diff --git a/.github/workflows/multi-mdx-regression.yml b/.github/workflows/multi-mdx-regression.yml
new file mode 100644
index 0000000..1213ab1
--- /dev/null
+++ b/.github/workflows/multi-mdx-regression.yml
@@ -0,0 +1,71 @@
+name: Multi-MDX Regression (IMP-91)
+
+# IMP-#91 u13 — auto-gate the mdx 01-05 acceptance set on every push to main
+# and on PRs targeting main. Failure of any integration test blocks the
+# commit. JSON report is emitted via pytest-json-report (u12 dep) and
+# uploaded as an artifact for u14/u15 status-board updater consumption.
+#
+# [[feedback_validation_first_for_closed_issues]] — fresh subprocess per CI run.
+# [[feedback_auto_pipeline_first]] — no manual review queue; deterministic gate.
+
+on:
+ push:
+ branches: [main]
+ pull_request:
+ branches: [main]
+
+jobs:
+ multi-mdx-regression:
+ runs-on: ubuntu-latest
+ timeout-minutes: 30
+ steps:
+ - name: Checkout
+ uses: actions/checkout@v4
+
+ - name: Set up Python 3.11
+ uses: actions/setup-python@v5
+ with:
+ python-version: "3.11"
+ cache: pip
+
+ - name: Install Chrome and ChromeDriver
+ uses: browser-actions/setup-chrome@v1
+ with:
+ install-chromedriver: true
+
+ - name: Install project (dev extras + selenium)
+ run: |
+ python -m pip install --upgrade pip
+ python -m pip install -e ".[dev]"
+ python -m pip install "selenium>=4.20"
+
+ - name: Run multi-mdx regression tests
+ run: |
+ python -m pytest -q -m integration \
+ tests/integration/test_multi_mdx_regression.py \
+ --json-report \
+ --json-report-file=imp91-report.json \
+ --json-report-omit keywords streams
+
+ - name: Upload pytest JSON report
+ if: always()
+ uses: actions/upload-artifact@v4
+ with:
+ name: imp91-multi-mdx-report
+ path: imp91-report.json
+ if-no-files-found: warn
+
+ - name: Update status-board markers (IMP-91 u15)
+ if: always()
+ run: |
+ python scripts/update_status_board.py \
+ --report imp91-report.json \
+ --board docs/architecture/PHASE-Z-PIPELINE-STATUS-BOARD.md
+
+ - name: Upload updated status board
+ if: always()
+ uses: actions/upload-artifact@v4
+ with:
+ name: imp91-status-board
+ path: docs/architecture/PHASE-Z-PIPELINE-STATUS-BOARD.md
+ if-no-files-found: warn
diff --git a/docs/architecture/PHASE-Z-PIPELINE-STATUS-BOARD.md b/docs/architecture/PHASE-Z-PIPELINE-STATUS-BOARD.md
index 4835c21..22aab12 100644
--- a/docs/architecture/PHASE-Z-PIPELINE-STATUS-BOARD.md
+++ b/docs/architecture/PHASE-Z-PIPELINE-STATUS-BOARD.md
@@ -167,6 +167,21 @@ Step 0 (사전 준비) 의 Figma → HTML 변환은 *precondition phase 의 작
---
+## 7. Multi-MDX regression markers (IMP-91)
+
+> CI workflow `.github/workflows/multi-mdx-regression.yml` rewrites these via `scripts/update_status_board.py` after each push / PR. Initial value `?` = not yet observed. `PASS` / `FAIL` / `ERR` / `SKIP` = last CI run outcome per axis × mdx. Untouched markers remain `?` so collection failures are loud, not silent.
+
+| axis | mdx 01 | mdx 02 | mdx 03 | mdx 04 | mdx 05 |
+|---|---|---|---|---|---|
+| F0 normalize | ? | ? | ? | ? | ? |
+| F1 V4 ranking | ? | ? | ? | ? | ? |
+| F2 slot_payload | ? | ? | ? | ? | ? |
+| F3 classifier-only AI | ? | ? | ? | ? | ? |
+| F4 layout | ? | ? | ? | ? | ? |
+| F5 final.html | ? | ? | ? | ? | ? |
+
+---
+
## 사용 방법
- 새 작업 들어오면 → 본 board 의 *어느 step* 의 status 를 바꾸는 작업인지 식별
diff --git a/pyproject.toml b/pyproject.toml
index ddf1ff8..494a5cf 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -22,6 +22,7 @@ dependencies = [
dev = [
"pytest>=8.0",
"pytest-asyncio>=0.24",
+ "pytest-json-report>=1.5",
"ruff>=0.8",
]
diff --git a/scripts/update_status_board.py b/scripts/update_status_board.py
new file mode 100644
index 0000000..cc2bc69
--- /dev/null
+++ b/scripts/update_status_board.py
@@ -0,0 +1,75 @@
+"""IMP-#91 u14 — idempotent status-board marker updater.
+
+Reads a pytest-json-report artifact emitted by the IMP-91 CI workflow and
+rewrites paired ``...`` markers
+inside the Phase Z status board with a single-character outcome symbol.
+
+Pure functions (``parse_outcomes`` / ``update_board_text``) are exposed so
+``tests/scripts/test_update_status_board.py`` can exercise the contract
+without invoking pytest. The CLI just wires file IO around them so the
+GitHub Actions step in u15 can call it deterministically. The updater is
+additive: untouched markers stay; missing outcomes render ``?`` so a
+collection failure is loud, not silent. [[feedback_auto_pipeline_first]]
+[[feedback_artifact_status_naming]]
+"""
+from __future__ import annotations
+
+import argparse
+import json
+import re
+from pathlib import Path
+from typing import Dict, Mapping, Tuple
+
+AXIS_FROM_TEST = {
+ "test_normalize_snapshot_matches": "F0",
+ "test_v4_ranking_snapshot_matches": "F1",
+ "test_slot_payload_snapshot_matches": "F2",
+ "test_ai_classifier_snapshot_matches": "F3",
+ "test_layout_snapshot_matches": "F4",
+ "test_final_html_snapshot_matches": "F5",
+}
+SYMBOL = {"passed": "PASS", "failed": "FAIL", "error": "ERR", "skipped": "SKIP"}
+NODEID_RE = re.compile(r"::(test_[a-z0-9_]+)\[(\d{2})\]$")
+MARKER_RE = re.compile(
+ r"()(.*?)()", re.DOTALL
+)
+
+
+def parse_outcomes(report: Mapping[str, object]) -> Dict[Tuple[str, str], str]:
+ out: Dict[Tuple[str, str], str] = {}
+ for test in report.get("tests", []) or []:
+ m = NODEID_RE.search(str(test.get("nodeid", "")))
+ if not m:
+ continue
+ axis = AXIS_FROM_TEST.get(m.group(1))
+ if not axis:
+ continue
+ out[(axis, m.group(2))] = SYMBOL.get(str(test.get("outcome")), "?")
+ return out
+
+
+def update_board_text(board: str, outcomes: Mapping[Tuple[str, str], str]) -> str:
+ def repl(match: "re.Match[str]") -> str:
+ key = (match.group(2), match.group(3))
+ symbol = outcomes.get(key, "?")
