update

src/mcts.jl

@@ -131,15 +131,11 @@ function expand(a::T1, node::MCTSNode, state::T2, decisionMaker::Function, state
                           )
       :Observation_1 => ""
     """
-    latestActionKey = GeneralUtils.findHighestIndexKey(thoughtDict, "Action")
-    _action = thoughtDict[latestActionKey]
-    action = _action[:action]
-    actioninput = _action[:input]
 
-    newState = MCTStransition(a, node.state, action, actioninput)  #[] Implement your transition function
+    newstate = MCTStransition(a, node.state, thoughtDict)  #[] Implement your transition function
     
-    if newState ∉ keys(node.children)
-        node.children[newState] = MCTSNode(newState, 0, 0.0, Dict{T, MCTSNode}())
+    if newstate ∉ keys(node.children)
+        node.children[newstate] = MCTSNode(newstate, 0, 0.0, Dict{T, MCTSNode}())
     end
   end
   error("--> expand")  
@@ -212,41 +208,61 @@ end
     one of YiemAgent's agent
   - `state::T2`
     current game state
-  - `action::String`
-    name of LLM's function to be used
-  - `actioninput::String`
-    input to LLM function
-  
+  - `thoughtDict::T2`
+    contain Thought, Action, Observation
+
 # Return
+  - `newstate::AbstractDict`
+    next game state
 
 # Example
 ```jldoctest
-julia> 
+julia> thoughtDict = Dict(
+  :Question=> "I want to buy a bottle of wine."
+  :Thought_1=>  "The customer wants to buy a bottle of wine. This is a good start!",
+  :Action_1=>   Dict{Symbol, Any}(
+                  :name=>"Chatbox", 
+                  :input=>"What occasion are you buying the wine for?"
+                  ),
+  :Observation_1 => ""
+)
 ```
 
 # TODO
-  - [] update docstring
-  - [WORKING] implement the function
+  - [x] update docstring
+  - [TESTING] implement the function
 
 # Signature
 """
-function MCTStransition(a::T1, state::T2, action::T3, 
-          actioninput::T3) where {T1<:agent, T2<:AbstractDict, T3<:AbstractString}
-
+function MCTStransition(a::T1, state::T2, thoughtDict::T2)::AbstractDict where {T1<:agent, T2<:AbstractDict}
+  latestThoughtKey, latestindice = GeneralUtils.findHighestIndexKey(thoughtDict, "Thought")
+  latestActionKey = GeneralUtils.findHighestIndexKey(thoughtDict, "Action")
+  _action = thoughtDict[latestActionKey]
+  actionname = _action[:name]
+  actioninput = _action[:input]
 
   # map action and input() to llm function
-  result =
-  if action == "chatbox"
-    virtualWineCustomerChatbox(a, input)  # user virtu
-  elseif action == "winestock"
+  response =
+  if actionname == "chatbox"
+    virtualWineCustomerChatbox(a, actioninput)  # user virtu
+  elseif actionname == "winestock"
 
-  elseif action == "finish"
+  elseif actionname == "finish"
 
   else
 
   end
+
+  # add Thought, action, observation to thoughtHistory
+  newstate = deepcopy(state)
+  newstate[:thoughtHistory][latestThoughtKey] = thoughtDict[latestThoughtKey]
+  newstate[:thoughtHistory][latestActionKey] = thoughtDict[latestActionKey]
+  latestObservationKey = Symbol("Observation_$(latestindice)")
+  newstate[:thoughtHistory][latestObservationKey] = response
+
+
   error("--> transition")
-  
+  return newstate
 end
 
 """