bluera-knowledge 0.20.0 → 0.21.0

package/dist/chunk-H25AEF47.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/services/watch.service.ts","../src/utils/ignore-patterns.ts","../src/utils/model-validation.ts"],"sourcesContent":["import { watch, type FSWatcher } from 'chokidar';\nimport { normalizeGlobPatterns } from '../utils/ignore-patterns.js';\nimport { validateStoreModelCompatibility } from '../utils/model-validation.js';\nimport type { IndexService } from './index.service.js';\nimport type { EmbeddingEngine } from '../db/embeddings.js';\nimport type { LanceStore } from '../db/lance.js';\nimport type { FileStore, RepoStore } from '../types/store.js';\n\nexport interface WatchServiceOptions {\n  ignorePatterns?: readonly string[];\n  /** Current embedding model ID for compatibility validation */\n  currentModelId?: string;\n}\n\nexport class WatchService {\n  private readonly watchers: Map<string, FSWatcher> = new Map();\n  private readonly pendingTimeouts: Map<string, NodeJS.Timeout> = new Map();\n  private readonly indexService: IndexService;\n  private readonly lanceStore: LanceStore;\n  private readonly embeddings: EmbeddingEngine;\n  private readonly ignorePatterns: readonly string[];\n  private readonly currentModelId: string | undefined;\n\n  constructor(\n    indexService: IndexService,\n    lanceStore: LanceStore,\n    embeddings: EmbeddingEngine,\n    options: WatchServiceOptions = {}\n  ) {\n    this.indexService = indexService;\n    this.lanceStore = lanceStore;\n    this.embeddings = embeddings;\n    // Use shared utility to normalize patterns to glob format with defaults\n    this.ignorePatterns = normalizeGlobPatterns(options.ignorePatterns ?? []);\n    this.currentModelId = options.currentModelId;\n  }\n\n  async watch(\n    store: FileStore | RepoStore,\n    debounceMs: number,\n    onReindex: (() => void) | undefined,\n    onError: (error: Error) => void\n  ): Promise<void> {\n    if (this.watchers.has(store.id)) {\n      return Promise.resolve(); // Already watching\n    }\n\n    let timeout: NodeJS.Timeout | null = null;\n\n    const watcher = watch(store.path, {\n      ignored: [...this.ignorePatterns],\n      persistent: true,\n      ignoreInitial: true,\n    });\n\n    const reindexHandler = (): void => {\n      if (timeout) clearTimeout(timeout);\n      timeout = setTimeout(() => {\n        this.pendingTimeouts.delete(store.id);\n        void (async (): Promise<void> => {\n          try {\n            // Validate model compatibility before incremental indexing\n            // If currentModelId is set, check that store was indexed with same model\n            if (this.currentModelId !== undefined) {\n              validateStoreModelCompatibility(store, { currentModelId: this.currentModelId });\n            }\n\n            this.lanceStore.setDimensions(await this.embeddings.ensureDimensions());\n            await this.lanceStore.initialize(store.id);\n\n            // Try incremental indexing first if available, fall back to full indexing\n            let useFullReindex = true;\n            if (typeof this.indexService.indexStoreIncremental === 'function') {\n              const incrementalResult = await this.indexService.indexStoreIncremental(store);\n              if (incrementalResult.success) {\n                useFullReindex = false;\n              }\n            }\n\n            if (useFullReindex) {\n              const fullResult = await this.indexService.indexStore(store);\n              if (!fullResult.success) {\n                onError(fullResult.error);\n                return;\n              }\n            }\n\n            onReindex?.