v0.1.6 (#45)

## What's New?
Performance updates for large capsules, admin panel enhancement and bug fixes

### Envd
- Fixed bug with sandbox metrics calculation
- Page cache drop and balloon inflation to reduce memfile snapshot
- Updated rpc timeout logic for better control
- Added tests

### Admin Panel
- Add/Remove platform admin
- Updated template deletion logic for fine grained permission

### Others
- Minor frontend visual improvement
- Minor bugfixes
- Version bump

Co-authored-by: Tasnim Kabir Sadik <tksadik92@gmail.com>
Reviewed-on: wrenn/wrenn#45
Co-authored-by: pptx704 <rafeed@omukk.dev>
Co-committed-by: pptx704 <rafeed@omukk.dev>

pkg/audit/logger.go

@@ -365,6 +365,14 @@ func (l *AuditLogger) LogUserDeactivate(ctx context.Context, ac auth.AuthContext
 	l.Log(ctx, newAdminEntry(ac, "user", id.FormatUserID(userID), "deactivate", "warning", map[string]any{"email": email}))
 }
 
+func (l *AuditLogger) LogUserGrantAdmin(ctx context.Context, ac auth.AuthContext, userID pgtype.UUID, email string) {
+	l.Log(ctx, newAdminEntry(ac, "user", id.FormatUserID(userID), "grant_admin", "success", map[string]any{"email": email}))
+}
+
+func (l *AuditLogger) LogUserRevokeAdmin(ctx context.Context, ac auth.AuthContext, userID pgtype.UUID, email string) {
+	l.Log(ctx, newAdminEntry(ac, "user", id.FormatUserID(userID), "revoke_admin", "warning", map[string]any{"email": email}))
+}
+
 // --- Team admin events (scope: admin) ---
 
 func (l *AuditLogger) LogTeamSetBYOC(ctx context.Context, ac auth.AuthContext, teamID pgtype.UUID, enabled bool) {

pkg/db/users.sql.go

@@ -415,6 +415,21 @@ func (q *Queries) ListUsersAdmin(ctx context.Context, arg ListUsersAdminParams)
 	return items, nil
 }
 
+const revokeUserAdmin = `-- name: RevokeUserAdmin :execrows
+UPDATE users u SET is_admin = false, updated_at = NOW()
+WHERE u.id = $1
+  AND u.is_admin = true
+  AND (SELECT COUNT(*) FROM users WHERE is_admin = true AND status != 'deleted') > 1
+`
+
+func (q *Queries) RevokeUserAdmin(ctx context.Context, id pgtype.UUID) (int64, error) {
+	result, err := q.db.Exec(ctx, revokeUserAdmin, id)
+	if err != nil {
+		return 0, err
+	}
+	return result.RowsAffected(), nil
+}
+
 const searchUsersByEmailPrefix = `-- name: SearchUsersByEmailPrefix :many
 SELECT id, email FROM users WHERE email LIKE $1 || '%' ORDER BY email LIMIT 10
 `

pkg/lifecycle/hostpool.go

@@ -47,7 +47,7 @@ func NewHostClientPoolTLS(tlsCfg *tls.Config) *HostClientPool {
 		TLSNextProto:          make(map[string]func(authority string, c *tls.Conn) http.RoundTripper),
 		MaxIdleConnsPerHost:   20,
 		IdleConnTimeout:       90 * time.Second,
-		ResponseHeaderTimeout: 45 * time.Second,
+		ResponseHeaderTimeout: 5 * time.Minute,
 		DialContext: (&net.Dialer{
 			Timeout:   10 * time.Second,
 			KeepAlive: 30 * time.Second,

pkg/service/sandbox.go

@@ -239,12 +239,26 @@ func (s *SandboxService) Pause(ctx context.Context, sandboxID, teamID pgtype.UUI
 	if _, err := agent.PauseSandbox(ctx, connect.NewRequest(&pb.PauseSandboxRequest{
 		SandboxId: sandboxIDStr,
 	})); err != nil {
-		// Revert status on failure.
-		if _, dbErr := s.DB.UpdateSandboxStatus(ctx, db.UpdateSandboxStatusParams{
-			ID: sandboxID, Status: "running",
+		// Check if the agent still has this sandbox. If it was destroyed
+		// (e.g. frozen VM couldn't be resumed), mark as "error" instead of
+		// reverting to "running" — which would create a ghost record.
+		// Use a fresh context since the original ctx may already be expired.
+		revertStatus := "running"
+		pingCtx, pingCancel := context.WithTimeout(context.Background(), 10*time.Second)
+		if _, pingErr := agent.PingSandbox(pingCtx, connect.NewRequest(&pb.PingSandboxRequest{
+			SandboxId: sandboxIDStr,
+		})); pingErr != nil {
+			revertStatus = "error"
+			slog.Warn("sandbox gone from agent after failed pause, marking as error", "sandbox_id", sandboxIDStr)
+		}
+		pingCancel()
+		dbCtx, dbCancel := context.WithTimeout(context.Background(), 5*time.Second)
+		if _, dbErr := s.DB.UpdateSandboxStatus(dbCtx, db.UpdateSandboxStatusParams{
+			ID: sandboxID, Status: revertStatus,
 		}); dbErr != nil {
 			slog.Warn("failed to revert sandbox status after pause error", "sandbox_id", sandboxIDStr, "error", dbErr)
 		}
+		dbCancel()
 		return db.Sandbox{}, fmt.Errorf("agent pause: %w", err)
 	}