@pleaseai/context-please-core 0.2.1 → 0.5.0

package/dist/context.d.ts

@@ -1,7 +1,7 @@
-import { Splitter } from './splitter';
-import { Embedding } from './embedding';
-import { VectorDatabase } from './vectordb';
-import { SemanticSearchResult } from './types';
+import type { Embedding } from './embedding';
+import type { Splitter } from './splitter';
+import type { SemanticSearchResult } from './types';
+import type { VectorDatabase } from './vectordb';
 import { FileSynchronizer } from './sync/synchronizer';
 export interface ContextConfig {
     embedding?: Embedding;
@@ -106,6 +106,31 @@ export declare class Context {
      * @returns Whether index exists
      */
     hasIndex(codebasePath: string): Promise<boolean>;
+    /**
+     * Get collection statistics from vector database
+     *
+     * Retrieves actual counts of indexed files and chunks by querying the vector database.
+     * This is more accurate than snapshot data which may be out of sync.
+     *
+     * @param codebasePath Codebase path to get stats for
+     * @returns Object with indexedFiles (unique files) and totalChunks, or null if:
+     *   - Collection doesn't exist in vector database
+     *   - Collection cannot be loaded (expected error)
+     *   - Query fails with known recoverable error
+     *
+     * @throws Error for unexpected failures (network errors, auth failures, programming bugs)
+     *
+     * @remarks
+     * - Uses a limit of 100k chunks. For larger codebases, stats may be underreported.
+     * - Queries only relativePath field to minimize data transfer
+     * - File count is derived by counting unique relativePath values
+     * - Performance: O(n) where n is min(actualChunks, 100000)
+     * - Warns if limit is reached (may indicate incomplete stats)
+     */
+    getCollectionStats(codebasePath: string): Promise<{
+        indexedFiles: number;
+        totalChunks: number;
+    } | null>;
     /**
      * Clear index
      * @param codebasePath Codebase path to clear index for
@@ -155,16 +180,16 @@ export declare class Context {
      */
     private getCodeFiles;
     /**
- * Process a list of files with streaming chunk processing
- * @param filePaths Array of file paths to process
- * @param codebasePath Base path for the codebase
- * @param onFileProcessed Callback called when each file is processed
- * @returns Object with processed file count and total chunk count
- */
+     * Process a list of files with streaming chunk processing
+     * @param filePaths Array of file paths to process
+     * @param codebasePath Base path for the codebase
+     * @param onFileProcessed Callback called when each file is processed
+     * @returns Object with processed file count and total chunk count
+     */
     private processFileList;
     /**
- * Process accumulated chunk buffer
- */
+     * Process accumulated chunk buffer
+     */
     private processChunkBuffer;
     /**
      * Process a batch of chunks

package/dist/context.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"context.d.ts","sourceRoot":"","sources":["../src/context.ts"],"names":[],"mappings":"AAAA,OAAO,EACH,QAAQ,EAGX,MAAM,YAAY,CAAC;AACpB,OAAO,EACH,SAAS,EAGZ,MAAM,aAAa,CAAC;AACrB,OAAO,EACH,cAAc,EAMjB,MAAM,YAAY,CAAC;AAEpB,OAAO,EAAE,oBAAoB,EAAE,MAAM,SAAS,CAAC;AAK/C,OAAO,EAAE,gBAAgB,EAAE,MAAM,qBAAqB,CAAC;AAiEvD,MAAM,WAAW,aAAa;IAC1B,SAAS,CAAC,EAAE,SAAS,CAAC;IACtB,cAAc,CAAC,EAAE,cAAc,CAAC;IAChC,YAAY,CAAC,EAAE,QAAQ,CAAC;IACxB,mBAAmB,CAAC,EAAE,MAAM,EAAE,CAAC;IAC/B,cAAc,CAAC,EAAE,MAAM,EAAE,CAAC;IAC1B,gBAAgB,CAAC,EAAE,MAAM,EAAE,CAAC;IAC5B,oBAAoB,CAAC,EAAE,MAAM,EAAE,CAAC;CACnC;AAED,qBAAa,OAAO;IAChB,OAAO,CAAC,SAAS,CAAY;IAC7B,OAAO,CAAC,cAAc,CAAiB;IACvC,OAAO,CAAC,YAAY,CAAW;IAC/B,OAAO,CAAC,mBAAmB,CAAW;IACtC,OAAO,CAAC,cAAc,CAAW;IACjC,OAAO,CAAC,aAAa,CAAuC;gBAEhD,MAAM,GAAE,aAAkB;IAkDtC;;OAEG;IACH,YAAY,IAAI,SAAS;IAIzB;;OAEG;IACH,iBAAiB,IAAI,cAAc;IAInC;;OAEG;IACH,eAAe,IAAI,QAAQ;IAI3B;;OAEG;IACH,sBAAsB,IAAI,MAAM,EAAE;IAIlC;;OAEG;IACH,iBAAiB,IAAI,MAAM,EAAE;IAI7B;;OAEG;IACH,gBAAgB,IAAI,GAAG,CAAC,MAAM,EAAE,gBAAgB,CAAC;IAIjD;;OAEG;IACH,eAAe,CAAC,cAAc,EAAE,MAAM,EAAE,YAAY,EAAE,gBAAgB,GAAG,IAAI;IAI7E;;OAEG;IACG,uBAAuB,CAAC,YAAY,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC;IAIlE;;OAEG;IACG,qBAAqB,CAAC,YAAY,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC;IAIhE;;OAEG;IACH,OAAO,CAAC,WAAW