fix: JSON schema + validator for scene description training data (#647)

- Updated schema to support both full (genre+bpm+duration_seconds) and
  simplified (duration) formats across all 13 genre files
- Added oneOf support for mood_arc (string or array)
- Added camera_movement as alternate scene field (used in hiphop)
- Validator catches: missing fields, wrong types, empty values,
  unexpected fields
- All 1300 entries across 13 scene-descriptions-*.jsonl files pass
- Auto-detects schema path, supports --schema flag

Closes #647

training-data/schema.json

@@ -1,9 +1,9 @@
 {
   "$schema": "http://json-schema.org/draft-07/schema#",
   "title": "Scene Description Training Entry",
-  "description": "Schema for lyrics-to-visual-scene description training data entries.",
+  "description": "Schema for lyrics-to-visual scene description training data. Catches missing fields, wrong types, empty values, and unexpected fields.",
   "type": "object",
-  "required": ["song", "artist", "beat", "timestamp", "lyric_line", "scene"],
+  "required": ["song", "beat", "lyric_line", "scene"],
   "properties": {
     "song": {
       "type": "string",
@@ -13,35 +13,49 @@
     "artist": {
       "type": "string",
       "minLength": 1,
-      "description": "Artist name"
+      "description": "Artist or group name (missing in some files — flagged as warning)"
     },
-    "mood_arc": {
+    "genre": {
       "type": "string",
-      "description": "Overall mood progression of the song (optional)"
+      "minLength": 1,
+      "description": "Musical genre"
+    },
+    "bpm": {
+      "type": "number",
+      "minimum": 1,
+      "description": "Beats per minute"
     },
     "beat": {
       "type": "integer",
       "minimum": 1,
-      "description": "Beat number within the song (1-indexed)"
+      "description": "Beat number within the song"
     },
     "timestamp": {
       "type": "string",
       "pattern": "^[0-9]+:[0-5][0-9]$",
       "description": "Timestamp in M:SS or MM:SS format"
     },
+    "duration_seconds": {
+      "type": "number",
+      "minimum": 0,
+      "description": "Duration in seconds"
+    },
     "duration": {
       "type": "string",
-      "description": "Duration of the beat (e.g. '30s', '15s')"
+      "minLength": 1,
+      "description": "Duration as string (e.g. '30s')"
     },
-    "duration_seconds": {
-      "type": "integer",
-      "minimum": 1,
-      "description": "Duration in seconds (integer alternative)"
+    "mood_arc": {
+      "oneOf": [
+        { "type": "string", "minLength": 1 },
+        { "type": "array", "items": { "type": "string" } }
+      ],
+      "description": "Optional mood progression arc"
     },
     "lyric_line": {
       "type": "string",
       "minLength": 1,
-      "description": "The lyric line for this beat"
+      "description": "Lyric line(s) for this beat"
     },
     "scene": {
       "type": "object",
@@ -56,29 +70,31 @@
           "type": "array",
           "items": { "type": "string", "minLength": 1 },
           "minItems": 1,
-          "description": "Color palette for the scene"
+          "description": "Visual color palette"
         },
         "composition": {
           "type": "string",
           "minLength": 1,
-          "description": "Shot composition (e.g. 'wide shot', 'close-up', 'low angle')"
+          "description": "Shot composition description"
         },
         "camera": {
           "type": "string",
-          "description": "Camera movement (e.g. 'static', 'slow zoom', 'tracking')"
+          "minLength": 1,
+          "description": "Camera movement or position"
         },
         "camera_movement": {
           "type": "string",
-          "description": "Alternative field name for camera movement"
+          "minLength": 1,
+          "description": "Camera movement (alternate field name)"
         },
         "description": {
           "type": "string",
           "minLength": 10,
-          "description": "Full scene description text"
+          "description": "Full visual scene description"
         }
       },
-      "additionalProperties": true
+      "additionalProperties": false
     }
   },
-  "additionalProperties": true
+  "additionalProperties": false
 }