feat: build vehicle data platform and production pipeline

2026-07-14 12:35:33 +08:00
parent b452be3b94
commit bb59303a4b
270 changed files with 88016 additions and 1975 deletions
--- a/go/vehicle-gateway/internal/stats/source_mileage.go
+++ b/go/vehicle-gateway/internal/stats/source_mileage.go
@@ -10,10 +10,16 @@ import (
 )

 const (
-	QualityOK                 = "OK"
-	QualityNoPreviousBaseline = "NO_PREVIOUS_BASELINE"
-	QualityInvalidDelta       = "INVALID_DELTA"
-	maxSelectedDailyMileageKM = 1000
+	QualityOK                     = "OK"
+	QualityNoPreviousBaseline     = "NO_PREVIOUS_BASELINE"
+	QualityInvalidDelta           = "INVALID_DELTA"
+	QualityReasonHistorical       = "historical_source_baseline"
+	QualityReasonCurrentDayFirst  = "current_day_first_baseline"
+	maxSelectedDailyMileageKM     = 2500
+	maxSelectedDailyMileageKMSQL  = "2500"
+	maxNegativeMileageJitterKMSQL = "1"
+	directSourceKeySuffix         = "@DIRECT"
+	platformSourceKeyPrefix       = "@PLATFORM:"
 )

 type SourceMileageSample struct {
@@ -37,14 +43,37 @@ type SourceMileageSample struct {
 }

 func SourceKey(protocol envelope.Protocol, phone string, deviceID string, sourceIP string) string {
+	identity, _ := sourceKeyIdentity(phone, deviceID)
+	return string(protocol) + ":" + identity + "@" + strings.TrimSpace(sourceIP)
+}
+
+func sourceKeyIdentity(phone string, deviceID string) (string, bool) {
 	identity := strings.TrimSpace(phone)
 	if identity == "" {
 		identity = strings.TrimSpace(deviceID)
 	}
 	if identity == "" {
-		identity = "unknown"
+		return "unknown", false
 	}
-	return string(protocol) + ":" + identity + "@" + strings.TrimSpace(sourceIP)
+	return identity, true
+}
+
+func SourceKeyForKind(protocol envelope.Protocol, phone string, deviceID string, sourceIP string, sourceKind string) string {
+	return SourceKeyForSource(protocol, phone, deviceID, sourceIP, sourceKind, "")
+}
+
+func SourceKeyForSource(protocol envelope.Protocol, phone string, deviceID string, sourceIP string, sourceKind string, sourceCode string) string {
+	identity, hasIdentity := sourceKeyIdentity(phone, deviceID)
+	if strings.EqualFold(strings.TrimSpace(sourceKind), "DIRECT") && hasIdentity {
+		return string(protocol) + ":" + identity + directSourceKeySuffix
+	}
+	if strings.EqualFold(strings.TrimSpace(sourceKind), "PLATFORM") && hasIdentity {
+		sourceCode = strings.TrimSpace(sourceCode)
+		if sourceCode != "" {
+			return string(protocol) + ":" + identity + platformSourceKeyPrefix + sourceCode
+		}
+	}
+	return SourceKey(protocol, phone, deviceID, sourceIP)
 }

 func SourceMileageSampleFromMetric(sample MetricSample, identity SourceIdentity) SourceMileageSample {
@@ -53,11 +82,12 @@ func SourceMileageSampleFromMetric(sample MetricSample, identity SourceIdentity)
 		VIN:             sample.VIN,
 		StatDate:        sample.StatDate,
 		Protocol:        sample.Protocol,
-		SourceKey:       SourceKey(sample.Protocol, sample.Phone, sample.DeviceID, identity.SourceIP),
+		SourceKey:       SourceKeyForSource(sample.Protocol, sample.Phone, sample.DeviceID, identity.SourceIP, identity.SourceKind, identity.SourceCode),
 		SourceIP:        identity.SourceIP,
 		SourceEndpoint:  identity.SourceEndpoint,
 		Phone:           sample.Phone,
 		DeviceID:        sample.DeviceID,
+		PlatformName:    firstNonEmpty(sample.PlatformName, identity.PlatformName),
 		FirstTotalKM:    sample.TotalMileageKM,
 		LatestTotalKM:   sample.TotalMileageKM,
 		DailyKM:         0,
@@ -69,6 +99,81 @@ func SourceMileageSampleFromMetric(sample MetricSample, identity SourceIdentity)
 	}
 }

+func firstNonEmpty(values ...string) string {
+	for _, value := range values {
+		value = strings.TrimSpace(value)
+		if value != "" {
+			return value
+		}
+	}
+	return ""
+}
+
+func NormalizeDailyMileageDelta(deltaKM float64) (float64, bool, string) {
+	return NormalizeDailyMileageDeltaForWindow(deltaKM, time.Time{}, time.Time{})
+}
+
+// DailyMileageFromDayBoundary keeps the business formula explicit: the
+// current day's latest cumulative odometer minus the nearest earlier
+// cumulative odometer from the same source.