+ return f"{match.group(1)}{symbol}{match.group(5)}"
+
+ return MARKER_RE.sub(repl, board)
+
+
+def main() -> int:
+ parser = argparse.ArgumentParser(description="IMP-91 status-board updater")
+ parser.add_argument("--report", required=True, type=Path)
+ parser.add_argument("--board", required=True, type=Path)
+ args = parser.parse_args()
+ report = json.loads(args.report.read_text(encoding="utf-8"))
+ outcomes = parse_outcomes(report)
+ args.board.write_text(
+ update_board_text(args.board.read_text(encoding="utf-8"), outcomes),
+ encoding="utf-8",
+ )
+ return 0
+
+
+if __name__ == "__main__":
+ raise SystemExit(main())
diff --git a/tests/integration/__init__.py b/tests/integration/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/integration/__snapshots__/ai_classifier.json b/tests/integration/__snapshots__/ai_classifier.json
new file mode 100644
index 0000000..17434ea
--- /dev/null
+++ b/tests/integration/__snapshots__/ai_classifier.json
@@ -0,0 +1,73 @@
+{
+ "_doc": "IMP-91 u9 — F3 classifier-only AI axis. Pin observed step12 per-unit classifier label / route_hint / AI-isolation flags + coverage_invariant + step15 fit_classification + step16 router_active + step18 failure_type. Default-OFF AI invariant ([[feedback_ai_isolation_contract]]): ai_called MUST be False for every unit unless AI_FALLBACK_ENABLED is flipped via .env (not via pipeline default). If any unit flips ai_called=True silently, this snapshot fails loudly per [[feedback_demo_env_toggle_policy]].",
+ "01": {
+ "units": [
+ {"source_section_ids": ["01-2"], "label": "use_as_is", "route_hint": "direct_render", "provisional": false, "ai_called": false, "skip_reason": "not_provisional", "apply_status": "no_proposal"},
+ {"source_section_ids": ["01-1"], "label": "use_as_is", "route_hint": "direct_render", "provisional": false, "ai_called": false, "skip_reason": "not_provisional", "apply_status": "no_proposal"}
+ ],
+ "coverage_invariant_status": "ok",
+ "fit_visual_check_passed": true,
+ "fit_classifications_count": 0,
+ "fit_categories_seen": [],
+ "router_active": false,
+ "router_routed_count": 0,
+ "router_v4_fallback_used_count": 0,
+ "failure_type": "not_attempted"
+ },
+ "02": {
+ "units": [
+ {"source_section_ids": ["02-1"], "label": "use_as_is", "route_hint": "direct_render", "provisional": false, "ai_called": false, "skip_reason": "not_provisional", "apply_status": "no_proposal"},
+ {"source_section_ids": ["02-2-sub-1", "02-2-sub-2"], "label": "use_as_is", "route_hint": "direct_render", "provisional": true, "ai_called": false, "skip_reason": "route_not_ai_adaptation:direct_render", "apply_status": "no_proposal"}
+ ],
+ "coverage_invariant_status": "ok",
+ "fit_visual_check_passed": true,
+ "fit_classifications_count": 0,
+ "fit_categories_seen": [],
+ "router_active": false,
+ "router_routed_count": 0,
+ "router_v4_fallback_used_count": 0,
+ "failure_type": "not_attempted"
+ },
+ "03": {
+ "units": [
+ {"source_section_ids": ["03-1"], "label": "use_as_is", "route_hint": "direct_render", "provisional": false, "ai_called": false, "skip_reason": "not_provisional", "apply_status": "no_proposal"},
+ {"source_section_ids": ["03-2"], "label": "use_as_is", "route_hint": "direct_render", "provisional": false, "ai_called": false, "skip_reason": "not_provisional", "apply_status": "no_proposal"}
+ ],
+ "coverage_invariant_status": "ok",
+ "fit_visual_check_passed": true,
+ "fit_classifications_count": 0,
+ "fit_categories_seen": [],
+ "router_active": false,
+ "router_routed_count": 0,
+ "router_v4_fallback_used_count": 0,
+ "failure_type": "not_attempted"
+ },
+ "04": {
+ "units": [
+ {"source_section_ids": ["04-2-sub-2"], "label": "light_edit", "route_hint": "deterministic_minor_adjustment", "provisional": false, "ai_called": false, "skip_reason": "not_provisional", "apply_status": "no_proposal"},
+ {"source_section_ids": ["04-2-sub-1"], "label": "restructure", "route_hint": "ai_adaptation_required", "provisional": true, "ai_called": false, "skip_reason": "router_short_circuit", "apply_status": "no_proposal"},
+ {"source_section_ids": ["04-1"], "label": "reject", "route_hint": "ai_adaptation_required", "provisional": true, "ai_called": false, "skip_reason": "router_short_circuit", "apply_status": "no_proposal"}
+ ],
+ "coverage_invariant_status": "ok",
+ "fit_visual_check_passed": true,
+ "fit_classifications_count": 0,
+ "fit_categories_seen": [],
+ "router_active": false,
+ "router_routed_count": 0,
+ "router_v4_fallback_used_count": 0,
+ "failure_type": "not_attempted"
+ },
+ "05": {
+ "units": [
+ {"source_section_ids": ["05-1", "05-2-sub-1", "05-2-sub-2"], "label": "empty_shell", "route_hint": null, "provisional": true, "ai_called": false, "skip_reason": "route_not_ai_adaptation:None", "apply_status": "no_proposal"}
+ ],
+ "coverage_invariant_status": "ok",
+ "fit_visual_check_passed": true,
+ "fit_classifications_count": 0,
+ "fit_categories_seen": [],
+ "router_active": false,
+ "router_routed_count": 0,
+ "router_v4_fallback_used_count": 0,
+ "failure_type": "not_attempted"
+ }
+}
diff --git a/tests/integration/__snapshots__/coverage.json b/tests/integration/__snapshots__/coverage.json
new file mode 100644
index 0000000..dae34be
--- /dev/null
+++ b/tests/integration/__snapshots__/coverage.json
@@ -0,0 +1,43 @@
+{
+ "_doc": "IMP-#91 u5 — full_mdx_coverage / aligned_section_ids / covered_section_ids / filtered_section_ids snapshot pinned from observed step20_slide_status.json across MDX_SET (mdx 01-05). Drift = real change in coverage outcome; re-baseline only with conscious explanation in commit body.",
+ "01": {
+ "full_mdx_coverage": true,
+ "rendered": true,
+ "visual_check_passed": true,
+ "aligned_section_ids": ["01-1", "01-2"],
+ "covered_section_ids": ["01-1", "01-2"],
+ "filtered_section_ids": []
+ },
+ "02": {
+ "full_mdx_coverage": true,
+ "rendered": true,
+ "visual_check_passed": true,
+ "aligned_section_ids": ["02-1", "02-2-sub-1", "02-2-sub-2"],
+ "covered_section_ids": ["02-1", "02-2-sub-1", "02-2-sub-2"],
+ "filtered_section_ids": []
+ },
+ "03": {
+ "full_mdx_coverage": true,
+ "rendered": true,
+ "visual_check_passed": true,
+ "aligned_section_ids": ["03-1", "03-2"],
+ "covered_section_ids": ["03-1", "03-2"],
+ "filtered_section_ids": []
+ },
+ "04": {
+ "full_mdx_coverage": true,
+ "rendered": true,
+ "visual_check_passed": true,
+ "aligned_section_ids": ["04-1", "04-2-sub-1", "04-2-sub-2"],
+ "covered_section_ids": ["04-1", "04-2-sub-1", "04-2-sub-2"],
+ "filtered_section_ids": []
+ },
+ "05": {
+ "full_mdx_coverage": false,
+ "rendered": true,
+ "visual_check_passed": true,
+ "aligned_section_ids": ["05-1", "05-2-sub-1", "05-2-sub-2"],
+ "covered_section_ids": ["05-1", "05-2-sub-1", "05-2-sub-2"],
+ "filtered_section_ids": ["05-1", "05-2-sub-1", "05-2-sub-2"]
+ }
+}
diff --git a/tests/integration/__snapshots__/final_html.json b/tests/integration/__snapshots__/final_html.json
new file mode 100644
index 0000000..0ce3442
--- /dev/null
+++ b/tests/integration/__snapshots__/final_html.json
@@ -0,0 +1,88 @@
+{
+ "_doc": "IMP-91 u11 — F5 final.html extraction axis. Pin step13_render.json metadata (step_status / pipeline_path_connected / render_inputs.zones_count / render_inputs.layout_preset / slide_title|footer non-empty / final_html_size_bytes) AND structural markers extracted from the on-disk final.html (HTML , slide root count, slide-footer presence, data-zone-position/data-template-id topology). The HTML-extracted zone topology MUST match the step12 slot_payload (position, template_id) sequence already pinned in slot_payload.json (u8) — Jinja2 renders from step12, not step09, so step12 is the correct upstream parity source (step09 selection vs step12 __empty__ collapse is intentional per IMP-87 honesty gate and surfaces in u8). Drift between final.html and slot_payload = render pipeline disconnect. on-disk final.html size_bytes MUST equal step13's reported final_html_size_bytes (byte parity = no truncation / no double-write race).",