();\n          } catch (e) {\n            const error = e instanceof Error ? e : new Error(String(e));\n            onError(error);\n          }\n        })();\n      }, debounceMs);\n      this.pendingTimeouts.set(store.id, timeout);\n    };\n\n    watcher.on('all', reindexHandler);\n\n    watcher.on('error', (e) => {\n      const error = e instanceof Error ? e : new Error(String(e));\n      onError(error);\n    });\n\n    this.watchers.set(store.id, watcher);\n    return Promise.resolve();\n  }\n\n  async unwatch(storeId: string): Promise<void> {\n    // Clear any pending timeout to prevent timer leak\n    const pendingTimeout = this.pendingTimeouts.get(storeId);\n    if (pendingTimeout) {\n      clearTimeout(pendingTimeout);\n      this.pendingTimeouts.delete(storeId);\n    }\n\n    const watcher = this.watchers.get(storeId);\n    if (watcher) {\n      await watcher.close();\n      this.watchers.delete(storeId);\n    }\n  }\n\n  async unwatchAll(): Promise<void> {\n    for (const [id] of this.watchers) {\n      await this.unwatch(id);\n    }\n  }\n}\n","/**\n * Unified ignore pattern handling for consistent behavior across IndexService and WatchService.\n *\n * Pattern normalization ensures the same config patterns work identically whether used\n * for fs.readdir scanning (IndexService) or chokidar watching (WatchService).\n */\n\n/** Default directories to always ignore */\nexport const DEFAULT_IGNORE_DIRS = ['node_modules', '.git', '.bluera', 'dist', 'build'] as const;\n\n/**\n * Normalize patterns to standard glob format for chokidar and micromatch.\n *\n * Transformations:\n * - 'node_modules' → '** /node_modules/**' (directory anywhere in tree)\n * - 'node_modules/**' → '** /node_modules/**' (explicit directory pattern)\n * - '*.min.js' → '**\\/*.min.js' (extension pattern anywhere)\n * - '** /foo/**' → unchanged (already in glob format)\n *\n * @param patterns - User-provided patterns from config\n * @param includeDefaults - Whether to include DEFAULT_IGNORE_DIRS (default: true)\n */\nexport function normalizeGlobPatterns(\n  patterns: readonly string[],\n  includeDefaults = true\n): string[] {\n  const result: string[] = [];\n\n  // Add defaults first\n  if (includeDefaults) {\n    for (const dir of DEFAULT_IGNORE_DIRS) {\n      result.push(`**/${dir}/**`);\n    }\n  }\n\n  // Process user patterns\n  for (const pattern of patterns) {\n    if (pattern.startsWith('**/') && pattern.endsWith('/**')) {\n      // Already in glob format\n      result.push(pattern);\n    } else if (pattern.endsWith('/**')) {\n      // Directory pattern: 'foo/**' → '**/foo/**'\n      result.push(`**/${pattern}`);\n    } else if (pattern.startsWith('*.')) {\n      // Extension pattern: '*.min.js' → '**/*.min.js'\n      result.push(`**/${pattern}`);\n    } else if (!pattern.includes('/') && !pattern.includes('*')) {\n      // Simple directory name: 'node_modules' → '**/node_modules/**'\n      result.push(`**/${pattern}/**`);\n    } else {\n      // Keep as-is (might be a specific path pattern)\n      result.push(pattern);\n    }\n  }\n\n  return result;\n}\n\n/**\n * Parsed patterns optimized for fs.readdir scanning.