Add Phase Z B4 source-shape-aware placement

- enable B1/B2/B4 source-shape-aware F13 placement behind env flag
- align F13 placement_trace with mapper top_bullets cardinality
- preserve canonical render output when flag is off

src/phase_z2_content_extractor.py

@@ -26,6 +26,7 @@ from __future__ import annotations
 
 import re
 from dataclasses import dataclass, field
+from typing import Optional
 
 # B1 v0 helper 처리 정직 기록 (기존 보고 정정 — 2026-04-30) :
 #   - `phase_z2_mapper` 미수정. 기존 mapper helper (`_extract_markdown_table` 등) move /
@@ -46,12 +47,14 @@ class ContentObject:
     """SPEC v1 §1.1 base schema. v0 = text_block + transform_table 만 지원.
 
     Fields :
-      id            : section 내 unique id (예: '03-2.transform-1' / '03-2.text-1')
-      type          : "text_block" | "transform_table"
-      role          : v0 = "summary" 만 (정밀화는 별 axis)
-      raw_payload   : 원본 markdown (자름 / 변형 X — 원문 보존 룰)
-      size_estimate : type 별 (line_count / rows 등)
-      type_specific : type 별 detail (SPEC v1 §1.2)
+      id                  : section 내 unique id (예: '03-2.transform-1' / '03-2.text-1')
+      type                : "text_block" | "transform_table"
+      role                : v0 = "summary" 만 (정밀화는 별 axis)
+      raw_payload         : 원본 markdown (자름 / 변형 X — 원문 보존 룰)
+      size_estimate       : type 별 (line_count / rows 등)
+      type_specific       : type 별 detail (SPEC v1 §1.2)
+      source_shape_index  : positional index within source_shape (Option 1, optional)
+      source_shape_kind   : "top_bullets" | "h3_subsections" | ... (Option 1, optional)
     """
 
     id: str
@@ -60,6 +63,8 @@ class ContentObject:
     raw_payload: str
     size_estimate: dict = field(default_factory=dict)
     type_specific: dict = field(default_factory=dict)
+    source_shape_index: Optional[int] = None
+    source_shape_kind: Optional[str] = None
 
 
 # ─── Transform table extraction ─────────────────────────────────
@@ -187,7 +192,7 @@ def _detect_text_block_specific(content: str) -> tuple[dict, int]:
 # ─── Public entry ───────────────────────────────────────────────
 
 
-def extract_content_objects(section) -> list[ContentObject]:
+def extract_content_objects(section, source_shape: Optional[str] = None) -> list[ContentObject]:
     """MDX section.raw_content → typed content_object list (SPEC v1 §1).
 
     v0 minimal :
@@ -196,15 +201,45 @@ def extract_content_objects(section) -> list[ContentObject]:
       - 미지원 type (table / image / diagram / details) = 무시 (별 axis)
       - 원문 (raw_payload) = 자름 / 변형 X (원문 보존 룰)
 
+    Option 1 (source_shape-aware) :
+      - source_shape="top_bullets" : raw_content 를 mapper.split_source 로 N units 분할 →
+        unit 별 ContentObject 1 개 (text_block) with source_shape_index=i / source_shape_kind="top_bullets"
+      - source_shape=None 또는 미지원 값 (h3_subsections 등) : 기존 legacy 동작
+
     Args :
-      section : MdxSection-like 객체 (section_id, raw_content 필드 필요)
+      section      : MdxSection-like 객체 (section_id, raw_content 필드 필요)
+      source_shape : "top_bullets" 시 source_shape-aware 분기. None 이면 legacy.
 
     Returns :
-      list[ContentObject]  — 0 ~ 2 개 (content 비어 있으면 0, transform-only 면 1, mixed 면 2)
+      list[ContentObject]  — legacy 0~2 / top_bullets N (bullet 수)
     """
     content = section.raw_content
     section_id = section.section_id
 
+    if source_shape == "top_bullets":
+        from phase_z2_mapper import split_source
+        units = split_source("top_bullets", content)
+        objects: list[ContentObject] = []
+        for i, unit in enumerate(units):
+            unit_text = unit if isinstance(unit, str) else str(unit)
+            if not unit_text.strip():
+                continue
+            text_specific, line_count = _detect_text_block_specific(unit_text)
+            objects.append(
+                ContentObject(
+                    id=f"{section_id}.text-{i + 1}",
+                    type="text_block",
+                    role="summary",
+                    raw_payload=unit_text.strip(),
+                    size_estimate={"line_count": line_count},
+                    type_specific=text_specific,
+                    source_shape_index=i,
+                    source_shape_kind="top_bullets",
+                )
+            )
+        return objects
+
+    # legacy path (source_shape=None 또는 미지원 값)
     objects: list[ContentObject] = []
 
     # 1. transform_table 추출 시도 (3-col with arrow)