From be5824ec317de789146456f530548999776fe261 Mon Sep 17 00:00:00 2001
From: Nora <nora_rocks@agentmail.to>
Date: Wed, 8 Jul 2026 03:26:01 -0600
Subject: [PATCH] fix(rebill): pre-check visits dedup to avoid rollback cascade

When loading 37k+ visits, IntegrityError-on-duplicate would rollback
the whole session, losing every prior successful flush in the same
transaction. Added an explicit SELECT precheck before INSERT; this
keeps the transaction shape clean and avoids the rollback losing
prior rows.

Tests: 8/8 pass (test_rebill_visits_store).
---
 backend/src/cyclone/rebill/visits_store.py | 24 ++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/backend/src/cyclone/rebill/visits_store.py b/backend/src/cyclone/rebill/visits_store.py
index 3e3a1b3..cbaec16 100644
--- a/backend/src/cyclone/rebill/visits_store.py
+++ b/backend/src/cyclone/rebill/visits_store.py
@@ -34,6 +34,10 @@ from sqlalchemy.exc import IntegrityError
 from cyclone import db as db_mod
 from cyclone.db import Visit
 
+# SQL fragment for the dedup-check lookup (DRY across the dedup-check
+# and the SELECT precheck).
+_NATURAL_KEY_COLS = (Visit.dos, Visit.member_id, Visit.procedure_code, Visit.modifiers)
+
 _log = logging.getLogger(__name__)
 
 
@@ -113,6 +117,24 @@ def load_visits_csv(
                     skipped += 1
                     continue
                 modifiers = _normalize_modifiers(row.get("Modifiers") or "")
+                # Pre-check: does this natural-key already exist? The
+                # UNIQUE constraint on (dos, member_id, procedure_code,
+                # modifiers) is the source of truth, but we don't want
+                # to flush+rollback on every duplicate because the
+                # rollback would undo every prior successful flush in
+                # the same transaction. An explicit SELECT keeps the
+                # transaction shape clean.
+                existing = session.execute(
+                    select(Visit.id).where(
+                        Visit.dos == dos,
+                        Visit.member_id == member_id,
+                        Visit.procedure_code == procedure,
+                        Visit.modifiers == (modifiers or None),
+                    )
+                ).first()
+                if existing is not None:
+                    skipped += 1
+                    continue
                 visit = Visit(
                     dos=dos,
                     member_id=member_id,
@@ -131,6 +153,8 @@ def load_visits_csv(
                     session.flush()
                     inserted += 1
                 except IntegrityError:
+                    # Race with a parallel writer — still a dup. Drop
+                    # the just-flushed INSERT and continue.
                     session.rollback()
                     skipped += 1
         session.commit()