+ "01": {
+ "step13_status": "done",
+ "step13_pipeline_path_connected": true,
+ "render_inputs_zones_count": 2,
+ "render_inputs_layout_preset": "horizontal-2",
+ "render_inputs_slide_title_nonempty": true,
+ "render_inputs_slide_footer_nonempty": true,
+ "html_title_matches_render_input": true,
+ "html_slide_root_count": 1,
+ "html_slide_footer_present": true,
+ "html_zone_count": 2,
+ "html_zone_topology": [
+ {"position": "top", "template_id": "bim_dx_comparison_table"},
+ {"position": "bottom", "template_id": "construction_bim_three_usage"}
+ ],
+ "final_html_size_matches_step13_reported": true
+ },
+ "02": {
+ "step13_status": "done",
+ "step13_pipeline_path_connected": true,
+ "render_inputs_zones_count": 2,
+ "render_inputs_layout_preset": "horizontal-2",
+ "render_inputs_slide_title_nonempty": true,
+ "render_inputs_slide_footer_nonempty": true,
+ "html_title_matches_render_input": true,
+ "html_slide_root_count": 1,
+ "html_slide_footer_present": true,
+ "html_zone_count": 2,
+ "html_zone_topology": [
+ {"position": "top", "template_id": "construction_goals_three_circle_intersection"},
+ {"position": "bottom", "template_id": "__empty__"}
+ ],
+ "final_html_size_matches_step13_reported": true
+ },
+ "03": {
+ "step13_status": "done",
+ "step13_pipeline_path_connected": true,
+ "render_inputs_zones_count": 2,
+ "render_inputs_layout_preset": "vertical-2",
+ "render_inputs_slide_title_nonempty": true,
+ "render_inputs_slide_footer_nonempty": true,
+ "html_title_matches_render_input": true,
+ "html_slide_root_count": 1,
+ "html_slide_footer_present": true,
+ "html_zone_count": 2,
+ "html_zone_topology": [
+ {"position": "left", "template_id": "three_parallel_requirements"},
+ {"position": "right", "template_id": "process_product_two_way"}
+ ],
+ "final_html_size_matches_step13_reported": true
+ },
+ "04": {
+ "step13_status": "done",
+ "step13_pipeline_path_connected": true,
+ "render_inputs_zones_count": 3,
+ "render_inputs_layout_preset": "top-1-bottom-2",
+ "render_inputs_slide_title_nonempty": true,
+ "render_inputs_slide_footer_nonempty": true,
+ "html_title_matches_render_input": true,
+ "html_slide_root_count": 1,
+ "html_slide_footer_present": true,
+ "html_zone_count": 3,
+ "html_zone_topology": [
+ {"position": "top", "template_id": "bim_issues_quadrant_four"},
+ {"position": "bottom-left", "template_id": "__empty__"},
+ {"position": "bottom-right", "template_id": "__empty__"}
+ ],
+ "final_html_size_matches_step13_reported": true
+ },
+ "05": {
+ "step13_status": "done",
+ "step13_pipeline_path_connected": true,
+ "render_inputs_zones_count": 1,
+ "render_inputs_layout_preset": "single",
+ "render_inputs_slide_title_nonempty": true,
+ "render_inputs_slide_footer_nonempty": true,
+ "html_title_matches_render_input": true,
+ "html_slide_root_count": 1,
+ "html_slide_footer_present": true,
+ "html_zone_count": 1,
+ "html_zone_topology": [
+ {"position": "primary", "template_id": "__empty__"}
+ ],
+ "final_html_size_matches_step13_reported": true
+ }
+}
diff --git a/tests/integration/__snapshots__/layout.json b/tests/integration/__snapshots__/layout.json
new file mode 100644
index 0000000..7117cb5
--- /dev/null
+++ b/tests/integration/__snapshots__/layout.json
@@ -0,0 +1,133 @@
+{
+ "_doc": "IMP-91 u10 — F4 layout snapshot (step07 + step08). Pins observed layout decision axes (preset / candidates / override / computation / dynamic flags) + planning geometry (heights_px / widths_px / ratios / col_ratios) + per-zone planning shape (position / min_height_px / frame_cardinality_strict / sub_zones_count / region_layout_candidates). step_status='partial' = schema-lock marker per Step 7/8 note (region-level ratio + count-based v0 marker stays a marker, never silently flipped). layout_override_applied=True ONLY for mdx 03 (project_mdx03_frame_lock 2026-05-15 user lock — axis A vertical-2 override). Source: src/phase_z2_pipeline.py step07/step08 emit; auto_layout_preset=None for mdx 05 single-preset path. drift in heights_px/ratios = content_weight_distribution shift; drift in computation = decision-path swap (regression signal axis distinct from preset).",
+ "01": {
+ "step7_step_status": "partial",
+ "step7_pipeline_path_connected": true,
+ "layout_preset": "horizontal-2",
+ "auto_layout_preset": "horizontal-2",
+ "layout_override_applied": false,
+ "zones_count": 2,
+ "unit_count": 2,
+ "layout_candidates": ["horizontal-2", "vertical-2"],
+ "computation": "min_height_first + content_weight_distribution",
+ "dynamic_rows": true,
+ "dynamic_cols": false,
+ "heights_px": [299, 272],
+ "widths_px": [1180],
+ "ratios": [0.511, 0.465],
+ "width_ratios": [1.0],
+ "step8_step_status": "partial",
+ "step8_pipeline_path_connected": true,
+ "zone_heights_px_planned": [299, 272],
+ "zone_widths_px_planned": [1180],
+ "zone_col_ratios_planned": [1.0],
+ "per_zone_layout_shape": [
+ {"position": "top", "min_height_px": 350, "frame_cardinality_strict": 2, "sub_zones_count": 3, "region_layout_candidates": ["region-single"]},
+ {"position": "bottom", "min_height_px": 320, "frame_cardinality_strict": 3, "sub_zones_count": 3, "region_layout_candidates": ["region-single"]}
+ ]
+ },
+ "02": {
+ "step7_step_status": "partial",
+ "step7_pipeline_path_connected": true,
+ "layout_preset": "horizontal-2",
+ "auto_layout_preset": "horizontal-2",
+ "layout_override_applied": false,
+ "zones_count": 2,
+ "unit_count": 2,
+ "layout_candidates": ["horizontal-2", "vertical-2"],
+ "computation": "min_height_first + content_weight_distribution",
+ "dynamic_rows": true,
+ "dynamic_cols": false,
+ "heights_px": [273, 298],
+ "widths_px": [1180],
+ "ratios": [0.467, 0.509],
+ "width_ratios": [1.0],
+ "step8_step_status": "partial",
+ "step8_pipeline_path_connected": true,
+ "zone_heights_px_planned": [273, 298],
+ "zone_widths_px_planned": [1180],
+ "zone_col_ratios_planned": [1.0],
+ "per_zone_layout_shape": [
+ {"position": "top", "min_height_px": 320, "frame_cardinality_strict": 3, "sub_zones_count": 4, "region_layout_candidates": ["region-single"]},
+ {"position": "bottom", "min_height_px": 350, "frame_cardinality_strict": 3, "sub_zones_count": 3, "region_layout_candidates": ["region-single"]}
+ ]
+ },
+ "03": {
+ "step7_step_status": "partial",
+ "step7_pipeline_path_connected": true,
+ "layout_preset": "vertical-2",
+ "auto_layout_preset": "horizontal-2",
+ "layout_override_applied": true,
+ "zones_count": 2,
+ "unit_count": 2,
+ "layout_candidates": ["horizontal-2", "vertical-2"],
+ "computation": "user_override_geometry",
+ "dynamic_rows": false,
+ "dynamic_cols": true,
+ "heights_px": [585],
+ "widths_px": [408, 758],
+ "ratios": [1.0],
+ "width_ratios": [0.35, 0.65],
+ "step8_step_status": "partial",
+ "step8_pipeline_path_connected": true,
+ "zone_heights_px_planned": [585],
+ "zone_widths_px_planned": [408, 758],
+ "zone_col_ratios_planned": [0.35, 0.65],
+ "per_zone_layout_shape": [
+ {"position": "left", "min_height_px": 230, "frame_cardinality_strict": 3, "sub_zones_count": 3, "region_layout_candidates": ["region-single"]},
+ {"position": "right", "min_height_px": 345, "frame_cardinality_strict": 2, "sub_zones_count": 2, "region_layout_candidates": ["region-single"]}
+ ]
+ },
+ "04": {
+ "step7_step_status": "partial",
+ "step7_pipeline_path_connected": true,
+ "layout_preset": "top-1-bottom-2",
+ "auto_layout_preset": "top-1-bottom-2",
+ "layout_override_applied": false,
+ "zones_count": 3,
+ "unit_count": 3,
+ "layout_candidates": ["top-1-bottom-2", "top-2-bottom-1", "left-1-right-2", "left-2-right-1"],
+ "computation": "2d_dynamic_aggregated",
+ "dynamic_rows": true,
+ "dynamic_cols": true,
+ "heights_px": [221, 350],
+ "widths_px": [583, 583],
+ "ratios": [0.378, 0.598],
+ "width_ratios": [0.494, 0.494],
+ "step8_step_status": "partial",
+ "step8_pipeline_path_connected": true,
+ "zone_heights_px_planned": [221, 350],
+ "zone_widths_px_planned": [583, 583],
+ "zone_col_ratios_planned": [0.494, 0.494],
+ "per_zone_layout_shape": [
