Add danbooru-mcp auto-start, git sync, status API endpoints, navbar status indicators, and LLM format retry

- app.py: add subprocess import; add _ensure_mcp_repo() to clone/pull
  danbooru-mcp from https://git.liveaodh.com/aodhan/danbooru-mcp into
  tools/danbooru-mcp/ at startup; add ensure_mcp_server_running() which
  calls _ensure_mcp_repo() then starts the Docker container if not running;
  add GET /api/status/comfyui and GET /api/status/mcp health endpoints;
  fix call_llm() to retry up to 3 times on unexpected response format
  (KeyError/IndexError), logging the raw response and prompting the LLM
  to respond with valid JSON before each retry
- templates/layout.html: add ComfyUI and MCP status dot indicators to
  navbar; add polling JS that checks both endpoints on load and every 30s
- static/style.css: add .service-status, .status-dot, .status-ok,
  .status-error, .status-checking styles and status-pulse keyframe animation
- .gitignore: add tools/ to exclude the cloned danbooru-mcp repo

data/detailers/smooth_booster_v4.json

@@ -1,24 +1,12 @@
 {
   "detailer_id": "smooth_booster_v4",
   "detailer_name": "Smooth Booster V4",
-  "prompt": [
-    "best quality",
-    "masterpiece",
-    "highres",
-    "smooth skin",
-    "clean lines",
-    "noise reduction",
-    "soft lighting",
-    "sharp focus",
-    "clear image",
-    "finely detailed",
-    "4k",
-    "polished"
-  ],
-  "focus": { "body": "", "detailer": "" },
+  "prompt": "absurdres, highres, photorealistic, realistic, shadow, chiaroscuro",
   "lora": {
     "lora_name": "Illustrious/Detailers/Smooth_Booster_v4.safetensors",
-    "lora_weight": 1.0,
-    "lora_triggers": "Smooth_Booster_v4"
+    "lora_weight": 0.5,
+    "lora_weight_min": 0.25,
+    "lora_weight_max": 0.8,
+    "lora_triggers": "Smooth_Quality"
   }
 }