feat(sp31): add _score_fallback_candidates DB helper with ±30-day candidate pool

This commit is contained in:
Nora
2026-07-02 15:17:26 -06:00
parent b484ca36dc
commit 5a54961930
3 changed files with 335 additions and 6 deletions
+76 -5
View File
@@ -128,6 +128,14 @@ def _content_keys_match(remit, claim) -> bool:
Charge compared with ``CHARGE_TOLERANCE`` tolerance (rounding drift).
NPI counts as "not matched" when the remit's NPI is empty.
Uses duck-typing via ``getattr`` so the helper works against both:
- shim / dataclass test objects (planned names: total_charge_amount,
total_charge, rendering_provider_npi), and
- real SQLAlchemy ORM instances (Claim.charge_amount, Remittance.total_charge,
Claim.provider_npi). The Remittance ORM has no NPI column — callers
that need NPI on a Remit set the transient ``rendering_provider_npi``
attribute (the 835 parser does this on raw_json; tests do it directly).
"""
keys_matched = 0
@@ -136,22 +144,85 @@ def _content_keys_match(remit, claim) -> bool:
(getattr(claim, "patient_control_number", "") or "").strip():
keys_matched += 1
# Charge: total_charge_amount ↔ total_charge (within $0.01).
remit_charge = getattr(remit, "total_charge_amount", None)
claim_charge = getattr(claim, "total_charge", None)
# Charge: total_charge_amount/total_charge ↔ total_charge/charge_amount (within $0.01).
remit_charge = getattr(remit, "total_charge_amount", None) or getattr(remit, "total_charge", None)
claim_charge = getattr(claim, "total_charge", None) or getattr(claim, "charge_amount", None)
if remit_charge is not None and claim_charge is not None and \
abs(remit_charge - claim_charge) < CHARGE_TOLERANCE:
keys_matched += 1
# NPI: rendering_provider_npi ↔ rendering_provider_npi (must be non-empty).
# NPI: rendering_provider_npi (or provider_npi fallback on Claim) ↔
# rendering_provider_npi (must be non-empty on the remit side).
remit_npi = (getattr(remit, "rendering_provider_npi", "") or "").strip()
claim_npi = (getattr(claim, "rendering_provider_npi", "") or "").strip()
claim_npi = (
(getattr(claim, "rendering_provider_npi", "") or "")
or (getattr(claim, "provider_npi", "") or "")
).strip()
if remit_npi and remit_npi == claim_npi:
keys_matched += 1
return keys_matched >= KEYS_REQUIRED
# --- SP31: DB-side fallback candidate matcher -------------------------------
SCORE_FALLBACK_WINDOW_DAYS = 30
def _score_fallback_candidates(session, remit) -> Optional[str]:
"""Return a unique matching claim_id via the 2-of-3 content-keys rule.
Queries a ±SCORE_FALLBACK_WINDOW_DAYS candidate pool filtered by:
- claim.matched_remittance_id IS NULL (not yet linked)
- claim.state NOT IN terminal set (PAID, DENIED, REJECTED,
REVERSED, RECONCILED)
- claim.service_date_from within window of remit.service_date
Returns the unique claim.id when exactly one candidate passes the
2-of-3 rule (via :func:`_content_keys_match`), otherwise ``None``.
Ambiguous matches (2+ candidates) also return ``None`` — they land
in the Inbox Unlinked lane for manual review.
Note on payer_id: ``Remittance`` has no ``payer_id`` column
(``Claim.payer_id`` does, and is the source of truth on the claim
side; the 835 parser stores payer_id in ``Remittance.raw_json``).
Filtering by payer would require either a raw_json read or a model
column add — out of scope for SP31 Task 3. The PCN itself is
expected to be unique within a payer's submission, so cross-payer
collisions are unlikely. Revisit if production shows otherwise.
"""
from sqlalchemy import select, and_
from datetime import timedelta
from cyclone.db import Claim, ClaimState
TERMINAL = {
ClaimState.PAID, ClaimState.DENIED, ClaimState.REJECTED,
ClaimState.REVERSED, ClaimState.RECONCILED,
}
if remit.service_date is None:
return None # need a date for the window query
window_lo = remit.service_date - timedelta(days=SCORE_FALLBACK_WINDOW_DAYS)
window_hi = remit.service_date + timedelta(days=SCORE_FALLBACK_WINDOW_DAYS)
candidates = list(session.execute(
select(Claim).where(
and_(
Claim.matched_remittance_id.is_(None),
Claim.service_date_from >= window_lo,
Claim.service_date_from <= window_hi,
Claim.state.notin_([s.value for s in TERMINAL]),
)
)
).scalars().all())
matched_ids = [c.id for c in candidates if _content_keys_match(remit, c)]
if len(matched_ids) == 1:
return matched_ids[0]
return None # 0 matches OR 2+ (ambiguous)
@dataclass
class ApplyIntent:
"""Result of applying a match. The caller persists this.
