predictions for glm with `se.fit = TRUE` throws an error

[vandenman]

Describe the bug
Calling predict with se.fit = TRUE on an object of class basglm (logistic regression) throws the error:

Error in array(STATS, dims[perm]) : 
  'data' must be of a vector type, was 'NULL'
In addition: Warning message:
In max(cumDim[cumDim <= lstats]) :
  no non-missing arguments to max; returning -Inf

To Reproduce

library(BAS)
library(MASS)
data(Pima.tr)


# enumeration  with default method="BAS"
pima.cch = bas.glm(type ~ ., data=Pima.tr, n.models= 2^7,
                   method="BAS",
                   betaprior=CCH(a=1, b=532/2, s=0), family=binomial(),
                   modelprior=beta.binomial(1,1))

try(predict(pima.cch, newdata=Pima.tr[1:10,], type="response", se.fit = TRUE))
#> Warning in max(cumDim[cumDim <= lstats]): no non-missing arguments to max;
#> returning -Inf
#> Error in array(STATS, dims[perm]) : 
#>   'data' must be of a vector type, was 'NULL'

glm_fit <- glm(type ~ ., data = Pima.tr, family = binomial())
predict(glm_fit, newdata = Pima.tr[1:10,], type = "response", se.fit = TRUE)
#> $fit
#>          1          2          3          4          5          6          7 
#> 0.06318139 0.81393846 0.07347296 0.65233283 0.03649077 0.32099021 0.06759699 
#>          8          9         10 
#> 0.64708680 0.58782564 0.77333901 
#> 
#> $se.fit
#>          1          2          3          4          5          6          7 
#> 0.02570134 0.10513608 0.03782698 0.13935359 0.01818461 0.11389870 0.02771771 
#>          8          9         10 
#> 0.16317946 0.19040925 0.10630820 
#> 
#> $residual.scale
#> [1] 1

^{Created on 2025-06-10 with reprex v2.1.1}

Expected behavior
Either:

• An intended error, if se.fit = TRUE is not supported.
• Actual results. The reprex above shows that stats::glm does produce a result, but I'm not sure how straightforward this is for the Bayesian version.