+func DailyMileageFromDayBoundary(previousBaselineKM float64, currentDayLatestKM float64) float64 {
+	return currentDayLatestKM - previousBaselineKM
+}
+
+func NormalizeDailyMileageDeltaForWindow(deltaKM float64, firstEventTime time.Time, latestEventTime time.Time) (float64, bool, string) {
+	if deltaKM < 0 && deltaKM >= -maxNegativeMileageJitterKM {
+		return 0, true, "negative_jitter_clamped"
+	}
+	maxMileage := float64(MileageQualityLimitKM(firstEventTime, latestEventTime))
+	if deltaKM < 0 || deltaKM > maxMileage {
+		return deltaKM, false, "outside_daily_range"
+	}
+	return deltaKM, true, ""
+}
+
+func MileageQualityWindowDays(firstEventTime time.Time, latestEventTime time.Time) int {
+	if firstEventTime.IsZero() || latestEventTime.IsZero() || !latestEventTime.After(firstEventTime) {
+		return 1
+	}
+	location := latestEventTime.Location()
+	firstYear, firstMonth, firstDay := firstEventTime.In(location).Date()
+	latestYear, latestMonth, latestDay := latestEventTime.Date()
+	firstDate := time.Date(firstYear, firstMonth, firstDay, 0, 0, 0, 0, time.UTC)
+	latestDate := time.Date(latestYear, latestMonth, latestDay, 0, 0, 0, 0, time.UTC)
+	days := int(latestDate.Sub(firstDate) / (24 * time.Hour))
+	if days < 1 {
+		return 1
+	}
+	return days
+}
+
+func MileageQualityLimitKM(firstEventTime time.Time, latestEventTime time.Time) int {
+	// When the previous natural day is missing, the business baseline walks
+	// farther back. Scale the plausibility guard by that calendar-day gap while
+	// preserving the exact cumulative-odometer difference in the current row.
+	return maxSelectedDailyMileageKM * MileageQualityWindowDays(firstEventTime, latestEventTime)
+}
+
+func ApplyMileageQualityRules(sample *SourceMileageSample) {
+	if sample == nil {
+		return
+	}
+	if sample.QualityStatus == "" {
+		sample.QualityStatus = QualityOK
+	}
+	if sample.QualityStatus != QualityOK {
+		return
+	}
+	normalized, ok, reason := NormalizeDailyMileageDeltaForWindow(sample.DailyKM, sample.FirstEventTime, sample.LatestEventTime)
+	sample.DailyKM = normalized
+	if reason != "" {
+		sample.QualityReason = reason
+	}
+	if !ok {
+		sample.QualityStatus = QualityInvalidDelta
+	}
+}
+
 func UpsertSourceMileage(ctx context.Context, exec Execer, sample SourceMileageSample) error {
 	if exec == nil {
 		panic("stats execer must not be nil")
@@ -79,6 +184,11 @@ func UpsertSourceMileage(ctx context.Context, exec Execer, sample SourceMileageS
 	if sample.QualityStatus == "" {
 		sample.QualityStatus = QualityOK
 	}
+	// MySQL DATETIME(0) may round 23:59:59.xxx into the next natural day.
+	// Truncate protocol event timestamps before persistence so day boundaries
+	// remain stable and match the TDengine event_time predicate.
+	sample.FirstEventTime = truncateMileageEventTime(sample.FirstEventTime)
+	sample.LatestEventTime = truncateMileageEventTime(sample.LatestEventTime)
 	_, err := exec.ExecContext(ctx, upsertSourceMileageSQL,
 		sample.VIN,
 		sample.StatDate,
@@ -101,6 +211,75 @@ func UpsertSourceMileage(ctx context.Context, exec Execer, sample SourceMileageS
 	return err
 }

+func truncateMileageEventTime(value time.Time) time.Time {
+	if value.IsZero() {
+		return value
+	}
+	return value.Truncate(time.Second)
+}
+
+func NormalizePlatformSourceMileage(ctx context.Context, exec Execer, vin string, statDate string, protocol envelope.Protocol) error {
+	if exec == nil {
+		panic("stats execer must not be nil")
+	}
+	if strings.TrimSpace(vin) == "" || strings.TrimSpace(statDate) == "" {
+		return nil
+	}
+	_, err := exec.ExecContext(ctx, normalizePlatformSourceMileageInsertSQL, vin, statDate, string(protocol))
+	if err != nil {
+		return err
+	}
+	_, err = exec.ExecContext(ctx, normalizePlatformSourceMileageDeleteSQL, vin, statDate, string(protocol))
+	return err
+}
+
+func NormalizePlatformSourceMileageForDate(ctx context.Context, db interface {
+	Execer
+	Queryer
+}, statDate string, protocol envelope.Protocol) (int, error) {
+	if db == nil {
+		panic("stats db must not be nil")
+	}
+	if strings.TrimSpace(statDate) == "" {
+		return 0, nil
+	}
+	rows, err := db.QueryContext(ctx, selectPlatformSourceMileageLegacyVINSQL, statDate, string(protocol))
