diff --git a/src/interface.jl b/src/interface.jl
index 0803f2f..3fa4973 100644
--- a/src/interface.jl
+++ b/src/interface.jl
@@ -371,10 +371,10 @@ function evaluator(state::T1, text2textInstructLLM::Function, llmFormatName::Str
       state["reward"] = responsedict["score"]
     end
 
-    println("\n--- SQLLLM evaluator() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
-    pprintln(responsedict)
-    println("---\n")
-
+    # println("\n--- SQLLLM evaluator() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+    # pprintln(responsedict)
+    # println("---\n")
+    # error(7777)
     return responsedict["score"]
   end
   error("Evaluator failed to generate an evaluation, Response: \n$response\n<|End of error|>")
@@ -596,16 +596,16 @@ function transition(state::T, args::NamedTuple
   end
 
   newNodeKey, newstate = makeNewState(state, thoughtDict, response)
-  progressvalue::Integer =
-    if response[:success]
-      8 # for faster agent response. if success just skip evaluation
-    else
-      evaluatorF(newstate, text2textInstructLLM, llmFormatName)
-    end
+  progressvalue::Integer = evaluatorF(newstate, text2textInstructLLM, llmFormatName)
+    # if response[:success]
+    #   8 # for faster agent response. if success just skip evaluation
+    # else
+    #   evaluatorF(newstate, text2textInstructLLM, llmFormatName)
+    # end
   
-  println("\n--- SQLLLM transition() thoughtDict ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
-  pprintln(thoughtDict)
-  println("---")
+  # println("\n--- SQLLLM transition() thoughtDict ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+  # pprintln(thoughtDict)
+  # println("---")
   # error("SQLLLM transition() end")
   return (newNodeKey=newNodeKey, newstate=newstate, progressvalue=progressvalue)
 end
@@ -727,42 +727,41 @@ function query(query::T, executeSQL::Function, text2textInstructLLM::Function;
 
   systemmsg = 
     """
-    <available_actions>
-      - RUNSQL, which you can use to execute SQL against the database. 
-        action_input for this function must be a single SQL query to be executed against the database.
-        For more effective text search, it's necessary to use case-insensitivity and the ILIKE operator.
-        Do not wrap the SQL as it will be executed against the database directly and SQL must be ended with ';'.
-    </available_actions>
-    <situation>
-      At each round of conversation, you will be given the following:
-      - user question
-      You are working under your mentor supervision and you are also eager to improve your helpfulness.
-    </situation>
-    <objective>
-      Consult the database search guidelines. Then find the data from a database to satisfy the user's question.
-    </objective>
-    <your responsibility includes>
-      Fulfill the objective.
-    </your responsibility includes>
-    <database search guidelines>
+   # database search guidelines
       - Keep SQL queries focused only on the provided information.
       - Do not create any table in the database
       - A junction table can be used to link tables together. Another use case is for filtering data.
       - If you can't find a single table that can be used to answer the user's query, try joining multiple tables to see if you can obtain the answer.
       - Text information in the database usually stored in lower case. If your search returns empty, try using lower case to search.
       - If there is no search result from the database, remove the restrictive criteria until a search result is available, and proceed from there.
-    </database search guidelines>
-    <you should then respond to the user with interleaving plan, action_name, action_input>
-      1) plan: Based on the current situation, state a complete action plan to complete the task. Be specific.
-      2) action_name: (Typically corresponds to the execution of the first step in your plan) Can be one of the available_actions name
-      3) action_input: The input to the action you are about to perform according to your plan.
+
+    # situation
+      At each round of conversation, you will be given the following:
+      - user question
+      You are working under your mentor supervision and you are also eager to improve your helpfulness.
+
+    # objective
+      Consult the database search guidelines. Then find the data from a database to satisfy the user's question.
+
+    # your responsibility includes
+      Fulfill the objective.
+    
+    # you should then respond to the user with interleaving plan, action_name, action_input
+      1) **plan**, Based on the current situation, state a complete action plan to complete the task and rationale. Be specific.
+      2) **action_name**, (Typically corresponds to the execution of the first step in your plan) Can be one of the available_actions name
+      3) **action_input**, The input to the action you are about to perform according to your plan.
       After the action is executed you gets "action_result". It is the output from the action you selected.
-    </you should then respond to the user with interleaving plan, action_name, action_input>
-    <you should only respond in JSON format as described below>
+
+    # you should only respond in JSON format as described below
       "plan": "...",
       "action_name": "...",
       "action_input": "..."
-    </you should only respond in JSON format as described below>
+
+     # available_actions
+      **RUNSQL**, which you can use to execute SQL against the database. 
+        The input must be a single SQL query to be executed against the database.
+        For more effective text search, it's necessary to use case-insensitivity and the ILIKE operator.
+        Do not wrap the SQL as it will be executed against the database directly and SQL must be ended with ';'.
     """
 
