Improve paired cast continuity and wording

caption_naturalizer.py

@@ -180,6 +180,18 @@ def _clean_clothing(text: str) -> str:
     return text.strip(" ,")
 
 
+def _body_phrase(body: Any, figure_note: Any = "") -> str:
+    body = _clean_text(body)
+    figure_note = _clean_text(figure_note)
+    if not body:
+        return figure_note
+    if not figure_note:
+        return f"{body} figure"
+    if "figure" in figure_note.lower():
+        return f"{body} build and {figure_note}"
+    return f"{body} figure with {figure_note}"
+
+
 def _single_caption_front(row: dict[str, Any]) -> dict[str, str]:
     caption = _clean_text(row.get("caption"))
     if not caption:
@@ -192,7 +204,7 @@ def _single_caption_front(row: dict[str, Any]) -> dict[str, str]:
     if not body_phrase:
         body = _clean_text(row.get("body_type") or row.get("body"))
         figure = _clean_text(row.get("figure"))
-        body_phrase = f"{body} figure with {figure}" if body and figure else f"{body} figure".strip()
+        body_phrase = _body_phrase(body, figure)
     front = f"{subject}, {age}, {body_phrase}, "
     if subject in ("woman", "man") and age and body_phrase and caption.startswith(front):
         try:
@@ -290,7 +302,7 @@ def _single_from_row(row: dict[str, Any], detail_level: str, keep_style: bool) -
     if not body_phrase:
         body = _clean_text(row.get("body_type") or row.get("body") or "")
         figure = _clean_text(row.get("figure"))
-        body_phrase = f"{body} figure with {figure}" if body and figure else f"{body} figure".strip()
+        body_phrase = _body_phrase(body, figure)
 
     skin = _row_value(row, "skin") or caption_front.get("caption_skin", "")
     hair = _row_value(row, "hair") or caption_front.get("caption_hair", "")
@@ -454,8 +466,48 @@ def _group_or_layout_from_row(row: dict[str, Any], detail_level: str, keep_style
     return _join_sentences(parts), "metadata(group_layout)"
 
 
+def _insta_of_pair_from_row(row: dict[str, Any], detail_level: str, keep_style: bool) -> tuple[str, str] | None:
+    if _clean_text(row.get("mode")).lower() != "insta/of":
+        return None
+    soft_row = row.get("softcore_row")
+    hard_row = row.get("hardcore_row")
+    if not isinstance(soft_row, dict) or not isinstance(hard_row, dict):
+        return None
+
+    hard_row_for_text = dict(hard_row)
+    options = row.get("options")
+    if isinstance(options, dict) and options.get("continuity") == "same_creator_same_room":
+        if soft_row.get("scene_text"):
+            hard_row_for_text["scene_text"] = soft_row["scene_text"]
+        if soft_row.get("composition"):
+            hard_row_for_text["composition"] = soft_row["composition"]
+
+    soft_text, _soft_method = _metadata_to_prose(soft_row, detail_level, keep_style)
+    hard_text, _hard_method = _metadata_to_prose(hard_row_for_text, detail_level, keep_style)
+    descriptor = _clean_text(row.get("shared_descriptor"))
+    cast_descriptors = row.get("shared_cast_descriptors")
+    if isinstance(cast_descriptors, list):
+        cast_descriptor_text = _human_join([_clean_text(item) for item in cast_descriptors if _clean_text(item)])
+    else:
+        cast_descriptor_text = _clean_text(cast_descriptors)
+
+    parts = []
+    if cast_descriptor_text:
+        parts.append(f"The shared cast descriptors are {cast_descriptor_text}")
+    elif descriptor:
+        parts.append(f"The shared creator descriptor is {descriptor}")
+    if soft_text:
+        parts.append(f"Softcore version: {soft_text}")
+    if hard_text:
+        parts.append(f"Hardcore version: {hard_text}")
+    if not parts:
+        return None
+    return _join_sentences(parts), "metadata(insta_of_pair)"
+
+
 def _metadata_to_prose(row: dict[str, Any], detail_level: str, keep_style: bool) -> tuple[str, str]:
     for builder in (
+        _insta_of_pair_from_row,
         _configured_cast_from_row,
         _single_from_row,
         _couple_from_row,