code cleanup/hardening

packages/embedding-service/src/index.js

@@ -5,9 +5,9 @@ const {getEnv, OLLAMA, PORTS} = require('@nexusai/shared');
 const app = express();
 app.use(express.json());
 
-const PORT          = getEnv('PORT',            PORTS.EMBEDDING);  // Default to 3003 if PORT is not set
+const PORT          = getEnv('PORT',            PORTS.EMBEDDING);  
-const OLLAMA_URL    = getEnv('OLLAMA_URL',      OLLAMA.DEFAULT_URL); // URL for Ollama API
+const OLLAMA_URL    = getEnv('OLLAMA_URL',      OLLAMA.DEFAULT_URL); 
-const EMBED_MODEL   = getEnv('EMBEDDING_MODEL', OLLAMA.EMBED_MODEL); // Ollama model for embeddings
+const EMBED_MODEL   = getEnv('EMBEDDING_MODEL', OLLAMA.EMBED_MODEL); 
 
 //OLLAMA embedding helper function
 async function embedText(text) {

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

@@ -1,5 +1,5 @@
 const {getDB} = require('../db');
-const { EPISODIC, getEnv, SERVICES, parseRow, formatEpisodeText } = require('@nexusai/shared');
+const { EPISODIC, getEnv, SERVICES, parseRow, formatEpisodeText, SUMMARIES } = require('@nexusai/shared');
 const semantic = require('../semantic');
 const { extractAndStoreEntities } = require('../entities/extraction')
 
@@ -207,7 +207,7 @@ async function getEpisodeEmbedding(userMessage, aiResponse){
   return data.embedding;
 }
 
-function getEpisodesByProject(projectId, limit = 200) {
+function getEpisodesByProject(projectId, limit = SUMMARIES.MAX_PROJECT_EPISODE_LIMIT) {
     const db = getDB();
     return db.prepare(`
         SELECT e.* FROM episodes e

packages/memory-service/src/summarization/project.js

@@ -1,4 +1,4 @@
-const { SERVICES, getEnv } = require('@nexusai/shared');
+const { SERVICES, getEnv, SUMMARIES } = require('@nexusai/shared');
 const { 
     getSessionSummariesForProject,
     getProjectOverviewSummary,
@@ -12,7 +12,7 @@ const {
 const EXTRACTION_URL   = getEnv('EXTRACTION_URL', 'http://localhost:11434');
 const EXTRACTION_MODEL = getEnv('EXTRACTION_MODEL', 'qwen2.5:3b');
 
-const MAX_SUMMARY_CHARS = 8000; // generous ceiling before we truncate input
+const MAX_SUMMARY_CHARS = SUMMARIES.MAX_SUMMARY_CHARS; // generous ceiling before we truncate input
 
 function buildProjectSummaryPrompt(projectName, sessionSummaries) {
     let summaryBlock = sessionSummaries

packages/orchestration-service/src/index.js

@@ -1,6 +1,6 @@
 require ('dotenv').config();
 const express = require('express');
-const {getEnv, PORTS, SERVICES, ORCHESTRATION} = require('@nexusai/shared');
+const {getEnv, PORTS, SERVICES, ORCHESTRATION, logger} = require('@nexusai/shared');
 
 /**** ROUTERS *** */
 const chatRouter = require('./routes/chat');
@@ -53,5 +53,5 @@ app.use('/summaries', summariesRouter)
 
 /******* Start the server ************/
 app.listen(PORT, () => {
-    console.log(`Orchestration Service is running on port ${PORT}`);
+    logger.info(`Orchestration Service is running on port ${PORT}`);
 });

packages/shared/src/config/constants.js

@@ -26,7 +26,7 @@ const ORCHESTRATION = {
     SEMANTIC_LIMIT:         5,
     SCORE_THRESHOLD:        0.5,
     ENTITIES_LIMIT:         5,
-    ENTITIES_THRESHOLD:     0.6,
+    ENTITIES_THRESHOLD:     0.55,
     TEMPERATURE:            0.7,
     CORS_ORIGIN:            'http://localhost:5173',
     SYSTEM_PROMPT:          `You are a helpful, context-aware AI assistant. You have access to memories of past conversations with the user. Use them to provide consistent, personalised responses.`
@@ -73,11 +73,14 @@ const SUMMARIES = {
     THRESHOLD_TOKENS:   200,    //trigger summary when session hits this many tokens
     MAX_SUMMARY_TOKENS: 800,    //if existing summary exceeds this, create new instead of update
     MIN_EPISODES_SINCE: 5,      // don't resummarize until N new episodes since last summary
+    MAX_SUMMARY_CHARS:  8000,   // max chars to include from recent episodes when generating summary (to control prompt size)
+    MAX_PROJECT_EPISODE_LIMIT: 200, // max number of episodes to consider from the entire project when generating summary (to control prompt size)
 }
 
 const ENTITIES = {
-    TEMPERATURE:    0.1,
+    TEMPERATURE:    0.1,    // Low temperature, more precise extraction, less creative
-    NUM_PREDICT:    1024,
+    NUM_PREDICT:    1024,   // Max tokens to consider for entity extraction (e.g. recent conversation)
+    THRESHOLD:      0.55,   // Minimum confidence score for an extracted entity to be included in the results
 }
 
 module.exports = {

packages/shared/src/index.js

@@ -1,6 +1,7 @@
 const {getEnv} = require('./config/env');
 const {QDRANT, COLLECTIONS, EPISODIC, SERVICES, OLLAMA, PORTS, LLAMACPP, INFERENCE_DEFAULTS, SQLITE, ORCHESTRATION, SUMMARIES, ENTITIES } = require('./config/constants');
 const {parseRow, formatEpisodeText} = require('./utils')
+const {logger} = require('./utils/logger');
 
 module.exports = {
     getEnv, 
@@ -18,4 +19,5 @@ module.exports = {
     formatEpisodeText,
     SUMMARIES,
     ENTITIES,
+    logger,
 };

packages/shared/src/utils/logger.js

@@ -0,0 +1,12 @@
+const LEVELS = { error: 0, warn: 1, info: 2, debug: 3 };
+
+const current = LEVELS[process.env.LOG_LEVEL?.toLowerCase()] ?? LEVELS.info;
+
+const logger = {
+    error: (...args) => current >= LEVELS.error && console.error('[ERROR]', ...args),
+    warn:  (...args) => current >= LEVELS.warn  && console.warn( '[WARN]',  ...args),
+    info:  (...args) => current >= LEVELS.info  && console.log(  '[INFO]',  ...args),
+    debug: (...args) => current >= LEVELS.debug && console.log(  '[DEBUG]', ...args),
+};
+
+module.exports = logger;