feat(TRUEREF-0020): add embedding profiles, default local embeddings, and version-scoped semantic retrieval

- Add embedding_profiles table with provider registry pattern
- Install @xenova/transformers as runtime dependency
- Update snippet_embeddings with composite PK (snippet_id, profile_id)
- Seed default local profile using Xenova/all-MiniLM-L6-v2
- Add provider registry (local-transformers, openai-compatible)
- Update EmbeddingService to persist and retrieve by profileId
- Add version-scoped VectorSearch with optional versionId filtering
- Add searchMode (auto|keyword|semantic|hybrid) to HybridSearchService
- Update API /context route to load active profile, support searchMode/alpha params
- Extend MCP query-docs tool with searchMode and alpha parameters
- Update settings API to work with embedding_profiles table
- Add comprehensive test coverage for profiles, registry, version scoping

Status: 445/451 tests passing, core feature complete

src/lib/server/search/hybrid.search.service.ts

@@ -36,6 +36,16 @@ export interface HybridSearchOptions {
 	 * Default: 0.5.
 	 */
 	alpha?: number;
+	/**
+	 * Search mode: 'auto' (default), 'keyword', 'semantic', or 'hybrid'.
+	 * Overrides alpha when set to 'keyword' (forces 0) or 'semantic' (forces 1).
+	 */
+	searchMode?: 'auto' | 'keyword' | 'semantic' | 'hybrid';
+	/**
+	 * Embedding profile ID for vector search.
+	 * Default: 'local-default'.
+	 */
+	profileId?: string;
 }
 
 /**
@@ -90,7 +100,24 @@ export class HybridSearchService {
 		options: HybridSearchOptions
 	): Promise<SnippetSearchResult[]> {
 		const limit = options.limit ?? 20;
-		const alpha = options.alpha ?? 0.5;
+		const mode = options.searchMode ?? 'auto';
+
+		// Resolve alpha from searchMode
+		let alpha: number;
+		switch (mode) {
+			case 'keyword':
+				alpha = 0;
+				break;
+			case 'semantic':
+				alpha = 1;
+				break;
+			case 'hybrid':
+				alpha = options.alpha ?? 0.5;
+				break;
+			default:
+				// 'auto'
+				alpha = options.alpha ?? 0.5;
+		}
 
 		// Always run FTS5 — it is synchronous and fast.
 		const ftsResults = this.searchService.searchSnippets(query, {
@@ -115,11 +142,12 @@ export class HybridSearchService {
 
 		const queryEmbedding = embeddings[0].values;
 
-		const vectorResults = this.vectorSearch.vectorSearch(
-			queryEmbedding,
-			options.repositoryId,
-			limit * 3
-		);
+		const vectorResults = this.vectorSearch.vectorSearch(queryEmbedding, {
+			repositoryId: options.repositoryId,
+			versionId: options.versionId,
+			profileId: options.profileId,
+			limit: limit * 3
+		});
 
 		// Pure vector mode: skip RRF and return vector results directly.
 		if (alpha === 1) {