Add prompt_template parameter for per-sample prompt customization.

[SokolovAnatoliy]

Fixes #201.

Solution

Add a prompt_template argument to Task$new() that:

1. Uses {{ column_name }} syntax (via ellmer::interpolate()) to reference metadata columns
2. Automatically prepends the interpolated template to each sample's input
3. Works with both generate() and generate_structured() solvers

Examples

With generate()

library(vitals)                                                                 
library(ellmer)                                                                 
library(tibble)                                                                 
                                                                               
shapes_data <- tibble(                                                          
 input = c(                                                                    
   "The shapes are square, circle and rhombus",                                
   "The shapes are square, circle and rhombus",                                
   "The shapes are square, circle and rhombus"                                 
 ),                                                                            
 target = c("square", "circle", "rhombus"),                                    
 shape_to_pick = c("square", "circle", "rhombus")                              
)                                                                               
                                                                               
tsk <- Task$new(                                                                
 dataset = shapes_data,                                                        
 solver = generate(chat_anthropic(model = "claude-sonnet-4-5")),               
 scorer = detect_match("any"),                                                 
 prompt_template = "Always pick {{ shape_to_pick }}. Just return the single chosen shape as 1 word.",                                                       
 dir = tempdir()                                                               
)                                                                               
                                                                               
tsk$eval()                                                                      

Desired result:

tsk$get_samples()$result
[1] "square"  "circle"  "rhombus"

With generate_structured()

type_shape <- type_object(                                                      
 shape = type_string("The name of the shape that was picked")                  
)                                                                               
                                                                               
shapes_data <- tibble(                                                          
 input = c(                                                                    
   "The shapes are square, circle and rhombus",                                
   "The shapes are square, circle and rhombus",                                
   "The shapes are square, circle and rhombus"                                 
 ),                                                                            
 target = c("square", "circle", "rhombus"),                                    
 shape_to_pick = c("square", "circle", "rhombus")                              
)                                                                               
                                                                               
tsk_str <- Task$new(                                                            
 dataset = shapes_data,                                                        
 solver = generate_structured(                                                 
   solver_chat = chat_anthropic(model = "claude-sonnet-4-5"),                  
   type = type_shape                                                           
 ),                                                                            
 scorer = detect_match("any"),                                                 
 prompt_template = "Always pick {{ shape_to_pick }}. Just return the single chosen shape as 1 word.",                                                       
 dir = tempdir()                                                               
)                                                                               
                                                                               
tsk_str$eval()                                                                  

Desired result:

tsk_str$get_samples()$result
[1] "[{\"shape\":\"square\"}]"  "[{\"shape\":\"circle\"}]"  "[{\"shape\":\"rhombus\"}]"

Implementation Notes

• The template is interpolated at the Task level in $solve(), keeping solvers simple and unchanged
• Uses ellmer::interpolate() which uses {{ }} syntax (avoids conflicts with JSON/R code)
• The interpolated template is prepended to the input with \n\n separator
• When prompt_template = NULL (default), behavior is unchanged

[simonpcouch]

Will close in favor of conversation on the related issue! Can reopen and revisit if need be.