M3: implement Data Quality Workbench

Five rule scanners (duplicate customers, missing fields, odometer regression, booking overlap, status conflict) run automatically after seed and via an explicit scan endpoint. Issue defer/reject/merge-customers endpoints with transactional customer merge (booking rewiring, tombstone, audit). Data Quality nav + workbench UI with two-column duplicate comparison and inline (non-native) confirm. Dashboard attention items now link to issues. 35 backend tests passing, ruff clean. Fixed a real false-positive bug in odometer-regression detection found through iteration on seed data, and two TS narrowing errors. Verified end-to-end via browser: S2 merge and S4 overlap scenarios.
This commit is contained in:
NuklearRabbit
2026-08-01 22:11:06 +02:00
parent 0091c57c7f
commit a7cbeaae3b
17 changed files with 1127 additions and 5 deletions
+2
View File
@@ -86,9 +86,11 @@ def get_dashboard(
detail=issue.evidence_json.get("summary", ""),
link_type=link_type,
link_ref=link_ref,
issue_ref=issue.public_ref,
)
)
attention_items.sort(key=lambda item: _SEVERITY_ORDER.get(item.severity, 3))
attention_items = attention_items[:8]
today = _today()
bookings = db.scalars(select(Booking)).all()
+146
View File
@@ -0,0 +1,146 @@
from __future__ import annotations
from fastapi import APIRouter, Depends, HTTPException, Query
from sqlalchemy import select
from sqlalchemy.orm import Session
from app.api.deps import get_current_user, get_db, require_operations_manager
from app.models.customer import Customer
from app.models.data_quality import DataQualityIssue
from app.models.vehicle import Vehicle
from app.schemas import (
CurrentUser,
DataQualityIssueDetailOut,
DataQualityIssueOut,
MergeCustomersRequest,
MergeCustomersResult,
ScanResultOut,
)
from app.services.data_quality import defer_issue, merge_customers, reject_issue, run_scan
router = APIRouter(prefix="/api/v1/data-quality", tags=["data-quality"])
def _to_out(issue: DataQualityIssue) -> DataQualityIssueOut:
return DataQualityIssueOut(
public_ref=issue.public_ref,
rule_type=issue.rule_type,
entity_type=issue.entity_type,
entity_ref=issue.evidence_json.get("entity_ref", ""),
severity=issue.severity,
status=issue.status,
evidence=issue.evidence_json,
detected_at=issue.detected_at,
resolved_at=issue.resolved_at,
)
@router.get("/issues", response_model=list[DataQualityIssueOut])
def list_issues(
status: str | None = Query(default=None),
rule_type: str | None = Query(default=None),
severity: str | None = Query(default=None),
db: Session = Depends(get_db),
_user: CurrentUser = Depends(get_current_user),
) -> list[DataQualityIssueOut]:
stmt = select(DataQualityIssue).order_by(DataQualityIssue.detected_at.desc())
if status:
stmt = stmt.where(DataQualityIssue.status == status)
if rule_type:
stmt = stmt.where(DataQualityIssue.rule_type == rule_type)
if severity:
stmt = stmt.where(DataQualityIssue.severity == severity)
issues = db.scalars(stmt).all()
return [_to_out(i) for i in issues]
def _snapshot(entity_type: str, ref: str, db: Session) -> dict | None:
if entity_type == "customer":
obj = db.scalar(select(Customer).where(Customer.public_ref == ref))
if obj is None:
return None
return {
"public_ref": obj.public_ref,
"first_name": obj.first_name,
"last_name": obj.last_name,
"email": obj.email,
"phone": obj.phone,
"postal_code": obj.postal_code,
"city": obj.city,
}
obj = db.scalar(select(Vehicle).where(Vehicle.public_ref == ref))
if obj is None:
return None
return {
"public_ref": obj.public_ref,
"make": obj.make,
"model": obj.model,
"location": obj.location,
"operational_status": obj.operational_status,
"odometer_km": obj.odometer_km,
}
@router.get("/issues/{public_ref}", response_model=DataQualityIssueDetailOut)
def get_issue(
public_ref: str,
db: Session = Depends(get_db),
_user: CurrentUser = Depends(get_current_user),
) -> DataQualityIssueDetailOut:
issue = db.scalar(select(DataQualityIssue).where(DataQualityIssue.public_ref == public_ref))
if issue is None:
raise HTTPException(status_code=404, detail="Data quality issue not found")
base = _to_out(issue)
related_refs = issue.evidence_json.get("related_refs", [])
related_entity_type = (
"customer" if issue.rule_type == "possible_duplicate_customer" else "vehicle"
)
return DataQualityIssueDetailOut(
**base.model_dump(),
entity_snapshot=_snapshot(issue.entity_type, base.entity_ref, db),
related_snapshots=[
snap
for ref in related_refs
if (snap := _snapshot(related_entity_type, ref, db)) is not None
],
)
@router.post("/issues/{public_ref}/defer", response_model=DataQualityIssueOut)
def defer(
public_ref: str,
db: Session = Depends(get_db),
user: CurrentUser = Depends(get_current_user),
) -> DataQualityIssueOut:
issue = defer_issue(db, public_ref, user)
return _to_out(issue)
@router.post("/issues/{public_ref}/reject", response_model=DataQualityIssueOut)
def reject(
public_ref: str,
db: Session = Depends(get_db),
user: CurrentUser = Depends(get_current_user),
) -> DataQualityIssueOut:
issue = reject_issue(db, public_ref, user)
return _to_out(issue)
@router.post("/issues/{public_ref}/merge-customers", response_model=MergeCustomersResult)
def merge(
public_ref: str,
body: MergeCustomersRequest,
db: Session = Depends(get_db),
user: CurrentUser = Depends(require_operations_manager),
) -> MergeCustomersResult:
result = merge_customers(db, public_ref, body.survivor_ref, body.field_overrides, user)
return MergeCustomersResult(**result)
@router.post("/scan", response_model=ScanResultOut)
def scan(
db: Session = Depends(get_db),
_user: CurrentUser = Depends(require_operations_manager),
) -> ScanResultOut:
result = run_scan(db)
return ScanResultOut(created=result.created)