\n */\nexport interface ScanningPatterns {\n  /** Directory names to skip during traversal (e.g., 'node_modules', '.git') */\n  dirs: Set<string>;\n  /** Predicate functions to test if a filename should be ignored (e.g., for '*.min.js') */\n  fileMatchers: Array<(filename: string) => boolean>;\n}\n\n/**\n * Parse patterns into structures optimized for fs.readdir filtering.\n *\n * This is more efficient than glob matching for directory traversal since\n * it allows early termination when encountering ignored directories.\n *\n * @param patterns - User-provided patterns from config\n * @param includeDefaults - Whether to include DEFAULT_IGNORE_DIRS (default: true)\n */\nexport function parseIgnorePatternsForScanning(\n  patterns: readonly string[],\n  includeDefaults = true\n): ScanningPatterns {\n  const dirs = new Set<string>();\n  const fileMatchers: Array<(filename: string) => boolean> = [];\n\n  // Add defaults first\n  if (includeDefaults) {\n    for (const dir of DEFAULT_IGNORE_DIRS) {\n      dirs.add(dir);\n    }\n  }\n\n  // Process user patterns\n  for (const pattern of patterns) {\n    if (pattern.startsWith('**/') && pattern.endsWith('/**')) {\n      // Glob format: '**/node_modules/**' → extract 'node_modules'\n      const inner = pattern.slice(3, -3);\n      if (!inner.includes('/') && !inner.includes('*')) {\n        dirs.add(inner);\n      }\n    } else if (pattern.endsWith('/**')) {\n      // Directory pattern: 'node_modules/**' → 'node_modules'\n      dirs.add(pattern.slice(0, -3));\n    } else if (pattern.startsWith('*.')) {\n      // Extension pattern: '*.min.js' → matches files ending with '.min.js'\n      const ext = pattern.slice(1); // Remove leading '*'\n      fileMatchers.push((filename) => filename.endsWith(ext));\n    } else if (!pattern.includes('/') && !pattern.includes('*')) {\n      // Simple directory name: 'node_modules' → treat as directory\n      dirs.add(pattern);\n    }\n    // Note: Complex patterns like 'src/**/*.test.ts' are not supported for scanning\n    // They would require full glob matching which defeats the purpose of fast scanning\n  }\n\n  return { dirs, fileMatchers };\n}\n","/**\n * Model Compatibility Validation\n *\n * Guards against searching or incrementally indexing stores with mismatched embedding models.\n * Ensures stores are only queried with the same model they were indexed with.\n */\n\nimport type { Store } from '../types/store.js';\n\nexport interface ModelValidationContext {\n  currentModelId: string;\n}\n\n/**\n * Validates that a store's embedding model matches the current configuration.\n *\n * @throws Error if store was indexed with a different model or has no model tracking\n */\nexport function validateStoreModelCompatibility(store: Store, ctx: ModelValidationContext): void {\n  // Stores without modelId (schemaVersion < 2) must be reindexed\n  if (!store.modelId) {\n    throw new Error(\n      `Store \"${store.name}\" has no model tracking (schema v1). ` +\n        `Reindex required: /bluera-knowledge:index ${store.name}`\n    );\n  }\n\n  if (store.modelId !