+ {"position": "top", "min_height_px": null, "frame_cardinality_strict": null, "sub_zones_count": 4, "region_layout_candidates": ["region-single"]},
+ {"position": "bottom-left", "min_height_px": 350, "frame_cardinality_strict": 4, "sub_zones_count": 5, "region_layout_candidates": ["region-single"]},
+ {"position": "bottom-right", "min_height_px": 350, "frame_cardinality_strict": null, "sub_zones_count": 1, "region_layout_candidates": ["region-single"]}
+ ]
+ },
+ "05": {
+ "step7_step_status": "partial",
+ "step7_pipeline_path_connected": true,
+ "layout_preset": "single",
+ "auto_layout_preset": null,
+ "layout_override_applied": false,
+ "zones_count": 1,
+ "unit_count": 1,
+ "layout_candidates": ["single"],
+ "computation": "fr_default_from_preset",
+ "dynamic_rows": false,
+ "dynamic_cols": false,
+ "heights_px": [585],
+ "widths_px": [1180],
+ "ratios": [1.0],
+ "width_ratios": [1.0],
+ "step8_step_status": "partial",
+ "step8_pipeline_path_connected": true,
+ "zone_heights_px_planned": [585],
+ "zone_widths_px_planned": [1180],
+ "zone_col_ratios_planned": [1.0],
+ "per_zone_layout_shape": [
+ {"position": "primary", "min_height_px": null, "frame_cardinality_strict": null, "sub_zones_count": 0, "region_layout_candidates": ["region-single"]}
+ ]
+ }
+}
diff --git a/tests/integration/__snapshots__/normalize.json b/tests/integration/__snapshots__/normalize.json
new file mode 100644
index 0000000..170c235
--- /dev/null
+++ b/tests/integration/__snapshots__/normalize.json
@@ -0,0 +1,83 @@
+{
+ "_doc": "IMP-91 u6 — F0 normalize axis snapshot (step02_normalized.json). Pins observed current state per [[feedback_validation_first_for_closed_issues]] / Stage 1 'do not invent a new expectation'. step_status='partial' is the schema-lock marker for IMP-02/03 (orphans + details detection unimplemented). adapter_enabled/used=false reflects default-OFF canary (chained adapter trace OFF). asset counts are step02 collection state (popups/images/tables list aggregation in stage0_normalized_assets); they may grow when IMP-03 detection lands and the snapshot will drift loudly.",
+ "01": {
+ "step_num": 2,
+ "step_status": "partial",
+ "pipeline_path_connected": true,
+ "sections_count": 2,
+ "section_ids": ["01-1", "01-2"],
+ "orphans_count": 0,
+ "details_count": 0,
+ "adapter_enabled": false,
+ "adapter_used": false,
+ "assets_popups_count": 0,
+ "assets_images_count": 0,
+ "assets_tables_count": 0,
+ "slide_title_nonempty": true,
+ "slide_footer_nonempty": true
+ },
+ "02": {
+ "step_num": 2,
+ "step_status": "partial",
+ "pipeline_path_connected": true,
+ "sections_count": 2,
+ "section_ids": ["02-1", "02-2"],
+ "orphans_count": 0,
+ "details_count": 0,
+ "adapter_enabled": false,
+ "adapter_used": false,
+ "assets_popups_count": 0,
+ "assets_images_count": 0,
+ "assets_tables_count": 0,
+ "slide_title_nonempty": true,
+ "slide_footer_nonempty": true
+ },
+ "03": {
+ "step_num": 2,
+ "step_status": "partial",
+ "pipeline_path_connected": true,
+ "sections_count": 2,
+ "section_ids": ["03-1", "03-2"],
+ "orphans_count": 0,
+ "details_count": 0,
+ "adapter_enabled": false,
+ "adapter_used": false,
+ "assets_popups_count": 0,
+ "assets_images_count": 0,
+ "assets_tables_count": 0,
+ "slide_title_nonempty": true,
+ "slide_footer_nonempty": true
+ },
+ "04": {
+ "step_num": 2,
+ "step_status": "partial",
+ "pipeline_path_connected": true,
+ "sections_count": 2,
+ "section_ids": ["04-1", "04-2"],
+ "orphans_count": 0,
+ "details_count": 0,
+ "adapter_enabled": false,
+ "adapter_used": false,
+ "assets_popups_count": 0,
+ "assets_images_count": 0,
+ "assets_tables_count": 0,
+ "slide_title_nonempty": true,
+ "slide_footer_nonempty": true
+ },
+ "05": {
+ "step_num": 2,
+ "step_status": "partial",
+ "pipeline_path_connected": true,
+ "sections_count": 2,
+ "section_ids": ["05-1", "05-2"],
+ "orphans_count": 0,
+ "details_count": 0,
+ "adapter_enabled": false,
+ "adapter_used": false,
+ "assets_popups_count": 0,
+ "assets_images_count": 0,
+ "assets_tables_count": 0,
+ "slide_title_nonempty": true,
+ "slide_footer_nonempty": true
+ }
+}
diff --git a/tests/integration/__snapshots__/slot_payload.json b/tests/integration/__snapshots__/slot_payload.json
new file mode 100644
index 0000000..4d7d048
--- /dev/null
+++ b/tests/integration/__snapshots__/slot_payload.json
@@ -0,0 +1,103 @@
+{
+ "_doc": "IMP-#91 u8 — F2 slot_payload axis. Pins step12_slot_payload.json per_zone structural shape (position / template_id / builder / slot_names / list_slot_counts / dict_slot_sub_counts / string_slot_nonempty) for mdx 01-05. Pins SHAPE not literal content — text edits in MDX won't drift this snapshot, but builder swap / slot rename / missing slot / list-cardinality drift will. __empty__ zones have builder=null and zero slots.",
+ "01": [
+ {
+ "position": "top",
+ "template_id": "bim_dx_comparison_table",
+ "builder": "compare_table_2col",
+ "slot_names": ["col_a_label", "col_b_label", "rows", "title"],
+ "list_slot_counts": {"rows": 2},
+ "dict_slot_sub_counts": {},
+ "string_slot_nonempty": {"col_a_label": true, "col_b_label": true, "title": true}
+ },
+ {
+ "position": "bottom",
+ "template_id": "construction_bim_three_usage",
+ "builder": "quadrant_flat_slots",
+ "slot_names": ["category_1_body", "category_1_label", "category_2_body", "category_2_label", "category_3_body", "category_3_label", "title"],
+ "list_slot_counts": {"category_1_body": 2, "category_2_body": 2, "category_3_body": 2},
+ "dict_slot_sub_counts": {},
+ "string_slot_nonempty": {"category_1_label": true, "category_2_label": true, "category_3_label": true, "title": true}
+ }
+ ],
+ "02": [
+ {
+ "position": "top",
+ "template_id": "construction_goals_three_circle_intersection",
+ "builder": "cycle_intersect_3",
+ "slot_names": ["circle_1_label", "circle_2_label", "circle_3_label", "intersection", "title"],
+ "list_slot_counts": {},
+ "dict_slot_sub_counts": {},
+ "string_slot_nonempty": {"circle_1_label": true, "circle_2_label": true, "circle_3_label": true, "intersection": false, "title": true}
+ },
+ {
+ "position": "bottom",
+ "template_id": "__empty__",
+ "builder": null,
+ "slot_names": [],
+ "list_slot_counts": {},
+ "dict_slot_sub_counts": {},
+ "string_slot_nonempty": {}
+ }
+ ],
+ "03": [
+ {
+ "position": "left",
+ "template_id": "three_parallel_requirements",
+ "builder": "items_with_role",
+ "slot_names": ["pillars", "title"],
+ "list_slot_counts": {"pillars": 3},
+ "dict_slot_sub_counts": {},
+ "string_slot_nonempty": {"title": true}
+ },
+ {
+ "position": "right",
+ "template_id": "process_product_two_way",
+ "builder": "process_product_pair",
+ "slot_names": ["banner_left", "banner_right", "process", "product", "title"],
+ "list_slot_counts": {},
+ "dict_slot_sub_counts": {"process": {"sections": 3}, "product": {"sections": 3}},
+ "string_slot_nonempty": {"banner_left": true, "banner_right": true, "title": true}
+ }
+ ],
+ "04": [
+ {
+ "position": "top",
+ "template_id": "bim_issues_quadrant_four",
+ "builder": "quadrant_flat_slots",
+ "slot_names": ["quadrant_1_body", "quadrant_1_label", "quadrant_2_body", "quadrant_2_label", "quadrant_3_body", "quadrant_3_label", "quadrant_4_body", "quadrant_4_label", "title"],
+ "list_slot_counts": {"quadrant_1_body": 2, "quadrant_2_body": 2, "quadrant_3_body": 2, "quadrant_4_body": 2},
+ "dict_slot_sub_counts": {},
+ "string_slot_nonempty": {"quadrant_1_label": true, "quadrant_2_label": true, "quadrant_3_label": true, "quadrant_4_label": true, "title": true}
+ },
+ {
+ "position": "bottom-left",
+ "template_id": "__empty__",
+ "builder": null,
+ "slot_names": [],
+ "list_slot_counts": {},
+ "dict_slot_sub_counts": {},
+ "string_slot_nonempty": {}
+ },
+ {
+ "position": "bottom-right",
+ "template_id": "__empty__",
+ "builder": null,
+ "slot_names": [],
+ "list_slot_counts": {},
+ "dict_slot_sub_counts": {},
+ "string_slot_nonempty": {}
+ }
+ ],
+ "05": [
+ {
+ "position": "primary",
+ "template_id": "__empty__",
+ "builder": null,
+ "slot_names": [],
