diff --git a/src/phase_z2_composition.py b/src/phase_z2_composition.py index 8050cb4..403b8d1 100644 --- a/src/phase_z2_composition.py +++ b/src/phase_z2_composition.py @@ -701,6 +701,12 @@ def select_composition_units(candidates, allowed_statuses: set[str]) -> list[Com selected.append(c) covered.update(c.source_section_ids) + # 2026-05-14 — MDX 자연 순서 (section_id 오름차순) 로 재정렬. + # 사용자 룰 (CLAUDE.md "정보 계층: 위 → 아래") + 04-1/04-2 score 차이로 인한 + # zone 거꾸로 배치 catch. score 는 viable selection 에만, position 은 MDX 순서. + # source_section_ids 첫 element 기준 lexicographic sort — "04-1" < "04-2" < "04-2.1" < "04-2.2". + selected.sort(key=lambda c: c.source_section_ids[0] if c.source_section_ids else "") + return selected diff --git a/src/phase_z2_pipeline.py b/src/phase_z2_pipeline.py index e882b04..04170d5 100644 --- a/src/phase_z2_pipeline.py +++ b/src/phase_z2_pipeline.py @@ -41,6 +41,7 @@ from jinja2 import Environment, FileSystemLoader, select_autoescape from phase_z2_composition import ( LAYOUT_PRESETS, CompositionUnit, + derive_parent_id, plan_composition, select_display_strategy_candidates, select_layout_candidates, @@ -85,6 +86,19 @@ V4_LABEL_TO_PHASE_Z_STATUS = { } MVP1_ALLOWED_STATUSES = {"matched_zone", "adapt_matched_zone"} +# Env toggle PHASE_Z_ALLOW_RESTRUCTURE (default OFF) — when "1/true/yes" 도 restructure +# (= extract_matched_zone) 통과시킴. AI fallback 대행 (사용자가 콘텐츠를 frame 구조에 맞게 +# 재정리한 mdx 를 제공) 시나리오용. MVP1 정책 자체는 무변 — env 켜진 세션만 영향. +if os.environ.get("PHASE_Z_ALLOW_RESTRUCTURE", "").strip().lower() in {"1", "true", "yes"}: + MVP1_ALLOWED_STATUSES = MVP1_ALLOWED_STATUSES | {"extract_matched_zone"} + +# Env toggle PHASE_Z_ALLOW_REJECT (default OFF) — when "1/true/yes" 도 reject +# (= fallback_candidate) 통과시킴. 사용자 룰 : "매칭점수 가장 높은 frame 의 구조, +# 요소, 색상 활용" — V4 가 의미적으로 reject 해도 structure 매칭 충분하면 강제 사용. +# 04-1 같은 all-reject section + 신규 등록 frame 강제 매핑 시나리오용. +if os.environ.get("PHASE_Z_ALLOW_REJECT", "").strip().lower() in {"1", "true", "yes"}: + MVP1_ALLOWED_STATUSES = MVP1_ALLOWED_STATUSES | {"fallback_candidate"} + # Step 9 v0 (사용자 lock 2026-05-08) — V4 label → application_mode 변환. # tuple = (application_mode, auto_applicable, delegated_to). # status.md §2 Q3 / Q7 lock 따라. @@ -184,7 +198,15 @@ def parse_mdx(mdx_path: Path) -> tuple[str, list[MdxSection], Optional[str]]: if footer_match: body = footer_match.group(1) bullet_match = re.search(r"\*\s*\*\*([^*]+)\*\*", body) - footer_text = (bullet_match.group(1).strip() if bullet_match else body.strip()) + if bullet_match: + footer_text = bullet_match.group(1).strip() + else: + # 2026-05-14 Q5 — markdown bullet marker `*` 시작 시 제거 (사용자 lock). + # `* 검증 없는 정책...` → `검증 없는 정책...` + plain = body.strip() + if plain.startswith("*"): + plain = plain[1:].lstrip() + footer_text = plain text = text[:footer_match.start()] + text[footer_match.end():] sections = [] @@ -372,47 +394,80 @@ def load_v4_result() -> dict: return yaml.safe_load(V4_RESULT_PATH.read_text(encoding="utf-8")) -def align_sections_to_v4_granularity(sections: list[MdxSection], v4: dict) -> list[MdxSection]: - """V4 section granularity 에 맞춰 sections 조정. +def align_sections_to_v4_granularity( + sections: list[MdxSection], + v4: dict, + *, + override_target_section_ids: Optional[list[str]] = None, +) -> list[MdxSection]: + """Align MDX sections to canonical sub-section granularity. - IMP-08 B-3 : canonical sub-section id ``${section_id}-sub-${ordinal}`` - (예 : ``04-2-sub-1``) 를 emit 하고, legacy