kyeongmin
c59864eb9a
Some checks failed
Multi-MDX Regression (IMP-91) / multi-mdx-regression (push) Failing after 31s
- u2~u5: tests/integration/test_multi_mdx_regression.py — MDX_SET=(01..05) cached integration runs + status/structural/visual snapshots + full_mdx_coverage assertion (9 snapshots populated for 01-05). - u6~u11: F0 normalize / F1 V4 ranking / F2 slot_payload / F3 classifier-only AI / F4 layout / F5 final.html axis per MDX_SET. - u12: pyproject.toml — pytest-json-report>=1.5 in dev extras. - u13: .github/workflows/multi-mdx-regression.yml — pytest+artifact CI. - u14: scripts/update_status_board.py + tests/scripts/test_update_status_board.py — idempotent JSON marker updater (3 unit tests pass). - u15: PHASE-Z-PIPELINE-STATUS-BOARD.md — 30 F0-F5 × mdx01-05 markers initialized `?` + workflow wiring. Stage 4 verify: 59/59 PASS targeted (smoke 6 + updater 3 + integration 50), 386/386 PASS regression umbrella, 0 failures. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
74 lines
4.1 KiB
JSON
74 lines
4.1 KiB
JSON
{
|
|
"_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"
|
|
}
|
|
}
|