== ctx.currentModelId) {\n    throw new Error(\n      `Model mismatch: Store \"${store.name}\" was indexed with \"${store.modelId}\", ` +\n        `but current config uses \"${ctx.currentModelId}\". ` +\n        `Reindex required: /bluera-knowledge:index ${store.name}`\n    );\n  }\n}\n\n/**\n * Check if a store's model matches the current configuration without throwing.\n *\n * @returns Object with compatibility status and details\n */\nexport function checkStoreModelCompatibility(\n  store: Store,\n  ctx: ModelValidationContext\n): {\n  compatible: boolean;\n  modelId: string | undefined;\n  reason?: string;\n} {\n  if (!store.modelId) {\n    return {\n      compatible: false,\n      modelId: undefined,\n      reason: 'Store has no model tracking (schema v1)',\n    };\n  }\n\n  if (store.modelId !== ctx.currentModelId) {\n    return {\n      compatible: false,\n      modelId: store.modelId,\n      reason: `Indexed with different model: ${store.modelId}`,\n    };\n  }\n\n  return {\n    compatible: true,\n    modelId: store.modelId,\n  };\n}\n"],"mappings":";AAAA,SAAS,aAA6B;;;ACQ/B,IAAM,sBAAsB,CAAC,gBAAgB,QAAQ,WAAW,QAAQ,OAAO;AAc/E,SAAS,sBACd,UACA,kBAAkB,MACR;AACV,QAAM,SAAmB,CAAC;AAG1B,MAAI,iBAAiB;AACnB,eAAW,OAAO,qBAAqB;AACrC,aAAO,KAAK,MAAM,GAAG,KAAK;AAAA,IAC5B;AAAA,EACF;AAGA,aAAW,WAAW,UAAU;AAC9B,QAAI,QAAQ,WAAW,KAAK,KAAK,QAAQ,SAAS,KAAK,GAAG;AAExD,aAAO,KAAK,OAAO;AAAA,IACrB,WAAW,QAAQ,SAAS,KAAK,GAAG;AAElC,aAAO,KAAK,MAAM,OAAO,EAAE;AAAA,IAC7B,WAAW,QAAQ,WAAW,IAAI,GAAG;AAEnC,aAAO,KAAK,MAAM,OAAO,EAAE;AAAA,IAC7B,WAAW,CAAC,QAAQ,SAAS,GAAG,KAAK,CAAC,QAAQ,SAAS,GAAG,GAAG;AAE3D,aAAO,KAAK,MAAM,OAAO,KAAK;AAAA,IAChC,OAAO;AAEL,aAAO,KAAK,OAAO;AAAA,IACrB;AAAA,EACF;AAEA,SAAO;AACT;AAqBO,SAAS,+BACd,UACA,kBAAkB,MACA;AAClB,QAAM,OAAO,oBAAI,IAAY;AAC7B,QAAM,eAAqD,CAAC;AAG5D,MAAI,iBAAiB;AACnB,eAAW,OAAO,qBAAqB;AACrC,WAAK,IAAI,GAAG;AAAA,IACd;AAAA,EACF;AAGA,aAAW,WAAW,UAAU;AAC9B,QAAI,QAAQ,WAAW,KAAK,KAAK,QAAQ,SAAS,KAAK,GAAG;AAExD,YAAM,QAAQ,QAAQ,MAAM,GAAG,EAAE;AACjC,UAAI,CAAC,MAAM,SAAS,GAAG,KAAK,CAAC,MAAM,SAAS,GAAG,GAAG;AAChD,aAAK,IAAI,KAAK;AAAA,MAChB;AAAA,IACF,WAAW,QAAQ,SAAS,KAAK,GAAG;AAElC,WAAK,IAAI,QAAQ,MAAM,GAAG,EAAE,CAAC;AAAA,IAC/B,WAAW,QAAQ,WAAW,IAAI,GAAG;AAEnC,YAAM,MAAM,QAAQ,MAAM,CAAC;AAC3B,mBAAa,KAAK,CAAC,aAAa,SAAS,SAAS,GAAG,CAAC;AAAA,IACxD,WAAW,CAAC,QAAQ,SAAS,GAAG,KAAK,CAAC,QAAQ,SAAS,GAAG,GAAG;AAE3D,WAAK,IAAI,OAAO;AAAA,IAClB;AAAA,EAGF;AAEA,SAAO,EAAE,MAAM,aAAa;AAC9B;;;ACjGO,SAAS,gCAAgC,OAAc,KAAmC;AAE/F,MAAI,CAAC,MAAM,SAAS;AAClB,UAAM,IAAI;AAAA,MACR,UAAU,MAAM,IAAI,kFAC2B,MAAM,IAAI;AAAA,IAC3D;AAAA,EACF;AAEA,MAAI,MAAM,YAAY,IAAI,gBAAgB;AACxC,UAAM,IAAI;AAAA,MACR,0BAA0B,MAAM,IAAI,uBAAuB,MAAM,OAAO,+BAC1C,IAAI,cAAc,gDACD,MAAM,IAAI;AAAA,IAC3D;AAAA,EACF;AACF;AAOO,SAAS,6BACd,OACA,KAKA;AACA,MAAI,CAAC,MAAM,SAAS;AAClB,WAAO;AAAA,MACL,YAAY;AAAA,MACZ,SAAS;AAAA,MACT,QAAQ;AAAA,IACV;AAAA,EACF;AAEA,MAAI,MAAM,YAAY,IAAI,gBAAgB;AACxC,WAAO;AAAA,MACL,YAAY;AAAA,MACZ,SAAS,MAAM;AAAA,MACf,QAAQ,iCAAiC,MAAM,OAAO;AAAA,IACxD;AAAA,EACF;AAEA,SAAO;AAAA,IACL,YAAY;AAAA,IACZ,SAAS,MAAM;AAAA,EACjB;AACF;;;AFvDO,IAAM,eAAN,MAAmB;AAAA,EACP,WAAmC,oBAAI,IAAI;AAAA,EAC3C,kBAA+C,oBAAI,IAAI;AAAA,EACvD;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EAEjB,YACE,cACA,YACA,YACA,UAA+B,CAAC,GAChC;AACA,SAAK,eAAe;AACpB,SAAK,aAAa;AAClB,SAAK,aAAa;AAElB,SAAK,iBAAiB,sBAAsB,QAAQ,kBAAkB,CAAC,CAAC;AACxE,SAAK,iBAAiB,QAAQ;AAAA,EAChC;AAAA,EAEA,MAAM,MACJ,OACA,YACA,WACA,SACe;AACf,QAAI,KAAK,SAAS,IAAI,MAAM,EAAE,GAAG;AAC/B,aAAO,QAAQ,QAAQ;AAAA,IACzB;AAEA,QAAI,UAAiC;AAErC,UAAM,UAAU,MAAM,MAAM,MAAM;AAAA,MAChC,SAAS,CAAC,GAAG,KAAK,cAAc;AAAA,MAChC,YAAY;AAAA,MACZ,eAAe;AAAA,IACjB,CAAC;AAED,UAAM,iBAAiB,MAAY;AACjC,UAAI,QAAS,cAAa,OAAO;AACjC,gBAAU,WAAW,MAAM;AACzB,aAAK,gBAAgB,OAAO,MAAM,EAAE;AACpC,cAAM,YAA2B;AAC/B,cAAI;AAGF,gBAAI,KAAK,mBAAmB,QAAW;AACrC,8CAAgC,OAAO,EAAE,gBAAgB,KAAK,eAAe,CAAC;AAAA,YAChF;AAEA,iBAAK,WAAW,cAAc,MAAM,KAAK,WAAW,iBAAiB,CAAC;AACtE,kBAAM,KAAK,WAAW,WAAW,MAAM,EAAE;AAGzC,gBAAI,iBAAiB;AACrB,gBAAI,OAAO,KAAK,aAAa,0BAA0B,YAAY;AACjE,oBAAM,oBAAoB,MAAM,KAAK,aAAa,sBAAsB,KAAK;AAC7E,kBAAI,kBAAkB,SAAS;AAC7B,iCAAiB;AAAA,cACnB;AAAA,YACF;AAEA,gBAAI,gBAAgB;AAClB,oBAAM,aAAa,MAAM,KAAK,aAAa,WAAW,KAAK;AAC3D,kBAAI,CAAC,WAAW,SAAS;AACvB,wBAAQ,WAAW,KAAK;AACxB;AAAA,cACF;AAAA,YACF;AAEA,wBAAY;AAAA,UACd,SAAS,GAAG;AACV,kBAAM,QAAQ,aAAa,QAAQ,IAAI,IAAI,MAAM,OAAO,CAAC,CAAC;AAC1D,oBAAQ,KAAK;AAAA,UACf;AAAA,QACF,GAAG;AAAA,MACL,GAAG,UAAU;AACb,WAAK,gBAAgB,IAAI,MAAM,IAAI,OAAO;AAAA,IAC5C;AAEA,YAAQ,GAAG,OAAO,cAAc;AAEhC,YAAQ,GAAG,SAAS,CAAC,MAAM;AACzB,YAAM,QAAQ,aAAa,QAAQ,IAAI,IAAI,MAAM,OAAO,CAAC,CAAC;AAC1D,cAAQ,KAAK;AAAA,IACf,CAAC;AAED,SAAK,SAAS,IAAI,MAAM,IAAI,OAAO;AACnC,WAAO,QAAQ,QAAQ;AAAA,EACzB;AAAA,EAEA,MAAM,QAAQ,SAAgC;AAE5C,UAAM,iBAAiB,KAAK,gBAAgB,IAAI,OAAO;AACvD,QAAI,gBAAgB;AAClB,mBAAa,cAAc;AAC3B,WAAK,gBAAgB,OAAO,OAAO;AAAA,IACrC;AAEA,UAAM,UAAU,KAAK,SAAS,IAAI,OAAO;AACzC,QAAI,SAAS;AACX,YAAM,QAAQ,MAAM;AACpB,WAAK,SAAS,OAAO,OAAO;AAAA,IAC9B;AAAA,EACF;AAAA,EAEA,MAAM,aAA4B;AAChC,eAAW,CAAC,EAAE,KAAK,KAAK,UAAU;AAChC,YAAM,KAAK,QAAQ,EAAE;AAAA,IACvB;AAAA,EACF;AACF;","names":[]}

package/dist/{chunk-26MBEEKM.js → chunk-VNHZ534Q.js}

@@ -2,7 +2,7 @@ import {
   createLogger,
   summarizePayload,
   truncateForLog
-} from "./chunk-PZE2MO7H.js";
+} from "./chunk-ZR23KJPJ.js";
 
 // src/crawl/intelligent-crawler.ts
 import { EventEmitter } from "events";
@@ -916,4 +916,4 @@ export {
   getCrawlStrategy,
   IntelligentCrawler
 };
-//# sourceMappingURL=chunk-26MBEEKM.js.map
+//# sourceMappingURL=chunk-VNHZ534Q.js.map

package/dist/{chunk-PZE2MO7H.js → chunk-ZR23KJPJ.js}

@@ -4,7 +4,7 @@ import {
 } from "./chunk-CLIMKLTW.js";
 import {
   parseIgnorePatternsForScanning
-} from "./chunk-HXBIIMYL.js";
+} from "./chunk-H25AEF47.js";
 import {
   __require
 } from "./chunk-DGUM43GV.js";
@@ -2063,12 +2063,12 @@ var DEFAULT_CONFIG = {
   version: 1,
   dataDir: ".bluera/bluera-knowledge/data",
   embedding: {
-    model: "Xenova/all-MiniLM-L6-v2",
+    model: "Xenova/bge-small-en-v1.5",
     batchSize: 32,
     dtype: "fp32",
     pooling: "mean",
     normalize: true,
-    queryPrefix: "",
+    queryPrefix: "Represent this sentence for searching relevant passages: ",
     docPrefix: "",
     maxInFlightBatches: 1
   },
@@ -3755,15 +3755,13 @@ function detectContentType(results) {
 }
 var SearchService = class {
   lanceStore;
-  embeddingEngine;
   codeUnitService;
   codeGraphService;
   graphCache;
   searchConfig;
   unsubscribeCacheInvalidation;
-  constructor(lanceStore, embeddingEngine, codeGraphService, searchConfig) {
+  constructor(lanceStore, codeGraphService, searchConfig) {
     this.lanceStore = lanceStore;
-    this.embeddingEngine = embeddingEngine;
     this.codeUnitService = new CodeUnitService();
     this.codeGraphService = codeGraphService;
     this.graphCache = /* @__PURE__ */ new Map();
@@ -3978,17 +3976,17 @@ var SearchService = class {
   /**
    * Fetch raw vector search results without normalization.
