wip: phase_z2 evidence 파이프라인 + matching 실험(phase2~26) + 프론트 trace 패널 진행분 스냅샷

- src: phase_z2 composition/mapper/pipeline/placement_planner/retry, ai_fallback(prompts/schema/validate), mdx_text_atoms 신규
- Front: PipelineTracePanel 신규, FramePanel/SlideCanvas/Home/designAgentApi 등 갱신 + 테스트 4종 추가
- templates/phase_z2: catalog(component_expansion_registry, node_slot_mapping 신규), frames, families, slide_base 갱신
- tests/matching: phase2~26 매칭 실험 스크립트·리포트·온톨로지 전체 (미커밋 진행분)
- tests: b4_v4 evidence, task5~28.5 시리즈, regression(imp95 baseline) 등 신규 테스트 대량 추가
- docs/reference: MDX 구조 인벤토리, MDX→Frame 구조 계약 문서
- scripts: mdx 계약/parity/coverage/viewport 체크, gitea comment, run sync 유틸
- .gitignore: tmp*.json, chromedriver, .orchestrator, *.pkl, Front_test* 등 임시/스냅샷 제외

미완성 작업의 보존용 스냅샷 커밋 (2026-07-02)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-07-02 17:03:42 +09:00
co-authored by Claude Opus 4.8
parent 97b7833a1b
commit b836e79ee1
527 changed files with 673036 additions and 717 deletions
+170
View File
@@ -0,0 +1,170 @@
# Structure Intent Diagnostic — 점수 통합 전 검수
**목적**: `structure_intent` 추론이 사람 직관과 맞는지 확인. 맞으면 Phase 24/25 점수에 통합 진입.
**범위**: 11 문제 frame 에만 intent 태깅. 나머지 21 frames 은 `neutral 0.5` 처리.
대상 11 frames: 13, 14, 17, 18, 20, 23, 24, 28, 29, 30, 31
**정의된 intent 종류** (10): category_comparison, concept_comparison, industry_comparison, multi_attribute_comparison, persona_benefit, problem_diagnosis, process_product_split, requirement_list, requirement_or_pillar, transformation_story
## MDX01-2 — BIM vs DX 다면 비교
- **정답 Frame**: `18`
- **MDX detected_intents**: `['concept_comparison', 'multi_attribute_comparison']`
- **MDX item_count**: 2
- **MDX relation_type**: compare
| 순위 | sid | template_id | frame_intents | compat | 비고 |
|-----|-----|-------------|---------------|--------|------|
| 1 | 18 | bim_dx_comparison_table | concept_comparison, multi_attribute_comparison | **1.00** | 🎯 정답 |
| 2 | 23 | app_sw_package_vs_solution | concept_comparison, multi_attribute_comparison | **1.00** | |
| 3 | 24 | engn_sw_three_types | category_comparison, multi_attribute_comparison | **1.00** | |
| 4 | 30 | industry_current_status_three_ | industry_comparison, multi_attribute_comparison | **1.00** | |
| 5 | 31 | industry_characteristics_three | industry_comparison, multi_attribute_comparison | **1.00** | |
| 6 | 21 | solution_engn_split_diagram | _(미태깅, neutral)_ | 0.50 | |
| 7 | 25 | commercial_sw_four_categories | _(미태깅, neutral)_ | 0.50 | |
| 8 | 26 | sw_dependency_four_problems | _(미태깅, neutral)_ | 0.50 | |
| 9 | 19 | design_method_distortion_three | _(미태깅, neutral)_ | 0.50 | |
| 10 | 27 | bim_adoption_central_split | _(미태깅, neutral)_ | 0.50 | |
| 11 | 12 | construction_goals_three_circl | _(미태깅, neutral)_ | 0.50 | |
| 12 | 15 | policy_goals_plus_execution_re | _(미태깅, neutral)_ | 0.50 | |
**하위 5개 (intent 불일치 확인용)**:
| 순위 | sid | template_id | frame_intents | compat |
|-----|-----|-------------|---------------|--------|
| 28 | 13 | three_parallel_requirements | requirement_list | 0.30 |