+	if err != nil {
+		return 0, err
+	}
+	defer rows.Close()
+
+	var vins []string
+	for rows.Next() {
+		var vin string
+		if err := rows.Scan(&vin); err != nil {
+			return 0, err
+		}
+		if strings.TrimSpace(vin) != "" {
+			vins = append(vins, vin)
+		}
+	}
+	if err := rows.Err(); err != nil {
+		return 0, err
+	}
+
+	normalized := 0
+	for _, vin := range vins {
+		if err := NormalizePlatformSourceMileage(ctx, db, vin, statDate, protocol); err != nil {
+			return normalized, err
+		}
+		if err := ProjectDailyMileage(ctx, db, vin, statDate, protocol); err != nil {
+			return normalized, err
+		}
+		normalized++
+	}
+	return normalized, nil
+}
+
+func ShouldNormalizePlatformSourceMileage(sample SourceMileageSample) bool {
+	return strings.Contains(sample.SourceKey, platformSourceKeyPrefix)
+}
+
 func ProjectDailyMileage(ctx context.Context, exec Execer, vin string, statDate string, protocol envelope.Protocol) error {
 	if exec == nil {
 		panic("stats execer must not be nil")
@@ -108,9 +287,25 @@ func ProjectDailyMileage(ctx context.Context, exec Execer, vin string, statDate
 	if strings.TrimSpace(vin) == "" || strings.TrimSpace(statDate) == "" {
 		return nil
 	}
-	if _, err := exec.ExecContext(ctx, clearSelectedSourceSQL, vin, statDate, string(protocol)); err != nil {
-		return err
+	if beginner, ok := exec.(txBeginner); ok {
+		tx, err := beginner.BeginTx(ctx, nil)
+		if err != nil {
+			return err
+		}
+		if err := projectDailyMileageWithExec(ctx, tx, vin, statDate, protocol); err != nil {
+			_ = tx.Rollback()
+			return err
+		}
+		return tx.Commit()
 	}
+	return projectDailyMileageWithExec(ctx, exec, vin, statDate, protocol)
+}
+
+type txBeginner interface {
+	BeginTx(context.Context, *sql.TxOptions) (*sql.Tx, error)
+}
+
+func projectDailyMileageWithExec(ctx context.Context, exec Execer, vin string, statDate string, protocol envelope.Protocol) error {
 	if _, err := exec.ExecContext(ctx, projectDailyMileageSQL,
 		vin,
 		statDate,
@@ -142,6 +337,70 @@ func ProjectDailyMileage(ctx context.Context, exec Execer, vin string, statDate
 	return err
 }

+const upsertSourceMergedFirstTotalSQL = `CASE
+    WHEN first_total_mileage_km IS NULL OR first_total_mileage_km <= 0
+      THEN VALUES(first_total_mileage_km)
+    WHEN first_event_time IS NULL OR VALUES(first_event_time) <= first_event_time
+      THEN VALUES(first_total_mileage_km)
+    ELSE first_total_mileage_km
+  END`
+
+const upsertSourceMergedLatestTotalSQL = `CASE
+    WHEN latest_total_mileage_km IS NULL OR latest_total_mileage_km <= 0
+      THEN VALUES(latest_total_mileage_km)
+    WHEN latest_event_time IS NULL OR VALUES(latest_event_time) >= latest_event_time
+      THEN VALUES(latest_total_mileage_km)
+    ELSE latest_total_mileage_km
+  END`
+
+const upsertSourceMergedFirstEventSQL = `CASE
+    WHEN first_event_time IS NULL OR VALUES(first_event_time) <= first_event_time
+      THEN VALUES(first_event_time)
+    ELSE first_event_time
+  END`
+
+const upsertSourceMergedLatestEventSQL = `CASE
+    WHEN latest_event_time IS NULL OR VALUES(latest_event_time) >= latest_event_time
+      THEN VALUES(latest_event_time)
+    ELSE latest_event_time
+  END`
+
+const upsertSourceMergedDeltaSQL = `(` + upsertSourceMergedLatestTotalSQL + ` - ` + upsertSourceMergedFirstTotalSQL + `)`
+
+const upsertSourceMergedDailySQL = `CASE
+    WHEN ` + upsertSourceMergedDeltaSQL + ` < 0
+     AND ` + upsertSourceMergedDeltaSQL + ` >= -` + maxNegativeMileageJitterKMSQL + `
+      THEN 0
+    ELSE ` + upsertSourceMergedDeltaSQL + `
+  END`
+
+const upsertSourceMergedOutsideDailyRangeSQL = `(` + upsertSourceMergedDailySQL + ` < 0 OR ` + upsertSourceMergedDailySQL + ` > ` + upsertSourceMergedMaxMileageSQL + `)`
+
+const upsertSourceMergedMissingPreviousBaselineSQL = `(` + upsertSourceMergedFirstEventSQL + ` >= CAST(CONCAT(VALUES(stat_date), ' 00:00:00') AS DATETIME))`
+
+const upsertSourceMergedQualityWindowDaysSQL = `GREATEST(1, DATEDIFF(DATE(` + upsertSourceMergedLatestEventSQL + `), DATE(` + upsertSourceMergedFirstEventSQL + `)))`
+