    * Returns results with raw cosine similarity scores [0-1].
+   * Uses LanceDB's embedding function for query embedding,
+   * ensuring consistent query/document embedding through a single code path.
    */
   async vectorSearchRaw(query, stores, limit) {
-    const queryVector = await this.embeddingEngine.embedQuery(query);
     const results = [];
     for (const storeId of stores) {
-      const hits = await this.lanceStore.search(storeId, queryVector, limit);
+      const hits = await this.lanceStore.searchText(storeId, query, limit);
       results.push(
         ...hits.map((r) => ({
           id: r.id,
           score: r.score,
-          // Raw cosine similarity (1 - distance)
           content: r.content,
           metadata: r.metadata
         }))
@@ -4822,6 +4820,9 @@ function extractRepoName(url) {
   return name;
 }
 
+// src/types/store.ts
+var CURRENT_SCHEMA_VERSION = 2;
+
 // src/services/store.service.ts
 async function fileExists4(path4) {
   try {
@@ -4836,12 +4837,21 @@ var StoreService = class {
   definitionService;
   gitignoreService;
   projectRoot;
+  embeddingModelId;
   registry = { stores: [] };
   constructor(dataDir, options) {
     this.dataDir = dataDir;
-    this.definitionService = options?.definitionService ?? void 0;
-    this.gitignoreService = options?.gitignoreService ?? void 0;
-    this.projectRoot = options?.projectRoot ?? void 0;
+    this.definitionService = options.definitionService ?? void 0;
+    this.gitignoreService = options.gitignoreService ?? void 0;
+    this.projectRoot = options.projectRoot ?? void 0;
+    this.embeddingModelId = options.embeddingModelId;
+  }
+  /**
+   * Get the current embedding model ID used for new stores.
+   * Used by model compatibility validation.
+   */
+  getCurrentModelId() {
+    return this.embeddingModelId;
   }
   async initialize() {
     await mkdir5(this.dataDir, { recursive: true });
@@ -4980,7 +4990,9 @@ var StoreService = class {
           tags: input.tags,
           status: "ready",
           createdAt: now,
-          updatedAt: now
+          updatedAt: now,
+          schemaVersion: CURRENT_SCHEMA_VERSION,
+          modelId: this.embeddingModelId
         };
         break;
       }
@@ -5025,7 +5037,9 @@ var StoreService = class {
           tags: input.tags,
           status: "ready",
           createdAt: now,
-          updatedAt: now
+          updatedAt: now,
+          schemaVersion: CURRENT_SCHEMA_VERSION,
+          modelId: this.embeddingModelId
         };
         break;
       }
@@ -5046,7 +5060,9 @@ var StoreService = class {
           tags: input.tags,
           status: "ready",
           createdAt: now,
-          updatedAt: now
+          updatedAt: now,
+          schemaVersion: CURRENT_SCHEMA_VERSION,
+          modelId: this.embeddingModelId
         };
         break;
       default: {
@@ -5425,12 +5441,12 @@ import { join as join11 } from "path";
 import { pipeline, env } from "@huggingface/transformers";
 env.cacheDir = join11(homedir2(), ".cache", "huggingface-transformers");
 var DEFAULT_EMBEDDING_CONFIG = {
-  model: "Xenova/all-MiniLM-L6-v2",
+  model: "Xenova/bge-small-en-v1.5",
   batchSize: 32,
   dtype: "fp32",
   pooling: "mean",
   normalize: true,
-  queryPrefix: "",
+  queryPrefix: "Represent this sentence for searching relevant passages: ",
   docPrefix: "",
   maxInFlightBatches: 1
 };
@@ -5654,6 +5670,88 @@ var EmbeddingEngine = class {
 
 // src/db/lance.ts
 import * as lancedb from "@lancedb/lancedb";
+import { LanceSchema } from "@lancedb/lancedb/embedding";
+import { Utf8 } from "apache-arrow";
+
+// src/db/lance-embedding-function.ts
+import { TextEmbeddingFunction, getRegistry } from "@lancedb/lancedb/embedding";
+import { Float32 } from "apache-arrow";
+var HuggingFaceEmbeddingFunction = class extends TextEmbeddingFunction {
+  engine;
+  embeddingConfig;
+  _ndims = null;
+  constructor(optionsRaw) {
+    super();
+    const options = this.resolveVariables(optionsRaw ?? {});
+    this.embeddingConfig = {
+      model: options.model ?? "Xenova/bge-small-en-v1.5",
+      batchSize: options.batchSize ?? 32,
+      dtype: options.dtype ?? "fp32",
+      pooling: options.pooling ?? "mean",
+      normalize: options.normalize ?? true,
+      queryPrefix: options.queryPrefix ?? "",
+      docPrefix: options.docPrefix ?? "",
+      maxInFlightBatches: 1
+      // Single-threaded for LanceDB integration
+    };
+    this.engine = new EmbeddingEngine(this.embeddingConfig);
+  }
+  /**
+   * Initialize the embedding model. Called by LanceDB before embeddings are computed.
