error(module: string, message: string, contextOrData?: LogContext | any, data?: any): void {
this.log(LogLevel.ERROR, module, message, contextOrData, data)
}
warn(module: string, message: string, contextOrData?: LogContext | any, data?: any): void {
this.log(LogLevel.WARN, module, message, contextOrData, data)
}
info(module: string, message: string, contextOrData?: LogContext | any, data?: any): void {
this.log(LogLevel.INFO, module, message, contextOrData, data)
}
debug(module: string, message: string, contextOrData?: LogContext | any, data?: any): void {
this.log(LogLevel.DEBUG, module, message, contextOrData, data)
}
trace(module: string, message: string, contextOrData?: LogContext | any, data?: any): void {
this.log(LogLevel.TRACE, module, message, contextOrData, data)
}
createModuleLogger(module: string) {
const self = this
return {
fatal: (message: string, contextOrData?: LogContext | any, data?: any) =>
self.fatal(module, message, contextOrData, data),
error: (message: string, contextOrData?: LogContext | any, data?: any) =>
self.error(module, message, contextOrData, data),
warn: (message: string, contextOrData?: LogContext | any, data?: any) =>
self.warn(module, message, contextOrData, data),
info: (message: string, contextOrData?: LogContext | any, data?: any) =>
self.info(module, message, contextOrData, data),
debug: (message: string, contextOrData?: LogContext | any, data?: any) =>
self.debug(module, message, contextOrData, data),
trace: (message: string, contextOrData?: LogContext | any, data?: any) =>
self.trace(module, message, contextOrData, data),
withContext: (context: LogContext) => {
const contextual = self.withContext(context)
return contextual.createModuleLogger(module)
},
startTimer: (label: string) => self.startTimer(`${module}:${label}`),
endTimer: (label: string) => self.endTimer(`${module}:${label}`)
}
}
async flush(): Promise<void> {
const flushPromises = this.config.transports
.filter(t => t.flush)
.map(t => t.flush!())
await Promise.all(flushPromises)
}
addTransport(transport: LogTransport): void {
this.config.transports.push(transport)
}
removeTransport(name: string): void {
this.config.transports = this.config.transports.filter(t => t.name !== name)
}
child(context: LogContext): StructuredLogger {
return this.withContext(context)
}
}
// Singleton instance
export const structuredLogger = StructuredLogger.getInstance()
// Convenience functions
export function createModuleLogger(module: string) {
return structuredLogger.createModuleLogger(module)
}
export function setLogContext(context: LogContext) {
structuredLogger.setContext(context)
}
export function withLogContext(context: LogContext) {
return structuredLogger.withContext(context)
}
// Correlation ID middleware helper
export function createCorrelationId(): string {
return randomUUID()
}
// Performance logging helper
export function logPerformance(
logger: ReturnType<typeof createModuleLogger>,
operation: string,
fn: () => any
): any {
logger.startTimer(operation)
try {
const result = fn()
if (result && typeof result.then === 'function') {
return result.finally(() => {
const duration = logger.endTimer(operation)
logger.debug(`${operation} completed`, { duration })
})
}
const duration = logger.endTimer(operation)
logger.debug(`${operation} completed`, { duration })
return result
} catch (error) {
const duration = logger.endTimer(operation)
logger.error(`${operation} failed`, { duration, error })
throw error
}
}
// Backward compatibility wrapper for existing logger
export class LoggerCompatibilityWrapper {
private moduleLogger: ReturnType<typeof createModuleLogger>
constructor(module: string = 'legacy') {
this.moduleLogger = createModuleLogger(module)
}
error(module: string, message: string, ...args: any[]): void {
this.moduleLogger.error(message, { module, data: args })
}
warn(module: string, message: string, ...args: any[]): void {
this.moduleLogger.warn(message, { module, data: args })
