feat(admin): hqsync repairs stale projected passwords

Its own package rather than a pass inside inject: inject writes three licence fields and nothing else, and that narrowness is what makes admin's reach into the control plane reviewable. Repairs by copying HQ's hash, not by re-hashing — two bcrypt hashes of one password differ by salt, so a re-hash would never converge. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-26 16:30:33 +01:00
parent 0f5ad1d836
commit 14b855fa9f
2 changed files with 118 additions and 0 deletions
@@ -0,0 +1,116 @@
+// Package hqsync keeps projected control-plane users consistent with the HQ
+// people they were projected from.
+//
+// It is separate from inject on purpose. inject writes exactly three licence
+// fields on `instances` and that narrowness is the reason admin's reach into
+// the control plane is reviewable at all; a password repair pass bolted onto it
+// would quietly turn it into "the package that writes whatever admin wants".
+// This one goes through cloudprov, which is the sanctioned user write path.
+package hqsync
+
+import (
+	"context"
+	"log"
+	"time"
+
+	"github.com/mrhid6/vantage/admin/internal/cloudprov"
+	"github.com/mrhid6/vantage/admin/internal/db"
+	"github.com/mrhid6/vantage/admin/internal/models"
+	"go.mongodb.org/mongo-driver/v2/bson"
+)
+
+// Interval matches inject's reconciler. Fifteen minutes is the worst-case
+// staleness a password change can suffer, which the spec accepts as
+// recoverable.
+const Interval = 15 * time.Minute
+
+// Reconcile compares every projected user's stored hash against the HQ hash it
+// came from, and repairs mismatches.
+//
+// The comparison is on the hash string, not the password: two bcrypt hashes of
+// one password differ by salt, so this repairs by COPYING HQ's hash rather than
+// re-hashing. That is also why propagation copies rather than re-derives.
+func Reconcile(ctx context.Context) (checked, repaired int, err error) {
+	cur, err := db.Admin("customer_users").Find(ctx,
+		bson.M{"password_hash": bson.M{"$nin": bson.A{nil, ""}}})
+	if err != nil {
+		return 0, 0, err
+	}
+	var people []models.CustomerUser
+	if err := cur.All(ctx, &people); err != nil {
+		return 0, 0, err
+	}
+
+	for _, p := range people {
+		projected, err := cloudprov.ProjectedUsers(ctx, p.UserID)
+		if err != nil {
+			log.Printf("hqsync: read projections of %s: %v", p.Email, err)
+			continue
+		}
+		stale := false
+		for _, u := range projected {
+			checked++
+			if u.PasswordHash != p.PasswordHash {
+				stale = true
+			}
+		}
+		if !stale {
+			// Clear a stale failure flag: the instances agree, whatever the
+			// flag says. Nothing reads the flag to decide what to repair.
+			if p.HQSyncFailedAt != nil {
+				_, _ = db.Admin("customer_users").UpdateOne(ctx,
+					bson.M{"user_id": p.UserID},
+					bson.M{"$unset": bson.M{"hq_sync_failed_at": ""}})
+			}
+			continue
+		}
+
+		n, err := cloudprov.SetPasswordHash(ctx, p.UserID, p.PasswordHash)
+		if err != nil {
+			log.Printf("hqsync: repair %s: %v", p.Email, err)
+			continue
+		}
+		repaired += int(n)
+		log.Printf("hqsync: repaired %d projected user(s) for %s", n, p.Email)
+		_, _ = db.Admin("customer_users").UpdateOne(ctx,
+			bson.M{"user_id": p.UserID},
+			bson.M{"$unset": bson.M{"hq_sync_failed_at": ""}})
+	}
+	return checked, repaired, nil
+}
+
+// Start runs once at boot, then on a ticker until ctx is cancelled.
+//
+// The boot pass is for the same reason inject's is: the likeliest moment for a
+// half-applied write is a deploy or a crash, and waiting a full interval to
+// notice means a customer's new password does not work somewhere for fifteen
+// minutes after we already know how to fix it.
+func Start(ctx context.Context) {
+	go func() {
+		runOnce(ctx)
+		t := time.NewTicker(Interval)
+		defer t.Stop()
+		for {
+			select {
+			case <-ctx.Done():
+				return
+			case <-t.C:
+				runOnce(ctx)
+			}
+		}
+	}()
+}
+
+func runOnce(ctx context.Context) {
+	runCtx, cancel := context.WithTimeout(ctx, 5*time.Minute)
+	defer cancel()
+
+	checked, repaired, err := Reconcile(runCtx)
+	if err != nil {
+		log.Printf("hqsync: %v", err)
+		return
+	}
+	if repaired > 0 {
+		log.Printf("hqsync: checked %d projected user(s), repaired %d", checked, repaired)
+	}
+}