update

src/interface.jl

@@ -318,46 +318,46 @@ function reflector()
 end
 
 
-""" Determine whether the state is a terminal state
+# """ Determine whether the state is a terminal state
 
-# Arguments
-  - `state::T`
-    a game state
+# # Arguments
+#   - `state::T`
+#     a game state
   
-# Return
-  - `(isterminalstate, reward)::Tuple{Bool, <:Number}`
+# # Return
+#   - `(isterminalstate, reward)::Tuple{Bool, <:Number}`
 
-# Example
-```jldoctest
-julia> 
-```
+# # Example
+# ```jldoctest
+# julia> 
+# ```
 
-# TODO
-  [PENDING] add Reflect()
+# # TODO
+#   [PENDING] add Reflect()
 
-# Signature
-"""
-function isterminal(state::T)::Tuple{Bool, <:Number} where {T<:AbstractDict}
-  latestObservationKey, _ = GeneralUtils.findHighestIndexKey(state[:thoughtHistory], "observation")
-  latestObservation = state[:thoughtHistory][latestObservationKey]
+# # Signature
+# """
+# function isterminal(state::T)::Tuple{Bool, <:Number} where {T<:AbstractDict}
+#   latestObservationKey, _ = GeneralUtils.findHighestIndexKey(state[:thoughtHistory], "observation")
+#   latestObservation = state[:thoughtHistory][latestObservationKey]
 
-  if latestObservation !== nothing
+#   if latestObservation !== nothing
 
-    # terminal condition is when the user select wine by putting <<winename>> in latest observation 
-    if occursin("<<", latestObservation) && occursin(">>", latestObservation)
-      isterminalstate = true
-      reward = 1
-    else
-      isterminalstate = false
-      reward = 0
-    end
-  else
-    isterminalstate = false
-    reward = 0
-  end
+#     # terminal condition is when the user select wine by putting <<winename>> in latest observation 
+#     if occursin("<<", latestObservation) && occursin(">>", latestObservation)
+#       isterminalstate = true
+#       reward = 1
+#     else
+#       isterminalstate = false
+#       reward = 0
+#     end
+#   else
+#     isterminalstate = false
+#     reward = 0
+#   end
 
-  return (isterminalstate, reward)
-end
+#   return (isterminalstate, reward)
+# end
 
 
 """ Chat with llm.
@@ -436,7 +436,10 @@ function conversation(a::T, userinput::Dict) where {T<:agent}
 
         # deepcopy the info to prevent modifying the info unintentionally during MCTS planning
         :customerinfo=> deepcopy(a.keywordinfo[:customerinfo]),
-        :storeinfo=> deepcopy(a.keywordinfo[:storeinfo]),  
+        :storeinfo=> deepcopy(a.keywordinfo[:storeinfo]),
+        :select=> nothing,
+        :reward=> 0,
+        :isterminal=> false,
         :thoughtHistory=> OrderedDict{Symbol, Any}( # contain question, thought_1, action_1, observation_1, thought_2, ...
           :question=> userinput[:text],
           )