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/faceglitch_il.json

@@ -1,26 +1,12 @@
 {
   "detailer_id": "faceglitch_il",
   "detailer_name": "Faceglitch Il",
-  "prompt": [
-    "glitch",
-    "glitch art",
-    "datamoshing",
-    "pixel sorting",
-    "chromatic aberration",
-    "vhs artifacts",
-    "distorted face",
-    "digital noise",
-    "signal error",
-    "corrupted image",
-    "cyberpunk",
-    "scanlines",
-    "interference",
-    "broken data"
-  ],
-  "focus": { "body": "head", "detailer": "face" },
+  "prompt": "glitch, faceless",
   "lora": {
     "lora_name": "Illustrious/Detailers/faceglitch_IL.safetensors",
-    "lora_weight": 1.0,
-    "lora_triggers": "faceglitch_IL"
+    "lora_weight": 1.1,
+    "lora_weight_min": 1.0,
+    "lora_weight_max": 1.2,
+    "lora_triggers": "faceless, glitch"
   }
 }