feat: add local inference provider with llama.cpp backend and HuggingFace model management (#6933)

Co-authored-by: Douwe Osinga <douwe@squareup.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: jh-block <jhugo@block.xyz>
Co-authored-by: Spence <spencermartin@squareup.com>
Co-authored-by: Michael Neale <michael.neale@gmail.com>

ui/desktop/src/components/settings/SettingsView.tsx

@@ -9,10 +9,11 @@ import ConfigSettings from './config/ConfigSettings';
 import PromptsSettingsSection from './PromptsSettingsSection';
 import { ExtensionConfig } from '../../api';
 import { MainPanelLayout } from '../Layout/MainPanelLayout';
-import { Bot, Share2, Monitor, MessageSquare, FileText, Keyboard } from 'lucide-react';
+import { Bot, Share2, Monitor, MessageSquare, FileText, Keyboard, HardDrive } from 'lucide-react';
 import { useState, useEffect, useRef } from 'react';
 import ChatSettingsSection from './chat/ChatSettingsSection';
 import KeyboardShortcutsSection from './keyboard/KeyboardShortcutsSection';
+import LocalInferenceSection from './localInference/LocalInferenceSection';
 import { CONFIGURATION_ENABLED } from '../../updates';
 import { trackSettingsTabViewed } from '../../utils/analytics';
 
@@ -54,6 +55,7 @@ export default function SettingsView({
         chat: 'chat',
         prompts: 'prompts',
         keyboard: 'keyboard',
+        'local-inference': 'local-inference',
       };
 
       const targetTab = sectionToTab[viewOptions.section];
@@ -112,6 +114,14 @@ export default function SettingsView({
                     <Bot className="h-4 w-4" />
                     Models
                   </TabsTrigger>
+                  <TabsTrigger
+                    value="local-inference"
+                    className="flex gap-2"
+                    data-testid="settings-local-inference-tab"
+                  >
+                    <HardDrive className="h-4 w-4" />
+                    Local Inference
+                  </TabsTrigger>
                   <TabsTrigger value="chat" className="flex gap-2" data-testid="settings-chat-tab">
                     <MessageSquare className="h-4 w-4" />
                     Chat
@@ -155,6 +165,13 @@ export default function SettingsView({
                   <ModelsSection setView={setView} />
                 </TabsContent>
 
+                <TabsContent
+                  value="local-inference"
+                  className="mt-0 focus-visible:outline-none focus-visible:ring-0"
+                >
+                  <LocalInferenceSection />
+                </TabsContent>
+
                 <TabsContent
                   value="chat"
                   className="mt-0 focus-visible:outline-none focus-visible:ring-0"