+const upsertSourceMergedMaxMileageSQL = `(` + upsertSourceMergedQualityWindowDaysSQL + ` * ` + maxSelectedDailyMileageKMSQL + `)`
+
+const normalizePlatformFirstTotalSQL = `CAST(SUBSTRING_INDEX(GROUP_CONCAT(s.first_total_mileage_km ORDER BY s.first_event_time ASC, s.updated_at ASC SEPARATOR ','), ',', 1) AS DECIMAL(18,3))`
+
+const normalizePlatformLatestTotalSQL = `CAST(SUBSTRING_INDEX(GROUP_CONCAT(s.latest_total_mileage_km ORDER BY s.latest_event_time DESC, s.updated_at DESC SEPARATOR ','), ',', 1) AS DECIMAL(18,3))`
+
+const normalizePlatformDeltaSQL = `(` + normalizePlatformLatestTotalSQL + ` - ` + normalizePlatformFirstTotalSQL + `)`
+
+const normalizePlatformDailySQL = `CASE
+    WHEN ` + normalizePlatformDeltaSQL + ` < 0
+     AND ` + normalizePlatformDeltaSQL + ` >= -` + maxNegativeMileageJitterKMSQL + `
+      THEN 0
+    ELSE ` + normalizePlatformDeltaSQL + `
+  END`
+
+const normalizePlatformQualityWindowDaysSQL = `GREATEST(1, DATEDIFF(DATE(MAX(s.latest_event_time)), DATE(MIN(s.first_event_time))))`
+
+const normalizePlatformMaxMileageSQL = `(` + normalizePlatformQualityWindowDaysSQL + ` * ` + maxSelectedDailyMileageKMSQL + `)`
+
+const normalizePlatformOutsideDailyRangeSQL = `(` + normalizePlatformDailySQL + ` < 0 OR ` + normalizePlatformDailySQL + ` > ` + normalizePlatformMaxMileageSQL + `)`
+
 const upsertSourceMileageSQL = `
 INSERT INTO vehicle_daily_mileage_source
  (vin, stat_date, protocol, source_key, source_ip, source_endpoint, phone, device_id, platform_name,
@@ -154,48 +413,186 @@ VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
 	  phone = VALUES(phone),
 	  device_id = VALUES(device_id),
 	  platform_name = COALESCE(NULLIF(TRIM(VALUES(platform_name)), ''), platform_name),
-	  first_total_mileage_km = CASE
-	    WHEN first_total_mileage_km IS NULL OR first_total_mileage_km <= 0
-	      THEN VALUES(first_total_mileage_km)
-	    ELSE LEAST(first_total_mileage_km, VALUES(first_total_mileage_km))
-	  END,
-	  latest_total_mileage_km = CASE
-	    WHEN latest_total_mileage_km IS NULL OR latest_total_mileage_km <= 0
-	      THEN VALUES(latest_total_mileage_km)
-	    ELSE GREATEST(latest_total_mileage_km, VALUES(latest_total_mileage_km))
-	  END,
-	  daily_mileage_km = GREATEST(
-	    CASE
-	      WHEN latest_total_mileage_km IS NULL OR latest_total_mileage_km <= 0
-	        THEN VALUES(latest_total_mileage_km)
-      ELSE latest_total_mileage_km
-    END,
-    VALUES(latest_total_mileage_km)
-  ) - CASE
-    WHEN first_total_mileage_km IS NULL OR first_total_mileage_km <= 0
-      THEN VALUES(first_total_mileage_km)
-    ELSE LEAST(first_total_mileage_km, VALUES(first_total_mileage_km))
-  END,
+	  first_total_mileage_km = ` + upsertSourceMergedFirstTotalSQL + `,
+	  latest_total_mileage_km = ` + upsertSourceMergedLatestTotalSQL + `,
+	  daily_mileage_km = ` + upsertSourceMergedDailySQL + `,
  sample_count = sample_count + VALUES(sample_count),
-  first_event_time = CASE
-    WHEN first_event_time IS NULL OR VALUES(first_event_time) < first_event_time
-      THEN VALUES(first_event_time)
-    ELSE first_event_time
+  first_event_time = ` + upsertSourceMergedFirstEventSQL + `,
+  latest_event_time = ` + upsertSourceMergedLatestEventSQL + `,
+  quality_status = CASE
+	WHEN ` + upsertSourceMergedOutsideDailyRangeSQL + ` THEN '` + QualityInvalidDelta + `'
+    ELSE '` + QualityOK + `'
  END,
-  latest_event_time = CASE
-    WHEN latest_event_time IS NULL OR VALUES(latest_event_time) > latest_event_time
-      THEN VALUES(latest_event_time)
-    ELSE latest_event_time
+  quality_reason = CASE
+    WHEN ` + upsertSourceMergedOutsideDailyRangeSQL + ` THEN 'outside_daily_range'
+    WHEN ` + upsertSourceMergedDailySQL + ` = 0 AND ` + upsertSourceMergedDeltaSQL + ` < 0 THEN 'negative_jitter_clamped'
+	WHEN ` + upsertSourceMergedMissingPreviousBaselineSQL + ` THEN '` + QualityReasonCurrentDayFirst + `'
+	ELSE '` + QualityReasonHistorical + `'
  END,
-  quality_status = VALUES(quality_status),
-  quality_reason = VALUES(quality_reason),
  updated_at = CURRENT_TIMESTAMP
 `

-const clearSelectedSourceSQL = `
-UPDATE vehicle_daily_mileage_source
-SET is_selected = 0
-WHERE vin = ? AND stat_date = ? AND protocol = ?
