fix: exclude __words__ keyword index from corruption detection and getStats()

The __words__ keyword index stores 50-5000 entries per entity (one per
word), which inflated avg entries/entity well above the corruption
threshold of 100. This caused:

1. validateConsistency() to falsely detect corruption on every startup,
   triggering unnecessary clearAllIndexData() + rebuild() cycles
2. getStats() to log false "Metadata index may be corrupted" warnings
   and report inflated totalEntries/totalIds stats

Both methods now skip __words__ when counting, so stats and health
checks reflect metadata fields only (noun, type, createdAt, etc.).
Keyword search is unaffected since the __words__ field index itself
is not modified.
This commit is contained in:
David Snelling 2026-01-27 15:38:21 -08:00
parent 32dbdcec61
commit 364360d447
128 changed files with 5637 additions and 5682 deletions

View file

@ -42,17 +42,17 @@ export interface SmartCSVOptions extends FormatHandlerOptions {
csvDelimiter?: string
csvHeaders?: boolean
/** Progress callback (v3.39.0: Enhanced with performance metrics) */
/** Progress callback (Enhanced with performance metrics) */
onProgress?: (stats: {
processed: number
total: number
entities: number
relationships: number
/** Rows per second (v3.39.0) */
/** Rows per second */
throughput?: number
/** Estimated time remaining in ms (v3.39.0) */
/** Estimated time remaining in ms */
eta?: number
/** Current phase (v3.39.0) */
/** Current phase */
phase?: string
}) => void
}
@ -169,7 +169,7 @@ export class SmartCSVImporter {
}
// Parse CSV using existing handler
// v4.5.0: Pass progress hooks to handler for file parsing progress
// Pass progress hooks to handler for file parsing progress
const processedData = await this.csvHandler.process(buffer, {
...options,
csvDelimiter: opts.csvDelimiter,
@ -217,7 +217,7 @@ export class SmartCSVImporter {
// Detect column names
const columns = this.detectColumns(rows[0], opts)
// Process each row with BATCHED PARALLEL PROCESSING (v3.39.0)
// Process each row with BATCHED PARALLEL PROCESSING
const extractedRows: ExtractedRow[] = []
const entityMap = new Map<string, string>()
const stats = {
@ -375,7 +375,7 @@ export class SmartCSVImporter {
total: rows.length,
entities: extractedRows.reduce((sum, row) => sum + 1 + row.relatedEntities.length, 0),
relationships: extractedRows.reduce((sum, row) => sum + row.relationships.length, 0),
// Additional performance metrics (v3.39.0)
// Additional performance metrics
throughput: Math.round(rowsPerSecond * 10) / 10,
eta: Math.round(estimatedTimeRemaining),
phase: 'extracting'

View file

@ -9,7 +9,7 @@
* - NaturalLanguageProcessor for relationship inference
* - Hierarchical relationship creation based on heading hierarchy
*
* v4.2.0: New format handler
* New format handler
* NO MOCKS - Production-ready implementation
*/
@ -187,7 +187,7 @@ export class SmartDOCXImporter {
await this.init()
}
// v4.5.0: Report parsing start
// Report parsing start
options.onProgress?.({
processed: 0,
entities: 0,
@ -200,7 +200,7 @@ export class SmartDOCXImporter {
// Extract HTML for structure analysis (headings, tables)
const htmlResult = await mammoth.convertToHtml({ buffer })
// v4.5.0: Report parsing complete
// Report parsing complete
options.onProgress?.({
processed: 0,
entities: 0,