+ "list_slot_counts": {},
+ "dict_slot_sub_counts": {},
+ "string_slot_nonempty": {}
+ }
+ ]
+}
diff --git a/tests/integration/__snapshots__/structural.json b/tests/integration/__snapshots__/structural.json
new file mode 100644
index 0000000..5e0a85f
--- /dev/null
+++ b/tests/integration/__snapshots__/structural.json
@@ -0,0 +1,43 @@
+{
+ "_doc": "IMP-#91 u3 structural snapshot — pins observed step20 overall + step09 per-zone selected_template_id per mdx in the 01-05 acceptance set. Each entry is fresh-run evidence (not aspirational). Update only when an intentional pipeline change moves the observed value; treat unexplained drift as regression. [[feedback_validation_first_for_closed_issues]] [[feedback_artifact_status_naming]]",
+ "01": {
+ "overall": "PASS",
+ "zone_count": 2,
+ "zones": [
+ {"position": "top", "selected_template_id": "bim_dx_comparison_table"},
+ {"position": "bottom", "selected_template_id": "construction_bim_three_usage"}
+ ]
+ },
+ "02": {
+ "overall": "PASS",
+ "zone_count": 2,
+ "zones": [
+ {"position": "top", "selected_template_id": "construction_goals_three_circle_intersection"},
+ {"position": "bottom", "selected_template_id": "three_persona_benefits"}
+ ]
+ },
+ "03": {
+ "overall": "PASS",
+ "zone_count": 2,
+ "zones": [
+ {"position": "left", "selected_template_id": "three_parallel_requirements"},
+ {"position": "right", "selected_template_id": "process_product_two_way"}
+ ]
+ },
+ "04": {
+ "overall": "PASS",
+ "zone_count": 3,
+ "zones": [
+ {"position": "top", "selected_template_id": "bim_issues_quadrant_four"},
+ {"position": "bottom-left", "selected_template_id": "sw_dependency_four_problems"},
+ {"position": "bottom-right", "selected_template_id": "pre_construction_model_info_stacked"}
+ ]
+ },
+ "05": {
+ "overall": "EMPTY_SHELL_NO_CONTENT",
+ "zone_count": 1,
+ "zones": [
+ {"position": "primary", "selected_template_id": "__empty__"}
+ ]
+ }
+}
diff --git a/tests/integration/__snapshots__/v4_ranking.json b/tests/integration/__snapshots__/v4_ranking.json
new file mode 100644
index 0000000..bdd8f16
--- /dev/null
+++ b/tests/integration/__snapshots__/v4_ranking.json
@@ -0,0 +1,112 @@
+{
+ "_doc": "IMP-91 u7 — F1 V4 ranking observed snapshot (step05_v4_evidence). Pins v4_source (POSIX-normalized), aligned_section_ids, and per-section {section_id, candidate_status, candidates: [{template_id, label, confidence}]}. confidence kept at current 4-decimal rounding. Sections appear in pipeline-emitted order.",
+ "01": {
+ "v4_source": "tests/matching/v4_full32_result.yaml",
+ "aligned_section_ids": ["01-1", "01-2"],
+ "sections": [
+ {
+ "section_id": "01-1",
+ "candidate_status": "ok",
+ "candidates": [
+ {"template_id": "construction_bim_three_usage", "label": "use_as_is", "confidence": 0.9101},
+ {"template_id": "construction_goals_three_circle_intersection", "label": "light_edit", "confidence": 0.8261},
+ {"template_id": "dx_sw_necessity_three_perspectives", "label": "light_edit", "confidence": 0.8168}
+ ]
+ },
+ {
+ "section_id": "01-2",
+ "candidate_status": "ok",
+ "candidates": [
+ {"template_id": "bim_dx_comparison_table", "label": "use_as_is", "confidence": 0.9459},
+ {"template_id": "app_sw_package_vs_solution", "label": "restructure", "confidence": 0.6813}
+ ]
+ }
+ ]
+ },
+ "02": {
+ "v4_source": "tests/matching/v4_full32_result.yaml",
+ "aligned_section_ids": ["02-1", "02-2-sub-1", "02-2-sub-2"],
+ "sections": [
+ {
+ "section_id": "02-1",
+ "candidate_status": "ok",
+ "candidates": [
+ {"template_id": "construction_goals_three_circle_intersection", "label": "use_as_is", "confidence": 0.914}
+ ]
+ },
+ {
+ "section_id": "02-2-sub-1",
+ "candidate_status": "no_non_reject_v4_candidate",
+ "candidates": []
+ },
+ {
+ "section_id": "02-2-sub-2",
+ "candidate_status": "no_non_reject_v4_candidate",
+ "candidates": []
+ }
+ ]
+ },
+ "03": {
+ "v4_source": "tests/matching/v4_full32_result.yaml",
+ "aligned_section_ids": ["03-1", "03-2"],
+ "sections": [
+ {
+ "section_id": "03-1",
+ "candidate_status": "ok",
+ "candidates": [
+ {"template_id": "three_parallel_requirements", "label": "use_as_is", "confidence": 0.9268},
+ {"template_id": "dx_sw_necessity_three_perspectives", "label": "light_edit", "confidence": 0.8413}
+ ]
+ },
+ {
+ "section_id": "03-2",
+ "candidate_status": "ok",
+ "candidates": [
+ {"template_id": "process_product_two_way", "label": "use_as_is", "confidence": 0.9198}
+ ]
+ }
+ ]
+ },
+ "04": {
+ "v4_source": "tests/matching/v4_full32_result.yaml",
+ "aligned_section_ids": ["04-1", "04-2-sub-1", "04-2-sub-2"],
+ "sections": [
+ {
+ "section_id": "04-1",
+ "candidate_status": "no_non_reject_v4_candidate",
+ "candidates": []
+ },
+ {
+ "section_id": "04-2-sub-1",
+ "candidate_status": "no_non_reject_v4_candidate",
+ "candidates": []
+ },
+ {
+ "section_id": "04-2-sub-2",
+ "candidate_status": "no_non_reject_v4_candidate",
+ "candidates": []
+ }
+ ]
+ },
+ "05": {
+ "v4_source": "tests/matching/v4_full32_result.yaml",
+ "aligned_section_ids": ["05-1", "05-2-sub-1", "05-2-sub-2"],
+ "sections": [
+ {
+ "section_id": "05-1",
+ "candidate_status": "no_non_reject_v4_candidate",
+ "candidates": []
+ },
+ {
+ "section_id": "05-2-sub-1",
+ "candidate_status": "no_non_reject_v4_candidate",
+ "candidates": []
+ },
+ {
+ "section_id": "05-2-sub-2",
+ "candidate_status": "no_non_reject_v4_candidate",
+ "candidates": []
+ }
+ ]
+ }
+}
diff --git a/tests/integration/__snapshots__/visual.json b/tests/integration/__snapshots__/visual.json
new file mode 100644
index 0000000..c0a0139
--- /dev/null
+++ b/tests/integration/__snapshots__/visual.json
@@ -0,0 +1,48 @@
+{
+ "_doc": "u4 — pin observed step14_visual_check overflow/clip per mdx 01-05. Fresh subprocess observation per [[feedback_validation_first_for_closed_issues]]; drift surfaces visual regression (overflow / clip) loudly per [[feedback_artifact_status_naming]] 3-axis honesty. Snapshot pinned to current-state, not to invented expectation (Stage 1 scope-lock).",
+ "01": {
+ "slide_overflowed": false,
+ "slide_body_overflowed": false,
+ "passed": true,
+ "zones": [
+ {"position": "top", "template_id": "bim_dx_comparison_table", "overflowed": false, "clipped_inner_count": 0},
+ {"position": "bottom", "template_id": "construction_bim_three_usage", "overflowed": false, "clipped_inner_count": 0}
+ ]
+ },
+ "02": {
+ "slide_overflowed": false,
+ "slide_body_overflowed": false,
+ "passed": true,
+ "zones": [
+ {"position": "top", "template_id": "construction_goals_three_circle_intersection", "overflowed": false, "clipped_inner_count": 0},
+ {"position": "bottom", "template_id": "__empty__", "overflowed": false, "clipped_inner_count": 0}
+ ]
+ },
+ "03": {
+ "slide_overflowed": false,
+ "slide_body_overflowed": false,
+ "passed": true,
+ "zones": [
+ {"position": "left", "template_id": "three_parallel_requirements", "overflowed": false, "clipped_inner_count": 0},
+ {"position": "right", "template_id": "process_product_two_way", "overflowed": false, "clipped_inner_count": 0}
+ ]
+ },
+ "04": {
+ "slide_overflowed": false,
+ "slide_body_overflowed": false,
+ "passed": true,
+ "zones": [
+ {"position": "top", "template_id": "bim_issues_quadrant_four", "overflowed": false, "clipped_inner_count": 0},
+ {"position": "bottom-left", "template_id": "__empty__", "overflowed": false, "clipped_inner_count": 0},
+ {"position": "bottom-right", "template_id": "__empty__", "overflowed": false, "clipped_inner_count": 0}
+ ]
+ },
+ "05": {
+ "slide_overflowed": false,
+ "slide_body_overflowed": false,
+ "passed": true,
+ "zones": [
+ {"position": "primary", "template_id": "__empty__", "overflowed": false, "clipped_inner_count": 0}
+ ]
+ }
+}
diff --git a/tests/integration/test_multi_mdx_regression.py b/tests/integration/test_multi_mdx_regression.py
new file mode 100644
index 0000000..f20562e
--- /dev/null
+++ b/tests/integration/test_multi_mdx_regression.py
@@ -0,0 +1,573 @@
+"""IMP-#91 u2 — multi-mdx regression CI scaffold (mdx 01-05 acceptance set).