 
@@ -975,11 +974,297 @@ function query(query::T, executeSQL::Function, text2textInstructLLM::Function;
   end
 
   println("\n--- SQLLLM query() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
-  println(resultState["result_raw"])
+  # pprintln(resultState)
   println("---\n")
   
   return (result_str=latest_action["action_result"], result_raw=resultState["result_raw"])
 end
+# function query(query::T, executeSQL::Function, text2textInstructLLM::Function;
+#   insertSQLVectorDB::Union{Function, Nothing}=nothing,
+#   similarSQLVectorDB::Union{Function, Nothing}=nothing,
+#   llmFormatName="qwen3"
+#   ) where {T<:AbstractString}
+
+#   # use similarSQLVectorDB to find similar SQL for the query
+#   sql, distance = similarSQLVectorDB(query)
+
+#   # if sql is really match, immediately check database then return
+#   if sql !== nothing && distance <= 1
+#     # query vector db to get wine
+#     response = SQLexecution(executeSQL, sql)
+#     if response[:success]
+#       return (result_str=response[:result_str], result_raw=response[:result_raw])
+#     else
+#       error(response[:errormsg])
+#     end 
+#   end
+
+#   """
+#   chathistory= [
+#      Dict(
+#         "role" => "system",
+#         "content" => [
+#           Dict("type" => "text", "text" => "You are a helpful assistant"),
+#         ]
+#       ),
+#     ]
+#   """
+
+#   systemmsg = 
+#     """
+#     <available_actions>
+#       - RUNSQL, which you can use to execute SQL against the database. 
+#         action_input for this function must be a single SQL query to be executed against the database.
+#         For more effective text search, it's necessary to use case-insensitivity and the ILIKE operator.
+#         Do not wrap the SQL as it will be executed against the database directly and SQL must be ended with ';'.
+#     </available_actions>
+#     <situation>
+#       At each round of conversation, you will be given the following:
+#       - user question
+#       You are working under your mentor supervision and you are also eager to improve your helpfulness.
+#     </situation>
+#     <objective>
+#       Consult the database search guidelines. Then find the data from a database to satisfy the user's question.
+#     </objective>
+#     <your responsibility includes>
+#       Fulfill the objective.
+#     </your responsibility includes>
+#     <database search guidelines>
+#       - Keep SQL queries focused only on the provided information.
+#       - Do not create any table in the database
+#       - A junction table can be used to link tables together. Another use case is for filtering data.
+#       - If you can't find a single table that can be used to answer the user's query, try joining multiple tables to see if you can obtain the answer.
+#       - Text information in the database usually stored in lower case. If your search returns empty, try using lower case to search.
+#       - If there is no search result from the database, remove the restrictive criteria until a search result is available, and proceed from there.
+#     </database search guidelines>
+#     <you should then respond to the user with interleaving plan, action_name, action_input>
+#       1) plan: Based on the current situation, state a complete action plan to complete the task. Be specific.
+#       2) action_name: (Typically corresponds to the execution of the first step in your plan) Can be one of the available_actions name
+#       3) action_input: The input to the action you are about to perform according to your plan.
+#       After the action is executed you gets "action_result". It is the output from the action you selected.
+#     </you should then respond to the user with interleaving plan, action_name, action_input>
+#     <you should only respond in JSON format as described below>
+#       "plan": "...",
+#       "action_name": "...",
+#       "action_input": "..."
+#     </you should only respond in JSON format as described below>
+#     """
+
+
+
+#   # do MCTS if no data in the database