}
info(module: string, message: string, ...args: any[]): void {
this.moduleLogger.info(message, { module, data: args })
}
debug(module: string, message: string, ...args: any[]): void {
this.moduleLogger.debug(message, { module, data: args })
}
trace(module: string, message: string, ...args: any[]): void {
this.moduleLogger.trace(message, { module, data: args })
}
createModuleLogger(module: string) {
const logger = createModuleLogger(module)
return {
error: (message: string, ...args: any[]) => logger.error(message, { data: args }),
warn: (message: string, ...args: any[]) => logger.warn(message, { data: args }),
info: (message: string, ...args: any[]) => logger.info(message, { data: args }),
debug: (message: string, ...args: any[]) => logger.debug(message, { data: args }),
trace: (message: string, ...args: any[]) => logger.trace(message, { data: args })
}
}
}
// Export types for external use
export type ModuleLogger = ReturnType<typeof createModuleLogger>
// Types are already exported above, no need to re-export

411
src/utils/writeBuffer.ts
View file

@ -1,411 +0,0 @@
/**
* Write Buffer
* Accumulates writes and flushes them in bulk to reduce S3 operations
* Implements intelligent deduplication and compression
*/
import { HNSWNoun, HNSWVerb } from '../coreTypes.js'
import { createModuleLogger } from './logger.js'
import { getGlobalBackpressure } from './adaptiveBackpressure.js'
interface BufferedWrite<T> {
id: string
data: T
timestamp: number
type: 'noun' | 'verb' | 'metadata'
retryCount: number
}
interface FlushResult {
successful: number
failed: number
duration: number
}
/**
* High-performance write buffer for bulk operations
*/
export class WriteBuffer<T> {
private logger = createModuleLogger('WriteBuffer')
// Buffer storage
private buffer = new Map<string, BufferedWrite<T>>()
// Configuration - More aggressive for high volume
private maxBufferSize = 2000 // Allow larger buffers
private flushInterval = 500 // Flush more frequently (0.5 seconds)
private minFlushSize = 50 // Lower minimum to flush sooner
private maxRetries = 3 // Maximum retry attempts
// State
private flushTimer: NodeJS.Timeout | null = null
private isFlushing = false
private lastFlush = Date.now()
private pendingFlush: Promise<FlushResult> | null = null
// Statistics
private totalWrites = 0
private totalFlushes = 0
private failedWrites = 0
private duplicatesRemoved = 0
// Write function
private writeFunction: (items: Map<string, T>) => Promise<void>
private type: 'noun' | 'verb' | 'metadata'
// Backpressure integration
private backpressure = getGlobalBackpressure()
constructor(
type: 'noun' | 'verb' | 'metadata',
writeFunction: (items: Map<string, T>) => Promise<void>,
options?: {
maxBufferSize?: number
flushInterval?: number
minFlushSize?: number
}
) {
this.type = type
this.writeFunction = writeFunction
if (options) {
this.maxBufferSize = options.maxBufferSize || this.maxBufferSize
this.flushInterval = options.flushInterval || this.flushInterval
this.minFlushSize = options.minFlushSize || this.minFlushSize
}
// Start periodic flush
this.startPeriodicFlush()
}
/**
* Add item to buffer
*/
public async add(id: string, data: T): Promise<void> {
// Check if we're already at capacity
if (this.buffer.size >= this.maxBufferSize) {
// Wait for current flush to complete
if (this.pendingFlush) {
await this.pendingFlush
}
// Force flush if still at capacity
if (this.buffer.size >= this.maxBufferSize) {
await this.flush('capacity')
}
}
// Check for duplicate and update if newer
const existing = this.buffer.get(id)
if (existing) {
// Update with newer data
existing.data = data
existing.timestamp = Date.now()
this.duplicatesRemoved++
} else {
// Add new item
this.buffer.set(id, {
id,
data,
timestamp: Date.now(),
type: this.type,
retryCount: 0
})
}
this.totalWrites++
// Log buffer growth periodically
if (this.totalWrites % 100 === 0) {
