Extract subject context policy

prompt_builder.py

@@ -47,6 +47,7 @@ try:
     from . import row_camera as row_camera_policy
     from . import row_location as row_location_policy
     from . import seed_config as seed_policy
+    from . import subject_context as subject_context_policy
     from .hardcore_text_cleanup import (
         sanitize_hardcore_axis_values as _sanitize_hardcore_axis_values,
         sanitize_hardcore_environment_anchors as _sanitize_hardcore_environment_anchors,
@@ -93,6 +94,7 @@ except ImportError:  # Allows local smoke tests with `python -c`.
     import row_camera as row_camera_policy
     import row_location as row_location_policy
     import seed_config as seed_policy
+    import subject_context as subject_context_policy
     from hardcore_text_cleanup import (
         sanitize_hardcore_axis_values as _sanitize_hardcore_axis_values,
         sanitize_hardcore_environment_anchors as _sanitize_hardcore_environment_anchors,
@@ -2498,59 +2500,16 @@ def _subject_context(
     women_count: int = 1,
     men_count: int = 1,
 ) -> dict[str, str]:
-    if subject_type in ("woman", "man", "single_any"):
-        return _appearance_for_subject(rng, subject_type, ethnicity, figure, no_plus_women, no_black)
-
-    if subject_type == "configured_cast":
-        return _configured_cast_context(women_count, men_count)
-
-    if subject_type == "couple":
-        primary_subject, subject_phrase, pose, effective_women_count, effective_men_count = _couple_type_from_counts(
-            rng,
-            women_count,
-            men_count,
-        )
-        return {
-            "subject_type": "couple",
-            "subject": primary_subject,
-            "subject_phrase": subject_phrase,
-            "age": g.choose(rng, g.COUPLE_AGES),
-            "body": g.choose(rng, ["slim and average", "curvy and broad", "stocky and curvy", "average and athletic"]),
-            "skin": "",
-            "hair": "",
-            "eyes": "",
-            "body_phrase": "",
-            "fallback_pose": pose,
-            "women_count": str(effective_women_count),
-            "men_count": str(effective_men_count),
-            "person_count": "2",
-        }
-
-    if subject_type == "group":
-        eth = "Asian " if ethnicity == "asian" else ""
-        return {
-            "subject_type": "group",
-            "subject": f"mixed {eth}adult group",
-            "subject_phrase": f"A mixed {eth}adult group of women and men",
-            "age": g.choose(rng, g.GROUP_AGES),
-            "body": "diverse",
-            "skin": "",
-            "hair": "",
-            "eyes": "",
-            "body_phrase": "diverse adult body types",
-        }
-
-    return {
-        "subject_type": subject_type,
-        "subject": "layout scene",
-        "subject_phrase": "Adult layout scene",
-        "age": "adult",
-        "body": "varied",
-        "skin": "",
-        "hair": "",
-        "eyes": "",
-        "body_phrase": "varied adult figures",
-    }
+    return subject_context_policy.subject_context(
+        rng,
+        subject_type,
+        ethnicity,
+        figure,
+        no_plus_women,
+        no_black,
+        women_count,
+        men_count,
+    )
 
 
 def _scene_pool(