How do I place an object derived from variables in a CSV into the theta.constraints function in MCMC?

Question

I have a data object that lists constraints for my MCMC (from library(MCMCpack) ) command:

constraints <- structure(list(state = c("CA", "CA", "CA", "CA"), justice = c("smith", 
                                                                             "lee", "bosworth", "dickens"), direction = c("-", "-", "+", "+"
                                                                             )), class = "data.frame", row.names = c(NA, -4L))

I create a function for my constraints:

constraints_list <- paste(constraints$justice, "='", constraints$direction, "'", sep = "", collapse = ", ")

I then have a different dataset that I'm using to run the MCMC on:

sheet<-structure(list(hall = c(1L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
                               0L, 0L, 0L, 1L), nolan = c(0L, 1L, 0L, 1L, 0L, 0L, 0L, 0L, 1L, 
                                                          1L, 1L, 1L, 0L, 0L), perez = c(1L, 1L, 1L, 1L, 1L, 0L, 0L, 0L, 
                                                                                         0L, 1L, 1L, 1L, 1L, 1L), chen = c(0L, 0L, 0L, 0L, 0L, 1L, 1L, 
                                                                                                                           1L, 1L, 1L, 0L, 0L, 0L, 0L), bush = c(1L, 1L, 1L, 1L, 1L, 0L, 
                                                                                                                                                                 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), simpson = c(0L, 1L, 0L, 1L, 
                                                                                                                                                                                                              0L, 1L, 0L, 1L, 0L, 1L, 0L, 1L, 0L, 1L), smith = c(0L, 0L, 0L, 
                                                                                                                                                                                                                                                                 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), lee = c(0L, 0L, 
                                                                                                                                                                                                                                                                                                                      0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), bosworth = c(1L, 
                                                                                                                                                                                                                                                                                                                                                                                    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), dickens = c(1L, 
                                                                                                                                                                                                                                                                                                                                                                                                                                                     1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), time = c(1L, 
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   1L, 2L, 2L, 3L, 3L, 4L, 4L, 5L, 5L, 6L, 6L, 7L, 7L), term = c(2020L, 
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 2020L, 2021L, 2021L, 2022L, 2022L, 2023L, 2023L, 2024L, 2024L, 
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 2025L, 2025L, 2026L, 2026L), observation = 1:14), class = "data.frame", row.names = c(NA, 
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       -14L))

And when I run this, I get an error:

result <- MCMCdynamicIRT1d(t(sheet[,1:10]),
                              item.time.map=sheet$time,
                              theta.start=NA,
                              mcmc=2500, burnin=250, thin=100,
                              verbose=1, tau2.start=rep(0.1, 23),
                              e0=0, E0=1,
                              a0=0, A0=1,
                              b0=0, B0=1, c0=-1, d0=-1,
                              store.item=FALSE,
                              theta.constraints=list(constraints_list))    

This is the error:

Error in lambda.constraints[[i]] : 
  attempt to select less than one element in integerOneIndex

When I look at the constraints_list I just see this:

[1] "smith='-', lee='-', bosworth='+', dickens='+'"

So when I manually plug the list into the MCMCdynamicIRT1d command, the code works as expected:

result <- MCMCdynamicIRT1d(t(sheet[,1:10]),
                              item.time.map=sheet$time,
                              theta.start=NA,
                              mcmc=2500, burnin=250, thin=100,
                              verbose=1, tau2.start=rep(0.1, 23),
                              e0=0, E0=1,
                              a0=0, A0=1,
                              b0=0, B0=1, c0=-1, d0=-1,
                              store.item=FALSE,
                              theta.constraints=list(smith='-', lee='-', bosworth='+', dickens='+'))  

How do I fix constraints_list so it will output the results as expected?