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.

src/augmentations/intelligentImport/FormatHandlerRegistry.ts

@@ -1,5 +1,5 @@
 /**
- * Format Handler Registry (v5.2.0)
+ * Format Handler Registry
  *
  * Central registry for format handlers with:
  * - MIME type-based routing

src/augmentations/intelligentImport/IntelligentImportAugmentation.ts

@@ -35,7 +35,7 @@ export class IntelligentImportAugmentation extends BaseAugmentation {
       enableCSV: true,
       enableExcel: true,
       enablePDF: true,
-      enableImage: true, // v5.2.0: Image handler enabled by default
+      enableImage: true, // Image handler enabled by default
       maxFileSize: 100 * 1024 * 1024, // 100MB default
       enableCache: true,
       cacheTTL: 24 * 60 * 60 * 1000, // 24 hours

src/augmentations/intelligentImport/handlers/csvHandler.ts

@@ -40,7 +40,7 @@ export class CSVHandler extends BaseFormatHandler {
     const buffer = Buffer.isBuffer(data) ? data : Buffer.from(data, 'utf-8')
     const totalBytes = buffer.length
 
-    // v4.5.0: Report total bytes for progress tracking
+    // Report total bytes for progress tracking
     if (progressHooks?.onBytesProcessed) {
       progressHooks.onBytesProcessed(0)
     }
@@ -55,7 +55,7 @@ export class CSVHandler extends BaseFormatHandler {
     // Detect delimiter if not specified
     const delimiter = options.csvDelimiter || this.detectDelimiter(text)
 
-    // v4.5.0: Report progress - parsing started
+    // Report progress - parsing started
     if (progressHooks?.onCurrentItem) {
       progressHooks.onCurrentItem(`Parsing CSV rows (delimiter: "${delimiter}")...`)
     }
@@ -75,7 +75,7 @@ export class CSVHandler extends BaseFormatHandler {
         cast: false // We'll do type inference ourselves
       })
 
-      // v4.5.0: Report bytes processed (entire file parsed)
+      // Report bytes processed (entire file parsed)
       if (progressHooks?.onBytesProcessed) {
         progressHooks.onBytesProcessed(totalBytes)
       }
@@ -83,7 +83,7 @@ export class CSVHandler extends BaseFormatHandler {
       // Convert to array of objects
       const data = Array.isArray(records) ? records : [records]
 
-      // v4.5.0: Report data extraction progress
+      // Report data extraction progress
       if (progressHooks?.onDataExtracted) {
         progressHooks.onDataExtracted(data.length, data.length)
       }
@@ -101,7 +101,7 @@ export class CSVHandler extends BaseFormatHandler {
           converted[key] = this.convertValue(value, types[key] || 'string')
         }
 
-        // v4.5.0: Report progress every 1000 rows
+        // Report progress every 1000 rows
         if (progressHooks?.onCurrentItem && index > 0 && index % 1000 === 0) {
           progressHooks.onCurrentItem(`Converting types: ${index}/${data.length} rows...`)
         }
@@ -111,7 +111,7 @@ export class CSVHandler extends BaseFormatHandler {
 
       const processingTime = Date.now() - startTime
 
-      // v4.5.0: Final progress update
+      // Final progress update
       if (progressHooks?.onCurrentItem) {
         progressHooks.onCurrentItem(`CSV processing complete: ${convertedData.length} rows`)
       }

src/augmentations/intelligentImport/handlers/excelHandler.ts

@@ -27,7 +27,7 @@ export class ExcelHandler extends BaseFormatHandler {
     const buffer = Buffer.isBuffer(data) ? data : Buffer.from(data, 'binary')
     const totalBytes = buffer.length
 
-    // v4.5.0: Report start
+    // Report start
     if (progressHooks?.onBytesProcessed) {
       progressHooks.onBytesProcessed(0)
     }
@@ -47,7 +47,7 @@ export class ExcelHandler extends BaseFormatHandler {
       // Determine which sheets to process
       const sheetsToProcess = this.getSheetsToProcess(workbook, options)
 
