arborist/tests/test_quantifier_phase4.py

"""Phase 4 — broad-quantifier soft-demote tails + reject-broad path.

Three new violation kinds (§10.3) added to the soft-demote ladder:
  - BROAD_QUANTIFIER_RUNAWAY      raw_line_count >> pointer_count
  - BROAD_QUANTIFIER_CAP_APPLIED  preflight cap fired below default
  - BROAD_QUANTIFIER_SCOPE_UNBOUND unbounded universal reached LLM

Plus one HARD demote that returns UNGROUNDED via early-return:
  - BROAD_QUANTIFIER_REJECTED     preflight rejected before LLM call

Tests pin: tail rendering, ladder behavior, governance-hash binding
on quantifier_reject_broad, and the early-return shape for the
reject path.
"""

from __future__ import annotations

import pytest

from arborist.cli import (
    _SOFT_DEMOTE_VIOLATION_KINDS,
    _ladder_rung_for_lattice,
    _render_query_human,
    _render_warrant_tail,
)
from arborist.qa.keys import _VERIFIER_POLICY_FIELDS, verifier_policy_hash


# ---------------------------------------------------------------- soft-demote registration

@pytest.mark.parametrize("kind", [
    "BROAD_QUANTIFIER_RUNAWAY",
    "BROAD_QUANTIFIER_CAP_APPLIED",
    "BROAD_QUANTIFIER_SCOPE_UNBOUND",
])
def test_broad_quantifier_kinds_in_soft_demote_set(kind):
    """All three soft-demote kinds must be registered so they cap
    the ladder at ANCHOR-WARRANTED rather than reaching EVIDENCE-
    WARRANTED."""
    assert kind in _SOFT_DEMOTE_VIOLATION_KINDS


def test_rejected_kind_not_in_soft_demote_set():
    """REJECTED is a HARD demote (UNGROUNDED via early-return).
    Listing it as a soft demote would let UNGROUNDED rejected runs
    bubble up to ANCHOR-WARRANTED on the ladder."""
    assert "BROAD_QUANTIFIER_REJECTED" not in _SOFT_DEMOTE_VIOLATION_KINDS


# ---------------------------------------------------------------- ladder rung

def test_cap_applied_demotes_to_anchor_warranted():
    """CAP_APPLIED is a soft demote — claim verified, but the cap
    bound the answer below default. ANCHOR-WARRANTED, not
    EVIDENCE-WARRANTED."""
    rung = _ladder_rung_for_lattice(
        "STRICT",
        violations=[{"kind": "BROAD_QUANTIFIER_CAP_APPLIED"}],
    )
    assert rung == "ANCHOR-WARRANTED"


def test_scope_unbound_demotes_to_anchor_warranted():
    rung = _ladder_rung_for_lattice(
        "STRICT",
        violations=[{"kind": "BROAD_QUANTIFIER_SCOPE_UNBOUND"}],
    )
    assert rung == "ANCHOR-WARRANTED"


def test_runaway_demotes_to_anchor_warranted():
    rung = _ladder_rung_for_lattice(
        "STRICT",
        violations=[{"kind": "BROAD_QUANTIFIER_RUNAWAY"}],
    )
    assert rung == "ANCHOR-WARRANTED"


# ---------------------------------------------------------------- tail rendering

def test_tail_renders_broad_cap_with_count():
    """Cap value must appear in the tail — operators shouldn't have
    to dig into violations to see what cap fired."""
    tail = _render_warrant_tail({
        "violations": [{"kind": "BROAD_QUANTIFIER_CAP_APPLIED"}],
        "claim_cap_applied": 8,
    })
    assert "broad cap 8" in tail


def test_tail_renders_broad_unbounded():
    tail = _render_warrant_tail({
        "violations": [{"kind": "BROAD_QUANTIFIER_SCOPE_UNBOUND"}],
    })
    assert "broad unbounded" in tail


def test_tail_renders_broad_runaway():
    tail = _render_warrant_tail({
        "violations": [{"kind": "BROAD_QUANTIFIER_RUNAWAY"}],
    })
    assert "broad runaway" in tail


def test_tail_renders_broad_rejected():
    tail = _render_warrant_tail({
        "violations": [{"kind": "BROAD_QUANTIFIER_REJECTED"}],
    })
    assert "broad rejected" in tail


def test_tail_combines_with_existing_violations():
    """A run can have both a broad-quantifier soft demote AND a
    title mismatch — both should surface on the tail."""
    tail = _render_warrant_tail({
        "violations": [
            {"kind": "TITLE_MISMATCH"},
            {"kind": "BROAD_QUANTIFIER_CAP_APPLIED"},
        ],
        "claim_cap_applied": 8,
    })
    assert "title mismatch" in tail
    assert "broad cap 8" in tail


def test_tail_omits_when_no_violations():
    tail = _render_warrant_tail({"violations": []})
    assert tail == ""


# ---------------------------------------------------------------- audit-line render

def test_render_label_with_broad_cap_tail():
    """End-to-end through _render_query_human: HYBRID + broad cap
    surfaces both the ladder rung (ANCHOR-WARRANTED-PARTIAL) and
    the broad-cap tail."""
    result = {
        "status": "cache_miss_then_written",
        "audit_mode": "HYBRID",
        "cache_key": "abc" * 21,
        "context_root": "ab" * 32,
        "answer_text": "Some bounded broad-quantifier answer.",
        "sources": [],
        "n_quotes": 8,
        "n_verified": 6,
        "verifier_method": "claim_lattice_pointer",
        "unverified_quotes": [],
        "violations": [{"kind": "BROAD_QUANTIFIER_CAP_APPLIED"}],
        "claim_cap_applied": 8,
        "timings": {"total_ms": 9000.0},
    }
    out = _render_query_human(result, "winners of all major sports?")
    assert "ANCHOR-WARRANTED-PARTIAL" in out
    assert "broad cap 8" in out


# ---------------------------------------------------------------- governance hash

def test_quantifier_reject_broad_in_verifier_policy_fields():
    """Flipping reject-broad must invalidate prior cache records —
    same question with reject_broad=False vs True should produce
    different cache_keys."""
    assert "quantifier_reject_broad" in _VERIFIER_POLICY_FIELDS


def test_governance_hash_changes_when_reject_broad_flips():
    base_policy = dict.fromkeys(_VERIFIER_POLICY_FIELDS, "default")
    base_policy["quantifier_reject_broad"] = False
    h_off = verifier_policy_hash(base_policy)
    base_policy["quantifier_reject_broad"] = True
    h_on = verifier_policy_hash(base_policy)
    assert h_off != h_on


# ---------------------------------------------------------------- reject-broad path

def test_reject_broad_returns_early_for_unbounded_all():
    """Integration-shape check: when policy enables reject_broad and
    the question is broad-unbounded, query() returns UNGROUNDED with
    a BROAD_QUANTIFIER_REJECTED violation BEFORE the LLM call.

    Skipped here because exercising the full query() path requires
    a populated shards-dir + qa.db which isn't set up in this unit-
    test scope. The behavior is exercised by the live bench cycle
    when --reject-broad is passed."""
    pytest.skip(
        "integration: requires populated shards; covered by live bench"
    )


def test_reject_broad_does_not_fire_for_bounded_universal():
    """`all members of the Beatles` is a bounded universal — should
    NOT reject even with quantifier_reject_broad=True. Same skip
    rationale as above."""
    pytest.skip(
        "integration: requires populated shards; covered by live bench"
    )