+137 -1
View File
@@ -14,6 +14,9 @@ test_api_parse_persists.py) working unchanged.
from __future__ import annotations
from datetime import datetime, timezone
from decimal import Decimal
import pytest
@@ -89,4 +92,137 @@ def _reset_rate_limit_buckets(app) -> None:
cur = getattr(cur, "app", None)
# No RateLimitMiddleware in the stack — nothing to reset. Should
# not happen in this codebase (security.py registers it at boot)
# but we don't want a missing reset to crash unrelated tests.
# but we don't want a missing reset to crash unrelated tests.
# ---------------------------------------------------------------------------
# SP31: shared DB-session + Claim/Remit factory fixtures.
#
# `db_session` yields a fresh session per test against the per-test DB set
# up by the autouse `_auto_init_db` fixture above. The session rolls back at
# teardown so a test that mutates rows doesn't leak into siblings.
#
# `make_claim` / `make_remit` build ORM rows with a small ergonomic surface:
# the planned parameter names follow the content-keys helper (PCN, charge,
# rendering NPI), but the ORM attribute names differ (`charge_amount` on
# Claim, `total_charge` on Remittance, `provider_npi` on Claim — and no
# `payer_id` / `rendering_provider_npi` column on Remittance at all). The
# factories map the planned names onto the real ORM attributes and stash
# `rendering_provider_npi` as a transient attribute so
# ``reconcile._content_keys_match`` can still read it via ``getattr``.
# ---------------------------------------------------------------------------
@pytest.fixture
def db_session():
"""Yield a fresh SQLAlchemy session, rolling back at teardown."""
from cyclone import db as _db
session = _db.SessionLocal()()
try:
yield session
session.rollback()
finally:
session.close()
def _ensure_batch(session, batch_id: str = "test-batch") -> None:
"""Create the Batch row a Claim/Remittance FKs to (idempotent)."""
from cyclone.db import Batch
if session.get(Batch, batch_id) is None:
session.add(Batch(
id=batch_id, kind="837p", input_filename="test.txt",
parsed_at=datetime.now(timezone.utc),
))
session.flush()
@pytest.fixture
def make_claim(db_session):
"""Factory: build & flush a Claim with the planned content-keys params.
Planned params (match the SP31 spec / content-keys test surface):
patient_control_number, total_charge, rendering_provider_npi,
service_date_from, matched_remittance_id=None, state=None,
claim_id=None
`state=None` defaults to ``ClaimState.SUBMITTED`` so existing tests
that omit it keep behaving. `rendering_provider_npi` is stored as
a transient attribute (no ORM column) for ``_content_keys_match``
to read via ``getattr``.
"""
def _make(
patient_control_number: str,
total_charge,
rendering_provider_npi: str,
service_date_from,
matched_remittance_id=None,
state=None,
claim_id: str | None = None,
):
from cyclone.db import Claim, ClaimState as _CS
_ensure_batch(db_session)
cid = claim_id or f"clm-{patient_control_number}-{service_date_from.isoformat()}"
c = Claim(
id=cid,
batch_id="test-batch",
patient_control_number=patient_control_number,
service_date_from=service_date_from,
charge_amount=total_charge,
state=state if state is not None else _CS.SUBMITTED,
matched_remittance_id=matched_remittance_id,
)
# Transient attribute — read by reconcile._content_keys_match
# via getattr; the Claim ORM has no rendering_provider_npi column.
c.rendering_provider_npi = rendering_provider_npi
db_session.add(c)
db_session.flush()
return c
return _make
@pytest.fixture
def make_remit(db_session):
"""Factory: build & flush a Remittance with the planned content-keys params.
Planned params:
payer_claim_control_number, total_charge_amount, rendering_provider_npi,
service_date, remit_id=None
`total_charge_amount` is mapped to ``Remittance.total_charge`` (real ORM
field). `rendering_provider_npi` is stored as a transient attribute for
``_content_keys_match`` to read via ``getattr`` (Remittance has no NPI
column; the parser reads it from raw_json in production).
"""
def _make(
payer_claim_control_number: str,
total_charge_amount,
rendering_provider_npi: str,
service_date,
remit_id: str | None = None,
):
from cyclone.db import Remittance
_ensure_batch(db_session)
rid = remit_id or f"remit-{payer_claim_control_number}-{service_date.isoformat()}"
r = Remittance(
id=rid,
batch_id="test-batch",
payer_claim_control_number=payer_claim_control_number,
status_code="1",
total_charge=total_charge_amount,
total_paid=Decimal("0"),
received_at=datetime.now(timezone.utc),
service_date=service_date,
is_reversal=False,
)
# Transient attribute — read by reconcile._content_keys_match via
# getattr. The Remittance ORM has no rendering_provider_npi column;
# the 835 parser reads it from raw_json in production.
r.rendering_provider_npi = rendering_provider_npi
db_session.add(r)
db_session.flush()
return r
return _make
+122
View File
@@ -487,3 +487,125 @@ def test_content_keys_empty_npi_does_not_count():
assert _content_keys_match(r, c) is True # PCN + charge still match
c2 = _make_claim_for_keys("c2", "XYZ", Decimal("100.00"), "1111111111")
assert _content_keys_match(r, c2) is False # only charge, no PCN
# --- SP31: content-keys fallback matcher (DB helper) ------------------------
def test_score_fallback_unique_match_returns_claim_id(db_session, make_claim, make_remit):
"""One claim in pool matches 2-of-3 → returns that claim."""