-      // v4.5.0: Report workbook loaded
+      // Report workbook loaded
       if (progressHooks?.onCurrentItem) {
         progressHooks.onCurrentItem(`Processing ${sheetsToProcess.length} sheets...`)
       }
@@ -59,7 +59,7 @@ export class ExcelHandler extends BaseFormatHandler {
       for (let sheetIndex = 0; sheetIndex < sheetsToProcess.length; sheetIndex++) {
         const sheetName = sheetsToProcess[sheetIndex]
 
-        // v4.5.0: Report current sheet
+        // Report current sheet
         if (progressHooks?.onCurrentItem) {
           progressHooks.onCurrentItem(
             `Reading sheet: ${sheetName} (${sheetIndex + 1}/${sheetsToProcess.length})`
@@ -117,19 +117,19 @@ export class ExcelHandler extends BaseFormatHandler {
           headers
         }
 
-        // v4.5.0: Estimate bytes processed (sheets are sequential)
+        // Estimate bytes processed (sheets are sequential)
         const bytesProcessed = Math.floor(((sheetIndex + 1) / sheetsToProcess.length) * totalBytes)
         if (progressHooks?.onBytesProcessed) {
           progressHooks.onBytesProcessed(bytesProcessed)
         }
 
-        // v4.5.0: Report extraction progress
+        // Report extraction progress
         if (progressHooks?.onDataExtracted) {
           progressHooks.onDataExtracted(allData.length, undefined) // Total unknown until complete
         }
       }
 
-      // v4.5.0: Report data extraction complete
+      // Report data extraction complete
       if (progressHooks?.onCurrentItem) {
         progressHooks.onCurrentItem(`Extracted ${allData.length} rows, inferring types...`)
       }
@@ -152,7 +152,7 @@ export class ExcelHandler extends BaseFormatHandler {
           }
         }
 
-        // v4.5.0: Report progress every 1000 rows (avoid spam)
+        // Report progress every 1000 rows (avoid spam)
         if (progressHooks?.onCurrentItem && index > 0 && index % 1000 === 0) {
           progressHooks.onCurrentItem(`Converting types: ${index}/${allData.length} rows...`)
         }
@@ -160,14 +160,14 @@ export class ExcelHandler extends BaseFormatHandler {
         return converted
       })
 
-      // v4.5.0: Final progress - all bytes processed
+      // Final progress - all bytes processed
       if (progressHooks?.onBytesProcessed) {
         progressHooks.onBytesProcessed(totalBytes)
       }
 
       const processingTime = Date.now() - startTime
 
-      // v4.5.0: Report completion
+      // Report completion
       if (progressHooks?.onCurrentItem) {
         progressHooks.onCurrentItem(
           `Excel complete: ${sheetsToProcess.length} sheets, ${convertedData.length} rows`

src/augmentations/intelligentImport/handlers/imageHandler.ts

@@ -1,5 +1,5 @@
 /**
- * Image Import Handler (v5.8.0 - Pure JavaScript)
+ * Image Import Handler
  *
  * Handles image files with:
  * - EXIF metadata extraction (camera, GPS, timestamps) via exifr
@@ -7,7 +7,7 @@
  * - Support for JPEG, PNG, WebP, GIF, TIFF, BMP, SVG
  *
  * NO NATIVE DEPENDENCIES - Pure JavaScript implementation
- * Replaces Sharp (v5.7.x) with lightweight pure-JS alternatives
+ * Replaces Sharp with lightweight pure-JS alternatives
  */
 
 import { BaseFormatHandler } from './base.js'
@@ -96,7 +96,7 @@ export interface ImageHandlerOptions extends FormatHandlerOptions {
  * Enables developers to import images into the knowledge graph with
  * full metadata extraction.
  *
- * v5.8.0: Pure JavaScript implementation (no native dependencies)
+ * Pure JavaScript implementation (no native dependencies)
  */
 export class ImageHandler extends BaseFormatHandler {
   readonly format = 'image'

src/augmentations/intelligentImport/handlers/pdfHandler.ts

@@ -52,7 +52,7 @@ export class PDFHandler extends BaseFormatHandler {
     const buffer = Buffer.isBuffer(data) ? data : Buffer.from(data, 'binary')
     const totalBytes = buffer.length
 