| 29 | 20 | dx_sw_necessity_three_perspect | requirement_or_pillar | 0.30 |
| 30 | 28 | sw_reality_three_emphasis | problem_diagnosis | 0.25 |
| 31 | 17 | bim_current_problems_paired | problem_diagnosis | 0.25 |
| 32 | 29 | process_product_two_way | process_product_split, transformation_story | 0.20 |
**🔎 문제 후보 진단**:
- Frame 29 `process_product_two_way`: intent=[process_product_split, transformation_story], compat=0.20 ✓ 낮음 (정상)
---
## MDX02 — 주체별 기대효과
- **정답 Frame**: `14`
- **MDX detected_intents**: `['persona_benefit']`
- **MDX item_count**: 3
- **MDX relation_type**: parallel
| 순위 | sid | template_id | frame_intents | compat | 비고 |
|-----|-----|-------------|---------------|--------|------|
| 1 | 14 | three_persona_benefits | persona_benefit | **1.00** | 🎯 정답 |
| 2 | 21 | solution_engn_split_diagram | _(미태깅, neutral)_ | 0.50 | |
| 3 | 25 | commercial_sw_four_categories | _(미태깅, neutral)_ | 0.50 | |
| 4 | 26 | sw_dependency_four_problems | _(미태깅, neutral)_ | 0.50 | |
| 5 | 19 | design_method_distortion_three | _(미태깅, neutral)_ | 0.50 | |
| 6 | 27 | bim_adoption_central_split | _(미태깅, neutral)_ | 0.50 | |
| 7 | 12 | construction_goals_three_circl | _(미태깅, neutral)_ | 0.50 | |
| 8 | 15 | policy_goals_plus_execution_re | _(미태깅, neutral)_ | 0.50 | |
| 9 | 32 | policy_achievement_five_goals | _(미태깅, neutral)_ | 0.50 | |
| 10 | 01 | sw_development_cycle_six_nodes | _(미태깅, neutral)_ | 0.50 | |
| 11 | 04 | domestic_bim_actor_relations | _(미태깅, neutral)_ | 0.50 | |
| 12 | 06 | compensation_complaint_map | _(미태깅, neutral)_ | 0.50 | |
**하위 5개 (intent 불일치 확인용)**:
| 순위 | sid | template_id | frame_intents | compat |
|-----|-----|-------------|---------------|--------|
| 28 | 31 | industry_characteristics_three | industry_comparison, multi_attribute_comparison | 0.40 |
| 29 | 13 | three_parallel_requirements | requirement_list | 0.30 |
| 30 | 29 | process_product_two_way | process_product_split, transformation_story | 0.30 |
| 31 | 28 | sw_reality_three_emphasis | problem_diagnosis | 0.20 |
| 32 | 17 | bim_current_problems_paired | problem_diagnosis | 0.20 |
**🔎 문제 후보 진단**:
- Frame 21 `solution_engn_split_diagram`: intent=[_(미태깅)_], compat=0.50 ⚠️ 높음 (문제)
---
## MDX03-1 — DX 필수요건 3요소
- **정답 Frame**: `13`
- **MDX detected_intents**: `['requirement_list']`
- **MDX item_count**: 3
- **MDX relation_type**: parallel
| 순위 | sid | template_id | frame_intents | compat | 비고 |
|-----|-----|-------------|---------------|--------|------|
| 1 | 13 | three_parallel_requirements | requirement_list | **1.00** | 🎯 정답 |
| 2 | 20 | dx_sw_necessity_three_perspect | requirement_or_pillar | **0.70** | |
| 3 | 21 | solution_engn_split_diagram | _(미태깅, neutral)_ | 0.50 | |
| 4 | 25 | commercial_sw_four_categories | _(미태깅, neutral)_ | 0.50 | |
| 5 | 26 | sw_dependency_four_problems | _(미태깅, neutral)_ | 0.50 | |
| 6 | 19 | design_method_distortion_three | _(미태깅, neutral)_ | 0.50 | |
| 7 | 27 | bim_adoption_central_split | _(미태깅, neutral)_ | 0.50 | |
| 8 | 12 | construction_goals_three_circl | _(미태깅, neutral)_ | 0.50 | |
| 9 | 15 | policy_goals_plus_execution_re | _(미태깅, neutral)_ | 0.50 | |