+   */
+  async init() {
+    this._ndims = await this.engine.ensureDimensions();
+  }
+  /**
+   * Return embedding dimensions. Must call init() first.
+   */
+  ndims() {
+    if (this._ndims === null) {
+      throw new Error("HuggingFaceEmbeddingFunction not initialized. Call init() first.");
+    }
+    return this._ndims;
+  }
+  /**
+   * Return embedding data type (always Float32 for our models).
+   */
+  embeddingDataType() {
+    return new Float32();
+  }
+  /**
+   * Generate embeddings for a batch of texts (documents).
+   * Called during table.add() operations.
+   */
+  async generateEmbeddings(texts) {
+    return this.engine.embedBatch(texts);
+  }
+  /**
+   * Compute embedding for a single query.
+   * Called during table.search(query) operations.
+   */
+  async computeQueryEmbeddings(data) {
+    const embedding = await this.engine.embedQuery(data);
+    return Array.from(embedding);
+  }
+  /**
+   * Get the model ID for provenance tracking.
+   */
+  getModelId() {
+    return this.embeddingConfig.model;
+  }
+  /**
+   * Get the full embedding config.
+   */
+  getConfig() {
+    return this.embeddingConfig;
+  }
+  /**
+   * Dispose the underlying engine to free resources.
+   */
+  async dispose() {
+    await this.engine.dispose();
+  }
+};
+getRegistry().register("HuggingFaceEmbeddingFunction")(HuggingFaceEmbeddingFunction);
 
 // src/types/document.ts
 import { z as z5 } from "zod";
@@ -5671,15 +5769,51 @@ var DocumentMetadataSchema = z5.object({
 }).loose();
 
 // src/db/lance.ts
+function isSearchHit(value) {
+  if (typeof value !== "object" || value === null) return false;
+  return "id" in value && "content" in value && "metadata" in value && "_distance" in value && typeof value.id === "string" && typeof value.content === "string" && typeof value.metadata === "string" && typeof value._distance === "number";
+}
+function parseDocumentMetadata(jsonStr) {
+  const parsed = DocumentMetadataSchema.parse(JSON.parse(jsonStr));
+  return {
+    ...parsed,
+    storeId: createStoreId(parsed.storeId)
+  };
+}
 var LanceStore = class {
   connection = null;
   tables = /* @__PURE__ */ new Map();
   dataDir;
   // eslint-disable-next-line @typescript-eslint/prefer-readonly -- set via setDimensions()
   _dimensions = null;
+  embeddingFunction = null;
   constructor(dataDir) {
     this.dataDir = dataDir;
   }
+  /**
+   * Set the embedding function for auto-embedding queries.
+   * Must be called before initialize() for new tables.
+   * The embedding function is initialized and its dimensions are used for schema creation.
+   */
+  async setEmbeddingFunction(config) {
+    this.embeddingFunction = new HuggingFaceEmbeddingFunction({
+      model: config.model,
+      batchSize: config.batchSize,
+      dtype: config.dtype,
+      pooling: config.pooling,
+      normalize: config.normalize,
+      queryPrefix: config.queryPrefix,
+      docPrefix: config.docPrefix
+    });
+    await this.embeddingFunction.init();
+    this._dimensions = this.embeddingFunction.ndims();
+  }
+  /**
+   * Check if embedding function is available for auto-embedding queries.
+   */
+  hasEmbeddingFunction() {
+    return this.embeddingFunction !== null;
+  }
   /**
    * Set the embedding dimensions. Must be called before initialize().
    * This allows dimensions to be derived from the embedding model at runtime.
@@ -5690,22 +5824,35 @@ var LanceStore = class {
   }
   async initialize(storeId) {
     if (this._dimensions === null) {
-      throw new Error("Dimensions not set. Call setDimensions() before initialize().");
+      throw new Error(
+        "Dimensions not set. Call setDimensions() or setEmbeddingFunction() before initialize()."