+const normalizePlatformSourceMileageInsertSQL = `
+INSERT INTO vehicle_daily_mileage_source
+  (vin, stat_date, protocol, source_key, source_ip, source_endpoint, phone, device_id, platform_name,
+   first_total_mileage_km, latest_total_mileage_km, daily_mileage_km, sample_count,
+   first_event_time, latest_event_time, quality_status, quality_reason)
+SELECT
+  s.vin,
+  s.stat_date,
+  s.protocol,
+  CONCAT(s.protocol, ':', COALESCE(NULLIF(TRIM(s.phone), ''), NULLIF(TRIM(s.device_id), '')), '` + platformSourceKeyPrefix + `', COALESCE(NULLIF(TRIM(ds.source_code), ''), vi.source_code)) AS stable_source_key,
+  SUBSTRING_INDEX(GROUP_CONCAT(s.source_ip ORDER BY s.latest_event_time DESC, s.updated_at DESC SEPARATOR ','), ',', 1) AS source_ip,
+  SUBSTRING_INDEX(GROUP_CONCAT(COALESCE(s.source_endpoint, '') ORDER BY s.latest_event_time DESC, s.updated_at DESC SEPARATOR ','), ',', 1) AS source_endpoint,
+  SUBSTRING_INDEX(GROUP_CONCAT(COALESCE(s.phone, '') ORDER BY s.latest_event_time DESC, s.updated_at DESC SEPARATOR ','), ',', 1) AS phone,
+  SUBSTRING_INDEX(GROUP_CONCAT(COALESCE(s.device_id, '') ORDER BY s.latest_event_time DESC, s.updated_at DESC SEPARATOR ','), ',', 1) AS device_id,
+  COALESCE(NULLIF(TRIM(SUBSTRING_INDEX(GROUP_CONCAT(COALESCE(NULLIF(TRIM(s.platform_name), ''), ds.platform_name, vi.platform_name, '') ORDER BY s.latest_event_time DESC, s.updated_at DESC SEPARATOR ','), ',', 1)), ''), MAX(TRIM(COALESCE(ds.platform_name, vi.platform_name)))) AS platform_name,
+  ` + normalizePlatformFirstTotalSQL + ` AS first_total_mileage_km,
+  ` + normalizePlatformLatestTotalSQL + ` AS latest_total_mileage_km,
+  ` + normalizePlatformDailySQL + ` AS daily_mileage_km,
+  SUM(s.sample_count) AS sample_count,
+  MIN(s.first_event_time) AS first_event_time,
+  MAX(s.latest_event_time) AS latest_event_time,
+  CASE
+	WHEN ` + normalizePlatformOutsideDailyRangeSQL + ` THEN '` + QualityInvalidDelta + `'
+    ELSE '` + QualityOK + `'
+  END AS quality_status,
+  CASE
+    WHEN ` + normalizePlatformOutsideDailyRangeSQL + ` THEN 'outside_daily_range'
+    WHEN ` + normalizePlatformDailySQL + ` = 0 AND ` + normalizePlatformDeltaSQL + ` < 0 THEN 'negative_jitter_clamped'
+	WHEN MIN(s.first_event_time) < CAST(CONCAT(s.stat_date, ' 00:00:00') AS DATETIME)
+	  THEN '` + QualityReasonHistorical + `'
+	ELSE '` + QualityReasonCurrentDayFirst + `'
+  END AS quality_reason
+FROM vehicle_daily_mileage_source s
+LEFT JOIN vehicle_data_source ds
+  ON ds.protocol = s.protocol AND ds.source_ip = s.source_ip
+ AND ds.enabled = 1
+ AND ds.source_kind = 'PLATFORM'
+ AND ds.source_code IS NOT NULL
+ AND TRIM(ds.source_code) <> ''
+LEFT JOIN (
+  SELECT
+    identifier_value AS phone,
+    MIN(TRIM(source_code)) AS source_code,
+    MIN(COALESCE(NULLIF(TRIM(oem), ''), NULLIF(TRIM(source_code), ''))) AS platform_name
+  FROM vehicle_identifier
+  WHERE protocol = 'JT808'
+    AND identifier_type = 'JT808_PHONE'
+    AND enabled = 1
+    AND source_code IS NOT NULL
+    AND TRIM(source_code) <> ''
+  GROUP BY identifier_value
+  HAVING COUNT(DISTINCT TRIM(source_code)) = 1
+) vi
+  ON s.protocol = 'JT808' AND vi.phone = TRIM(s.phone)
+WHERE s.vin = ?
