refactor: remove K-medoids algorithm completely

package.json

@@ -1,6 +1,6 @@
 {
   "name": "joplin-plugin-note-categorization",
-  "version": "0.1.7",
+  "version": "0.1.8",
   "scripts": {
     "dist": "webpack --env joplin-plugin-config=buildMain && webpack --env joplin-plugin-config=buildExtraScripts && npm run copyAssets && webpack --env joplin-plugin-config=createArchive",
     "prepare": "npm run dist",

src/manifest.json

@@ -2,7 +2,7 @@
 	"manifest_version": 1,
 	"id": "com.harsh16gupta.notecategorization",
 	"app_min_version": "3.5",
-	"version": "0.1.7",
+	"version": "0.1.8",
 	"name": "Note Categorization Plugin",
 	"description": "AI-based note categorisation: clusters notes semantically, suggests tags and notebook structures, and detects stale notes.",
 	"author": "Harsh Gupta",

src/pipeline/clustering/autoK.ts

@@ -1,7 +1,5 @@
 import { DistanceFn, silhouetteScore } from './metrics';
 import { kmeans } from './kmeans';
-// NOTE: kmedoids is not used in the default pipeline (too slow), but kept here for manual benchmarking
-import { kmedoids } from './kmedoids';
 import { log } from '../../utils/logger';
 
 /** Absolute minimum K to try (silhouette needs at least 2 clusters). */
@@ -107,23 +105,18 @@ export function computeKRange(n: number): [number, number] {
  * produces more useful note categories.
  *
  * @param vectors    Input data points (N x D), already UMAP-reduced if applicable
- * @param algorithm  Which algorithm to use: 'kmeans' or 'kmedoids' (note: kmedoids is not used in the default pipeline)
+ * @param algorithm  Which algorithm to use: 'kmeans'
  * @param distFn     Distance function (cosine or euclidean)
  * @param seed       Seed for reproducible initialization
  * @returns          The optimal K, its assignments, and its silhouette score
  */
-export function findOptimalK(
-	vectors: number[][],
-	algorithm: 'kmeans' | 'kmedoids',
-	distFn: DistanceFn,
-	seed: number,
-): AutoKResult {
+export function findOptimalK(vectors: number[][], algorithm: 'kmeans', distFn: DistanceFn, seed: number): AutoKResult {
 	const n = vectors.length;
 	const [minK, maxK] = computeKRange(n);
 
 	log(`Auto-K: sweeping K=${minK}..${maxK} for ${algorithm} (N=${n})`);
 
-	const clusterFn = algorithm === 'kmeans' ? kmeans : kmedoids;
+	const clusterFn = kmeans;
 
 	// Collect all valid (k, score, assignments) candidates
 	const candidates: { k: number; score: number; assignments: number[] }[] = [];

src/pipeline/clustering/benchmark.ts

@@ -1,8 +1,6 @@
 import { CategorizationConfig, BenchmarkResult, ClusteringStrategy } from '../../types/cluster';
 import { DistanceFn, getDistanceFn, silhouetteScore, euclideanDistance } from './metrics';
 import { kmeans } from './kmeans';
-// NOTE: kmedoids is not used in the default pipeline (too slow), but kept here for manual benchmarking
-import { kmedoids } from './kmedoids';
 import { hdbscan } from './hdbscan';
 import { findOptimalK } from './autoK';
 import { UmapProjector } from '../UmapProjector';
@@ -26,8 +24,6 @@ export function runStrategy(
 	switch (strategy.algorithm) {
 		case 'kmeans':
 			return kmeans(vectors, strategy.K ?? DEFAULT_K, distFn, seed);
-		case 'kmedoids': // NOTE: not used in default pipeline strategies (too slow)
-			return kmedoids(vectors, strategy.K ?? DEFAULT_K, distFn, seed);
 		case 'hdbscan':
 			return hdbscan(vectors, strategy.minClusterSize ?? DEFAULT_MIN_CLUSTER_SIZE, strategy.minSamples, distFn);
 		default:
@@ -150,7 +146,7 @@ export function benchmark(
 			let assignments: number[];
 			let score: number;
 
-			if (strategy.K === 'auto' && (strategy.algorithm === 'kmeans' || strategy.algorithm === 'kmedoids')) {
+			if (strategy.K === 'auto' && strategy.algorithm === 'kmeans') {
 				// Auto-K: sweep K range and pick the best
 				const autoResult = findOptimalK(clusteringVectors, strategy.algorithm, clusterDistFn, config.seed);
 				assignments = autoResult.assignments;

src/types/cluster.ts

@@ -1,11 +1,10 @@
-// NOTE: 'kmedoids' is kept in the type for compatibility but is not used in the default pipeline strategies (too slow)
-export type ClusteringAlgorithm = 'kmeans' | 'kmedoids' | 'hdbscan';
+export type ClusteringAlgorithm = 'kmeans' | 'hdbscan';
 
 export interface ClusteringStrategy {
 	/** Human-readable label for this run, e.g. 'kmeans-5' */
 	name: string;
 	algorithm: ClusteringAlgorithm;
-	/** Number of clusters (kmeans / kmedoids). Use 'auto' for automatic selection via silhouette sweep. Note: kmedoids is not active in the default pipeline. */
+	/** Number of clusters (kmeans). Use 'auto' for automatic selection via silhouette sweep. */
 	K?: number | 'auto';
 	/** Minimum points to form a cluster (hdbscan, default: 3) */
 	minClusterSize?: number;

src/webview/pages/SettingsPage.tsx

@@ -27,7 +27,7 @@ export const SettingsPage: React.FC = () => {
 					• <strong>Embedding Model:</strong> all-MiniLM-L6-v2 (384-dim)
 				</div>
 				<div className="config-card-item">
-					• <strong>Clustering Strategies:</strong> Auto K-Means, Auto K-Medoids, HDBSCAN
+					• <strong>Clustering Strategies:</strong> Auto K-Means, HDBSCAN
 				</div>
 			</div>
 		</div>

test/pipeline/clustering/autoK.test.ts

@@ -150,11 +150,9 @@ describe('autoK findOptimalK', () => {
 		expect(res1).toEqual(res2);
 	});
 
-	it('works with both kmeans and kmedoids', () => {
+	it('finds optimal K using kmeans', () => {
 		const resKmeans = findOptimalK(THREE_CLUSTERS, 'kmeans', euclideanDistance, 42);
-		const resKmedoids = findOptimalK(THREE_CLUSTERS, 'kmedoids', euclideanDistance, 42);
 		expect(resKmeans.bestK).toBe(3);
-		expect(resKmedoids.bestK).toBe(3);
 	});
 
 	it('falls back to K=1 when no valid clustering is possible', () => {