;IAQnB;;OAEG;IACI,iBAAiB,CAAC,YAAY,EAAE,MAAM,GAAG,MAAM;IAQtD;;;;;;OAMG;IACG,aAAa,CACf,YAAY,EAAE,MAAM,EACpB,gBAAgB,CAAC,EAAE,CAAC,QAAQ,EAAE;QAAE,KAAK,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,UAAU,EAAE,MAAM,CAAA;KAAE,KAAK,IAAI,EAC5G,YAAY,GAAE,OAAe,GAC9B,OAAO,CAAC;QAAE,YAAY,EAAE,MAAM,CAAC;QAAC,WAAW,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,WAAW,GAAG,eAAe,CAAA;KAAE,CAAC;IA8D1F,eAAe,CACjB,YAAY,EAAE,MAAM,EACpB,gBAAgB,CAAC,EAAE,CAAC,QAAQ,EAAE;QAAE,KAAK,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,UAAU,EAAE,MAAM,CAAA;KAAE,KAAK,IAAI,GAC7G,OAAO,CAAC;QAAE,KAAK,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAC;QAAC,QAAQ,EAAE,MAAM,CAAA;KAAE,CAAC;YAgFlD,gBAAgB;IAkB9B;;;;;;OAMG;IACG,cAAc,CAAC,YAAY,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,IAAI,GAAE,MAAU,EAAE,SAAS,GAAE,MAAY,EAAE,UAAU,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,oBAAoB,EAAE,CAAC;IA6G1J;;;;OAIG;IACG,QAAQ,CAAC,YAAY,EAAE,MAAM,GAAG,OAAO,CAAC,OAAO,CAAC;IAKtD;;;;OAIG;IACG,UAAU,CACZ,YAAY,EAAE,MAAM,EACpB,gBAAgB,CAAC,EAAE,CAAC,QAAQ,EAAE;QAAE,KAAK,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,UAAU,EAAE,MAAM,CAAA;KAAE,KAAK,IAAI,GAC7G,OAAO,CAAC,IAAI,CAAC;IAqBhB;;;OAGG;IACH,oBAAoB,CAAC,cAAc,EAAE,MAAM,EAAE,GAAG,IAAI;IAUpD;;;OAGG;IACH,uBAAuB,CAAC,cAAc,EAAE,MAAM,EAAE,GAAG,IAAI;IAYvD;;OAEG;IACH,6BAA6B,IAAI,IAAI;IAKrC;;;OAGG;IACH,eAAe,CAAC,SAAS,EAAE,SAAS,GAAG,IAAI;IAK3C;;;OAGG;IACH,oBAAoB,CAAC,cAAc,EAAE,cAAc,GAAG,IAAI;IAK1D;;;OAGG;IACH,cAAc,CAAC,QAAQ,EAAE,QAAQ,GAAG,IAAI;IAKxC;;OAEG;YACW,iBAAiB;IAkC/B;;OAEG;YACW,YAAY;IA6B1B;;;;;;GAMD;YACe,eAAe;IAiI7B;;GAED;YACe,kBAAkB;IAgBhC;;OAEG;YACW,iBAAiB;IAsE/B;;OAEG;IACH,OAAO,CAAC,wBAAwB;IA2BhC;;;;;;;OAOG;IACH,OAAO,CAAC,UAAU;IAMlB;;;;OAIG;WACU,yBAAyB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,EAAE,CAAC;IAa3E;;;;OAIG;YACW,kBAAkB;IA4BhC;;;;OAIG;YACW,eAAe;IAwB7B;;;OAGG;YACW,oBAAoB;IAWlC;;;;;OAKG;YACW,cAAc;IAsB5B;;;;;OAKG;IACH,OAAO,CAAC,oBAAoB;IAiB5B;;;;;OAKG;IACH,OAAO,CAAC,cAAc;IAmBtB;;;;;OAKG;IACH,OAAO,CAAC,eAAe;IAUvB;;;;OAIG;IACH,OAAO,CAAC,0BAA0B;IAoBlC;;;;OAIG;IACH,OAAO,CAAC,8BAA8B;IAmBtC;;;OAGG;IACH,mBAAmB,CAAC,gBAAgB,EAAE,MAAM,EAAE,GAAG,IAAI;IAerD;;OAEG;IACH,eAAe,IAAI;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,kBAAkB,EAAE,OAAO,CAAC;QAAC,kBAAkB,CAAC,EAAE,MAAM,EAAE,CAAA;KAAE;IAkB/F;;;OAGG;IACH,mBAAmB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO;IAY9C;;;OAGG;IACH,8BAA8B,CAAC,QAAQ,EAAE,MAAM,GAAG;QAAE,QAAQ,EAAE,KAAK,GAAG,WAAW,CAAC;QAAC,MAAM,EAAE,MAAM,CAAA;KAAE;CAoBtG"}
+{"version":3,"file":"context.d.ts","sourceRoot":"","sources":["../src/context.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,SAAS,EAEV,MAAM,aAAa,CAAA;AACpB,OAAO,KAAK,EAEV,QAAQ,EACT,MAAM,YAAY,CAAA;AACnB,OAAO,KAAK,EAAE,oBAAoB,EAAE,MAAM,SAAS,CAAA;AACnD,OAAO,KAAK,EAGV,cAAc,EAGf,MAAM,YAAY,CAAA;AAUnB,OAAO,EAAE,gBAAgB,EAAE,MAAM,qBAAqB,CAAA;AAqGtD,MAAM,WAAW,aAAa;IAC5B,SAAS,CAAC,EAAE,SAAS,CAAA;IACrB,cAAc,CAAC,EAAE,cAAc,CAAA;IAC/B,YAAY,CAAC,EAAE,QAAQ,CAAA;IACvB,mBAAmB,CAAC,EAAE,MAAM,EAAE,CAAA;IAC9B,cAAc,CAAC,EAAE,MAAM,EAAE,CAAA;IACzB,gBAAgB,CAAC,EAAE,MAAM,EAAE,CAAA;IAC3B,oBAAoB,CAAC,EAAE,MAAM,EAAE,CAAA;CAChC;AAED,qBAAa,OAAO;IAClB,OAAO,CAAC,SAAS,CAAW;IAC5B,OAAO,CAAC,cAAc,CAAgB;IACtC,OAAO,CAAC,YAAY,CAAU;IAC9B,OAAO,CAAC,mBAAmB,CAAU;IACrC,OAAO,CAAC,cAAc,CAAU;IAChC,OAAO,CAAC,aAAa,CAAsC;gBAE/C,MAAM,GAAE,aAAkB;IAkDtC;;OAEG;IACH,YAAY,IAAI,SAAS;IAIzB;;OAEG;IACH,iBAAiB,IAAI,cAAc;IAInC;;OAEG;IACH,eAAe,IAAI,QAAQ;IAI3B;;OAEG;IACH,sBAAsB,IAAI,MAAM,EAAE;IAIlC;;OAEG;IACH,iBAAiB,IAAI,MAAM,EAAE;IAI7B;;OAEG;IACH,gBAAgB,IAAI,GAAG,CAAC,MAAM,EAAE,gBAAgB,CAAC;IAIjD;;OAEG;IACH,eAAe,CAAC,cAAc,EAAE,MAAM,EAAE,YAAY,EAAE,gBAAgB,GAAG,IAAI;IAI7E;;OAEG;IACG,uBAAuB,CAAC,YAAY,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC;IAIlE;;OAEG;IACG,qBAAqB,CAAC,YAAY,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC;IAIhE;;OAEG;IACH,OAAO,CAAC,WAAW;IAQnB;;OAEG;IACI,iBAAiB,CAAC,YAAY,EAAE,MAAM,GAAG,MAAM;IAQtD;;;;;;OAMG;IACG,aAAa,CACjB,YAAY,EAAE,MAAM,EACpB,gBAAgB,CAAC,EAAE,CAAC,QAAQ,EAAE;QAAE,KAAK,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,UAAU,EAAE,MAAM,CAAA;KAAE,KAAK,IAAI,EAC5G,YAAY,GAAE,OAAe,GAC5B,OAAO,CAAC;QAAE,YAAY,EAAE,MAAM,CAAC;QAAC,WAAW,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,WAAW,GAAG,eAAe,CAAA;KAAE,CAAC;IA8D1F,eAAe,CACnB,YAAY,EAAE,MAAM,EACpB,gBAAgB,CAAC,EAAE,CAAC,QAAQ,EAAE;QAAE,KAAK,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