+      );
     }
     this.connection ??= await lancedb.connect(this.dataDir);
     const tableName = this.getTableName(storeId);
     const tableNames = await this.connection.tableNames();
     if (!tableNames.includes(tableName)) {
-      const table = await this.connection.createTable(tableName, [
-        {
-          id: "__init__",
-          content: "",
-          vector: new Array(this._dimensions).fill(0),
-          metadata: "{}"
-        }
-      ]);
-      await table.delete('id = "__init__"');
-      this.tables.set(tableName, table);
+      if (this.embeddingFunction !== null) {
+        const schema = LanceSchema({
+          id: new Utf8(),
+          content: this.embeddingFunction.sourceField(),
+          vector: this.embeddingFunction.vectorField(),
+          metadata: new Utf8()
+        });
+        const table = await this.connection.createEmptyTable(tableName, schema);
+        this.tables.set(tableName, table);
+      } else {
+        const table = await this.connection.createTable(tableName, [
+          {
+            id: "__init__",
+            content: "",
+            vector: new Array(this._dimensions).fill(0),
+            metadata: "{}"
+          }
+        ]);
+        await table.delete('id = "__init__"');
+        this.tables.set(tableName, table);
+      }
     } else {
       const table = await this.connection.openTable(tableName);
       this.tables.set(tableName, table);
@@ -5749,6 +5896,29 @@ var LanceStore = class {
       };
     });
   }
+  /**
+   * Search using a text query with automatic embedding.
+   * Requires setEmbeddingFunction() to have been called.
+   * Uses the embedding function to compute query embeddings consistently with document embeddings.
+   */
+  async searchText(storeId, query, limit) {
+    if (this.embeddingFunction === null) {
+      throw new Error(
+        "Embedding function not set. Call setEmbeddingFunction() before searchText()."
+      );
+    }
+    const queryEmbedding = await this.embeddingFunction.computeQueryEmbeddings(query);
+    const table = await this.getTable(storeId);
+    const searchQuery = table.vectorSearch(queryEmbedding).limit(limit).distanceType("cosine");
+    const rawResults = await searchQuery.toArray();
+    const results = rawResults.filter(isSearchHit);
+    return results.map((r) => ({
+      id: createDocumentId(r.id),
+      content: r.content,
+      score: 1 - r._distance,
+      metadata: parseDocumentMetadata(r.metadata)
+    }));
+  }
   async createFtsIndex(storeId) {
     const table = await this.getTable(storeId);
     await table.createIndex("content", {
@@ -5865,12 +6035,7 @@ var LazyServiceContainer = class {
   get search() {
     if (this._search === null) {
       logger4.debug("Lazy-initializing SearchService");
-      this._search = new SearchService(
-        this.lance,
-        this.embeddings,
-        this.codeGraph,
-        this.appConfig.search
-      );
+      this._search = new SearchService(this.lance, this.codeGraph, this.appConfig.search);
     }
     return this._search;
   }
@@ -5929,7 +6094,8 @@ async function createLazyServices(configPath, dataDir, projectRoot) {
   const storeOptions = {
     definitionService,
     gitignoreService,
-    projectRoot: resolvedProjectRoot
+    projectRoot: resolvedProjectRoot,
+    embeddingModelId: appConfig.embedding.model
   };
   const store = new StoreService(resolvedDataDir, storeOptions);
   await store.initialize();
@@ -5950,19 +6116,21 @@ async function createServices(configPath, dataDir, projectRoot) {
   const lance = new LanceStore(resolvedDataDir);
   const embeddings = new EmbeddingEngine(appConfig.embedding);
   await embeddings.initialize();
+  await lance.setEmbeddingFunction(appConfig.embedding);
   const resolvedProjectRoot = config.resolveProjectRoot();
   const definitionService = new StoreDefinitionService(resolvedProjectRoot);
   const gitignoreService = new GitignoreService(resolvedProjectRoot);
   const storeOptions = {
     definitionService,
     gitignoreService,
-    projectRoot: resolvedProjectRoot
+    projectRoot: resolvedProjectRoot,
+    embeddingModelId: appConfig.embedding.model
   };
   const store = new StoreService(resolvedDataDir, storeOptions);
   await store.initialize();
   const codeGraph = new CodeGraphService(resolvedDataDir, pythonBridge);
   const manifest = new ManifestService(resolvedDataDir);
-  const search = new SearchService(lance, embeddings, codeGraph, appConfig.search);
+  const search = new SearchService(lance, codeGraph, appConfig.search);
   const index = new IndexService(lance, embeddings, {
     codeGraphService: codeGraph,
     manifestService: manifest,
@@ -6054,4 +6222,4 @@ export {
   createServices,
   destroyServices
 };
-//# sourceMappingURL=chunk-PZE2MO7H.js.map
+//# sourceMappingURL=chunk-ZR23KJPJ.js.map