+
+Session-scoped subprocess cache that runs each MDX acceptance fixture
+exactly once. u3-u11 extend this module with per-axis assertions
+(structural / visual / coverage / F0-F5). u2 alone pins the cache
+contract: each mdx in ``MDX_SET`` produces a run directory under
+``data/runs/<run_id>/phase_z2/`` containing the step JSONs and
+``final.html`` that downstream parametrized tests will read.
+
+[[feedback_validation_first_for_closed_issues]] — fresh subprocess per
+session, no frozen artifacts. [[feedback_artifact_status_naming]] — the
+overall status (PASS / RENDERED_WITH_VISUAL_REGRESSION /
+PARTIAL_COVERAGE / EMPTY_SHELL_NO_CONTENT) is asserted in u3-u5; u2
+only pins the artifact-production contract.
+"""
+from __future__ import annotations
+
+import json
+import re
+import subprocess
+import sys
+import uuid
+from pathlib import Path
+from typing import Dict, List, NamedTuple
+
+import pytest
+
+REPO_ROOT = Path(__file__).resolve().parents[2]
+SAMPLES_DIR = REPO_ROOT / "samples" / "mdx_batch"
+RUNS_DIR = REPO_ROOT / "data" / "runs"
+SNAPSHOTS_DIR = Path(__file__).resolve().parent / "__snapshots__"
+MDX_SET = ("01", "02", "03", "04", "05")
+
+
+class PipelineRun(NamedTuple):
+ mdx_id: str
+ run_id: str
+ returncode: int
+ stdout: str
+ stderr: str
+ run_dir: Path
+
+
+@pytest.fixture(scope="session")
+def multi_mdx_runs() -> Dict[str, PipelineRun]:
+ """Run the Phase Z pipeline once per mdx in ``MDX_SET`` (session-cached)."""
+ cache: Dict[str, PipelineRun] = {}
+ for mdx_id in MDX_SET:
+ run_id = f"imp91_{mdx_id}_{uuid.uuid4().hex[:8]}"
+ cp = subprocess.run(
+ [
+ sys.executable,
+ "-m",
+ "src.phase_z2_pipeline",
+ str(SAMPLES_DIR / f"{mdx_id}.mdx"),
+ run_id,
+ ],
+ capture_output=True,
+ text=True,
+ timeout=360,
+ cwd=str(REPO_ROOT),
+ )
+ cache[mdx_id] = PipelineRun(
+ mdx_id=mdx_id,
+ run_id=run_id,
+ returncode=cp.returncode,
+ stdout=cp.stdout,
+ stderr=cp.stderr,
+ run_dir=RUNS_DIR / run_id / "phase_z2",
+ )
+ return cache
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize("mdx_id", MDX_SET)
+def test_pipeline_run_produces_step20_status(
+ mdx_id: str, multi_mdx_runs: Dict[str, PipelineRun]
+) -> None:
+ """Cache contract: every mdx subprocess produces step20_slide_status.json."""
+ run = multi_mdx_runs[mdx_id]
+ status_path = run.run_dir / "steps" / "step20_slide_status.json"
+ assert status_path.is_file(), (
+ f"{mdx_id}.mdx run {run.run_id} did not produce {status_path} "
+ f"(returncode={run.returncode}); stderr tail: {run.stderr[-800:]}"
+ )
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize("mdx_id", MDX_SET)
+def test_structural_snapshot_matches(
+ mdx_id: str, multi_mdx_runs: Dict[str, PipelineRun]
+) -> None:
+ """u3 — pin observed overall + per-zone selected_template_id against snapshot."""
+ snapshot = json.loads((SNAPSHOTS_DIR / "structural.json").read_text(encoding="utf-8"))
+ expected = snapshot[mdx_id]
+ run = multi_mdx_runs[mdx_id]
+ status = json.loads(
+ (run.run_dir / "steps" / "step20_slide_status.json").read_text(encoding="utf-8")
+ )["data"]
+ frame_sel = json.loads(
+ (run.run_dir / "steps" / "step09_frame_selection.json").read_text(encoding="utf-8")
+ )["data"]
+ zones = frame_sel.get("per_zone", [])
+ actual_zones = [
+ {"position": z.get("position"), "selected_template_id": z.get("selected_template_id")}
+ for z in zones
+ ]
+ assert status.get("overall") == expected["overall"], (
+ f"{mdx_id}.mdx overall drift: expected {expected['overall']!r}, "
+ f"got {status.get('overall')!r}"
+ )
+ assert len(actual_zones) == expected["zone_count"], (
+ f"{mdx_id}.mdx zone_count drift: expected {expected['zone_count']}, "
+ f"got {len(actual_zones)} (zones={actual_zones})"
+ )
+ assert actual_zones == expected["zones"], (
+ f"{mdx_id}.mdx zone topology drift: expected {expected['zones']}, "
+ f"got {actual_zones}"
+ )
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize("mdx_id", MDX_SET)
+def test_visual_snapshot_matches(
+ mdx_id: str, multi_mdx_runs: Dict[str, PipelineRun]
+) -> None:
+ """u4 — pin observed step14 visual_check overflow/clip against snapshot."""
+ snapshot = json.loads((SNAPSHOTS_DIR / "visual.json").read_text(encoding="utf-8"))
+ expected = snapshot[mdx_id]
+ run = multi_mdx_runs[mdx_id]
+ visual = json.loads(
+ (run.run_dir / "steps" / "step14_visual_check.json").read_text(encoding="utf-8")
+ )["data"]
+ slide_overflowed = visual.get("slide", {}).get("overflowed")
+ slide_body_overflowed = visual.get("slide_body", {}).get("overflowed")
+ visual_passed = visual.get("passed")
+ actual_zones = [
+ {
+ "position": z.get("position"),
+ "template_id": z.get("template_id"),
+ "overflowed": z.get("overflowed"),
+ "clipped_inner_count": len(z.get("clipped_inner") or []),
+ }
+ for z in visual.get("zones", [])
+ ]
+ assert slide_overflowed == expected["slide_overflowed"], (
+ f"{mdx_id}.mdx slide.overflowed drift: expected {expected['slide_overflowed']}, "
+ f"got {slide_overflowed}"
+ )
+ assert slide_body_overflowed == expected["slide_body_overflowed"], (
+ f"{mdx_id}.mdx slide_body.overflowed drift: expected {expected['slide_body_overflowed']}, "
+ f"got {slide_body_overflowed}"
+ )
+ assert visual_passed == expected["passed"], (
+ f"{mdx_id}.mdx visual_check.passed drift: expected {expected['passed']}, "
+ f"got {visual_passed}"
+ )
+ assert actual_zones == expected["zones"], (
+ f"{mdx_id}.mdx zone visual drift: expected {expected['zones']}, "
+ f"got {actual_zones}"
+ )
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize("mdx_id", MDX_SET)
+def test_coverage_snapshot_matches(
+ mdx_id: str, multi_mdx_runs: Dict[str, PipelineRun]
+) -> None:
+ """u5 — pin observed full_mdx_coverage + section_id parity against snapshot."""
+ snapshot = json.loads((SNAPSHOTS_DIR / "coverage.json").read_text(encoding="utf-8"))
+ expected = snapshot[mdx_id]
+ run = multi_mdx_runs[mdx_id]
+ status = json.loads(
+ (run.run_dir / "steps" / "step20_slide_status.json").read_text(encoding="utf-8")
+ )["data"]
+ assert status.get("rendered") == expected["rendered"], (
+ f"{mdx_id}.mdx rendered drift: expected {expected['rendered']}, "
+ f"got {status.get('rendered')}"
+ )
+ assert status.get("visual_check_passed") == expected["visual_check_passed"], (
+ f"{mdx_id}.mdx visual_check_passed drift: expected {expected['visual_check_passed']}, "
+ f"got {status.get('visual_check_passed')}"
+ )
+ assert status.get("full_mdx_coverage") == expected["full_mdx_coverage"], (
+ f"{mdx_id}.mdx full_mdx_coverage drift: expected {expected['full_mdx_coverage']}, "
+ f"got {status.get('full_mdx_coverage')}"
+ )
+ assert sorted(status.get("aligned_section_ids") or []) == sorted(expected["aligned_section_ids"]), (
+ f"{mdx_id}.mdx aligned_section_ids drift: expected {expected['aligned_section_ids']}, "
+ f"got {status.get('aligned_section_ids')}"
+ )
+ assert sorted(status.get("covered_section_ids") or []) == sorted(expected["covered_section_ids"]), (
+ f"{mdx_id}.mdx covered_section_ids drift: expected {expected['covered_section_ids']}, "
+ f"got {status.get('covered_section_ids')}"
+ )
+ assert sorted(status.get("filtered_section_ids") or []) == sorted(expected["filtered_section_ids"]), (
+ f"{mdx_id}.mdx filtered_section_ids drift: expected {expected['filtered_section_ids']}, "
+ f"got {status.get('filtered_section_ids')}"
+ )
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize("mdx_id", MDX_SET)
+def test_normalize_snapshot_matches(
+ mdx_id: str, multi_mdx_runs: Dict[str, PipelineRun]
+) -> None:
+ """u6 — F0 normalize: pin observed step02_normalized shape per mdx."""
