feat: upgrade voice pipeline — MLX Whisper STT (20x faster), Qwen3.5 MoE LLM, fix HA tool calling

- Replace faster-whisper with wyoming-mlx-whisper (whisper-large-v3-turbo, MLX Metal GPU)
  STT latency: 8.4s → 400ms for short voice commands
- Add Qwen3.5-35B-A3B (MoE, 3B active params, Q8_0) to Ollama — 26.7 tok/s vs 5.4 tok/s (70B)
- Add model preload launchd service to pin voice model in VRAM permanently
- Fix HA tool calling: set commands.native=true, symlink ha-ctl to PATH
- Add pipeline benchmark script (STT/LLM/TTS latency profiling)
- Add service restart buttons and STT endpoint to dashboard
- Bind Vite dev server to 0.0.0.0 for LAN access

Total estimated pipeline latency: ~27s → ~4s

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

homeai-llm/launchd/com.homeai.preload-models.plist

@@ -0,0 +1,28 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN"
+  "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+  <key>Label</key>
+  <string>com.homeai.preload-models</string>
+
+  <key>ProgramArguments</key>
+  <array>
+    <string>/bin/bash</string>
+    <string>/Users/aodhan/gitea/homeai/homeai-llm/scripts/preload-models.sh</string>
+  </array>
+
+  <key>RunAtLoad</key>
+  <true/>
+
+  <key>StandardOutPath</key>
+  <string>/tmp/homeai-preload-models.log</string>
+
+  <key>StandardErrorPath</key>
+  <string>/tmp/homeai-preload-models-error.log</string>
+
+  <!-- Delay 15s to let Ollama start first -->
+  <key>ThrottleInterval</key>
+  <integer>15</integer>
+</dict>
+</plist>