this.logger.info(`📈 BUFFER GROWTH: ${this.buffer.size} ${this.type} items buffered (${this.totalWrites} total writes, ${this.duplicatesRemoved} deduplicated)`)
}
// Check if we should flush
this.checkFlush()
}
/**
* Check if we should flush
*/
private checkFlush(): void {
const bufferSize = this.buffer.size
const timeSinceFlush = Date.now() - this.lastFlush
// Immediate flush conditions
if (bufferSize >= this.maxBufferSize) {
this.flush('size')
return
}
// Time-based flush with minimum size
if (timeSinceFlush >= this.flushInterval && bufferSize >= this.minFlushSize) {
this.flush('time')
return
}
// Adaptive flush based on system load
const backpressureStatus = this.backpressure.getStatus()
if (backpressureStatus.queueLength > 1000 && bufferSize > 10) {
// System under pressure - flush smaller batches more frequently
this.flush('pressure')
}
}
/**
* Flush buffer to storage
*/
public async flush(reason: string = 'manual'): Promise<FlushResult> {
// Prevent concurrent flushes
if (this.isFlushing) {
if (this.pendingFlush) {
return this.pendingFlush
}
return { successful: 0, failed: 0, duration: 0 }
}
// Nothing to flush
if (this.buffer.size === 0) {
return { successful: 0, failed: 0, duration: 0 }
}
this.isFlushing = true
const startTime = Date.now()
// Create flush promise
this.pendingFlush = this.doFlush(reason, startTime)
try {
const result = await this.pendingFlush
return result
} finally {
this.isFlushing = false
this.pendingFlush = null
}
}
/**
* Perform the actual flush
*/
private async doFlush(reason: string, startTime: number): Promise<FlushResult> {
const itemsToFlush = new Map<string, T>()
const flushingItems = new Map<string, BufferedWrite<T>>()
// Take items from buffer
let count = 0
for (const [id, item] of this.buffer.entries()) {
itemsToFlush.set(id, item.data)
flushingItems.set(id, item)
count++
// Limit batch size for better performance
if (count >= 500) {
break
}
}
// Remove from buffer
for (const id of itemsToFlush.keys()) {
this.buffer.delete(id)
}
this.logger.warn(`🔄 BUFFERING: Flushing ${itemsToFlush.size} ${this.type} items (buffer had ${this.buffer.size + itemsToFlush.size}) - reason: ${reason}`)
try {
// Request permission from backpressure system
const opId = `flush-${Date.now()}`
await this.backpressure.requestPermission(opId, 2) // Higher priority
try {
// Perform bulk write
await this.writeFunction(itemsToFlush)
// Success
this.backpressure.releasePermission(opId, true)
this.totalFlushes++
this.lastFlush = Date.now()
const duration = Date.now() - startTime
this.logger.warn(`🚀 BATCH FLUSH: ${itemsToFlush.size} ${this.type} items → 1 bulk S3 operation (${duration}ms, reason: ${reason})`)
return {
successful: itemsToFlush.size,
failed: 0,
duration
}
} catch (error) {
// Release with error
this.backpressure.releasePermission(opId, false)
throw error
}
} catch (error) {
this.logger.error(`Flush failed: ${error}`)
// Put items back with retry count
for (const [id, item] of flushingItems.entries()) {
item.retryCount++
if (item.retryCount < this.maxRetries) {
// Put back for retry
this.buffer.set(id, item)
} else {
// Max retries exceeded
this.failedWrites++
this.logger.error(`Max retries exceeded for ${this.type} ${id}`)
}
}
const duration = Date.now() - startTime
return {
successful: 0,
failed: itemsToFlush.size,
duration
}
}
}
/**
* Start periodic flush timer
*/
private startPeriodicFlush(): void {
if (this.flushTimer) {
return
}
this.flushTimer = setInterval(() => {
if (this.buffer.size > 0) {
const timeSinceFlush = Date.now() - this.lastFlush
// Flush if we have items and enough time has passed
if (timeSinceFlush >= this.flushInterval) {
this.flush('periodic').catch(error => {
this.logger.error('Periodic flush failed:', error)
})
}
}
}, Math.min(100, this.flushInterval / 2))
}
/**
* Stop periodic flush timer
*/
public stop(): void {
if (this.flushTimer) {
clearInterval(this.flushTimer)
this.flushTimer = null
}
}
/**
* Force flush all pending writes
*/
public async forceFlush(): Promise<FlushResult> {
