From e63a0e8fd774fcb2138ea4cc0ca697f6f919ce7f Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@localai.io>
Date: Wed, 20 May 2026 22:16:54 +0000
Subject: [PATCH] feat(usage): backfill Source on pre-feature usage rows

InitDB now classifies any pre-existing usage_record with an empty
source: 'legacy-api-key' user -> legacy, everything else -> web.
The backfill is idempotent (only touches NULL/empty rows).

Refs: #9862
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---
 core/http/auth/db.go         |  8 ++++++-
 core/http/auth/usage.go      | 22 +++++++++++++++++++
 core/http/auth/usage_test.go | 42 ++++++++++++++++++++++++++++++++++++
 3 files changed, 71 insertions(+), 1 deletion(-)

diff --git a/core/http/auth/db.go b/core/http/auth/db.go
index d860e5068..5d94557ea 100644
--- a/core/http/auth/db.go
+++ b/core/http/auth/db.go
@@ -38,9 +38,15 @@ func InitDB(databaseURL string) (*gorm.DB, error) {
 	}
 
 	// Backfill: users created before the provider column existed have an empty
-	// provider — treat them as local accounts so the UI can identify them.
+	// provider - treat them as local accounts so the UI can identify them.
 	db.Exec("UPDATE users SET provider = ? WHERE provider = '' OR provider IS NULL", ProviderLocal)
 
+	// Backfill: pre-feature usage_records have no source column. Classify them so the
+	// new per-source aggregators include them.
+	if err := BackfillUsageSource(db); err != nil {
+		return nil, fmt.Errorf("failed to backfill usage source: %w", err)
+	}
+
 	// Create composite index on users(provider, subject) for fast OAuth lookups
 	if err := db.Exec("CREATE INDEX IF NOT EXISTS idx_users_provider_subject ON users(provider, subject)").Error; err != nil {
 		// Ignore error on postgres if index already exists
diff --git a/core/http/auth/usage.go b/core/http/auth/usage.go
index ad56ee309..99cecef77 100644
--- a/core/http/auth/usage.go
+++ b/core/http/auth/usage.go
@@ -138,6 +138,28 @@ func GetUserUsage(db *gorm.DB, userID, period string) ([]UsageBucket, error) {
 	return buckets, nil
 }
 
+// BackfillUsageSource sets the Source column on pre-feature usage rows.
+// Idempotent: only touches rows where source is NULL or empty.
+//   - rows whose user_id == "legacy-api-key" -> UsageSourceLegacy
+//   - everything else                        -> UsageSourceWeb
+func BackfillUsageSource(db *gorm.DB) error {
+	// Legacy first (more specific predicate)
+	if err := db.Exec(
+		`UPDATE usage_records SET source = ? WHERE (source IS NULL OR source = '') AND user_id = ?`,
+		UsageSourceLegacy, "legacy-api-key",
+	).Error; err != nil {
+		return fmt.Errorf("backfill legacy usage source: %w", err)
+	}
+	// Everything else -> web
+	if err := db.Exec(
+		`UPDATE usage_records SET source = ? WHERE (source IS NULL OR source = '')`,
+		UsageSourceWeb,
+	).Error; err != nil {
+		return fmt.Errorf("backfill web usage source: %w", err)
+	}
+	return nil
+}
+
 // GetAllUsage returns aggregated usage for all users (admin). Optional userID filter.
 func GetAllUsage(db *gorm.DB, period, userID string) ([]UsageBucket, error) {
 	sqlite := isSQLiteDB(db)
diff --git a/core/http/auth/usage_test.go b/core/http/auth/usage_test.go
index c3ad1e43f..41ff1bd65 100644
--- a/core/http/auth/usage_test.go
+++ b/core/http/auth/usage_test.go
@@ -159,6 +159,48 @@ var _ = Describe("Usage", func() {
 		})
 	})
 
+	Describe("Usage source backfill", func() {
+		It("backfills 'web' for pre-feature rows", func() {
+			db := testDB()
+
+			rawDB, err := db.DB()
+			Expect(err).ToNot(HaveOccurred())
+			_, err = rawDB.Exec(
+				`INSERT INTO usage_records (user_id, source, model, created_at, total_tokens, prompt_tokens, completion_tokens, duration) VALUES (?, '', ?, ?, 0, 0, 0, 0)`,
+				"user-x", "gpt-4", time.Now())
+			Expect(err).ToNot(HaveOccurred())
+
+			Expect(auth.BackfillUsageSource(db)).To(Succeed())
+
+			var loaded auth.UsageRecord
+			Expect(db.Where("user_id = ?", "user-x").First(&loaded).Error).To(Succeed())
+			Expect(loaded.Source).To(Equal(auth.UsageSourceWeb))
+		})
+
+		It("backfills 'legacy' for pre-feature rows with legacy-api-key user_id", func() {
+			db := testDB()
+
+			rawDB, err := db.DB()
+			Expect(err).ToNot(HaveOccurred())
+			_, err = rawDB.Exec(
+				`INSERT INTO usage_records (user_id, source, model, created_at, total_tokens, prompt_tokens, completion_tokens, duration) VALUES (?, '', ?, ?, 0, 0, 0, 0)`,
+				"legacy-api-key", "gpt-4", time.Now())
+			Expect(err).ToNot(HaveOccurred())
+
+			Expect(auth.BackfillUsageSource(db)).To(Succeed())
+
+			var loaded auth.UsageRecord
+			Expect(db.Where("user_id = ?", "legacy-api-key").First(&loaded).Error).To(Succeed())
+			Expect(loaded.Source).To(Equal(auth.UsageSourceLegacy))
+		})
+
+		It("is idempotent on re-run", func() {
+			db := testDB()
+			Expect(auth.BackfillUsageSource(db)).To(Succeed())
+			Expect(auth.BackfillUsageSource(db)).To(Succeed())
+		})
+	})
+
 	Describe("UsageRecord with source fields", func() {
 		It("persists Source, APIKeyID, APIKeyName", func() {
 			db := testDB()