logger updates

packages/inference-service/src/index.js

@@ -1,6 +1,6 @@
 require ('dotenv').config();
 const express = require('express');
-const {getEnv, PORTS, OLLAMA} = require('@nexusai/shared');
+const {getEnv, PORTS, OLLAMA, logger} = require('@nexusai/shared');
 const inferenceRouter = require('./routes/inference');
 
 const app = express();
@@ -24,5 +24,5 @@ app.use('/', inferenceRouter);
 
 // Start the server
 app.listen(PORT, () => {
-    console.log(`Inference Service is running on port ${PORT}`);
+    logger.info(`Inference Service is running on port ${PORT}`);
 });

packages/inference-service/src/providers/llamacpp.js

@@ -1,4 +1,4 @@
-const { getEnv, LLAMACPP, INFERENCE_DEFAULTS } = require("@nexusai/shared");
+const { getEnv, LLAMACPP, INFERENCE_DEFAULTS, logger } = require("@nexusai/shared");
 
 const BASE_URL = getEnv("INFERENCE_URL", LLAMACPP.DEFAULT_URL);
 const DEFAULT_MODEL = getEnv("DEFAULT_MODEL", LLAMACPP.DEFAULT_MODEL);
@@ -89,7 +89,7 @@ async function* completeStream(prompt, options = {}) {
     }
   }
 
-  console.log('[llamacpp] finalTokenCount:', finalTokenCount);
+  logger.info('[llamacpp] finalTokenCount:', finalTokenCount);
 
   yield { response: '', done: true, model: finalModel, tokenCount: finalTokenCount };
 }

packages/inference-service/src/routes/inference.js

@@ -1,5 +1,6 @@
 const { Router } = require('express');
 const { complete, completeStream } = require('../infer');
+const { logger } = require('@nexusai/shared');
 
 const router = Router();
 
@@ -15,7 +16,7 @@ router.post('/complete', async (req, res) => {
         const result = await complete (prompt, {model, temperature, maxTokens, topP, topK, repeatPenalty});
         res.json(result);
     } catch (error) {
-        console.error('[Inference] Completion error:', error.message);
+        logger.error('[Inference] Completion error:', error.message);
         res.status(500).json({ error: error.message });
     }
 });
@@ -42,7 +43,7 @@ router.post('/complete/stream', async (req, res) => {
                 // capture final metadata from the done signal
                 lastModel  = chunk.model      ?? lastModel;
                 tokenCount = chunk.tokenCount ?? tokenCount;
-                console.log('[inference router] tokenCount from chunk:', chunk.tokenCount, '→', tokenCount);
+                logger.info('[inference router] tokenCount from chunk:', chunk.tokenCount, '→', tokenCount);
             }
         }
 
@@ -51,7 +52,7 @@ router.post('/complete/stream', async (req, res) => {
         res.write('data: [DONE]\n\n');
 
     } catch (err) {
-        console.error('[Inference] Streaming error:', err.message);
+        logger.error('[Inference] Streaming error:', err.message);
         res.write(`data: ${JSON.stringify({ error: err.message })}\n\n`);
     } finally {
         res.end();