// Flush everything regardless of size
const oldMinSize = this.minFlushSize
this.minFlushSize = 0
try {
const result = await this.flush('force')
// Flush any remaining items
while (this.buffer.size > 0) {
const additionalResult = await this.flush('force-remaining')
result.successful += additionalResult.successful
result.failed += additionalResult.failed
result.duration += additionalResult.duration
}
return result
} finally {
this.minFlushSize = oldMinSize
}
}
/**
* Get buffer statistics
*/
public getStats(): {
bufferSize: number
totalWrites: number
totalFlushes: number
failedWrites: number
duplicatesRemoved: number
avgFlushSize: number
} {
return {
bufferSize: this.buffer.size,
totalWrites: this.totalWrites,
totalFlushes: this.totalFlushes,
failedWrites: this.failedWrites,
duplicatesRemoved: this.duplicatesRemoved,
avgFlushSize: this.totalFlushes > 0 ? this.totalWrites / this.totalFlushes : 0
}
}
/**
* Adjust parameters based on load
*/
public adjustForLoad(pendingRequests: number): void {
if (pendingRequests > 10000) {
// Extreme load - buffer more aggressively
this.maxBufferSize = 5000
this.flushInterval = 500
this.minFlushSize = 500
} else if (pendingRequests > 1000) {
// High load
this.maxBufferSize = 2000
this.flushInterval = 1000
this.minFlushSize = 200
} else if (pendingRequests > 100) {
// Moderate load
this.maxBufferSize = 1000
this.flushInterval = 2000
this.minFlushSize = 100
} else {
// Low load - optimize for latency
this.maxBufferSize = 500
this.flushInterval = 5000
this.minFlushSize = 50
}
}
}
// Global write buffers
const writeBuffers = new Map<string, WriteBuffer<any>>()
/**
* Get or create a write buffer
*/
export function getWriteBuffer<T>(
id: string,
type: 'noun' | 'verb' | 'metadata',
writeFunction: (items: Map<string, T>) => Promise<void>
): WriteBuffer<T> {
if (!writeBuffers.has(id)) {
writeBuffers.set(id, new WriteBuffer<T>(type, writeFunction))
}
return writeBuffers.get(id)!
}
/**
* Flush all write buffers
*/
export async function flushAllBuffers(): Promise<void> {
const promises: Promise<FlushResult>[] = []
for (const buffer of writeBuffers.values()) {
promises.push(buffer.forceFlush())
}
await Promise.all(promises)
}
/**
* Clear all write buffers
*/
export function clearWriteBuffers(): void {
for (const buffer of writeBuffers.values()) {
buffer.stop()
}
writeBuffers.clear()
}

333
src/vfs/FSCompat.ts
View file

@ -1,333 +0,0 @@
/**
* fs-Compatible Interface for VFS
*
* Provides a drop-in replacement for Node's fs module
* that uses VFS for storage instead of the real filesystem.
*
* Usage:
* import { FSCompat } from '@soulcraft/brainy/vfs'
* const fs = new FSCompat(brain.vfs)
*
* // Now use like Node's fs
* await fs.promises.readFile('/path')
* fs.createReadStream('/path').pipe(output)
*/
import { VirtualFileSystem } from './VirtualFileSystem.js'
import type {
ReadOptions,
WriteOptions,
MkdirOptions,
VFSStats,
VFSDirent
} from './types.js'
export class FSCompat {
/**
* Promise-based API (like fs.promises)
*/
public readonly promises: FSPromises
constructor(private vfs: VirtualFileSystem) {
this.promises = new FSPromises(vfs)
}
// ============= Callback-style methods (for compatibility) =============
readFile(path: string, callback: (err: Error | null, data?: Buffer) => void): void
readFile(path: string, encoding: BufferEncoding, callback: (err: Error | null, data?: string) => void): void
readFile(path: string, options: any, callback?: any): void {
if (typeof options === 'function') {
callback = options
options = {}
}
this.vfs.readFile(path, options)
.then(data => {
if (options?.encoding) {
callback(null, data.toString(options.encoding))
} else {
callback(null, data)
}
})
.catch(err => callback(err))
}
writeFile(path: string, data: Buffer | string, callback: (err: Error | null) => void): void
writeFile(path: string, data: Buffer | string, options: any, callback?: any): void {
if (typeof options === 'function') {
callback = options
options = {}
}