V4 키 (``04-2.1``) 는 - ``v4_alias_keys`` 로 보존하여 ``_resolve_v4_section_key`` 가 alias 경로로 - 매칭한다. canonical ordinal id 는 frontend drag/drop override 와 동일 - schema (`section_id-sub-N`). + Default behaviour (V4-driven granularity, backward compatible) : + - V4 has section_id exact key -> keep section unchanged (parent + granularity rendering, parent-level V4 evidence applies). + - V4 missing + H3 sub-sections -> drill into sub-sections, emit + canonical ids ``${section_id}-sub-${ordinal}`` with optional + decimal alias for legacy V4 keys (e.g. ``04-2.1``). + - V4 missing + no H3 -> pass through (downstream V4 lookup + will naturally abort with no_v4_section). - N-R5 alias guard : heading_number 가 decimal (``2.1``) 일 때만 alias - emit. integer-only (``1``) / non-numeric heading 은 alias 0 — sibling - parent V4 evidence 로 잘못 promote 되는 collision 방지 (RULE 0). + IMP-08 B-3 / Stage 5 R2 blocker-fix — ``override_target_section_ids`` + is the list of section ids that drag/drop override CLI flags target. + When any override target matches ``${section_id}-sub-N`` for a section + whose parent is otherwise V4-aligned, that section is force-drilled so + sub-section ids become addressable. This keeps the default rendering + path on V4 granularity while making drag/drop deterministic regardless + of whether V4 carries a parent exact key. - 각 section 에 대해 : - - V4 에 section.section_id 키 있음 → 그대로 유지 (## level 매칭) - - V4 에 키 없고 raw_content 에 ### sub-section 존재 → ### 로 drill - - V4 에 키 없고 ### 도 없음 → 원본 그대로 (V4 lookup 단계에서 자연스럽게 abort) + Each drilled sub-section carries : + - heading_number : decimal "2.1" / integer "1" / None (bare H3 title). + - v4_alias_keys : legacy V4 keys to try when the canonical ordinal + id misses. Populated only when ``heading_number`` matches the + decimal pattern ``\\d+\\.\\d+`` (N-R5 guard) — integer-only or + bare H3 produces no alias to avoid sibling-parent V4 collisions. - 설계 원칙 : - - parser (parse_mdx) = MDX 만 앎 (V4 무관) - - aligner (이 함수) = V4 키 기준 granularity 결정 - - runtime parser 가 matching artifact 의 granularity 를 *따라가는* 구조 + Design boundary : + - parser (``parse_mdx``) = MDX-only knowledge (V4-agnostic). + - aligner (this function) = canonical sub-id schema, MDX-driven on + force_drill, V4-driven otherwise. + - resolver (``_resolve_v4_section_key``) = exact > alias > None, + never auto-promotes to parent/sibling (axis 7 hybrid lock). """ v4_keys = set(v4.get("mdx_sections", {}).keys()) + + # Build the set of parent ids whose sub-ids are explicitly targeted by + # an override. These sections must be drilled even if V4 also carries + # the parent key exactly. Parents derived from canonical "X-sub-N" ids + # only — non-sub ids (top-level overrides) do not trigger drilling. + force_drill_parents: set[str] = set() + if override_target_section_ids: + for sid in override_target_section_ids: + parent = derive_parent_id(sid) + if parent and sid != parent: + force_drill_parents.add(parent) + aligned: list[MdxSection] = [] - # IMP-08 B-3 : capture optional heading-number prefix (decimal "2.1" or - # integer "1") + heading title. None group = bare "### Title". + # Capture optional heading-number prefix (decimal "2.1" or integer "1") + # plus the heading title. None group = bare "### Title". sub_pattern = re.compile( r"^###\s+(?:(\d+(?:\.\d+)?)\s+)?(.+?)$", re.MULTILINE ) decimal_re = re.compile(r"\d+\.