C.E.L_Slide_test2/tests/test_mdx04_vp_routing.py

"""IMP-#85 u6 — mdx04 VP routing regression against the real V4 evidence.

Scope (Stage 2 lock):
  - Use the production ``tests/matching/v4_full32_result.yaml`` + the production
    ``templates/phase_z2/catalog/frame_contracts.yaml`` (no fixtures, no mocks).
  - Prove that ``sw_dependency_four_problems`` (VP rank-1 on ``04-2.1``, VP
    rank-2 on ``04-2.2``) is excluded from ``lookup_v4_candidates`` after u4,
    while ``lookup_v4_all_judgments`` retains it as Step 7-A raw telemetry.
  - Guard mdx03 dynamically — the actual rank-1 winners on ``03-1`` / ``03-2``
    must be non-VP per catalog AND must survive into live candidates.
  - VP gating is asserted data-driven (catalog ``visual_pending: true`` flag),
    never hard-coded — matches Stage 1/2 ``feedback_no_hardcoding`` guardrail.

Out of scope:
  - Implementing the 17 missing VP builders (별 P0 backlog, IMP-04b / #42).
  - VP semantics redefinition or VP frame removal from V4 evidence.
  - Adapter pipeline redesign.
"""
from __future__ import annotations

from src.phase_z2_mapper import get_contract
from src.phase_z2_pipeline import (
    load_v4_result,
    lookup_v4_all_judgments,
    lookup_v4_candidates,
)

CRASH_TEMPLATE_ID = "sw_dependency_four_problems"


def _rank1_template_id(v4: dict, section_id: str) -> str:
    judgments = v4["mdx_sections"][section_id]["judgments_full32"]
    return judgments[0]["template_id"]


# ─── Dynamic catalog proof — VP flag is data-driven ─────────────


def test_crash_template_is_visual_pending_in_catalog():
    """Catalog declares ``sw_dependency_four_problems.visual_pending: true``.

    Locks the data-driven contract — the entire u4 / u6 chain rests on this
    YAML flag, not a hard-coded frame allow-list. If the catalog ever drops
    the flag without registering the ``cards_4_grid`` builder, this assertion
    surfaces the regression before mdx04 crashes the mapper.
    """
    contract = get_contract(CRASH_TEMPLATE_ID)
    assert isinstance(contract, dict), CRASH_TEMPLATE_ID
    assert contract.get("visual_pending") is True


# ─── mdx04-2.1 — VP frame at rank 1 ─────────────────────────────


def test_mdx04_2_1_vp_rank_1_marked_blocked_runtime():
    """``04-2.1`` rank-1 VP crash frame — Emergency P2 (2026-05-26) 이후
    drop 이 아니라 candidate_status='blocked_runtime' 으로 보존·표시된다.
    crash 방지는 status 기반 라우팅(자동 렌더 제외)이 담당. 구 drop 계약은
    include_blocked_runtime=False 로 존속."""
    v4 = load_v4_result()
    assert _rank1_template_id(v4, "04-2.1") == CRASH_TEMPLATE_ID

    candidates = lookup_v4_candidates(v4, "04-2.1", max_n=6)
    by_tid = {c.template_id: c for c in candidates}
    assert CRASH_TEMPLATE_ID in by_tid
    assert by_tid[CRASH_TEMPLATE_ID].candidate_status == "blocked_runtime"
    # VP 후보는 auto_renderable 로 분류되면 안 된다 (crash-path 차단 핵심)
    for c in candidates:
        contract = get_contract(c.template_id) or {}
        if contract.get("visual_pending") is True:
            assert c.candidate_status == "blocked_runtime"

    legacy = lookup_v4_candidates(
        v4, "04-2.1", max_n=6, include_blocked_runtime=False,
    )
    assert CRASH_TEMPLATE_ID not in [c.template_id for c in legacy]


def test_mdx04_2_1_retains_vp_frame_in_raw_judgments():
    """Step 7-A axis preservation — raw 32-entry telemetry still carries VP."""
    v4 = load_v4_result()
    all_tids = [j.template_id for j in lookup_v4_all_judgments(v4, "04-2.1")]
    assert CRASH_TEMPLATE_ID in all_tids


# ─── mdx04-2.2 — VP frame at rank 2 ─────────────────────────────


def test_mdx04_2_2_vp_rank_2_marked_blocked_runtime():
    """``04-2.2`` rank-2 VP crash frame — Emergency P2: 보존 + blocked_runtime.
    비-VP rank-1 이 선두 유지, VP 는 status 로 자동 렌더에서 제외."""
    v4 = load_v4_result()
    rank_1 = _rank1_template_id(v4, "04-2.2")
    rank_1_contract = get_contract(rank_1) or {}
    # Pre-condition for this regression: rank-1 on 04-2.2 is non-VP.
    assert rank_1_contract.get("visual_pending") is not True

    candidates = lookup_v4_candidates(v4, "04-2.2", max_n=6)
    tids = [c.template_id for c in candidates]

    assert tids[0] == rank_1
    by_tid = {c.template_id: c for c in candidates}
    if CRASH_TEMPLATE_ID in by_tid:
        assert by_tid[CRASH_TEMPLATE_ID].candidate_status == "blocked_runtime"

    legacy = lookup_v4_candidates(
        v4, "04-2.2", max_n=6, include_blocked_runtime=False,
    )
    assert CRASH_TEMPLATE_ID not in [c.template_id for c in legacy]


def test_mdx04_2_2_retains_vp_frame_in_raw_judgments():
    """Raw judgments path preserves VP frame regardless of its rank."""
    v4 = load_v4_result()
    all_tids = [j.template_id for j in lookup_v4_all_judgments(v4, "04-2.2")]
    assert CRASH_TEMPLATE_ID in all_tids


# ─── mdx03 dynamic guard — non-VP rank-1 survives ───────────────


def test_mdx03_rank_1_non_vp_survives_live_candidates():
    """Non-VP rank-1 winners on mdx03 sections must still win after u4.

    Dynamic check — pulls rank-1 from the V4 yaml + catalog VP flag at runtime.
    No hard-coded template_id list; only the regression contract is asserted.
    """
    v4 = load_v4_result()
    for section_id in ("03-1", "03-2"):
        rank_1 = _rank1_template_id(v4, section_id)
        contract = get_contract(rank_1) or {}
        assert contract.get("visual_pending") is not True, (
            f"{section_id} rank-1 ({rank_1}) unexpectedly VP — guard precondition broken"
        )
        candidates = lookup_v4_candidates(v4, section_id, max_n=6)
        tids = [c.template_id for c in candidates]
        assert tids and tids[0] == rank_1, (
            f"{section_id}: expected rank-1 ({rank_1}) live, got {tids}"
        )