View file

@ -36,17 +36,17 @@ export interface SmartExcelOptions extends FormatHandlerOptions {
typeColumn?: string // e.g., "Type", "Category"
relatedColumn?: string // e.g., "Related Terms", "See Also"
/** Progress callback (v3.38.0: Enhanced with performance metrics) */
/** Progress callback (Enhanced with performance metrics) */
onProgress?: (stats: {
processed: number
total: number
entities: number
relationships: number
/** Rows per second (v3.38.0) */
/** Rows per second */
throughput?: number
/** Estimated time remaining in ms (v3.38.0) */
/** Estimated time remaining in ms */
eta?: number
/** Current phase (v3.38.0) */
/** Current phase */
phase?: string
}) => void
}
@ -111,7 +111,7 @@ export interface SmartExcelResult {
}
}
/** Sheet-specific data for VFS extraction (v4.2.0) */
/** Sheet-specific data for VFS extraction */
sheets?: Array<{
name: string
rows: ExtractedRow[]
@ -161,7 +161,7 @@ export class SmartExcelImporter {
const opts = {
enableNeuralExtraction: true,
enableRelationshipInference: true,
// CONCEPT EXTRACTION PRODUCTION-READY (v3.33.0+):
// CONCEPT EXTRACTION PRODUCTION-READY:
// Type embeddings are now pre-computed at build time - zero runtime cost!
// All 42 noun types + 127 verb types instantly available
//
@ -184,7 +184,7 @@ export class SmartExcelImporter {
}
// Parse Excel using existing handler
// v4.5.0: Pass progress hooks to handler for file parsing progress
// Pass progress hooks to handler for file parsing progress
const processedData = await this.excelHandler.process(buffer, {
...options,
totalBytes: buffer.length,
@ -227,7 +227,7 @@ export class SmartExcelImporter {
return this.emptyResult(startTime)
}
// CRITICAL FIX (v4.8.6): Detect columns per-sheet, not globally
// CRITICAL FIX: Detect columns per-sheet, not globally
// Different sheets may have different column structures (Term vs Name, etc.)
// Group rows by sheet and detect columns for each sheet separately
const rowsBySheet = new Map<string, typeof rows>()
@ -247,7 +247,7 @@ export class SmartExcelImporter {
}
}
// Process each row with BATCHED PARALLEL PROCESSING (v3.38.0)
// Process each row with BATCHED PARALLEL PROCESSING
const extractedRows: ExtractedRow[] = []
const entityMap = new Map<string, string>()
const stats = {
@ -269,7 +269,7 @@ export class SmartExcelImporter {
chunk.map(async (row, chunkIndex) => {
const i = chunkStart + chunkIndex
// CRITICAL FIX (v4.8.6): Use sheet-specific column mapping
// CRITICAL FIX: Use sheet-specific column mapping
const sheet = row._sheet || 'default'
const columns = columnsBySheet.get(sheet) || this.detectColumns(row, opts)
@ -353,7 +353,7 @@ export class SmartExcelImporter {
}
// ============================================
// v4.9.0: Enhanced column-based relationship detection
// Enhanced column-based relationship detection
// ============================================
// Parse explicit "Related Terms" column
if (relatedTerms) {
@ -379,7 +379,7 @@ export class SmartExcelImporter {
}
}
// v4.9.0: Check for additional relationship-indicating columns
// Check for additional relationship-indicating columns
// Expanded patterns for various relationship types
const relationshipColumnPatterns = [
{ pattern: /^(location|home|lives in|resides|dwelling|place)$/i, defaultType: VerbType.LocatedAt },
@ -485,14 +485,14 @@ export class SmartExcelImporter {
total: rows.length,
entities: extractedRows.reduce((sum, row) => sum + 1 + row.relatedEntities.length, 0),
relationships: extractedRows.reduce((sum, row) => sum + row.relationships.length, 0),
// Additional performance metrics (v3.38.0)
// Additional performance metrics
throughput: Math.round(rowsPerSecond * 10) / 10,
eta: Math.round(estimatedTimeRemaining),
phase: 'extracting'
} as any)
}
// Group rows by sheet for VFS extraction (v4.2.0)
// Group rows by sheet for VFS extraction
const sheetGroups = new Map<string, ExtractedRow[]>()
extractedRows.forEach((extractedRow, index) => {
const originalRow = rows[index]

View file

@ -167,7 +167,7 @@ export class SmartJSONImporter {
...options
}
// v4.5.0: Report parsing start
// Report parsing start
opts.onProgress({
processed: 0,
entities: 0,
@ -186,7 +186,7 @@ export class SmartJSONImporter {
jsonData = data
}
// v4.5.0: Report parsing complete, starting traversal
// Report parsing complete, starting traversal
opts.onProgress({
processed: 0,
entities: 0,
@ -228,7 +228,7 @@ export class SmartJSONImporter {
}
)
// v4.5.0: Report completion
// Report completion
opts.onProgress({
processed: nodesProcessed,
entities: entities.length,