,UAAU,EAAE,MAAM,CAAA;KAAE,KAAK,IAAI,GAC3G,OAAO,CAAC;QAAE,KAAK,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAC;QAAC,QAAQ,EAAE,MAAM,CAAA;KAAE,CAAC;YAiFlD,gBAAgB;IAkB9B;;;;;;OAMG;IACG,cAAc,CAAC,YAAY,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,IAAI,GAAE,MAAU,EAAE,SAAS,GAAE,MAAY,EAAE,UAAU,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,oBAAoB,EAAE,CAAC;IA2H1J;;;;OAIG;IACG,QAAQ,CAAC,YAAY,EAAE,MAAM,GAAG,OAAO,CAAC,OAAO,CAAC;IAKtD;;;;;;;;;;;;;;;;;;;;OAoBG;IACG,kBAAkB,CAAC,YAAY,EAAE,MAAM,GAAG,OAAO,CAAC;QAAE,YAAY,EAAE,MAAM,CAAC;QAAC,WAAW,EAAE,MAAM,CAAA;KAAE,GAAG,IAAI,CAAC;IA2E7G;;;;OAIG;IACG,UAAU,CACd,YAAY,EAAE,MAAM,EACpB,gBAAgB,CAAC,EAAE,CAAC,QAAQ,EAAE;QAAE,KAAK,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,UAAU,EAAE,MAAM,CAAA;KAAE,KAAK,IAAI,GAC3G,OAAO,CAAC,IAAI,CAAC;IA0BhB;;;OAGG;IACH,oBAAoB,CAAC,cAAc,EAAE,MAAM,EAAE,GAAG,IAAI;IAUpD;;;OAGG;IACH,uBAAuB,CAAC,cAAc,EAAE,MAAM,EAAE,GAAG,IAAI;IAavD;;OAEG;IACH,6BAA6B,IAAI,IAAI;IAKrC;;;OAGG;IACH,eAAe,CAAC,SAAS,EAAE,SAAS,GAAG,IAAI;IAK3C;;;OAGG;IACH,oBAAoB,CAAC,cAAc,EAAE,cAAc,GAAG,IAAI;IAK1D;;;OAGG;IACH,cAAc,CAAC,QAAQ,EAAE,QAAQ,GAAG,IAAI;IAKxC;;OAEG;YACW,iBAAiB;IAmC/B;;OAEG;YACW,YAAY;IA8B1B;;;;;;OAMG;YACW,eAAe;IA4I7B;;OAEG;YACW,kBAAkB;IAiBhC;;OAEG;YACW,iBAAiB;IAuE/B;;OAEG;IACH,OAAO,CAAC,wBAAwB;IA2BhC;;;;;;;OAOG;IACH,OAAO,CAAC,UAAU;IAMlB;;;;OAIG;WACU,yBAAyB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,EAAE,CAAC;IAc3E;;;;OAIG;YACW,kBAAkB;IA8BhC;;;;OAIG;YACW,eAAe;IAyB7B;;;OAGG;YACW,oBAAoB;IAYlC;;;;;OAKG;YACW,cAAc;IAwB5B;;;;;OAKG;IACH,OAAO,CAAC,oBAAoB;IAiB5B;;;;;OAKG;IACH,OAAO,CAAC,cAAc;IAoBtB;;;;;OAKG;IACH,OAAO,CAAC,eAAe;IAUvB;;;;OAIG;IACH,OAAO,CAAC,0BAA0B;IAqBlC;;;;OAIG;IACH,OAAO,CAAC,8BAA8B;IAoBtC;;;OAGG;IACH,mBAAmB,CAAC,gBAAgB,EAAE,MAAM,EAAE,GAAG,IAAI;IAgBrD;;OAEG;IACH,eAAe,IAAI;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,kBAAkB,EAAE,OAAO,CAAC;QAAC,kBAAkB,CAAC,EAAE,MAAM,EAAE,CAAA;KAAE;IAmB/F;;;OAGG;IACH,mBAAmB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO;IAY9C;;;OAGG;IACH,8BAA8B,CAAC,QAAQ,EAAE,MAAM,GAAG;QAAE,QAAQ,EAAE,KAAK,GAAG,WAAW,CAAC;QAAC,MAAM,EAAE,MAAM,CAAA;KAAE;CAqBpG"}

package/dist/context.js

@@ -34,20 +34,40 @@ var __importStar = (this && this.__importStar) || (function () {
 })();
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.Context = void 0;
-const splitter_1 = require("./splitter");
+const crypto = __importStar(require("node:crypto"));
+const fs = __importStar(require("node:fs"));
+const path = __importStar(require("node:path"));
 const embedding_1 = require("./embedding");
-const qdrant_vectordb_1 = require("./vectordb/qdrant-vectordb");
-const env_manager_1 = require("./utils/env-manager");
-const fs = __importStar(require("fs"));
-const path = __importStar(require("path"));
-const crypto = __importStar(require("crypto"));
+const splitter_1 = require("./splitter");
 const synchronizer_1 = require("./sync/synchronizer");
+const env_manager_1 = require("./utils/env-manager");
+const qdrant_vectordb_1 = require("./vectordb/qdrant-vectordb");
 const DEFAULT_SUPPORTED_EXTENSIONS = [
     // Programming languages
-    '.ts', '.tsx', '.js', '.jsx', '.py', '.java', '.cpp', '.c', '.h', '.hpp',
-    '.cs', '.go', '.rs', '.php', '.rb', '.swift', '.kt', '.scala', '.m', '.mm',
+    '.ts',
+    '.tsx',
+    '.js',
+    '.jsx',
+    '.py',
+    '.java',
+    '.cpp',
+    '.c',
+    '.h',
+    '.hpp',
+    '.cs',
+    '.go',
+    '.rs',
+    '.php',
+    '.rb',
+    '.swift',
+    '.kt',
+    '.scala',
+    '.m',
+    '.mm',
     // Text and markup files
-    '.md', '.markdown', '.ipynb',
+    '.md',
+    '.markdown',
+    '.ipynb',
     // '.txt',  '.json', '.yaml', '.yml', '.xml', '.html', '.htm',
     // '.css', '.scss', '.less', '.sql', '.sh', '.bash', '.env'
 ];
@@ -93,9 +113,23 @@ const DEFAULT_IGNORE_PATTERNS = [
     '*.polyfills.js',
     '*.runtime.js',
     '*.map', // source map files
-    'node_modules', '.git', '.svn', '.hg', 'build', 'dist', 'out',
-    'target', '.vscode', '.idea', '__pycache__', '.pytest_cache',
-    'coverage', '.nyc_output', 'logs', 'tmp', 'temp'
+    'node_modules',
+    '.git',
+    '.svn',
+    '.hg',
+    'build',
+    'dist',
+    'out',
+    'target',
+    '.vscode',
+    '.idea',
+    '__pycache__',
+    '.pytest_cache',
+    'coverage',
+    '.nyc_output',
+    'logs',
+    'tmp',
+    'temp',
