fix: improve JSON parsing fallback and default to gemma4

scripts/generate_scene_descriptions.py

@@ -144,15 +144,22 @@ def describe_image(
             # Parse JSON from response
             json_match = re.search(r"\{[\s\S]*\}", response_text)
             if json_match:
-                parsed = json.loads(json_match.group())
-                # Validate required fields
-                required = ["mood", "colors", "composition", "camera", "description"]
-                if all(k in parsed for k in required):
-                    return parsed
+                try:
+                    parsed = json.loads(json_match.group())
+                    # Validate required fields
+                    required = ["mood", "colors", "composition", "camera", "description"]
+                    if all(k in parsed for k in required):
+                        if parsed["description"]:  # Ensure non-empty description
+                            return parsed
+                except json.JSONDecodeError:
+                    pass
 
-            # Fallback: return raw description
+            # Fallback: model returned natural language — wrap it
+            # Clean up markdown formatting
+            clean = re.sub(r"[*_`#]", "", response_text).strip()
+            clean = re.sub(r"\n{3,}", "\n\n", clean)
             return {
-                "description": response_text[:500],
+                "description": clean[:500] if clean else response_text[:500],
                 "mood": "unknown",
                 "colors": [],
                 "composition": "unknown",
@@ -295,7 +302,7 @@ def main():
     )
     parser.add_argument("--input", "-i", required=True, help="Input directory with media files")
     parser.add_argument("--output", "-o", default="training-data/scene-descriptions-auto.jsonl")
-    parser.add_argument("--model", "-m", default="", help="Ollama model name (auto-detects if empty)")
+    parser.add_argument("--model", "-m", default="gemma4:latest", help="Ollama model name (auto-detects if empty)")
     parser.add_argument("--ollama-url", default="http://localhost:11434")
     parser.add_argument("--limit", "-l", type=int, default=0, help="Max files to process (0=all)")
     parser.add_argument("--dry-run", action="store_true", help="List files without generating")