model inference settings

packages/chat-client/src/api/orchestration.js

@@ -195,3 +195,9 @@ export async function getServiceHealth() {
   if (!res.ok) throw new Error(`Failed to fetch health: ${res.status}`);
   return res.json();
 }
+
+export async function getModelProps() {
+  const res = await fetch(`${BASE_URL}/models/props`);
+  if (!res.ok) throw new Error('Failed to fetch model props');
+  return res.json();
+}

packages/chat-client/src/components/SettingsView.jsx

@@ -2,6 +2,7 @@ import React, { useState, useEffect, useCallback } from 'react';
 import { useSettings } from '../hooks/useSettings';
 import { getServiceHealth } from '../api/orchestration';
 import { useModels } from '../hooks/useModels';
+import { getModelProps } from '../api/orchestration';
 
 export default function SettingsView({ onNavigate }) {
   const { settings, saveSetting, saving } = useSettings();
@@ -243,6 +244,11 @@ function ModelsSection({ onNavigate }) {
   const [selectedInfo, setSelectedInfo] = useState(null);
   const {settings, saveSetting, saving} = useSettings();
 
+  const [modelProps, setModelProps] = useState(null);
+  useEffect(() => {
+    getModelProps().then(setModelProps).catch(() => {});
+  }, []);
+
   // Sync info panel when selection changes
   useEffect(() => {
     const m = models.find(m => m.value === selectedModel);
@@ -325,6 +331,15 @@ function ModelsSection({ onNavigate }) {
             {selectedInfo.description && (
               <InfoLine label="Description" value={selectedInfo.description} />
             )}
+            <InfoLine
+              label="Context"
+              value={modelProps ? `${modelProps.contextWindow.toLocaleString()} tokens` : '—'}
+            />
+            <InfoLine
+              label="Loaded"
+              value={modelProps?.modelAlias ?? '—'}
+              mono
+            />
           </div>
           <p className="text-xs text-muted" style={{ marginTop: 4, fontStyle: 'italic' }}>
             Model loading and parameter configuration coming soon

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

@@ -4,6 +4,9 @@ const fs = require('fs');
 const path = require('path');
 const appSettings = require('../config/settings');
 
+const { getEnv, SERVICES } = require('@nexusai/shared');
+const INFERENCE_SERVICE_URL = getEnv('INFERENCE_SERVICE_URL', SERVICES.INFERENCE_URL);
+
 router.get('/', (req, res) => {
   const { modelsFolderPath } = appSettings.load();
 
@@ -40,6 +43,21 @@ router.get('/', (req, res) => {
   }
 });
 
+router.get('/props', async (req, res) => {
+  try {
+    const response = await fetch(`${INFERENCE_SERVICE_URL}/props`);
+    if (!response.ok) throw new Error(`Inference service error: ${response.status}`);
+    const data = await response.json();
+    res.json({
+      contextWindow: data.n_ctx,
+      modelAlias: data.model_alias,
+    });
+  } catch (err) {
+    console.error('[models/props]', err.message);
+    res.status(503).json({ error: 'Could not reach inference service' });
+  }
+});
+
 function getFileSizeMB(filepath) {
   try {
     const bytes = fs.statSync(filepath).size;