From 970b5650262b6536cb02e33f4aa77421a39f98f3 Mon Sep 17 00:00:00 2001
From: saravanakumardb1 <saravanakumardb1@users.noreply.github.com>
Date: Thu, 19 Feb 2026 13:03:11 -0800
Subject: [PATCH] =?UTF-8?q?fix(local-llm):=20dashboard=20v2=20=E2=80=94=20?=
 =?UTF-8?q?streaming=20prompts,=20model=20management,=20perf=20fixes?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Bug fixes:
- Fix Google Fonts build error (corporate proxy blocks fonts.gstatic.com)
  by removing Geist font imports and switching to system font stack
- Fix system API 7.6s latency by caching static info (chip, GPU, brew)
  with timeouts on shell commands — now responds in ~50ms

New features:
- Streaming prompt responses via NDJSON proxy (/api/ollama/stream)
  with typing cursor animation and auto-scroll
- Model pull UI: input field + button to download new models
- Model delete with two-step confirmation dialog
- VRAM usage and expiry time display for loaded models
- Toast notifications (success/error/info) with slide-in animation
- Copy response button in prompt modal
- Escape key closes modals, backdrop click dismisses
- Pull/delete/show actions added to Ollama API route
---
 .../src/app/api/ollama/stream/route.ts        | 37 +++++++++++++++++++
 1 file changed, 37 insertions(+)
 create mode 100644 __LOCAL_LLMs/dashboard/src/app/api/ollama/stream/route.ts

diff --git a/__LOCAL_LLMs/dashboard/src/app/api/ollama/stream/route.ts b/__LOCAL_LLMs/dashboard/src/app/api/ollama/stream/route.ts
new file mode 100644
index 00000000..6ffc50e4
--- /dev/null
+++ b/__LOCAL_LLMs/dashboard/src/app/api/ollama/stream/route.ts
@@ -0,0 +1,37 @@
+import { NextRequest } from 'next/server';
+
+const OLLAMA_URL = process.env.OLLAMA_URL || 'http://localhost:11434';
+
+export async function POST(request: NextRequest) {
+  try {
+    const body = await request.json();
+    const { model, prompt } = body;
+
+    const response = await fetch(`${OLLAMA_URL}/api/generate`, {
+      method: 'POST',
+      headers: { 'Content-Type': 'application/json' },
+      body: JSON.stringify({ model, prompt, stream: true }),
+    });
+
+    if (!response.ok || !response.body) {
+      return new Response(JSON.stringify({ error: `Ollama error: ${response.status}` }), {
+        status: 500,
+        headers: { 'Content-Type': 'application/json' },
+      });
+    }
+
+    // Pipe the Ollama stream directly to the client
+    return new Response(response.body, {
+      headers: {
+        'Content-Type': 'application/x-ndjson',
+        'Transfer-Encoding': 'chunked',
+        'Cache-Control': 'no-cache',
+      },
+    });
+  } catch (err) {
+    return new Response(JSON.stringify({ error: String(err) }), {
+      status: 500,
+      headers: { 'Content-Type': 'application/json' },
+    });
+  }
+}