+ snapshot = json.loads((SNAPSHOTS_DIR / "normalize.json").read_text(encoding="utf-8"))
+ expected = snapshot[mdx_id]
+ run = multi_mdx_runs[mdx_id]
+ raw = json.loads(
+ (run.run_dir / "steps" / "step02_normalized.json").read_text(encoding="utf-8")
+ )
+ d = raw["data"]
+ diag = d.get("stage0_adapter_diagnostics", {}) or {}
+ assets = d.get("stage0_normalized_assets", {}) or {}
+ actual = {
+ "step_num": raw.get("step_num"),
+ "step_status": raw.get("step_status"),
+ "pipeline_path_connected": raw.get("pipeline_path_connected"),
+ "sections_count": d.get("sections_count"),
+ "section_ids": [s.get("section_id") for s in d.get("sections", [])],
+ "orphans_count": len(d.get("orphans") or []),
+ "details_count": len(d.get("details") or []),
+ "adapter_enabled": diag.get("enabled"),
+ "adapter_used": diag.get("used"),
+ "assets_popups_count": len(assets.get("popups") or []),
+ "assets_images_count": len(assets.get("images") or []),
+ "assets_tables_count": len(assets.get("tables") or []),
+ "slide_title_nonempty": bool(d.get("slide_title")),
+ "slide_footer_nonempty": bool(d.get("slide_footer")),
+ }
+ for key, want in expected.items():
+ got = actual[key]
+ assert got == want, (
+ f"{mdx_id}.mdx normalize.{key} drift: expected {want!r}, got {got!r}"
+ )
+ assert len(d.get("sections", [])) == expected["sections_count"], (
+ f"{mdx_id}.mdx sections list length mismatch with sections_count: "
+ f"sections_count={expected['sections_count']}, got len(sections)={len(d.get('sections', []))}"
+ )
+ for sect in d.get("sections", []):
+ assert (sect.get("raw_content_length") or 0) > 0, (
+ f"{mdx_id}.mdx section {sect.get('section_id')!r} has empty raw_content "
+ f"(length={sect.get('raw_content_length')!r}) — normalize lost content"
+ )
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize("mdx_id", MDX_SET)
+def test_v4_ranking_snapshot_matches(
+ mdx_id: str, multi_mdx_runs: Dict[str, PipelineRun]
+) -> None:
+ """u7 — F1 V4 ranking: pin observed step05_v4_evidence per mdx.
+
+ Pins ``v4_source`` (POSIX-normalized for cross-platform stability),
+ ``aligned_section_ids``, and per-section
+ ``{section_id, candidate_status, candidates: [{template_id, label, confidence}]}``
+ in pipeline-emitted order. Confidence stays at the current 4-decimal
+ rounding emitted by the V4 yaml; drift any axis fails loudly so a
+ re-baseline is a conscious commit, not a silent shift.
+ """
+ snapshot = json.loads((SNAPSHOTS_DIR / "v4_ranking.json").read_text(encoding="utf-8"))
+ expected = snapshot[mdx_id]
+ run = multi_mdx_runs[mdx_id]
+ raw = json.loads(
+ (run.run_dir / "steps" / "step05_v4_evidence.json").read_text(encoding="utf-8")
+ )
+ data = raw["data"]
+ actual_v4_source = str(data.get("v4_source") or "").replace("\\", "/")
+ actual_sections = [
+ {
+ "section_id": ev.get("section_id"),
+ "candidate_status": ev.get("candidate_status"),
+ "candidates": [
+ {
+ "template_id": c.get("template_id"),
+ "label": c.get("label"),
+ "confidence": c.get("confidence"),
+ }
+ for c in (ev.get("v4_candidates") or [])
+ ],
+ }
+ for ev in (data.get("evidence_per_section") or [])
+ ]
+ assert actual_v4_source == expected["v4_source"], (
+ f"{mdx_id}.mdx v4_source drift: expected {expected['v4_source']!r}, "
+ f"got {actual_v4_source!r}"
+ )
+ assert data.get("aligned_section_ids") == expected["aligned_section_ids"], (
+ f"{mdx_id}.mdx aligned_section_ids drift: expected {expected['aligned_section_ids']}, "
+ f"got {data.get('aligned_section_ids')}"
+ )
+ assert actual_sections == expected["sections"], (
+ f"{mdx_id}.mdx V4 ranking drift: expected {expected['sections']}, "
+ f"got {actual_sections}"
+ )
+
+
+def _slot_payload_zone_shape(zone: dict) -> dict:
+ """Reduce a step12 per_zone entry to a content-agnostic structural shape.
+
+ Pins builder + slot names + per-slot list cardinality + dict sub-list
+ counts + string non-empty flags. MDX text edits don't drift this; a
+ builder swap, slot rename, missing slot, or list-cardinality change
+ does. Sub-dict shape pins ``sections`` length only — deeper field
+ pinning would require a fresh u8'-axis snapshot.
+ """
+ sp = zone.get("slot_payload") or {}
+ slot_names = sorted(sp.keys())
+ list_slot_counts: dict = {}
+ dict_slot_sub_counts: dict = {}
+ string_slot_nonempty: dict = {}
+ for name in slot_names:
+ value = sp[name]
+ if isinstance(value, list):
+ list_slot_counts[name] = len(value)
+ elif isinstance(value, dict):
+ sub: dict = {}
+ for sub_key, sub_val in value.items():
+ if isinstance(sub_val, list):
+ sub[sub_key] = len(sub_val)
+ dict_slot_sub_counts[name] = sub
+ elif isinstance(value, str):
+ string_slot_nonempty[name] = bool(value.strip())
+ return {
+ "position": zone.get("position"),
+ "template_id": zone.get("template_id"),
+ "builder": zone.get("builder"),
+ "slot_names": slot_names,
+ "list_slot_counts": list_slot_counts,
+ "dict_slot_sub_counts": dict_slot_sub_counts,
+ "string_slot_nonempty": string_slot_nonempty,
+ }
+
+
+_AI_UNIT_KEYS = (
+ "source_section_ids", "label", "route_hint", "provisional",
+ "ai_called", "skip_reason", "apply_status",
+)
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize("mdx_id", MDX_SET)
+def test_ai_classifier_snapshot_matches(
+ mdx_id: str, multi_mdx_runs: Dict[str, PipelineRun]
+) -> None:
+ """u9 — F3 classifier-only AI: pin step12/15/16/18 classifier signals.
+
+ [[feedback_ai_isolation_contract]] / [[feedback_demo_env_toggle_policy]]
+ central invariant: ``ai_called`` MUST stay False per unit by default;
+ activation requires explicit .env toggle, never pipeline default.
+ """
+ snapshot = json.loads((SNAPSHOTS_DIR / "ai_classifier.json").read_text(encoding="utf-8"))
+ expected = snapshot[mdx_id]
+ steps = multi_mdx_runs[mdx_id].run_dir / "steps"
+ ai = json.loads((steps / "step12_ai_repair.json").read_text(encoding="utf-8"))["data"]
+ fit = json.loads((steps / "step15_fit_classification.json").read_text(encoding="utf-8"))["data"]
+ router = json.loads((steps / "step16_router_decision.json").read_text(encoding="utf-8"))["data"]
+ failure = json.loads((steps / "step18_failure_classification.json").read_text(encoding="utf-8"))["data"]
+ units = [{k: u.get(k) for k in _AI_UNIT_KEYS} for u in (ai.get("per_unit") or [])]
+ actual = {
+ "units": units,
+ "coverage_invariant_status": (ai.get("coverage_invariant") or {}).get("status"),
+ "fit_visual_check_passed": fit.get("visual_check_passed"),
+ "fit_classifications_count": len(fit.get("classifications") or []),
+ "fit_categories_seen": fit.get("categories_seen") or [],
+ "router_active": router.get("router_active"),
+ "router_routed_count": router.get("routed_count"),
+ "router_v4_fallback_used_count": (router.get("v4_fallback_summary") or {}).get("fallback_used_count"),
+ "failure_type": failure.get("failure_type"),
+ }
+ for key, want in expected.items():
+ assert actual[key] == want, (
+ f"{mdx_id}.mdx ai_classifier.{key} drift: expected {want!r}, got {actual[key]!r}"
+ )
+ breaches = [u for u in units if u["ai_called"] is not False]
+ assert not breaches, (
+ f"{mdx_id}.mdx F3 AI-isolation breach (ai_called must be False by default): {breaches}"
+ )
+
+
+def _layout_zone_shape(zone: dict) -> dict:
+ """Reduce a step08 per_zone_plan entry to a content-agnostic F4 layout shape."""