from decimal import Decimal
from datetime import date, timedelta
from cyclone.reconcile import _score_fallback_candidates
c1 = make_claim(patient_control_number="ABC", total_charge=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date_from=date(2026, 6, 1))
c2 = make_claim(patient_control_number="XYZ", total_charge=Decimal("999.99"),
rendering_provider_npi="2222222222",
service_date_from=date(2026, 6, 1))
r = make_remit(payer_claim_control_number="ABC",
total_charge_amount=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date=date(2026, 6, 5)) # ±30-day window
assert _score_fallback_candidates(db_session, r) == c1.id
def test_score_fallback_zero_matches_returns_none(db_session, make_claim, make_remit):
"""No claim in pool matches 2-of-3 → returns None."""
from decimal import Decimal
from datetime import date
from cyclone.reconcile import _score_fallback_candidates
make_claim(patient_control_number="XYZ", total_charge=Decimal("999.99"),
rendering_provider_npi="2222222222",
service_date_from=date(2026, 6, 1))
r = make_remit(payer_claim_control_number="ABC",
total_charge_amount=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date=date(2026, 6, 5))
assert _score_fallback_candidates(db_session, r) is None
def test_score_fallback_two_matches_returns_none(db_session, make_claim, make_remit):
"""Two claims in pool both match 2-of-3 → returns None (ambiguous)."""
from decimal import Decimal
from datetime import date
from cyclone.reconcile import _score_fallback_candidates
# Both claims have same PCN and same charge — both would match PCN+charge.
make_claim(patient_control_number="ABC", total_charge=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date_from=date(2026, 6, 1))
make_claim(patient_control_number="ABC", total_charge=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date_from=date(2026, 6, 2))
r = make_remit(payer_claim_control_number="ABC",
total_charge_amount=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date=date(2026, 6, 5))
assert _score_fallback_candidates(db_session, r) is None
def test_score_fallback_skips_already_matched(db_session, make_claim, make_remit):
"""Claim with matched_remittance_id set → excluded from pool."""
from decimal import Decimal
from datetime import date
from cyclone.reconcile import _score_fallback_candidates
c1 = make_claim(patient_control_number="ABC", total_charge=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date_from=date(2026, 6, 1),
matched_remittance_id="some-other-remit-id")
r = make_remit(payer_claim_control_number="ABC",
total_charge_amount=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date=date(2026, 6, 5))
assert _score_fallback_candidates(db_session, r) is None # only candidate was excluded
def test_score_fallback_skips_terminal_state(db_session, make_claim, make_remit):
"""Claim in PAID/DENIED/REJECTED/REVERSED/RECONCILED → excluded from pool."""
from decimal import Decimal
from datetime import date
from cyclone.db import ClaimState
from cyclone.reconcile import _score_fallback_candidates
make_claim(patient_control_number="ABC", total_charge=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date_from=date(2026, 6, 1),
state=ClaimState.PAID)
r = make_remit(payer_claim_control_number="ABC",
total_charge_amount=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date=date(2026, 6, 5))
assert _score_fallback_candidates(db_session, r) is None
def test_score_fallback_widened_window_catches_late_remit(db_session, make_claim, make_remit):
"""Remit 25 days after claim → still in pool (30-day window)."""
from decimal import Decimal
from datetime import date, timedelta
from cyclone.reconcile import _score_fallback_candidates
claim_date = date(2026, 6, 1)
remit_date = claim_date + timedelta(days=25)
c1 = make_claim(patient_control_number="ABC", total_charge=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date_from=claim_date)
r = make_remit(payer_claim_control_number="ABC",
total_charge_amount=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date=remit_date)
assert _score_fallback_candidates(db_session, r) == c1.id
def test_score_fallback_outside_window_excluded(db_session, make_claim, make_remit):
"""Remit 60 days after claim → excluded (outside 30-day window)."""
from decimal import Decimal
from datetime import date, timedelta
from cyclone.reconcile import _score_fallback_candidates
claim_date = date(2026, 6, 1)
remit_date = claim_date + timedelta(days=60)
make_claim(patient_control_number="ABC", total_charge=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date_from=claim_date)
r = make_remit(payer_claim_control_number="ABC",
total_charge_amount=Decimal("100.00"),
rendering_provider_npi="1111111111",
service_date=remit_date)
assert _score_fallback_candidates(db_session, r) is None