-    // v4.5.0: Report start
+    // Report start
     if (progressHooks?.onBytesProcessed) {
       progressHooks.onBytesProcessed(0)
     }
@@ -74,7 +74,7 @@ export class PDFHandler extends BaseFormatHandler {
       const metadata = await pdfDoc.getMetadata()
       const numPages = pdfDoc.numPages
 
-      // v4.5.0: Report document loaded
+      // Report document loaded
       if (progressHooks?.onCurrentItem) {
         progressHooks.onCurrentItem(`Processing ${numPages} pages...`)
       }
@@ -85,7 +85,7 @@ export class PDFHandler extends BaseFormatHandler {
       let detectedTables = 0
 
       for (let pageNum = 1; pageNum <= numPages; pageNum++) {
-        // v4.5.0: Report current page
+        // Report current page
         if (progressHooks?.onCurrentItem) {
           progressHooks.onCurrentItem(`Processing page ${pageNum} of ${numPages}`)
         }
@@ -131,19 +131,19 @@ export class PDFHandler extends BaseFormatHandler {
           }
         }
 
-        // v4.5.0: Estimate bytes processed (pages are sequential)
+        // Estimate bytes processed (pages are sequential)
         const bytesProcessed = Math.floor((pageNum / numPages) * totalBytes)
         if (progressHooks?.onBytesProcessed) {
           progressHooks.onBytesProcessed(bytesProcessed)
         }
 
-        // v4.5.0: Report extraction progress
+        // Report extraction progress
         if (progressHooks?.onDataExtracted) {
           progressHooks.onDataExtracted(allData.length, undefined) // Total unknown until complete
         }
       }
 
-      // v4.5.0: Final progress - all bytes processed
+      // Final progress - all bytes processed
       if (progressHooks?.onBytesProcessed) {
         progressHooks.onBytesProcessed(totalBytes)
       }
@@ -153,7 +153,7 @@ export class PDFHandler extends BaseFormatHandler {
 
       const processingTime = Date.now() - startTime
 
-      // v4.5.0: Report completion
+      // Report completion
       if (progressHooks?.onCurrentItem) {
         progressHooks.onCurrentItem(
           `PDF complete: ${numPages} pages, ${allData.length} items extracted`

src/augmentations/intelligentImport/index.ts

@@ -18,14 +18,14 @@ export { ExcelHandler } from './handlers/excelHandler.js'
 export { PDFHandler } from './handlers/pdfHandler.js'
 export { ImageHandler } from './handlers/imageHandler.js'
 
-// Format Handler Registry (v5.2.0)
+// Format Handler Registry
 export {
   FormatHandlerRegistry,
   globalHandlerRegistry
 } from './FormatHandlerRegistry.js'
 export type { HandlerRegistration } from './FormatHandlerRegistry.js'
 
-// Image Handler Types (v5.2.0)
+// Image Handler Types
 export type {
   ImageMetadata,
   EXIFData,

src/augmentations/intelligentImport/types.ts

@@ -88,13 +88,13 @@ export interface FormatHandlerOptions {
   streaming?: boolean
 
   /**
-   * Progress hooks (v4.5.0)
+   * Progress hooks
    * Handlers call these to report progress during processing
    */
   progressHooks?: FormatHandlerProgressHooks
 
   /**
-   * Total file size in bytes (v4.5.0)
+   * Total file size in bytes
    * Used for progress percentage calculation
    */
   totalBytes?: number
@@ -168,7 +168,7 @@ export interface IntelligentImportConfig {
   /** Enable PDF handler */
   enablePDF: boolean
 
-  /** Enable Image handler (v5.2.0) */
+  /** Enable Image handler */
   enableImage: boolean
 
   /** Default options for CSV */
@@ -180,7 +180,7 @@ export interface IntelligentImportConfig {
   /** Default options for PDF */
   pdfDefaults?: Partial<FormatHandlerOptions>
 
-  /** Default options for Image (v5.2.0) */
+  /** Default options for Image */
   imageDefaults?: Partial<FormatHandlerOptions>
 
   /** Maximum file size to process (bytes) */