const buffer = Buffer.isBuffer(data) ? data : Buffer.from(data, options?.encoding || 'utf8')
this.vfs.writeFile(path, buffer, options)
.then(() => callback(null))
.catch(err => callback(err))
}
mkdir(path: string, callback: (err: Error | null) => void): void
mkdir(path: string, options: any, callback?: any): void {
if (typeof options === 'function') {
callback = options
options = {}
}
this.vfs.mkdir(path, options)
.then(() => callback(null))
.catch(err => callback(err))
}
rmdir(path: string, callback: (err: Error | null) => void): void
rmdir(path: string, options: any, callback?: any): void {
if (typeof options === 'function') {
callback = options
options = {}
}
this.vfs.rmdir(path, options)
.then(() => callback(null))
.catch(err => callback(err))
}
readdir(path: string, callback: (err: Error | null, files?: string[]) => void): void
readdir(path: string, options: any, callback?: any): void {
if (typeof options === 'function') {
callback = options
options = {}
}
this.vfs.readdir(path, options)
.then(files => callback(null, files))
.catch(err => callback(err))
}
stat(path: string, callback: (err: Error | null, stats?: VFSStats) => void): void {
this.vfs.stat(path)
.then(stats => callback(null, stats))
.catch(err => callback(err))
}
lstat(path: string, callback: (err: Error | null, stats?: VFSStats) => void): void {
this.vfs.lstat(path)
.then(stats => callback(null, stats))
.catch(err => callback(err))
}
unlink(path: string, callback: (err: Error | null) => void): void {
this.vfs.unlink(path)
.then(() => callback(null))
.catch(err => callback(err))
}
rename(oldPath: string, newPath: string, callback: (err: Error | null) => void): void {
this.vfs.rename(oldPath, newPath)
.then(() => callback(null))
.catch(err => callback(err))
}
copyFile(src: string, dest: string, callback: (err: Error | null) => void): void
copyFile(src: string, dest: string, flags: number, callback: (err: Error | null) => void): void
copyFile(src: string, dest: string, flagsOrCallback: any, callback?: any): void {
if (typeof flagsOrCallback === 'function') {
callback = flagsOrCallback
} else {
// flags provided but not used
}
this.vfs.copy(src, dest)
.then(() => callback(null))
.catch(err => callback(err))
}
exists(path: string, callback: (exists: boolean) => void): void {
this.vfs.exists(path)
.then(exists => callback(exists))
.catch(() => callback(false))
}
access(path: string, callback: (err: Error | null) => void): void
access(path: string, mode: number, callback: (err: Error | null) => void): void
access(path: string, modeOrCallback: any, callback?: any): void {
if (typeof modeOrCallback === 'function') {
callback = modeOrCallback
} else {
// mode provided but not used
}
this.vfs.exists(path)
.then(exists => {
if (exists) {
callback(null)
} else {
const err: any = new Error('ENOENT: no such file or directory')
err.code = 'ENOENT'
callback(err)
}
})
.catch(err => callback(err))
}
appendFile(path: string, data: Buffer | string, callback: (err: Error | null) => void): void
appendFile(path: string, data: Buffer | string, options: any, callback?: any): void {
if (typeof options === 'function') {
callback = options
options = {}
}
const buffer = Buffer.isBuffer(data) ? data : Buffer.from(data, options?.encoding || 'utf8')
this.vfs.appendFile(path, buffer, options)
.then(() => callback(null))
.catch(err => callback(err))
}
// ============= Stream methods =============
createReadStream(path: string, options?: any) {
return this.vfs.createReadStream(path, options)
}
createWriteStream(path: string, options?: any) {
return this.vfs.createWriteStream(path, options)
}
// ============= Watch methods =============
watch(path: string, listener?: any) {
return this.vfs.watch(path, listener)
}
watchFile(path: string, listener: any) {
return this.vfs.watchFile(path, listener)
}
unwatchFile(path: string) {
return this.vfs.unwatchFile(path)
}
// ============= Additional methods =============
/**
