Add shared ai-service container as AI provider intermediary

All feature containers now POST messages to ai-service (port 8010) instead
of calling AI providers directly. ai-service routes to LM Studio, Ollama,
or Anthropic based on /config/ai_service_config.json. doc-service AI
providers removed; replaced by httpx ai_client.py. Backend settings
restructured to /api/settings/ai. Frontend gets dedicated AIAdminSettingsPage
and AI Service card in AppsPage.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

frontend/src/pages/AppsPage.tsx

@@ -21,6 +21,14 @@ const APPS: AppCard[] = [
     path: "/apps/documents",
     settingsPath: "/apps/documents/settings/admin",
   },
+  {
+    slug: "ai",
+    name: "AI Service",
+    description: "Shared AI provider for all features. Configure model, credentials, and connection.",
+    status: "available",
+    path: "",
+    settingsPath: "/apps/ai/settings/admin",
+  },
 ];
 
 export default function AppsPage() {
@@ -55,7 +63,7 @@ export default function AppsPage() {
               </div>
               <p style={{ margin: 0, color: "#555", fontSize: 14 }}>{app.description}</p>
               <div style={{ display: "flex", gap: 8, marginTop: "auto" }}>
-                {app.status === "available" && (
+                {app.status === "available" && app.path && (
                   <Link
                     to={app.path}
                     style={{