feat: implement Actions Gallery with character integration and triple LoRA chaining

- Added Actions gallery with CRUD and JSON sync
- Implemented Triple LoRA workflow (Character -> Outfit -> Action)
- Added character-integrated previews for Actions with style matching
- Implemented granular prompt selection and default persistence for Actions
- Added detailed development guide for extending gallery features

data/actions/belly_dancing.json

@@ -1,16 +1,25 @@
 {
-    "action_id": "belly_dancing",
-    "action_name": "Belly Dancing",
-    "action": {
-        "full_body": "belly dancing",
-        "head": "",
-        "eyes": "",
-        "arms": "hands above head",
-        "hands": "hands together",
-        "torso": "",
-        "pelvis": "shaking hips",
-        "legs": "",
-        "feet": "",
-        "additional": ""
-    }
+  "action_id": "belly_dancing",
+  "action_name": "Belly Dancing",
+  "action": {
+    "full_body": "belly dancing, standing",
+    "head": "",
+    "eyes": "",
+    "arms": "hands above head",
+    "hands": "palms together",
+    "torso": "",
+    "pelvis": "swaying hips",
+    "legs": "",
+    "feet": "",
+    "additional": ""
+  },
+  "lora": {
+    "lora_name": "",
+    "lora_weight": 1.0,
+    "lora_triggers": ""
+  },
+  "tags": [
+    "belly dancing",
+    "dance"
+  ]
 }