 ];
 class Context {
     constructor(config = {}) {
@@ -104,7 +138,7 @@ class Context {
         this.embedding = config.embedding || new embedding_1.OpenAIEmbedding({
             apiKey: env_manager_1.envManager.get('OPENAI_API_KEY') || 'your-openai-api-key',
             model: 'text-embedding-3-small',
-            ...(env_manager_1.envManager.get('OPENAI_BASE_URL') && { baseURL: env_manager_1.envManager.get('OPENAI_BASE_URL') })
+            ...(env_manager_1.envManager.get('OPENAI_BASE_URL') && { baseURL: env_manager_1.envManager.get('OPENAI_BASE_URL') }),
         });
         if (!config.vectorDatabase) {
             throw new Error('VectorDatabase is required. Please provide a vectorDatabase instance in the config.');
@@ -118,18 +152,18 @@ class Context {
             ...DEFAULT_SUPPORTED_EXTENSIONS,
             ...(config.supportedExtensions || []),
             ...(config.customExtensions || []),
-            ...envCustomExtensions
+            ...envCustomExtensions,
         ];
         // Remove duplicates
         this.supportedExtensions = [...new Set(allSupportedExtensions)];
-        // Load custom ignore patterns from environment variables  
+        // Load custom ignore patterns from environment variables
         const envCustomIgnorePatterns = this.getCustomIgnorePatternsFromEnv();
         // Start with default ignore patterns
         const allIgnorePatterns = [
             ...DEFAULT_IGNORE_PATTERNS,
             ...(config.ignorePatterns || []),
             ...(config.customIgnorePatterns || []),
-            ...envCustomIgnorePatterns
+            ...envCustomIgnorePatterns,
         ];
         // Remove duplicates
         this.ignorePatterns = [...new Set(allIgnorePatterns)];
@@ -253,7 +287,7 @@ class Context {
                 phase: `Processing files (${fileIndex}/${totalFiles})...`,
                 current: fileIndex,
                 total: totalFiles,
-                percentage: Math.round(progressPercentage)
+                percentage: Math.round(progressPercentage),
             });
         });
         console.log(`[Context] ✅ Codebase indexing completed! Processed ${result.processedFiles} files in total, generated ${result.totalChunks} code chunks`);
@@ -261,12 +295,12 @@ class Context {
             phase: 'Indexing complete!',
             current: result.processedFiles,
             total: codeFiles.length,
-            percentage: 100
+            percentage: 100,
         });
         return {
             indexedFiles: result.processedFiles,
             totalChunks: result.totalChunks,
-            status: result.status
+            status: result.status,
         };
     }
     async reindexByChange(codebasePath, progressCallback) {
@@ -321,7 +355,7 @@ class Context {
             updateProgress(`Deleted old chunks for ${file}`);
         }
         // Handle added and modified files
-        const filesToIndex = [...added, ...modified].map(f => path.join(codebasePath, f));
+        const filesToIndex = [...added, ...modified].map((f) => path.join(codebasePath, f));
         if (filesToIndex.length > 0) {
             await this.processFileList(filesToIndex, codebasePath, (filePath, fileIndex, totalFiles) => {
                 updateProgress(`Indexed ${filePath} (${fileIndex}/${totalFiles})`);
@@ -336,7 +370,7 @@ class Context {
         const escapedPath = relativePath.replace(/\\/g, '\\\\');
         const results = await this.vectorDatabase.query(collectionName, `relativePath == "${escapedPath}"`, ['id']);
         if (results.length > 0) {
-            const ids = results.map(r => r.id).filter(id => id);
+            const ids = results.map((r) => r.id).filter((id) => id);
             if (ids.length > 0) {
                 await this.vectorDatabase.delete(collectionName, ids);
                 console.log(`[Context] Deleted ${ids.length} chunks for file ${relativePath}`);
@@ -371,6 +405,17 @@ class Context {
             catch (error) {
                 console.log(`[Context] ⚠️  Collection '${collectionName}' exists but may be empty or not properly indexed:`, error);
             }
+            // Load BM25 model if using Qdrant and model is not yet trained
+            if (this.vectorDatabase instanceof qdrant_vectordb_1.QdrantVectorDatabase) {