\d+") for section in sections: - if section.section_id in v4_keys: + force_drill = section.section_id in force_drill_parents + if section.section_id in v4_keys and not force_drill: + # V4 carries this section exactly and no override targets a + # sub-id under it: keep parent granularity (backward compat). aligned.append(section) continue sub_matches = list(sub_pattern.finditer(section.raw_content)) if not sub_matches: - aligned.append(section) # drill 불가, V4 lookup 에서 abort 됨 + # No H3 sub-sections: cannot drill. Pass section through; + # downstream V4 lookup aborts with no_v4_section when needed. + aligned.append(section) continue mdx_id = section.section_id.split("-")[0] # e.g., "04" @@ -530,7 +585,7 @@ def lookup_v4_match_with_fallback( section_id: str, *, raw_content: Optional[str] = None, - max_rank: int = 3, + max_rank: Optional[int] = None, alias_keys: Optional[list] = None, ) -> tuple[Optional[V4Match], dict]: """Select V4 rank-1, or promote rank-2/3 when rank-1 is not auto-renderable. @@ -538,6 +593,13 @@ def lookup_v4_match_with_fallback( This is an IMP-05 selector only. It uses existing V4 labels, frame-contract presence, and the Phase Z capacity precheck; it does not call calculate_fit. """ + # 2026-05-14 — max_rank env toggle PHASE_Z_MAX_RANK (default 3). + # 보고용 : 등록 frame rank 가 4+ 인 경우 (예: mdx05-2 의 rank 10) 도 통과시킴. + if max_rank is None: + try: + max_rank = int(os.environ.get("PHASE_Z_MAX_RANK", "3")) + except ValueError: + max_rank = 3 resolved = _resolve_v4_section_key(v4, section_id, alias_keys=alias_keys) sec = v4.get("mdx_sections", {}).get(resolved) if resolved else None trace = { @@ -556,7 +618,20 @@ def lookup_v4_match_with_fallback( trace["fallback_reason"] = "no_v4_section" return None, trace - judgments = (sec.get("judgments_full32") or [])[:max_rank] + # 2026-05-14 — fallback chain sort = label priority + confidence (frontend 와 동일). + # 사용자 룰 : "reject 외 다른 label 있으면 reject 는 ranking 상단 X". + # judgments_full32 는 confidence desc only. 그대로 iterate 시 reject (conf 높은) 가 + # light_edit (conf 낮은) 보다 먼저 선택될 수 있음. label priority 우선 정렬. + _LABEL_PRIORITY = {"use_as_is": 0, "light_edit": 1, "restructure": 2, "reject": 3} + all_judgments = sec.get("judgments_full32") or [] + judgments_sorted = sorted( + all_judgments, + key=lambda j: ( + _LABEL_PRIORITY.get(j.get("label"), 99), + -float(j.get("confidence") or 0), + ), + ) + judgments = judgments_sorted[:max_rank] if not judgments: trace["fallback_reason"] = "empty_v4_judgments" return None, trace @@ -822,14 +897,19 @@ def build_layout_css(layout_preset: str, zones_data: list[dict], # ── Step D-ext : user override 처리 ── if override_zone_geometries: if layout_preset == "horizontal-2": - # heights_px override — zone 의 h 비율로 SLIDE_BODY_HEIGHT 분배. + # heights_px override — zone 의 h 비율로 (SLIDE_BODY_HEIGHT - gap) 분배. + # 2026-05-14 BUGFIX (Axis A) — 원래 SLIDE_BODY_HEIGHT 만 사용해서 zone + # heights 합 + gap 이 slide-body 보다 +gap px overflow. gap 빼고 + # 분배 (compute_zone_layout 의 normal path 와 동일 logic). ratios = [] for pos in positions: geom = override_zone_geometries.get(pos) ratios.append(float(geom["h"]) if geom else 0.0) total = sum(ratios) if total > 0: - heights_px = [int(round(r / total * SLIDE_BODY_HEIGHT)) for r in ratios] + n = len(ratios) + available = SLIDE_BODY_HEIGHT - gap * (n - 1) + heights_px = [int(round(r / total * available)) for r in ratios] rows = " ".join(f"{h}px" for h in heights_px) return { "areas": preset["css_areas"], @@ -1390,7 +1470,13 @@ def render_slide(slide_title: str, slide_footer: Optional[str], zone["partial_html"] = "" continue partial = env.get_template(f"families/{zone['template_id']}.html") - zone["partial_html"] = partial.render(slot_payload=zone["slot_payload"]) + # 2026-05-14 — partial 에 assets_dir 전달. figma asset PNG/SVG 참조 가능. + # assets_dir = "assets/" (run-relative). final.html 의 + # 상대 path 와 matching — frontend `/data/runs/.../assets/...