+  AND s.stat_date = ?
+  AND s.protocol = ?
+  AND s.quality_status IN ('` + QualityOK + `', '` + QualityNoPreviousBaseline + `')
+  AND COALESCE(NULLIF(TRIM(ds.source_code), ''), vi.source_code) IS NOT NULL
+  AND COALESCE(NULLIF(TRIM(s.phone), ''), NULLIF(TRIM(s.device_id), '')) IS NOT NULL
+  AND s.source_key <> CONCAT(s.protocol, ':', COALESCE(NULLIF(TRIM(s.phone), ''), NULLIF(TRIM(s.device_id), '')), '` + platformSourceKeyPrefix + `', COALESCE(NULLIF(TRIM(ds.source_code), ''), vi.source_code))
+GROUP BY s.vin, s.stat_date, s.protocol, stable_source_key
+ON DUPLICATE KEY UPDATE
+  source_ip = CASE
+    WHEN latest_event_time IS NULL OR VALUES(latest_event_time) >= latest_event_time THEN VALUES(source_ip)
+    ELSE source_ip
+  END,
+  source_endpoint = CASE
+    WHEN latest_event_time IS NULL OR VALUES(latest_event_time) >= latest_event_time THEN VALUES(source_endpoint)
+    ELSE source_endpoint
+  END,
+  phone = COALESCE(NULLIF(TRIM(VALUES(phone)), ''), phone),
+  device_id = COALESCE(NULLIF(TRIM(VALUES(device_id)), ''), device_id),
+  platform_name = COALESCE(NULLIF(TRIM(VALUES(platform_name)), ''), platform_name),
+  first_total_mileage_km = ` + upsertSourceMergedFirstTotalSQL + `,
+  latest_total_mileage_km = ` + upsertSourceMergedLatestTotalSQL + `,
+  daily_mileage_km = ` + upsertSourceMergedDailySQL + `,
+  sample_count = sample_count + VALUES(sample_count),
+  first_event_time = CASE
+    WHEN first_event_time IS NULL OR VALUES(first_event_time) <= first_event_time THEN VALUES(first_event_time)
+    ELSE first_event_time
+  END,
+  latest_event_time = CASE
+    WHEN latest_event_time IS NULL OR VALUES(latest_event_time) >= latest_event_time THEN VALUES(latest_event_time)
+    ELSE latest_event_time
+  END,
+  quality_status = CASE
+	WHEN ` + upsertSourceMergedOutsideDailyRangeSQL + ` THEN '` + QualityInvalidDelta + `'
+    ELSE '` + QualityOK + `'
+  END,
+  quality_reason = CASE
+    WHEN ` + upsertSourceMergedOutsideDailyRangeSQL + ` THEN 'outside_daily_range'
+    WHEN ` + upsertSourceMergedDailySQL + ` = 0 AND ` + upsertSourceMergedDeltaSQL + ` < 0 THEN 'negative_jitter_clamped'
+	WHEN ` + upsertSourceMergedMissingPreviousBaselineSQL + ` THEN '` + QualityReasonCurrentDayFirst + `'
+	ELSE '` + QualityReasonHistorical + `'
+  END,
+  updated_at = CURRENT_TIMESTAMP
+`
+
+const normalizePlatformSourceMileageDeleteSQL = `
+DELETE s
+FROM vehicle_daily_mileage_source s
+LEFT JOIN vehicle_data_source ds
+  ON ds.protocol = s.protocol AND ds.source_ip = s.source_ip
+ AND ds.enabled = 1
+ AND ds.source_kind = 'PLATFORM'
+ AND ds.source_code IS NOT NULL
+ AND TRIM(ds.source_code) <> ''
+LEFT JOIN (
+  SELECT
+    identifier_value AS phone,
+    MIN(TRIM(source_code)) AS source_code
+  FROM vehicle_identifier
+  WHERE protocol = 'JT808'
+    AND identifier_type = 'JT808_PHONE'
+    AND enabled = 1
+    AND source_code IS NOT NULL
+    AND TRIM(source_code) <> ''
+  GROUP BY identifier_value
+  HAVING COUNT(DISTINCT TRIM(source_code)) = 1
+) vi
+  ON s.protocol = 'JT808' AND vi.phone = TRIM(s.phone)
+WHERE s.vin = ?
+  AND s.stat_date = ?
+  AND s.protocol = ?