+                const bm25Generator = this.vectorDatabase.getBM25Generator();
+                if (!bm25Generator.isTrained()) {
+                    console.log('[Context] 📂 BM25 model not loaded, attempting to load from disk...');
+                    const loaded = await this.vectorDatabase.loadBM25Model(collectionName);
+                    if (!loaded) {
+                        console.warn('[Context] ⚠️  Failed to load BM25 model. Hybrid search quality may be degraded.');
+                    }
+                }
+            }
             // 1. Generate query vector
             console.log(`[Context] 🔍 Generating embeddings for query: "${query}"`);
             const queryEmbedding = await this.embedding.embed(query);
@@ -380,16 +425,16 @@ class Context {
             const searchRequests = [
                 {
                     data: queryEmbedding.vector,
-                    anns_field: "vector",
-                    param: { "nprobe": 10 },
-                    limit: topK
+                    anns_field: 'vector',
+                    param: { nprobe: 10 },
+                    limit: topK,
                 },
                 {
                     data: query,
-                    anns_field: "sparse_vector",
-                    param: { "drop_ratio_search": 0.2 },
-                    limit: topK
-                }
+                    anns_field: 'sparse_vector',
+                    param: { drop_ratio_search: 0.2 },
+                    limit: topK,
+                },
             ];
             console.log(`[Context] 🔍 Search request 1 (dense): anns_field="${searchRequests[0].anns_field}", vector_dim=${queryEmbedding.vector.length}, limit=${searchRequests[0].limit}`);
             console.log(`[Context] 🔍 Search request 2 (sparse): anns_field="${searchRequests[1].anns_field}", query_text="${query}", limit=${searchRequests[1].limit}`);
@@ -398,20 +443,20 @@ class Context {
             const searchResults = await this.vectorDatabase.hybridSearch(collectionName, searchRequests, {
                 rerank: {
                     strategy: 'rrf',
-                    params: { k: 100 }
+                    params: { k: 100 },
                 },
                 limit: topK,
-                filterExpr
+                filterExpr,
             });
             console.log(`[Context] 🔍 Raw search results count: ${searchResults.length}`);
             // 4. Convert to semantic search result format
-            const results = searchResults.map(result => ({
+            const results = searchResults.map((result) => ({
                 content: result.document.content,
                 relativePath: result.document.relativePath,
                 startLine: result.document.startLine,
                 endLine: result.document.endLine,
                 language: result.document.metadata.language || 'unknown',
-                score: result.score
+                score: result.score,
             }));
             console.log(`[Context] ✅ Found ${results.length} relevant hybrid results`);
             if (results.length > 0) {
@@ -426,13 +471,13 @@ class Context {
             // 2. Search in vector database
             const searchResults = await this.vectorDatabase.search(collectionName, queryEmbedding.vector, { topK, threshold, filterExpr });
             // 3. Convert to semantic search result format
-            const results = searchResults.map(result => ({
+            const results = searchResults.map((result) => ({
                 content: result.document.content,
                 relativePath: result.document.relativePath,
                 startLine: result.document.startLine,
                 endLine: result.document.endLine,
                 language: result.document.metadata.language || 'unknown',
-                score: result.score
+                score: result.score,
             }));
             console.log(`[Context] ✅ Found ${results.length} relevant results`);
             return results;
@@ -447,6 +492,80 @@ class Context {
         const collectionName = this.getCollectionName(codebasePath);
         return await this.vectorDatabase.hasCollection(collectionName);
     }
+    /**
+     * Get collection statistics from vector database
+     *
+     * Retrieves actual counts of indexed files and chunks by querying the vector database.