| 10 | 32 | policy_achievement_five_goals | _(미태깅, neutral)_ | 0.50 | |
| 11 | 01 | sw_development_cycle_six_nodes | _(미태깅, neutral)_ | 0.50 | |
| 12 | 04 | domestic_bim_actor_relations | _(미태깅, neutral)_ | 0.50 | |
**하위 5개 (intent 불일치 확인용)**:
| 순위 | sid | template_id | frame_intents | compat |
|-----|-----|-------------|---------------|--------|
| 28 | 30 | industry_current_status_three_ | industry_comparison, multi_attribute_comparison | 0.30 |
| 29 | 31 | industry_characteristics_three | industry_comparison, multi_attribute_comparison | 0.30 |
| 30 | 29 | process_product_two_way | process_product_split, transformation_story | 0.20 |
| 31 | 28 | sw_reality_three_emphasis | problem_diagnosis | 0.15 |
| 32 | 17 | bim_current_problems_paired | problem_diagnosis | 0.15 |
**🔎 문제 후보 진단**:
- Frame 28 `sw_reality_three_emphasis`: intent=[problem_diagnosis], compat=0.15 ✓ 낮음 (정상)
---
## MDX03-2 — 과정/결과 혁신
- **정답 Frame**: `29`
- **MDX detected_intents**: `['process_product_split', 'transformation_story']`
- **MDX item_count**: 2
- **MDX relation_type**: compare
| 순위 | sid | template_id | frame_intents | compat | 비고 |
|-----|-----|-------------|---------------|--------|------|
| 1 | 29 | process_product_two_way | process_product_split, transformation_story | **1.00** | 🎯 정답 |
| 2 | 21 | solution_engn_split_diagram | _(미태깅, neutral)_ | 0.50 | |
| 3 | 25 | commercial_sw_four_categories | _(미태깅, neutral)_ | 0.50 | |
| 4 | 26 | sw_dependency_four_problems | _(미태깅, neutral)_ | 0.50 | |
| 5 | 19 | design_method_distortion_three | _(미태깅, neutral)_ | 0.50 | |
| 6 | 27 | bim_adoption_central_split | _(미태깅, neutral)_ | 0.50 | |
| 7 | 12 | construction_goals_three_circl | _(미태깅, neutral)_ | 0.50 | |
| 8 | 15 | policy_goals_plus_execution_re | _(미태깅, neutral)_ | 0.50 | |
| 9 | 32 | policy_achievement_five_goals | _(미태깅, neutral)_ | 0.50 | |
| 10 | 01 | sw_development_cycle_six_nodes | _(미태깅, neutral)_ | 0.50 | |
| 11 | 04 | domestic_bim_actor_relations | _(미태깅, neutral)_ | 0.50 | |
| 12 | 06 | compensation_complaint_map | _(미태깅, neutral)_ | 0.50 | |
**하위 5개 (intent 불일치 확인용)**:
| 순위 | sid | template_id | frame_intents | compat |
|-----|-----|-------------|---------------|--------|
| 28 | 13 | three_parallel_requirements | requirement_list | 0.20 |
| 29 | 18 | bim_dx_comparison_table | concept_comparison, multi_attribute_comparison | 0.20 |
| 30 | 23 | app_sw_package_vs_solution | concept_comparison, multi_attribute_comparison | 0.20 |
| 31 | 28 | sw_reality_three_emphasis | problem_diagnosis | 0.15 |
| 32 | 17 | bim_current_problems_paired | problem_diagnosis | 0.15 |
**🔎 문제 후보 진단**:
- Frame 18 `bim_dx_comparison_table`: intent=[concept_comparison, multi_attribute_comparison], compat=0.20 ✓ 낮음 (정상)
---
## 검수 가이드
1. **정답 Frame 이 상위에 있는가** — compat ≥ 0.8 예상
2. **문제 후보 (MDX01-2×29, MDX03-1×28, MDX03-2×18) 가 0.4 이하인가** — 낮으면 의도대로 intent 가 걸러냄
3. **MDX detected_intents 가 자연스러운가** — AI 추론 결과 검토
4. **미태깅 frame (neutral 0.5) 이 정답보다 위에 오는가** — 있으면 부분 적용 한계 = 추가 태깅 필요
모두 통과하면 → Phase 24/25 점수 통합 진입.