View file

@ -174,7 +174,7 @@ export class SmartMarkdownImporter {
...options
}
// v4.5.0: Report parsing start
// Report parsing start
opts.onProgress({
processed: 0,
total: 0,
@ -185,7 +185,7 @@ export class SmartMarkdownImporter {
// Parse markdown into sections
const parsedSections = this.parseMarkdown(markdown, opts)
// v4.5.0: Report parsing complete
// Report parsing complete
opts.onProgress({
processed: 0,
total: parsedSections.length,
@ -218,7 +218,7 @@ export class SmartMarkdownImporter {
})
}
// v4.5.0: Report completion
// Report completion
const totalEntities = sections.reduce((sum, s) => sum + s.entities.length, 0)
const totalRelationships = sections.reduce((sum, s) => sum + s.relationships.length, 0)
opts.onProgress({

View file

@ -40,17 +40,17 @@ export interface SmartPDFOptions extends FormatHandlerOptions {
/** Group by page or full document */
groupBy?: 'page' | 'document'
/** Progress callback (v3.39.0: Enhanced with performance metrics) */
/** Progress callback (Enhanced with performance metrics) */
onProgress?: (stats: {
processed: number
total: number
entities: number
relationships: number
/** Sections per second (v3.39.0) */
/** Sections per second */
throughput?: number
/** Estimated time remaining in ms (v3.39.0) */
/** Estimated time remaining in ms */
eta?: number
/** Current phase (v3.39.0) */
/** Current phase */
phase?: string
}) => void
}
@ -181,7 +181,7 @@ export class SmartPDFImporter {
}
// Parse PDF using existing handler
// v4.5.0: Pass progress hooks to handler for file parsing progress
// Pass progress hooks to handler for file parsing progress
const processedData = await this.pdfHandler.process(buffer, {
...options,
totalBytes: buffer.length,
@ -228,7 +228,7 @@ export class SmartPDFImporter {
// Group data by page or combine into single document
const grouped = this.groupData(data, opts)
// Process each group with BATCHED PARALLEL PROCESSING (v3.39.0)
// Process each group with BATCHED PARALLEL PROCESSING
const sections: ExtractedSection[] = []
const entityMap = new Map<string, string>()
const stats = {
@ -270,7 +270,7 @@ export class SmartPDFImporter {
total: totalGroups,
entities: sections.reduce((sum, s) => sum + s.entities.length, 0),
relationships: sections.reduce((sum, s) => sum + s.relationships.length, 0),
// Additional performance metrics (v3.39.0)
// Additional performance metrics
throughput: Math.round(sectionsPerSecond * 10) / 10,
eta: Math.round(estimatedTimeRemaining),
phase: 'extracting'
@ -367,7 +367,7 @@ export class SmartPDFImporter {
const combinedText = texts.join('\n\n')
// Parallel extraction: entities AND concepts at the same time (v3.39.0)
// Parallel extraction: entities AND concepts at the same time
const [extractedEntities, concepts] = await Promise.all([
// Extract entities if enabled
options.enableNeuralExtraction && combinedText.length > 0

View file

@ -8,7 +8,7 @@
* - NaturalLanguageProcessor for relationship inference
* - Hierarchical relationship creation (parent-child, contains, etc.)
*
* v4.2.0: New format handler
* New format handler
* NO MOCKS - Production-ready implementation
*/
@ -159,7 +159,7 @@ export class SmartYAMLImporter {
): Promise<SmartYAMLResult> {
const startTime = Date.now()
// v4.5.0: Report parsing start
// Report parsing start
options.onProgress?.({
processed: 0,
entities: 0,
@ -178,7 +178,7 @@ export class SmartYAMLImporter {
throw new Error(`Failed to parse YAML: ${error.message}`)
}
// v4.5.0: Report parsing complete
// Report parsing complete
options.onProgress?.({
processed: 0,
entities: 0,