+  AND s.quality_status IN ('` + QualityOK + `', '` + QualityNoPreviousBaseline + `')
+  AND COALESCE(NULLIF(TRIM(ds.source_code), ''), vi.source_code) IS NOT NULL
+  AND COALESCE(NULLIF(TRIM(s.phone), ''), NULLIF(TRIM(s.device_id), '')) IS NOT NULL
+  AND s.source_key <> CONCAT(s.protocol, ':', COALESCE(NULLIF(TRIM(s.phone), ''), NULLIF(TRIM(s.device_id), '')), '` + platformSourceKeyPrefix + `', COALESCE(NULLIF(TRIM(ds.source_code), ''), vi.source_code))
+`
+
+const selectPlatformSourceMileageLegacyVINSQL = `
+SELECT DISTINCT s.vin
+FROM vehicle_daily_mileage_source s
+LEFT JOIN vehicle_data_source ds
+  ON ds.protocol = s.protocol AND ds.source_ip = s.source_ip
+ AND ds.enabled = 1
+ AND ds.source_kind = 'PLATFORM'
+ AND ds.source_code IS NOT NULL
+ AND TRIM(ds.source_code) <> ''
+LEFT JOIN (
+  SELECT
+    identifier_value AS phone,
+    MIN(TRIM(source_code)) AS source_code
+  FROM vehicle_identifier
+  WHERE protocol = 'JT808'
+    AND identifier_type = 'JT808_PHONE'
+    AND enabled = 1
+    AND source_code IS NOT NULL
+    AND TRIM(source_code) <> ''
+  GROUP BY identifier_value
+  HAVING COUNT(DISTINCT TRIM(source_code)) = 1
+) vi
+  ON s.protocol = 'JT808' AND vi.phone = TRIM(s.phone)
+WHERE s.stat_date = ?
+  AND s.protocol = ?
+  AND s.quality_status IN ('` + QualityOK + `', '` + QualityNoPreviousBaseline + `')
+  AND COALESCE(NULLIF(TRIM(ds.source_code), ''), vi.source_code) IS NOT NULL
+  AND COALESCE(NULLIF(TRIM(s.phone), ''), NULLIF(TRIM(s.device_id), '')) IS NOT NULL
+  AND s.source_key <> CONCAT(s.protocol, ':', COALESCE(NULLIF(TRIM(s.phone), ''), NULLIF(TRIM(s.device_id), '')), '` + platformSourceKeyPrefix + `', COALESCE(NULLIF(TRIM(ds.source_code), ''), vi.source_code))
+ORDER BY s.vin
 `

 const projectDailyMileageSQL = `
@@ -209,15 +606,25 @@ SELECT
  s.daily_mileage_km,
  s.latest_total_mileage_km
 FROM vehicle_daily_mileage_source s
-JOIN vehicle_data_source ds
+LEFT JOIN vehicle_data_source ds
  ON ds.protocol = s.protocol AND ds.source_ip = s.source_ip
 WHERE s.vin = ?
  AND s.stat_date = ?
  AND s.protocol = ?
  AND s.quality_status = '` + QualityOK + `'
-  AND s.daily_mileage_km BETWEEN 0 AND ?
-  AND ds.enabled = 1
-ORDER BY ds.trust_priority,
+  AND s.daily_mileage_km BETWEEN 0 AND (? * GREATEST(1, DATEDIFF(DATE(s.latest_event_time), DATE(s.first_event_time))))
+  AND (ds.id IS NULL OR ds.enabled = 1 OR (
+    COALESCE(NULLIF(TRIM(ds.source_kind), ''), 'UNKNOWN') = 'UNKNOWN'
+    AND (ds.source_code IS NULL OR TRIM(ds.source_code) = '')
+    AND (ds.platform_name IS NULL OR TRIM(ds.platform_name) = '')
+  ))
+ORDER BY CASE COALESCE(NULLIF(NULLIF(TRIM(ds.source_kind), ''), 'UNKNOWN'), CASE WHEN s.source_key LIKE '%` + platformSourceKeyPrefix + `%' THEN 'PLATFORM' WHEN s.source_key LIKE '%` + directSourceKeySuffix + `' THEN 'DIRECT' ELSE 'UNKNOWN' END)
+           WHEN 'PLATFORM' THEN 0
+           WHEN 'DIRECT' THEN 1
+           WHEN 'UNKNOWN' THEN 2
+           ELSE 3
+         END,
+         COALESCE(ds.trust_priority, 100000),
         s.sample_count DESC,
         s.latest_event_time DESC,
         s.source_key ASC
@@ -231,22 +638,32 @@ ON DUPLICATE KEY UPDATE

 const markSelectedSourceSQL = `
 UPDATE vehicle_daily_mileage_source s
-JOIN (
+LEFT JOIN (
  SELECT
    s2.source_key,
    s2.vin,
    s2.stat_date,
    s2.protocol
  FROM vehicle_daily_mileage_source s2
-  JOIN vehicle_data_source ds
+  LEFT JOIN vehicle_data_source ds
    ON ds.protocol = s2.protocol AND ds.source_ip = s2.source_ip
  WHERE s2.vin = ?
    AND s2.stat_date = ?
    AND s2.protocol = ?
    AND s2.quality_status = '` + QualityOK + `'
-    AND s2.daily_mileage_km BETWEEN 0 AND ?
