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/looks/zhezhiwuwail.json

@@ -0,0 +1,21 @@
+{
+  "look_id": "zhezhiwuwail",
+  "look_name": "Zhezhiwuwail",
+  "character_id": "",
+  "positive": "1girl, zhezhi_(wuthering_waves), long_hair, black_hair, pink_hair, streaked_hair, multicolored_hair, twintails, two_side_up, glasses, multicolored_eyes, chinese_clothes, bare_shoulders, detached_sleeves, elbow_gloves, fingerless_gloves, white_pantyhose, earrings, blush",
+  "negative": "low_quality, worst_quality, short_hair",
+  "lora": {
+    "lora_name": "Illustrious/Looks/ZhezhiWuwaIL.safetensors",
+    "lora_weight": 0.9,
+    "lora_triggers": "zhezhiwuwa",
+    "lora_weight_min": 0.9,
+    "lora_weight_max": 0.9
+  },
+  "tags": [
+    "character",
+    "wuthering_waves",
+    "female",
+    "glasses",
+    "streaked_hair"
+  ]
+}