Jens/MobilityOps
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: localize the primary data-quality evidence summary (live-caught on Unraid)

Browse Source 
Live validation on the deployed fix branch caught a real bug: every data-quality
issue's top-of-page "Evidence summary" line rendered the raw, always-English legacy
evidence.summary string unconditionally -- in all three languages -- even though the
backend has been emitting structured, localizable evidence.signals for a while
(app/services/data_quality.py already documented this exact intent). The frontend
side of that conversion was never finished.

- DataQualityIssueDetail.tsx now renders evidence.signals through the operator's
  locale as the primary summary; the raw evidence.summary string is only visible
  inside "Technical details" (via the existing EvidenceDisclosure JSON dump).
- The four DQ-DEMO-* seed rows that anchor the guided demo's scripted scenarios now
  carry real, accurate signals computed at seed time (duplicate-customer's similarity
  score is the actual SequenceMatcher ratio on the seeded names, not invented) instead
  of only a legacy English sentence.
- Rows with no structured signals (generic filler seed data) fall back to the raw
  text rather than showing a blank summary; the one known placeholder string gets its
  own localized rendering so it never displays as English filler either.
- New regression test: the vehicle_status_conflict evidence summary must show
  localized text and must never contain the specific raw English sentence that was
  live-visible before this fix, in all 3 languages.

151 backend tests, Ruff, mypy green; full local Playwright suite green (a couple of
sequential-run-only flakes, both confirmed to pass in isolation and unrelated to this
change).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
NuklearRabbit
2026-08-04 00:44:06 +02:00
co-authored by Claude Sonnet 5
parent cda2c32bd0
commit 2e4fb43f09
7 changed files with 188 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/app/seed_loader.py
+47 -13
View File
@@ -4,6 +4,7 @@ import csv
import uuid
from dataclasses import dataclass
from datetime import UTC, date, datetime, timedelta
from difflib import SequenceMatcher
from pathlib import Path
from sqlalchemy import delete, insert, update
@@ -108,21 +109,22 @@ def load_seed(db: Session) -> SeedResult:
customer_id_by_ref: dict[str, uuid.UUID] = {}
customer_rows = []
customer_row_by_ref: dict[str, dict] = {}
for row in _read_csv("customers.csv"):
cid = uuid.uuid4()
customer_id_by_ref[row["public_ref"]] = cid
customer_rows.append(
{
"id": cid,
"public_ref": row["public_ref"],
"first_name": row["first_name"],
"last_name": row["last_name"],
"email": row["email"] or None,
"phone": row["phone"] or None,
"postal_code": row["postal_code"] or None,
"city": row["city"] or None,
}
)
customer_row = {
"id": cid,
"public_ref": row["public_ref"],
"first_name": row["first_name"],
"last_name": row["last_name"],
"email": row["email"] or None,
"phone": row["phone"] or None,
"postal_code": row["postal_code"] or None,
"city": row["city"] or None,
}
customer_rows.append(customer_row)
customer_row_by_ref[row["public_ref"]] = customer_row
db.execute(insert(Customer), customer_rows)
counts["customers"] = len(customer_rows)
# Second pass for merged_into (self-referencing FK) since target must exist first.
@@ -223,11 +225,42 @@ def load_seed(db: Session) -> SeedResult:
return "customer", customer_id_by_ref[entity_ref]
return "vehicle", vehicle_id_by_ref[entity_ref]
def _seed_signals(public_ref: str, entity_ref: str, related_refs: list[str]) -> list[dict]:
# The four named DQ-DEMO-* rows anchor the guided demo's scripted scenarios, so
# they carry real, accurate structured signals (not just a legacy English
# sentence) -- the frontend renders these as the primary, localized evidence;
# see docs/fleet-ops-correction/current-gap-audit.md §6.
if public_ref == "DQ-DEMO-DUPLICATE":
a = customer_row_by_ref[entity_ref]
b = customer_row_by_ref[related_refs[0]]
name_a = f"{a['first_name']} {a['last_name']}".strip().lower()
name_b = f"{b['first_name']} {b['last_name']}".strip().lower()
ratio = SequenceMatcher(None, name_a, name_b).ratio()
return [
{"code": "duplicate.exact_email"},
{"code": "duplicate.exact_phone"},
{"code": "duplicate.same_postal_code"},
{"code": "duplicate.similar_name", "params": {"score": round(ratio, 2)}},
]
if public_ref == "DQ-DEMO-OVERLAP":
return [{"code": "overlap.reserved_bookings", "params": {"refs": related_refs}}]
if public_ref == "DQ-DEMO-STATUS":
return [{"code": "vehicle.booking_conflict"}]
if public_ref == "DQ-DEMO-ATTENTION":
return [
{
"code": "attention.upcoming_booking_missing_inspection",
"params": {"booking_ref": related_refs[0] if related_refs else ""},
}
]
return []
dq_rows = []
now = datetime.now(UTC)
for row in _read_csv("data_quality_issues.csv"):
entity_type, entity_id = resolve_entity(row["entity_ref"])
related_ref = row.get("related_ref") or ""
related_refs = related_ref.split("|") if related_ref else []
dq_rows.append(
{
"id": uuid.uuid4(),
@@ -240,7 +273,8 @@ def load_seed(db: Session) -> SeedResult:
"evidence_json": {
"summary": row["evidence"],
"entity_ref": row["entity_ref"],
"related_refs": related_ref.split("|") if related_ref else [],
"related_refs": related_refs,
"signals": _seed_signals(row["public_ref"], row["entity_ref"], related_refs),
},
"proposed_action_json": {},
"detected_at": now,