+     * This is more accurate than snapshot data which may be out of sync.
+     *
+     * @param codebasePath Codebase path to get stats for
+     * @returns Object with indexedFiles (unique files) and totalChunks, or null if:
+     *   - Collection doesn't exist in vector database
+     *   - Collection cannot be loaded (expected error)
+     *   - Query fails with known recoverable error
+     *
+     * @throws Error for unexpected failures (network errors, auth failures, programming bugs)
+     *
+     * @remarks
+     * - Uses a limit of 100k chunks. For larger codebases, stats may be underreported.
+     * - Queries only relativePath field to minimize data transfer
+     * - File count is derived by counting unique relativePath values
+     * - Performance: O(n) where n is min(actualChunks, 100000)
+     * - Warns if limit is reached (may indicate incomplete stats)
+     */
+    async getCollectionStats(codebasePath) {
+        const collectionName = this.getCollectionName(codebasePath);
+        // Check if collection exists
+        const hasCollection = await this.vectorDatabase.hasCollection(collectionName);
+        if (!hasCollection) {
+            return null;
+        }
+        try {
+            // Query documents up to limit (may not retrieve all chunks if codebase exceeds this limit)
+            // Note: This is a best-effort approach. For codebases with >100k chunks, consider pagination.
+            const allDocs = await this.vectorDatabase.query(collectionName, '', // Empty filter expression (no filtering, query all documents)
+            ['relativePath'], // Only need file path for counting
+            100000);
+            const totalChunks = allDocs.length;
+            // Warn if we hit the query limit - actual collection may be larger
+            if (totalChunks === 100000) {
+                console.warn(`[Context] ⚠️  Retrieved maximum limit of 100k chunks for ${codebasePath}. ` +
+                    `Actual total may be higher. Stats may be incomplete.`);
+            }
+            // Filter out documents with missing relativePath before counting
+            const validPaths = allDocs
+                .map((doc) => doc.relativePath)
+                .filter((path) => path != null && path !== '');
+            const uniqueFiles = new Set(validPaths).size;
+            return {
+                indexedFiles: uniqueFiles,
+                totalChunks,
+            };
+        }
+        catch (error) {
+            const dbType = this.vectorDatabase.constructor.name;
+            // Log with full context for debugging
+            console.error(`[Context] ❌ Failed to retrieve collection stats\n` +
+                `  Codebase: ${codebasePath}\n` +
+                `  Collection: ${collectionName}\n` +
+                `  Database: ${dbType}\n` +
+                `  Error:`, error);
+            // Only catch specific expected errors - let unexpected errors propagate
+            if (error instanceof Error) {
+                const errorMsg = error.message;
+                // Known recoverable errors that should return null
+                if (errorMsg.includes('collection not loaded') ||
+                    errorMsg.includes('collection not exist') ||
+                    errorMsg.includes('Failed to query')) {
+                    console.warn(`[Context] ⚠️  Collection exists but query failed (recoverable): ${errorMsg}`);
+                    return null;
+                }
+            }
+            // All other errors indicate serious problems and should propagate
+            // (network failures, auth errors, programming bugs, etc.)
