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>

features/doc-service/app/routers/documents.py

@@ -17,7 +17,7 @@ from app.models.category import DocumentCategory
 from app.models.category_assignment import CategoryAssignment
 from app.models.document import Document
 from app.schemas.document import DocumentOut, DocumentStatusOut, DocumentTypeUpdate
-from app.services.ai import get_provider
+from app.services.ai_client import AIServiceError, classify_document
 from app.services.config_reader import load_doc_config
 from app.services.storage import delete_file, get_upload_path, save_upload
 
@@ -91,9 +91,7 @@ async def process_document(doc_id: str) -> None:
 
         try:
             text = await asyncio.to_thread(_extract_pdf_text, doc.file_path)
-            config = await load_doc_config()
-            provider = get_provider(config["ai"])
-            result = await provider.classify_document(text)
+            result = await classify_document(text)
 
             doc.raw_text = text[:500_000]  # cap stored text at 500k chars
             doc.extracted_data = json.dumps(result)