Merge pull request #74 from colbymchenry/feat/always-enable-embeddings

feat: Always enable embeddings, remove config toggle

README.md

@@ -645,8 +645,7 @@ The `.codegraph/config.json` file controls indexing behavior:
   "frameworks": [],
   "maxFileSize": 1048576,
   "extractDocstrings": true,
-  "trackCallSites": true,
+  "trackCallSites": true
-  "enableEmbeddings": false
 }
 ```
 
@@ -660,7 +659,6 @@ The `.codegraph/config.json` file controls indexing behavior:
 | `maxFileSize` | Skip files larger than this (bytes) | `1048576` (1MB) |
 | `extractDocstrings` | Whether to extract docstrings from code | `true` |
 | `trackCallSites` | Whether to track call site locations | `true` |
-| `enableEmbeddings` | Enable semantic search embeddings | `false` |
 
 ## 🌐 Supported Languages
 

__tests__/vectors.test.ts

@@ -286,9 +286,10 @@ export function processData(input: string): string {
       expect(cg.isEmbeddingsInitialized()).toBe(false);
     });
 
-    it('should return null embedding stats when not initialized', () => {
+    it('should return embedding stats even before initialization', () => {
       const stats = cg.getEmbeddingStats();
-      expect(stats).toBeNull();
+      expect(stats).not.toBeNull();
+      expect(stats!.totalVectors).toBe(0);
     });
 
     it('should throw when calling semanticSearch without initialization', async () => {

src/config.ts

@@ -67,7 +67,6 @@ export function validateConfig(config: unknown): config is CodeGraphConfig {
   if (typeof c.maxFileSize !== 'number') return false;
   if (typeof c.extractDocstrings !== 'boolean') return false;
   if (typeof c.trackCallSites !== 'boolean') return false;
-  if (typeof c.enableEmbeddings !== 'boolean') return false;
 
   // Validate include/exclude are string arrays
   if (!c.include.every((p) => typeof p === 'string')) return false;
@@ -128,7 +127,6 @@ function mergeConfig(
     maxFileSize: overrides.maxFileSize ?? defaults.maxFileSize,
     extractDocstrings: overrides.extractDocstrings ?? defaults.extractDocstrings,
     trackCallSites: overrides.trackCallSites ?? defaults.trackCallSites,
-    enableEmbeddings: overrides.enableEmbeddings ?? defaults.enableEmbeddings,
     customPatterns: overrides.customPatterns ?? defaults.customPatterns,
   };
 }

src/index.ts

@@ -157,12 +157,9 @@ export class CodeGraph {
     this.resolver = createResolver(projectRoot, queries);
     this.graphManager = new GraphQueryManager(queries);
     this.traverser = new GraphTraverser(queries);
-    // Vector manager is created lazily when embeddings are enabled
+    // Vector manager — always created, embeddings generated lazily on first use
-    // Uses global ~/.codegraph/models directory for shared embedding models
+    this.vectorManager = createVectorManager(db.getDb(), queries, {});
-    if (config.enableEmbeddings) {
+    // Context builder (uses vector manager for semantic search)
-      this.vectorManager = createVectorManager(db.getDb(), queries, {});
-    }
-    // Context builder (uses vector manager if available)
     this.contextBuilder = createContextBuilder(
       projectRoot,
       queries,

src/types.ts

@@ -462,9 +462,6 @@ export interface CodeGraphConfig {
   /** Whether to track call sites */
   trackCallSites: boolean;
 
-  /** Whether to compute embeddings for semantic search */
-  enableEmbeddings: boolean;
-
   /** Custom symbol patterns to extract */
   customPatterns?: {
     /** Name for this pattern group */
@@ -675,7 +672,6 @@ export const DEFAULT_CONFIG: CodeGraphConfig = {
   maxFileSize: 1024 * 1024, // 1MB
   extractDocstrings: true,
   trackCallSites: true,
-  enableEmbeddings: false,
 };
 
 // =============================================================================

src/visualizer/server.ts

@@ -236,16 +236,14 @@ ${symbolIndex}`;
 
       // GET /api/embeddings/status
       if (pathname === '/api/embeddings/status') {
-        const config = this.cg.getConfig();
         const embeddingStats = this.cg.getEmbeddingStats();
-        const isEnabled = config.enableEmbeddings === true;
         const isInitialized = this.cg.isEmbeddingsInitialized();
         const totalVectors = embeddingStats?.totalVectors ?? 0;
         const stats = this.cg.getStats();
         // Consider ready if we have vectors for at least half the eligible nodes
         const eligibleNodes = stats.nodeCount - (stats.nodesByKind.file ?? 0) - (stats.nodesByKind.import ?? 0);
-        const isReady = isEnabled && totalVectors > 0 && totalVectors >= eligibleNodes * 0.5;
+        const isReady = totalVectors > 0 && totalVectors >= eligibleNodes * 0.5;
-        json({ isEnabled, isInitialized, isReady, totalVectors, eligibleNodes });
+        json({ isEnabled: true, isInitialized, isReady, totalVectors, eligibleNodes });
         return;
       }
 
@@ -262,14 +260,7 @@ ${symbolIndex}`;
         };
 
         try {
-          // Step 1: Enable embeddings in config
+          // Step 1: Initialize embedding model (downloads on first use)
-          send('status', { phase: 'config', message: 'Enabling embeddings...' });
-          const config = this.cg.getConfig();
-          if (!config.enableEmbeddings) {
-            this.cg.updateConfig({ enableEmbeddings: true });
-          }
-
-          // Step 2: Initialize embedding model (downloads on first use)
           send('status', { phase: 'model', message: 'Loading embedding model (first time may download ~30MB)...' });
           await this.cg.initializeEmbeddings();
           send('status', { phase: 'model', message: 'Embedding model ready' });