+ sub_zones = zone.get("sub_zones_planned") or []
+ return {
+ "position": zone.get("position"),
+ "min_height_px": zone.get("min_height_px"),
+ "frame_cardinality_strict": zone.get("frame_cardinality_strict"),
+ "sub_zones_count": len(sub_zones),
+ "region_layout_candidates": zone.get("region_layout_candidates") or [],
+ }
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize("mdx_id", MDX_SET)
+def test_layout_snapshot_matches(
+ mdx_id: str, multi_mdx_runs: Dict[str, PipelineRun]
+) -> None:
+ """u10 — F4 layout: pin step07_layout + step08_zone_region_ratios per mdx.
+
+ Pins the layout decision path (``layout_preset`` /
+ ``auto_layout_preset`` / ``layout_override_applied`` /
+ ``layout_candidates`` / ``computation``) + planning geometry
+ (``heights_px`` / ``widths_px`` / ``ratios`` / ``width_ratios``) +
+ per-zone planning shape (``position`` / ``min_height_px`` /
+ ``frame_cardinality_strict`` / ``sub_zones_count`` /
+ ``region_layout_candidates``). ``step_status='partial'`` is the
+ Step 7/8 schema-lock marker (region-level ratio + count-based v0).
+ mdx 03 is the only ``layout_override_applied=True`` case (vertical-2
+ user override per project_mdx03_frame_lock 2026-05-15 lock); drift
+ here flips F4 layer-A axis. mdx 04 ``top`` zone pins ``None`` for
+ min_height_px + frame_cardinality_strict (no frame cardinality on
+ the top zone — observed current state, not invented).
+ """
+ snapshot = json.loads((SNAPSHOTS_DIR / "layout.json").read_text(encoding="utf-8"))
+ expected = snapshot[mdx_id]
+ run = multi_mdx_runs[mdx_id]
+ s7 = json.loads(
+ (run.run_dir / "steps" / "step07_layout.json").read_text(encoding="utf-8")
+ )
+ s8 = json.loads(
+ (run.run_dir / "steps" / "step08_zone_region_ratios.json").read_text(encoding="utf-8")
+ )
+ d7 = s7.get("data") or {}
+ d8 = s8.get("data") or {}
+ css = d7.get("layout_css") or {}
+ actual = {
+ "step7_step_status": s7.get("step_status"),
+ "step7_pipeline_path_connected": s7.get("pipeline_path_connected"),
+ "layout_preset": d7.get("layout_preset"),
+ "auto_layout_preset": d7.get("auto_layout_preset"),
+ "layout_override_applied": d7.get("layout_override_applied"),
+ "zones_count": d7.get("zones_count"),
+ "unit_count": d7.get("unit_count"),
+ "layout_candidates": d7.get("layout_candidates") or [],
+ "computation": css.get("computation"),
+ "dynamic_rows": css.get("dynamic_rows"),
+ "dynamic_cols": css.get("dynamic_cols"),
+ "heights_px": css.get("heights_px"),
+ "widths_px": css.get("widths_px"),
+ "ratios": css.get("ratios"),
+ "width_ratios": css.get("width_ratios"),
+ "step8_step_status": s8.get("step_status"),
+ "step8_pipeline_path_connected": s8.get("pipeline_path_connected"),
+ "zone_heights_px_planned": d8.get("zone_heights_px_planned"),
+ "zone_widths_px_planned": d8.get("zone_widths_px_planned"),
+ "zone_col_ratios_planned": d8.get("zone_col_ratios_planned"),
+ "per_zone_layout_shape": [
+ _layout_zone_shape(z) for z in (d8.get("per_zone_plan") or [])
+ ],
+ }
+ for key, want in expected.items():
+ got = actual[key]
+ assert got == want, (
+ f"{mdx_id}.mdx layout.{key} drift: expected {want!r}, got {got!r}"
+ )
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize("mdx_id", MDX_SET)
+def test_slot_payload_snapshot_matches(
+ mdx_id: str, multi_mdx_runs: Dict[str, PipelineRun]
+) -> None:
+ """u8 — F2 slot_payload: pin observed step12_slot_payload per_zone shape per mdx.
+
+ Snapshot pins content-agnostic structural shape (builder + slot
+ names + list cardinality + dict sub-list counts + string non-empty
+ flags), not literal payload text. MDX wording tweaks won't drift
+ this; builder swap, slot rename, slot count drift, or __empty__
+ transitions will. Empty zones must have ``builder is None`` and no
+ slots — this is the IMP-87 empty_shell honesty contract surface for
+ F2.
+ """
+ snapshot = json.loads((SNAPSHOTS_DIR / "slot_payload.json").read_text(encoding="utf-8"))
+ expected = snapshot[mdx_id]
+ run = multi_mdx_runs[mdx_id]
+ raw = json.loads(
+ (run.run_dir / "steps" / "step12_slot_payload.json").read_text(encoding="utf-8")
+ )
+ per_zone = raw["data"].get("per_zone") or []
+ actual = [_slot_payload_zone_shape(z) for z in per_zone]
+ assert len(actual) == len(expected), (
+ f"{mdx_id}.mdx step12 zone_count drift: expected {len(expected)}, "
+ f"got {len(actual)} (positions={[z.get('position') for z in actual]})"
+ )
+ for idx, (act, exp) in enumerate(zip(actual, expected)):
+ assert act == exp, (
+ f"{mdx_id}.mdx step12 zone[{idx}] ({exp.get('position')!r}) shape drift: "
+ f"expected {exp}, got {act}"
+ )
+
+
+_ZONE_TAG_RE = re.compile(
+ r'<div[^>]*\sdata-zone-position="([^"]+)"[^>]*\sdata-template-id="([^"]+)"',
+ re.IGNORECASE,
+)
+_SLIDE_ROOT_RE = re.compile(r'<div\s+class="slide"\s+data-page="1"')
+_TITLE_RE = re.compile(r'<title>([^<]*)', re.IGNORECASE)
+
+
+def _extract_html_zone_topology(html: str) -> List[dict]:
+ """Extract (position, template_id) pairs in document order from final.html."""
+ return [
+ {"position": m.group(1), "template_id": m.group(2)}
+ for m in _ZONE_TAG_RE.finditer(html)
+ ]
+
+
+@pytest.mark.integration
+@pytest.mark.parametrize("mdx_id", MDX_SET)
+def test_final_html_snapshot_matches(
+ mdx_id: str, multi_mdx_runs: Dict[str, PipelineRun]
+) -> None:
+ """u11 — F5 final.html extraction: pin step13_render metadata + on-disk HTML structure.
+
+ Cross-snapshot parity gate: ``html_zone_topology`` (extracted from
+ final.html via ``data-zone-position`` / ``data-template-id`` markers)
+ MUST equal step12 slot_payload (u8) ``(position, template_id)``
+ sequence — Jinja2 renders from step12, not step09, so this is the
+ correct upstream parity (step09 selection vs step12 ``__empty__``
+ collapse is intentional per IMP-87 honesty gate and surfaces in u8).
+ Drift between final.html and slot_payload = render pipeline
+ disconnect. ``final.html`` on-disk size also MUST equal step13's
+ reported ``final_html_size_bytes`` — byte parity proves no
+ truncation / no double-write race.
+ """
+ snapshot = json.loads((SNAPSHOTS_DIR / "final_html.json").read_text(encoding="utf-8"))
+ expected = snapshot[mdx_id]
+ run = multi_mdx_runs[mdx_id]
+ raw13 = json.loads(
+ (run.run_dir / "steps" / "step13_render.json").read_text(encoding="utf-8")
+ )
+ d13 = raw13.get("data") or {}
+ ri = d13.get("render_inputs") or {}
+ final_path = run.run_dir / "final.html"
+ assert final_path.is_file(), f"{mdx_id}.mdx final.html missing at {final_path}"
+ html = final_path.read_text(encoding="utf-8")
+ title_match = _TITLE_RE.search(html)
+ html_title = title_match.group(1).strip() if title_match else ""
+ html_topology = _extract_html_zone_topology(html)
+ actual = {
+ "step13_status": raw13.get("step_status"),
+ "step13_pipeline_path_connected": raw13.get("pipeline_path_connected"),
+ "render_inputs_zones_count": ri.get("zones_count"),
+ "render_inputs_layout_preset": ri.get("layout_preset"),
+ "render_inputs_slide_title_nonempty": bool((ri.get("slide_title") or "").strip()),
+ "render_inputs_slide_footer_nonempty": bool((ri.get("slide_footer") or "").strip()),
+ "html_title_matches_render_input": html_title == (ri.get("slide_title") or "").strip(),
+ "html_slide_root_count": len(_SLIDE_ROOT_RE.findall(html)),
+ "html_slide_footer_present": '