+            throw error;
+        }
+    }
     /**
      * Clear index
      * @param codebasePath Codebase path to clear index for
@@ -461,6 +580,10 @@ class Context {
         if (collectionExists) {
             await this.vectorDatabase.dropCollection(collectionName);
         }
+        // Delete BM25 model if using Qdrant
+        if (this.vectorDatabase instanceof qdrant_vectordb_1.QdrantVectorDatabase) {
+            await this.vectorDatabase.deleteBM25Model(collectionName);
+        }
         // Delete snapshot file
         await synchronizer_1.FileSynchronizer.deleteSnapshot(codebasePath);
         progressCallback?.({ phase: 'Index cleared', current: 100, total: 100, percentage: 100 });
@@ -475,7 +598,7 @@ class Context {
         const mergedPatterns = [...DEFAULT_IGNORE_PATTERNS, ...ignorePatterns];
         const uniquePatterns = [];
         const patternSet = new Set(mergedPatterns);
-        patternSet.forEach(pattern => uniquePatterns.push(pattern));
+        patternSet.forEach((pattern) => uniquePatterns.push(pattern));
         this.ignorePatterns = uniquePatterns;
         console.log(`[Context] 🚫 Updated ignore patterns: ${ignorePatterns.length} new + ${DEFAULT_IGNORE_PATTERNS.length} default = ${this.ignorePatterns.length} total patterns`);
     }
@@ -490,7 +613,7 @@ class Context {
         const mergedPatterns = [...this.ignorePatterns, ...customPatterns];
         const uniquePatterns = [];
         const patternSet = new Set(mergedPatterns);
-        patternSet.forEach(pattern => uniquePatterns.push(pattern));
+        patternSet.forEach((pattern) => uniquePatterns.push(pattern));
         this.ignorePatterns = uniquePatterns;
         console.log(`[Context] 🚫 Added ${customPatterns.length} custom ignore patterns. Total: ${this.ignorePatterns.length} patterns`);
     }
@@ -584,15 +707,15 @@ class Context {
         return files;
     }
     /**
- * Process a list of files with streaming chunk processing
- * @param filePaths Array of file paths to process
- * @param codebasePath Base path for the codebase
- * @param onFileProcessed Callback called when each file is processed
- * @returns Object with processed file count and total chunk count
- */
+     * Process a list of files with streaming chunk processing
+     * @param filePaths Array of file paths to process
+     * @param codebasePath Base path for the codebase
+     * @param onFileProcessed Callback called when each file is processed
+     * @returns Object with processed file count and total chunk count
+     */
     async processFileList(filePaths, codebasePath, onFileProcessed) {
         const isHybrid = this.getIsHybrid();
-        const EMBEDDING_BATCH_SIZE = Math.max(1, parseInt(env_manager_1.envManager.get('EMBEDDING_BATCH_SIZE') || '100', 10));
+        const EMBEDDING_BATCH_SIZE = Math.max(1, Number.parseInt(env_manager_1.envManager.get('EMBEDDING_BATCH_SIZE') || '100', 10));
         const CHUNK_LIMIT = 450000;
         console.log(`[Context] 🔧 Using EMBEDDING_BATCH_SIZE: ${EMBEDDING_BATCH_SIZE}`);
         // For Qdrant hybrid search, we need to train BM25 on the full corpus first
@@ -662,12 +785,15 @@ class Context {
         if (needsBM25Training && allChunks.length > 0) {
             console.log(`[Context] 🎓 Training BM25 on ${allChunks.length} chunks for Qdrant hybrid search...`);
             // Extract corpus texts for BM25 training
-            const corpus = allChunks.map(item => item.chunk.content);
+            const corpus = allChunks.map((item) => item.chunk.content);
             // Get BM25 generator and train it
             if (this.vectorDatabase instanceof qdrant_vectordb_1.QdrantVectorDatabase) {
+                const collectionName = this.getCollectionName(codebasePath);
                 const bm25Generator = this.vectorDatabase.getBM25Generator();
                 bm25Generator.learn(corpus);
                 console.log(`[Context] ✅ BM25 training completed on ${corpus.length} documents`);
+                // Save BM25 model to disk for future use
+                await this.vectorDatabase.saveBM25Model(collectionName);
             }
             // Now process all chunks in batches
             console.log(`[Context] 📝 Processing ${allChunks.length} chunks in batches of ${EMBEDDING_BATCH_SIZE}...`);
@@ -702,17 +828,17 @@ class Context {
         return {
             processedFiles,
             totalChunks,
-            status: limitReached ? 'limit_reached' : 'completed'
+            status: limitReached ? 'limit_reached' : 'completed',
         };
     }
     /**
- * Process accumulated chunk buffer
- */
+     * Process accumulated chunk buffer
+     */
     async processChunkBuffer(chunkBuffer) {
         if (chunkBuffer.length === 0)
             return;
         // Extract chunks and ensure they all have the same codebasePath
-        const chunks = chunkBuffer.map(item => item.chunk);
+        const chunks = chunkBuffer.map((item) => item.chunk);
         const codebasePath = chunkBuffer[0].codebasePath;
         // Estimate tokens (rough estimation: 1 token ≈ 4 characters)
         const estimatedTokens = chunks.reduce((sum, chunk) => sum + Math.ceil(chunk.content.length / 4), 0);
@@ -727,7 +853,7 @@ class Context {
     async processChunkBatch(chunks, codebasePath) {
         const isHybrid = this.getIsHybrid();
         // Generate embedding vectors
-        const chunkContents = chunks.map(chunk => chunk.content);
+        const chunkContents = chunks.map((chunk) => chunk.content);
         const embeddings = await this.embedding.embedBatch(chunkContents);
         if (isHybrid === true) {
             // Create hybrid vector documents
@@ -750,8 +876,8 @@ class Context {
                         ...restMetadata,
                         codebasePath,
                         language: chunk.metadata.language || 'unknown',
-                        chunkIndex: index
-                    }
+                        chunkIndex: index,
+                    },
                 };
             });
             // Store to vector database
@@ -778,8 +904,8 @@ class Context {
