ai-stack: vendor the local-ai full AI stack as a new service

Vendor the functional source of github.com/outis1one/local-ai into
./ai-stack (22 files) and add services/ai-stack.sh, which copies the
source to ~/docker/ai-stack and hands off to the app's VRAM-aware
installer (local-ai-setup.sh). The stack bundles Ollama, Open WebUI,
RAG + MCP servers, ChromaDB, SearXNG, Kiwix, Gitea, InvokeAI, ComfyUI
and Portainer.

Cloud LLM providers (Groq/DeepInfra/OpenAI/OpenRouter) are optionally
wired into Open WebUI via the plural OPENAI_API_BASE_URLS list, with the
local RAG connection kept as the first entry so RAG keeps working. Open
WebUI ships built-in auth, so Caddy is configured without Authelia.

Excludes the upstream's two bundled copies of this very project
(ubuntu-post-install.sh, ubuntu-post-install-main.zip) — stale and
circular. Coexists with the existing ai-gpu service.

Also fix the install-function names for ai-gpu and ai-stack: the
dispatcher calls install_<raw-name>, so the function must be
install_ai-gpu / install_ai-stack (hyphen), matching the working
mail-archiver / wg-easy services. ai-gpu was previously uninstallable.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Nb2vJ8W7bHKx1JXVvpCraH

services/ai-gpu.sh

@@ -195,7 +195,7 @@ fi
 
 register_service ai-gpu utilities "GPU AI stack — InvokeAI image gen + Ollama/OpenWebUI LLM (6 GB VRAM)" 9090
 
-install_ai_gpu() {
+install_ai-gpu() {
     require_docker || return 1
     log_info "Installing AI GPU stack (InvokeAI + Ollama/OpenWebUI + portal)..."
     log_info "Requires: nvidia GPU with 6 GB+ VRAM, nvidia-container-toolkit installed."
@@ -681,4 +681,4 @@ MD
     echo ""
 }
 
-[[ "${_RUN_STANDALONE:-0}" == 1 ]] && install_ai_gpu
+[[ "${_RUN_STANDALONE:-0}" == 1 ]] && install_ai-gpu