Share formatter field label policy

docs/prompt-architecture-improvement-plan.md

@@ -73,7 +73,8 @@ routes:
 - JSON row detection from `metadata_json` or source text;
 - trigger-prefix stripping with route-specific trigger candidate lists;
 - `Avoid:` positive/negative splitting for fallback text;
-- prompt field extraction such as `Setting:` or `Composition:`;
+- the shared prompt field-label inventory and extraction such as `Setting:`,
+  `Sexual scene:`, `Camera control:`, or `Composition:`;
 - row-value fallback from metadata fields to labeled prompt text.
 
 It must not make formatter-style decisions. Krea prose, SDXL tags, and training
@@ -261,8 +262,9 @@ Already isolated:
   first-person body geometry, and selected-position-axis priority before loose
   context fallback.
 - `formatter_input.py` owns shared metadata/source JSON detection, trigger
-  stripping, prompt-field extraction, `Avoid:` splitting, and row-value
-  fallback for Krea, SDXL, and caption routes.
+  stripping, the shared prompt field-label inventory, prompt-field extraction,
+  `Avoid:` splitting, and row-value fallback for Krea, SDXL, and caption
+  routes.
 
 Improve later: