chat client clean up and switch to llama.cpp with models folder network sharing

packages/orchestration-service/src/routes/chat.js

@@ -36,10 +36,14 @@ router.post('/stream', async (req, res) => {
     res.flushHeaders();
 
     try {
-        await chatStream(sessionId, message, (delta) => {
-            res.write(`data: ${JSON.stringify({ text: delta})}\n\n`)
-        })
-        res.write(`data: ${JSON.stringify({done: true})}\n\n`);
+        const { model, tokenCount } = await chatStream(
+            sessionId, 
+            message, 
+            (delta) => { res.write(`data: ${JSON.stringify({ text: delta })}\n\n`) },
+            { model: req.body.model, temperature: req.body.temperature }
+        );
+
+        res.write(`data: ${JSON.stringify({ done: true, model, tokenCount })}\n\n`);
     } catch (err) {
         res.write(`data: ${JSON.stringify({error: err.message})}\n\n`);
     } finally {

packages/orchestration-service/src/routes/models.js

@@ -0,0 +1,21 @@
+// routes/models.js
+const express = require('express');
+const router = express.Router();
+const fs = require('fs');
+const path = require('path');
+const {getEnv} = require('@nexusai/shared');
+
+const MODELS_PATH = getEnv('MODELS_MANIFEST_PATH', path.join(__dirname, '../models.json'));
+
+router.get('/', (req, res) => {
+  try {
+    const raw = fs.readFileSync(MODELS_PATH, 'utf8');
+    const models = JSON.parse(raw);
+    res.json(models);
+  } catch (err) {
+    console.error('[models] Failed to read manifest:', err.message);
+    res.status(500).json({ error: 'Could not load models manifest' });
+  }
+});
+
+module.exports = router;