View file

@ -40,10 +40,10 @@ export interface VFSStructureOptions {
/** Create metadata file */
createMetadataFile?: boolean
/** Import tracking context (v4.10.0) */
/** Import tracking context */
trackingContext?: TrackingContext
/** Progress callback (v4.11.1) - Reports VFS creation progress */
/** Progress callback - Reports VFS creation progress */
onProgress?: (progress: {
stage: 'directories' | 'entities' | 'metadata'
message: string
@ -98,7 +98,7 @@ export class VFSStructureGenerator {
// Get brain's cached VFS instance (creates if doesn't exist)
this.vfs = this.brain.vfs
// CRITICAL FIX (v4.10.2): Always call vfs.init() explicitly
// CRITICAL FIX: Always call vfs.init() explicitly
// The previous code tried to check if initialized via stat('/') but this was unreliable
// vfs.init() is idempotent, so calling it multiple times is safe
await this.vfs.init()
@ -123,7 +123,7 @@ export class VFSStructureGenerator {
// Ensure VFS is initialized
await this.init()
// v4.11.1: Calculate total operations for progress tracking
// Calculate total operations for progress tracking
const groups = this.groupEntities(importResult, options)
const totalEntities = Array.from(groups.values()).reduce((sum, entities) => sum + entities.length, 0)
const totalOperations =
@ -161,7 +161,7 @@ export class VFSStructureGenerator {
try {
await this.vfs.mkdir(options.rootPath, {
recursive: true,
metadata: trackingMetadata // v4.10.0: Add tracking metadata
metadata: trackingMetadata // Add tracking metadata
})
result.directories.push(options.rootPath)
result.operations++
@ -179,7 +179,7 @@ export class VFSStructureGenerator {
if (options.preserveSource && options.sourceBuffer && options.sourceFilename) {
const sourcePath = `${options.rootPath}/_source${this.getExtension(options.sourceFilename)}`
await this.vfs.writeFile(sourcePath, options.sourceBuffer, {
metadata: trackingMetadata // v4.10.0: Add tracking metadata
metadata: trackingMetadata // Add tracking metadata
})
result.files.push({
path: sourcePath,
@ -200,7 +200,7 @@ export class VFSStructureGenerator {
try {
await this.vfs.mkdir(groupPath, {
recursive: true,
metadata: trackingMetadata // v4.10.0: Add tracking metadata
metadata: trackingMetadata // Add tracking metadata
})
result.directories.push(groupPath)
result.operations++
@ -242,7 +242,7 @@ export class VFSStructureGenerator {
await this.vfs.writeFile(entityPath, JSON.stringify(entityJson, null, 2), {
metadata: {
...trackingMetadata, // v4.10.0: Add tracking metadata
...trackingMetadata, // Add tracking metadata
entityId: extracted.entity.id
}
})
@ -253,7 +253,7 @@ export class VFSStructureGenerator {
})
result.operations++
// v4.11.1: Report progress every 10 entities (or on last entity)
// Report progress every 10 entities (or on last entity)
if (entityCount % 10 === 0 || entityCount === entities.length) {
reportProgress('entities', `Created ${entityCount}/${entities.length} ${groupName} files`)
}
@ -280,7 +280,7 @@ export class VFSStructureGenerator {
}
await this.vfs.writeFile(relationshipsPath, JSON.stringify(relationshipsJson, null, 2), {
metadata: trackingMetadata // v4.10.0: Add tracking metadata
metadata: trackingMetadata // Add tracking metadata
})
result.files.push({
path: relationshipsPath,
@ -322,7 +322,7 @@ export class VFSStructureGenerator {
}
await this.vfs.writeFile(metadataPath, JSON.stringify(metadataJson, null, 2), {
metadata: trackingMetadata // v4.10.0: Add tracking metadata
metadata: trackingMetadata // Add tracking metadata
})
result.files.push({
path: metadataPath,
@ -332,7 +332,7 @@ export class VFSStructureGenerator {
reportProgress('metadata', 'Created metadata file')
}
// v4.11.1: Final progress update
// Final progress update
if (options.onProgress) {
options.onProgress({
stage: 'metadata',
@ -355,7 +355,7 @@ export class VFSStructureGenerator {
): Map<string, typeof importResult.rows> {
const groups = new Map<string, typeof importResult.rows>()
// Handle sheet-based grouping (v4.2.0)
// Handle sheet-based grouping
if (options.groupBy === 'sheet' && importResult.sheets && importResult.sheets.length > 0) {
for (const sheet of importResult.sheets) {
groups.set(sheet.name, sheet.rows)