                         ...restMetadata,
                         codebasePath,
                         language: chunk.metadata.language || 'unknown',
-                        chunkIndex: index
-                    }
+                        chunkIndex: index,
+                    },
                 };
             });
             // Store to vector database
@@ -811,7 +937,7 @@ class Context {
             '.scala': 'scala',
             '.m': 'objective-c',
             '.mm': 'objective-c',
-            '.ipynb': 'jupyter'
+            '.ipynb': 'jupyter',
         };
         return languageMap[ext] || 'text';
     }
@@ -838,8 +964,8 @@ class Context {
             const content = await fs.promises.readFile(filePath, 'utf-8');
             return content
                 .split('\n')
-                .map(line => line.trim())
-                .filter(line => line && !line.startsWith('#')); // Filter out empty lines and comments
+                .map((line) => line.trim())
+                .filter((line) => line && !line.startsWith('#')); // Filter out empty lines and comments
         }
         catch (error) {
             console.warn(`[Context] ⚠️  Could not read ignore file ${filePath}: ${error}`);
@@ -853,7 +979,7 @@ class Context {
      */
     async loadIgnorePatterns(codebasePath) {
         try {
-            let fileBasedPatterns = [];
+            const fileBasedPatterns = [];
             // Load all .xxxignore files in codebase directory
             const ignoreFiles = await this.findIgnoreFiles(codebasePath);
             for (const ignoreFile of ignoreFiles) {
@@ -887,14 +1013,14 @@ class Context {
             const entries = await fs.promises.readdir(codebasePath, { withFileTypes: true });
             const ignoreFiles = [];
             for (const entry of entries) {
-                if (entry.isFile() &&
-                    entry.name.startsWith('.') &&
-                    entry.name.endsWith('ignore')) {
+                if (entry.isFile()
+                    && entry.name.startsWith('.')
+                    && entry.name.endsWith('ignore')) {
                     ignoreFiles.push(path.join(codebasePath, entry.name));
                 }
             }
             if (ignoreFiles.length > 0) {
-                console.log(`📄 Found ignore files: ${ignoreFiles.map(f => path.basename(f)).join(', ')}`);
+                console.log(`📄 Found ignore files: ${ignoreFiles.map((f) => path.basename(f)).join(', ')}`);
             }
             return ignoreFiles;
         }
@@ -909,7 +1035,7 @@ class Context {
      */
     async loadGlobalIgnoreFile() {
         try {
-            const homeDir = require('os').homedir();
+            const homeDir = require('node:os').homedir();
             const globalIgnorePath = path.join(homeDir, '.context', '.contextignore');
             return await this.loadIgnoreFile(globalIgnorePath, 'global .contextignore');
         }
@@ -975,7 +1101,7 @@ class Context {
         if (pattern.endsWith('/')) {
             const dirPattern = pattern.slice(0, -1);
             const pathParts = filePath.split('/');
-            return pathParts.some(part => this.simpleGlobMatch(part, dirPattern));
+            return pathParts.some((part) => this.simpleGlobMatch(part, dirPattern));
         }
         // Handle file patterns
         if (pattern.includes('/')) {
@@ -1015,9 +1141,9 @@ class Context {
         try {
             const extensions = envExtensions
                 .split(',')
-                .map(ext => ext.trim())
-                .filter(ext => ext.length > 0)
-                .map(ext => ext.startsWith('.') ? ext : `.${ext}`); // Ensure extensions start with dot
+                .map((ext) => ext.trim())
+                .filter((ext) => ext.length > 0)
+                .map((ext) => ext.startsWith('.') ? ext : `.${ext}`); // Ensure extensions start with dot
             return extensions;
         }
         catch (error) {
@@ -1038,8 +1164,8 @@ class Context {
         try {
             const patterns = envIgnorePatterns
                 .split(',')
-                .map(pattern => pattern.trim())
-                .filter(pattern => pattern.length > 0);
+                .map((pattern) => pattern.trim())
+                .filter((pattern) => pattern.length > 0);
             return patterns;
         }
         catch (error) {
@@ -1055,7 +1181,7 @@ class Context {
         if (customExtensions.length === 0)
             return;
         // Ensure extensions start with dot
-        const normalizedExtensions = customExtensions.map(ext => ext.startsWith('.') ? ext : `.${ext}`);
+        const normalizedExtensions = customExtensions.map((ext) => ext.startsWith('.') ? ext : `.${ext}`);
         // Merge current extensions with new custom extensions, avoiding duplicates
         const mergedExtensions = [...this.supportedExtensions, ...normalizedExtensions];
         const uniqueExtensions = [...new Set(mergedExtensions)];
@@ -1072,13 +1198,13 @@ class Context {
             return {
                 type: 'ast',
                 hasBuiltinFallback: true,
-                supportedLanguages: AstCodeSplitter.getSupportedLanguages()
+                supportedLanguages: AstCodeSplitter.getSupportedLanguages(),
             };
         }
         else {
             return {
                 type: 'langchain',
-                hasBuiltinFallback: false
+                hasBuiltinFallback: false,
             };
         }
     }
@@ -1108,13 +1234,13 @@ class Context {
                 strategy: isSupported ? 'ast' : 'langchain',
                 reason: isSupported
                     ? 'Language supported by AST parser'
-                    : 'Language not supported by AST, will fallback to LangChain'
+                    : 'Language not supported by AST, will fallback to LangChain',
             };
         }
         else {
             return {
                 strategy: 'langchain',
-                reason: 'Using LangChain splitter directly'
+                reason: 'Using LangChain splitter directly',
             };
         }
     }