-    AND ds.enabled = 1
-  ORDER BY ds.trust_priority,
+    AND s2.daily_mileage_km BETWEEN 0 AND (? * GREATEST(1, DATEDIFF(DATE(s2.latest_event_time), DATE(s2.first_event_time))))
+    AND (ds.id IS NULL OR ds.enabled = 1 OR (
+      COALESCE(NULLIF(TRIM(ds.source_kind), ''), 'UNKNOWN') = 'UNKNOWN'
+      AND (ds.source_code IS NULL OR TRIM(ds.source_code) = '')
+      AND (ds.platform_name IS NULL OR TRIM(ds.platform_name) = '')
+    ))
+  ORDER BY CASE COALESCE(NULLIF(NULLIF(TRIM(ds.source_kind), ''), 'UNKNOWN'), CASE WHEN s2.source_key LIKE '%` + platformSourceKeyPrefix + `%' THEN 'PLATFORM' WHEN s2.source_key LIKE '%` + directSourceKeySuffix + `' THEN 'DIRECT' ELSE 'UNKNOWN' END)
+             WHEN 'PLATFORM' THEN 0
+             WHEN 'DIRECT' THEN 1
+             WHEN 'UNKNOWN' THEN 2
+             ELSE 3
+           END,
+           COALESCE(ds.trust_priority, 100000),
           s2.sample_count DESC,
           s2.latest_event_time DESC,
           s2.source_key ASC
@@ -256,7 +673,7 @@ JOIN (
 AND selected_source.vin = s.vin
 AND selected_source.stat_date = s.stat_date
 AND selected_source.protocol = s.protocol
-SET s.is_selected = 1
+SET s.is_selected = CASE WHEN selected_source.source_key IS NULL THEN 0 ELSE 1 END
 WHERE s.vin = ? AND s.stat_date = ? AND s.protocol = ?
 `

@@ -302,60 +719,30 @@ func lookupPreviousSourceBaseline(ctx context.Context, query Queryer, vin string
 	return sourceBaseline{
 		LatestTotalKM:   latestTotal.Float64,
 		LatestEventTime: latestEvent.Time,
-		QualityReason:   "historical_source_baseline",
+		QualityReason:   QualityReasonHistorical,
 	}, latestTotal.Valid, nil
 }

-func lookupCurrentSourceBaseline(ctx context.Context, query Queryer, vin string, statDate string, protocol envelope.Protocol, sourceKey string) (sourceBaseline, bool, error) {
-	if query == nil || strings.TrimSpace(vin) == "" || strings.TrimSpace(statDate) == "" || strings.TrimSpace(sourceKey) == "" {
-		return sourceBaseline{}, false, nil
-	}
-	rows, err := query.QueryContext(ctx, currentSourceBaselineSQL, vin, statDate, string(protocol), sourceKey)
-	if err != nil {
-		return sourceBaseline{}, false, err
-	}
-	defer rows.Close()
-	if !rows.Next() {
-		if err := rows.Err(); err != nil {
-			return sourceBaseline{}, false, err
-		}
-		return sourceBaseline{}, false, nil
-	}
-	var firstTotal sql.NullFloat64
-	var firstEvent sql.NullTime
-	if err := rows.Scan(&firstTotal, &firstEvent); err != nil {
-		return sourceBaseline{}, false, err
-	}
-	if err := rows.Err(); err != nil {
-		return sourceBaseline{}, false, err
-	}
-	return sourceBaseline{
-		LatestTotalKM:   firstTotal.Float64,
-		LatestEventTime: firstEvent.Time,
-		QualityReason:   "current_day_first_sample",
-	}, firstTotal.Valid, nil
+// LookupLatestSourceBaselineBefore returns the nearest durable odometer for the
+// same VIN, protocol and source before statDate. Missing calendar days are
+// skipped automatically.
+func LookupLatestSourceBaselineBefore(ctx context.Context, query Queryer, vin string, statDate string, protocol envelope.Protocol, sourceKey string) (float64, time.Time, bool, error) {
+	baseline, found, err := lookupPreviousSourceBaseline(ctx, query, vin, statDate, protocol, sourceKey)
+	return baseline.LatestTotalKM, baseline.LatestEventTime, found, err
 }

 const previousSourceBaselineSQL = `
 SELECT latest_total_mileage_km, latest_event_time
 FROM vehicle_daily_mileage_source
 WHERE vin = ?
-  AND stat_date < ?
+	AND stat_date < ?
  AND protocol = ?
  AND source_key = ?
-  AND quality_status = '` + QualityOK + `'
+  AND latest_total_mileage_km IS NOT NULL
+  AND latest_total_mileage_km > 0
+  AND latest_event_time IS NOT NULL
+  AND latest_event_time >= CAST(CONCAT(stat_date, ' 00:00:00') AS DATETIME)
+  AND latest_event_time < DATE_ADD(CAST(CONCAT(stat_date, ' 00:00:00') AS DATETIME), INTERVAL 1 DAY)
 ORDER BY stat_date DESC, latest_event_time DESC
 LIMIT 1
 `
-
-const currentSourceBaselineSQL = `
-SELECT first_total_mileage_km, first_event_time
-FROM vehicle_daily_mileage_source
-WHERE vin = ?
-  AND stat_date = ?
-  AND protocol = ?
-  AND source_key = ?
-  AND quality_status = '` + QualityOK + `'
-ORDER BY latest_event_time DESC
-LIMIT 1
-`