* Import a directory from real filesystem (VFS extension)
*/
async importDirectory(sourcePath: string, options?: any) {
return this.vfs.importDirectory(sourcePath, options)
}
/**
* Search files semantically (VFS extension)
*/
async search(query: string, options?: any) {
return this.vfs.search(query, options)
}
}
/**
* Promise-based fs API (like fs.promises)
*/
class FSPromises {
constructor(private vfs: VirtualFileSystem) {}
async readFile(path: string, options?: any): Promise<Buffer | string> {
const buffer = await this.vfs.readFile(path, options)
if (options?.encoding) {
return buffer.toString(options.encoding)
}
return buffer
}
async writeFile(path: string, data: Buffer | string, options?: any): Promise<void> {
const buffer = Buffer.isBuffer(data) ? data : Buffer.from(data, options?.encoding || 'utf8')
return this.vfs.writeFile(path, buffer, options)
}
async mkdir(path: string, options?: any): Promise<void> {
return this.vfs.mkdir(path, options)
}
async rmdir(path: string, options?: any): Promise<void> {
return this.vfs.rmdir(path, options)
}
async readdir(path: string, options?: any): Promise<string[] | VFSDirent[]> {
return this.vfs.readdir(path, options)
}
async stat(path: string): Promise<VFSStats> {
return this.vfs.stat(path)
}
async lstat(path: string): Promise<VFSStats> {
return this.vfs.lstat(path)
}
async unlink(path: string): Promise<void> {
return this.vfs.unlink(path)
}
async rename(oldPath: string, newPath: string): Promise<void> {
return this.vfs.rename(oldPath, newPath)
}
async copyFile(src: string, dest: string, flags?: number): Promise<void> {
return this.vfs.copy(src, dest)
}
async access(path: string, mode?: number): Promise<void> {
const exists = await this.vfs.exists(path)
if (!exists) {
const err: any = new Error('ENOENT: no such file or directory')
err.code = 'ENOENT'
throw err
}
}
async appendFile(path: string, data: Buffer | string, options?: any): Promise<void> {
const buffer = Buffer.isBuffer(data) ? data : Buffer.from(data, options?.encoding || 'utf8')
return this.vfs.appendFile(path, buffer, options)
}
async realpath(path: string): Promise<string> {
return this.vfs.realpath(path)
}
async chmod(path: string, mode: number): Promise<void> {
return this.vfs.chmod(path, mode)
}
async chown(path: string, uid: number, gid: number): Promise<void> {
return this.vfs.chown(path, uid, gid)
}
async utimes(path: string, atime: Date, mtime: Date): Promise<void> {
return this.vfs.utimes(path, atime, mtime)
}
async symlink(target: string, path: string): Promise<void> {
return this.vfs.symlink(target, path)
}
async readlink(path: string): Promise<string> {
return this.vfs.readlink(path)
}
// VFS Extensions
async search(query: string, options?: any) {
return this.vfs.search(query, options)
}
async findSimilar(path: string, options?: any) {
return this.vfs.findSimilar(path, options)
}
async importDirectory(sourcePath: string, options?: any) {
return this.vfs.importDirectory(sourcePath, options)
}
}
// Export a convenience function to create fs replacement
export function createFS(vfs: VirtualFileSystem): FSCompat {
return new FSCompat(vfs)
}

27
src/vfs/index.ts
View file

@ -1,27 +0,0 @@
/**
* Brainy Virtual Filesystem
*
* A simplified fs-compatible filesystem that stores data in Brainy
* Works across all storage adapters and scales to millions of files
*/
// Core VFS
export { VirtualFileSystem } from './VirtualFileSystem.js'
export { PathResolver } from './PathResolver.js'
export * from './types.js'
// MIME Type Detection
export { MimeTypeDetector, mimeDetector } from './MimeTypeDetector.js'
// fs compatibility layer
export { FSCompat, createFS } from './FSCompat.js'
// Directory import
export { DirectoryImporter } from './importers/DirectoryImporter.js'
// Streaming
export { VFSReadStream } from './streams/VFSReadStream.js'
export { VFSWriteStream } from './streams/VFSWriteStream.js'
// Convenience alias
export { VirtualFileSystem as VFS } from './VirtualFileSystem.js'