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/ai-service/.env.example

@@ -0,0 +1,12 @@
+AI_PROVIDER=lmstudio
+
+LMSTUDIO_BASE_URL=http://host.docker.internal:1234/v1
+LMSTUDIO_API_KEY=your-lmstudio-api-key
+LMSTUDIO_MODEL=local-model
+
+OLLAMA_BASE_URL=http://host.docker.internal:11434/v1
+OLLAMA_MODEL=llama3.2
+OLLAMA_API_KEY=ollama
+
+ANTHROPIC_API_KEY=sk-ant-your-key-here
+ANTHROPIC_MODEL=claude-haiku-4-5-20251001