feat(admin): cloud injection and the 15-minute reconciler

Injection is a single UpdateOne of three licence fields, so it is
idempotent and safe to re-run. The control plane caches licence state for
60 seconds, so an injected licence takes effect within a minute with no
restart.

Deliver never fails its caller. The reconciler, not the issuance path, is
what actually guarantees a cloud instance ends up holding the licence admin
says it holds -- injection at issue time is best-effort and this is the
backstop.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

admin/internal/inject/inject.go

@@ -0,0 +1,150 @@
+// Package inject writes licences onto control-plane instance documents.
+//
+// This is admin's ONLY write path into the control plane, and it touches exactly
+// three fields on one collection. If this package ever grows a second write
+// target, that is a design change and not a refactor.
+package inject
+
+import (
+	"context"
+	"fmt"
+	"log"
+	"time"
+
+	"github.com/mrhid6/vantage/admin/internal/db"
+	"github.com/mrhid6/vantage/admin/internal/models"
+	"github.com/mrhid6/vantage/shared/license"
+	sharedmodels "github.com/mrhid6/vantage/shared/models"
+	"go.mongodb.org/mongo-driver/v2/bson"
+)
+
+// ReconcileInterval is how often every cloud instance is compared against what
+// admin believes it should hold.
+//
+// This job, not the issuance path, is what guarantees eventual consistency.
+// Injection at issue time is best-effort; this is the backstop.
+const ReconcileInterval = 15 * time.Minute
+
+// Cloud writes the licence onto the control-plane instance document.
+//
+// Idempotent and safe to re-run: it is a single UpdateOne of three fields with
+// no read-modify-write. Retries three times with backoff.
+//
+// The control plane caches licence state for 60 seconds, so this takes effect
+// within a minute with no restart.
+func Cloud(ctx context.Context, lic *models.License) error {
+	set := bson.M{"$set": bson.M{
+		"license_blob":   lic.Blob,
+		"license_tier":   lic.Tier,
+		"license_expiry": lic.ExpiresAt,
+	}}
+
+	var lastErr error
+	for attempt := 1; attempt <= 3; attempt++ {
+		res, err := db.Control("instances").UpdateOne(ctx,
+			bson.M{"instance_id": lic.InstanceID}, set)
+		if err == nil {
+			if res.MatchedCount == 0 {
+				return fmt.Errorf("no control-plane instance %s", lic.InstanceID)
+			}
+			return nil
+		}
+		lastErr = err
+		time.Sleep(time.Duration(attempt) * 2 * time.Second)
+	}
+	return fmt.Errorf("inject after 3 attempts: %w", lastErr)
+}
+
+// Deliver injects and records the outcome without ever failing the caller.
+//
+// A licence that is recorded but not injected is recoverable — the reconciler
+// will fix it within 15 minutes, and staff can see it on the health endpoint.
+// Failing the purchase because one write failed would be worse.
+func Deliver(ctx context.Context, lic *models.License) {
+	if err := Cloud(ctx, lic); err != nil {
+		log.Printf("INJECTION FAILED instance=%s licence=%s: %v", lic.InstanceID, lic.LicenseID, err)
+		now := time.Now().UTC()
+		_, _ = db.Admin("admin_instances").UpdateOne(ctx,
+			bson.M{"instance_id": lic.InstanceID},
+			bson.M{"$set": bson.M{"inject_failed_at": now}})
+		return
+	}
+	_, _ = db.Admin("admin_instances").UpdateOne(ctx,
+		bson.M{"instance_id": lic.InstanceID},
+		bson.M{"$unset": bson.M{"inject_failed_at": ""}})
+}
+
+// Reconcile compares every active cloud instance's current licence against the
+// blob actually stored in the control plane, and re-injects on mismatch.
+func Reconcile(ctx context.Context) (checked, repaired int, err error) {
+	cur, err := db.Admin("admin_instances").Find(ctx, bson.M{
+		"deployment":      license.DeploymentCloud,
+		"status":          models.StatusActive,
+		"current_license": bson.M{"$ne": ""},
+	})
+	if err != nil {
+		return 0, 0, err
+	}
+	var instances []models.Instance
+	if err := cur.All(ctx, &instances); err != nil {
+		return 0, 0, err
+	}
+
+	for _, inst := range instances {
+		checked++
+
+		var lic models.License
+		if err := db.Admin("licenses").FindOne(ctx,
+			bson.M{"license_id": inst.CurrentLicense}).Decode(&lic); err != nil {
+			log.Printf("reconcile: instance %s references unknown licence %s", inst.InstanceID, inst.CurrentLicense)
+			continue
+		}
+
+		var remote sharedmodels.Instance
+		if err := db.Control("instances").FindOne(ctx,
+			bson.M{"instance_id": inst.InstanceID}).Decode(&remote); err != nil {
+			log.Printf("reconcile: no control-plane instance %s: %v", inst.InstanceID, err)
+			continue
+		}
+
+		if remote.LicenseBlob == lic.Blob {
+			continue
+		}
+
+		log.Printf("reconcile: repairing instance %s (licence %s)", inst.InstanceID, lic.LicenseID)
+		if err := Cloud(ctx, &lic); err != nil {
+			log.Printf("reconcile: repair failed for %s: %v", inst.InstanceID, err)
+			continue
+		}
+		repaired++
+		_, _ = db.Admin("admin_instances").UpdateOne(ctx,
+			bson.M{"instance_id": inst.InstanceID},
+			bson.M{"$unset": bson.M{"inject_failed_at": ""}})
+	}
+	return checked, repaired, nil
+}
+
+// StartReconciler runs Reconcile on a ticker until ctx is cancelled.
+func StartReconciler(ctx context.Context) {
+	go func() {
+		t := time.NewTicker(ReconcileInterval)
+		defer t.Stop()
+		for {
+			select {
+			case <-ctx.Done():
+				return
+			case <-t.C:
+				runCtx, cancel := context.WithTimeout(ctx, 5*time.Minute)
+				checked, repaired, err := Reconcile(runCtx)
+				cancel()
+				if err != nil {
+					log.Printf("reconcile: %v", err)
+					continue
+				}
+				if repaired > 0 {
+					log.Printf("reconcile: checked %d, repaired %d", checked, repaired)
+				}
+			}
+		}
+	}()
+}