` serve. + zone["partial_html"] = partial.render( + slot_payload=zone["slot_payload"], + assets_dir=zone.get("assets_dir") or "", + ) base = env.get_template("slide_base.html") return base.render( @@ -2076,8 +2162,21 @@ def run_phase_z2_mvp1( # 2. Load V4 v4 = load_v4_result() - # 3. Align sections to V4 granularity (### drill if needed) - sections = align_sections_to_v4_granularity(sections, v4) + # 3. Align sections to V4 granularity (### drill if needed). + # IMP-08 B-3 / Stage 5 R2 : forward override target ids so sub-id + # drag/drop targets force-drill their parent section even when V4 + # carries the parent exact key (deterministic drag/drop addressing). + _override_target_sids: list[str] = [] + if override_section_assignments: + for _sids in override_section_assignments.values(): + for _sid in _sids: + if isinstance(_sid, str) and _sid: + _override_target_sids.append(_sid) + sections = align_sections_to_v4_granularity( + sections, + v4, + override_target_section_ids=_override_target_sids or None, + ) print(f" aligned : sections={len(sections)} ({[s.section_id for s in sections]})") # ─── Step 5: V4 매칭 evidence (non-reject max-6 후보 list — 사용자 lock 2026-05-08) ─── @@ -2131,11 +2230,12 @@ def run_phase_z2_mvp1( v4_fallback_traces: dict[str, dict] = {} def lookup_fn(sid: str) -> Optional[V4Match]: + # max_rank None → lookup_v4_match_with_fallback 가 PHASE_Z_MAX_RANK env (default 3) 사용. match, trace = lookup_v4_match_with_fallback( v4, sid, raw_content=section_content_by_id.get(sid), - max_rank=3, + max_rank=None, alias_keys=section_alias_by_id.get(sid), ) v4_fallback_traces[sid] = trace @@ -2643,6 +2743,10 @@ def run_phase_z2_mvp1( "slot_payload": slot_payload, "content_weight": content_weight, "min_height_px": min_height_px, + # 2026-05-14 — partial.render() 가 assets_dir 을 zone.get() 으로 읽으므로 + # zones_data 에도 포함해야 figma asset PNG 경로가 final.html 에 박힘. + # as_posix() — Windows 에서 str(Path) 는 backslash 라 url() 에서 404. + "assets_dir": assets_dir.relative_to(run_dir).as_posix() if assets_dir else None, "assignment_source": plan_assignment_source, "section_assignment_override": plan_section_override, }) @@ -2671,7 +2775,7 @@ def run_phase_z2_mvp1( "min_height_px": min_height_px, "slot_payload_keys": sorted(slot_payload.keys()), "content_truncated_count": truncated_count, # None / N (builder 가 N 개 자름) - "assets_dir": str(assets_dir.relative_to(run_dir)) if assets_dir else None, + "assets_dir": assets_dir.relative_to(run_dir).as_posix() if assets_dir else None, "content_weight": content_weight, # trace-only runtime 연결 v0 — B1 → B2 → B4 chain 결과 (render 미영향). "placement_trace": placement_trace, @@ -2871,7 +2975,7 @@ def run_phase_z2_mvp1( # reporting only. Runtime selection goes through _resolve_v4_section_key # (4 sites). Direct dict lookup here is intentional — debug_zones carries # dict-shape entries without v4_alias_keys plumbing, and a miss here only - # yields a "V4 entry 없음" report line (runtime impact zero). + # yields a "V4 entry missing" report line (runtime impact zero). try: with open(V4_RESULT_PATH, encoding="utf-8") as _vf: _v4_full = yaml.safe_load(_vf) diff --git a/tests/test_phase_z2_subsection_schema.py b/tests/test_phase_z2_subsection_schema.py index 0955b68..ae96a3e 100644 --- a/tests/test_phase_z2_subsection_schema.py +++ b/tests/test_phase_z2_subsection_schema.py @@ -111,7 +111,9 @@ def test_mdx_section_default_construction_preserves_4_positional_callers(): def test_align_passthrough_when_v4_key_exact_match(): - # Section already aligned to V4 key — aligner keeps it untouched. + # Section already aligned to V4 key (no H3 sub-sections, no override + # target): aligner keeps it untouched. Parent-level V4 evidence + # flows via exact-match lookup. sections = [_section("04-1", 1, "1. Top", "body")] v4 = {"mdx_sections": {"04-1": {"judgments_full32": []}}} out = align_sections_to_v4_granularity(sections, v4) @@ -119,6 +121,63 @@ def test_align_passthrough_when_v4_key_exact_match(): assert out[0].section_id == "04-1" +def test_align_parent_v4_exact_keeps_section_when_no_override_targets_sub(): + # Backward-compat axis: when V4 carries the parent exact key and no + # drag/drop override targets a sub-id of this section, the aligner + # MUST keep the parent (preserves V4 evidence at parent granularity). + raw = "### 2.1 First\nbody1\n### 2.2 Second\nbody2\n" + sections = [_section("03-2", 2, "2. Parent", raw)] + v4 = {"mdx_sections": {"03-2": {"judgments_full32": []}}} + out = align_sections_to_v4_granularity(sections, v4) + assert [s.section_id for s in out] == ["03-2"] + + +def test_align_force_drills_when_override_targets_sub_id_with_parent_in_v4(): + # Stage 5 R2 blocker-fix regression: when V4 has the parent exact key + # AND an override targets a sub-id of that section, the aligner MUST + # drill regardless of V4 parent presence. This makes drag/drop + # addressing deterministic across all V4 yaml shapes. + raw = "### 2.1 First\nbody1\n### 2.2 Second\nbody2\n" + sections = [_section("04-2", 2, "2. Parent", raw)] + v4 = { + "mdx_sections": { + "04-2": {"judgments_full32": []}, # parent V4 entry present + "04-2.1": {"judgments_full32": []}, # plus decimal sub entries + "04-2.2": {"judgments_full32": []}, + } + } + out = align_sections_to_v4_granularity( + sections, v4, override_target_section_ids=["04-2-sub-1"] + ) + # Force-drill: parent id MUST be replaced by canonical sub-ids. + assert [s.section_id for s in out] == ["04-2-sub-1", "04-2-sub-2"] + # Decimal aliases preserved (N-R5: decimal heading_number). + assert out[0].v4_alias_keys == ["04-2.1"] + assert out[1].v4_alias_keys == ["04-2.2"] + + +def test_align_top_level_override_target_does_not_force_drill_other_sections(): + # Top-level override target ("primary=03-1") has no derive_parent_id, + # so it MUST NOT force-drill any section. Only "X-sub-N" targets + # trigger force-drill on parent X. + raw = "### 2.1 First\nbody1\n" + sections = [ + _section("03-1", 1, "1. Top", "body"), + _section("03-2", 2, "2. Parent", raw), + ] + v4 = { + "mdx_sections": { + "03-1": {"judgments_full32": []}, + "03-2": {"judgments_full32": []}, + } + } + out = align_sections_to_v4_granularity( + sections, v4, override_target_section_ids=["03-1"] + ) + # No sub-id target -> both sections kept at parent granularity. + assert [s.section_id for s in out] == ["03-1", "03-2"] + + def test_align_drill_emits_canonical_ordinal_id_with_decimal_alias(): # Decimal H3 headings -> canonical ordinal id + decimal alias (legacy V4 key). raw = "### 2.1 First\nbody1\n### 2.2 Second\nbody2\n"