refinement fixes

packages/memory-service/src/entities/extraction.js

@@ -7,6 +7,7 @@ const EXTRACTION_MODEL = getEnv('EXTRACTION_MODEL', 'qwen2.5:3b'); // ChatML for
 const EMBEDDING_SERVICE_URL = getEnv('EMBEDDING_SERVICE_URL', SERVICES.EMBEDDING_URL);
 
 const ENTITY_TYPES = ENTITIES.TYPES;
+
 const IGNORED_NAMES = new Set([
   'good morning', 'good night', 'good evening', 'good afternoon',
   'hello', 'hi', 'hey', 'goodbye', 'bye', 'thanks', 'thank you', 'morning',
@@ -39,7 +40,6 @@ function buildExtractionPrompt(userMessage, aiResponse, knownEntities = []) {
         `Entity types: ${ENTITY_TYPES.join(', ')}`,
         'Use "character" for any fictional, game, or media characters (e.g. characters from anime, games, books, TV shows, movies)',
         'Use "person" only for real people',
-        'Do not extract greetings, pleasantries, or conversational filler (e.g. "good morning", "thanks") as entities.',
         'For each entity provide:',
         '  "name": short proper noun only (max 4 words)',
         '  "type": one of the valid types',
@@ -131,7 +131,7 @@ async function extractAndStoreEntities(userMessage, aiResponse, episodeId=null,
 
         for (const { name, type, notes } of entities) {
             if (!name || !type || !ENTITY_TYPES.includes(type)) continue;
-            if (IGNORED_NAMES.includes(name.toLowerCase())) continue;
+            if (isIgnoredName(name)) continue;
 
             const entity = upsertEntity(name, type, notes ?? null);
             entityMap.set(`${name}::${type}`, entity);

packages/memory-service/src/semantic/index.js

@@ -108,7 +108,7 @@ async function deleteEntity(id) {
 //Filter-based, 
 async function deleteEpisodesBySession(sessionId) {
     const client = getClient();
-    await client.delete(CoLLECTIONS.EPISODES, {
+    await client.delete(COLLECTIONS.EPISODES, {
         wait: true,
         filter: {
             must: [{ key: 'sessionId', match: { value: sessionId } }]