+#   # add extra context for Evaluator so that it knows the observation is from seaching a database
+#   initialstate = Dict{String, Any}(
+#     "reward"=> 0,
+#     "isterminal"=> false,
+#     "evaluation"=> "None",
+#     "evaluationscore"=> 0,
+#     "suggestion"=> "None",
+#     "accepted_as_answer"=> "No",
+#     "chathistory"=> Vector{Dict{String, Any}}(),  # store system, user and assistant msg
+#     "question"=> query,
+#     "context"=> Dict{String, Any}(),
+#     "action_history"=> OrderedDict{String, Any}(
+#       # "1"=> Dict("plan"=> "...", "action_name"=> "...", "action_input"=> "...", "action_result"=> "..."),
+#       # "2"=> Dict("plan"=> "...", "action_name"=> "...", "action_input"=> "...", "action_result"=> "..."),
+#       # ...
+#     ),
+#     )
+
+#   systemmsg_dict =  Dict(
+#       "role" => "system",
+#       "content" => [
+#         Dict("type" => "text", "text" => systemmsg),
+#       ]
+#     )
+#   usermsg = Dict(
+#       "role" => "user",
+#       "content" => [
+#         Dict("type" => "text", "text" => query),
+#       ]
+#     )
+#   push!(initialstate["chathistory"], systemmsg_dict)
+#   push!(initialstate["chathistory"], usermsg)
+  
+#   #XXX find a way to recreate the schema from a existing database
+#   table_schema = 
+#     """
+#     create table customer (
+#       customer_id uuid primary key default gen_random_uuid (),
+#       customer_firstname varchar(128),
+#       customer_lastname varchar(128),
+#       customer_displayname varchar(128) not null,
+#       customer_username varchar(128),
+#       customer_password varchar(128),
+#       customer_gender varchar(128),
+#       country	varchar(128),
+#       telephone varchar(128),
+#       email varchar(128) not null,
+#       customer_birthdate varchar(128),
+#       note text,
+      
+#       other_attributes jsonb,
+#       created_time timestamptz default current_timestamp,
+#       updated_time timestamptz default current_timestamp,
+#       description	text
+#     );
+
+#     create table retailer (
+#       retailer_id uuid primary key default gen_random_uuid (),
+#       retailer_name varchar(128) not null,
+#       retailer_username varchar(128) not null,
+#       retailer_password varchar(128) not null,
+#       retailer_address	text not null,
+#       country	varchar(128) not null,
+#       contact_person varchar(128) not null,
+#       telephone	varchar(128) not null,
+#       email	varchar(128) not null,
+#       note text,
+      
+#       other_attributes jsonb,
+#       created_time timestamptz default current_timestamp,
+#       updated_time timestamptz default current_timestamp,
+#       description	text
+#     ); 
+
+#     create table food (
+#       food_id uuid primary key default gen_random_uuid (),
+#       food_name varchar(128) not null,
+#       country	varchar(128),
+#       spiciness	integer,
+#       sweetness	integer,
+#       sourness	integer,
+#       savoriness	integer, 
+#       bitterness	integer,
+#       serving_temperature	integer,
+#       image_url jsonb,
+#       note text,
+#       other_attributes jsonb,
+
+#       created_time timestamptz default current_timestamp,
+#       updated_time timestamptz default current_timestamp,
+#       description	text
+#     );
+
+#     create table wine (
+#       wine_id uuid primary key default gen_random_uuid (),
+#       seo_name varchar(128) not null,
+#       wine_name varchar(128) not null,
+#       winery varchar(128) not null,
+#       vintage integer not null,
+#       region varchar(128) not null,
+#       country	varchar(128) not null,
+#       wine_type	varchar(128) not null,
+#       grape	varchar(128) not null,
+#       serving_temperature	varchar(128) not null,
+#       intensity	integer,
+#       sweetness	integer,
+#       tannin integer,
+#       acidity integer,
+#       fizziness	integer,
+#       tasting_notes text,
+#       image_url jsonb,
+#       manufacturer_sku text,
+#       note text,
+#       other_attributes jsonb,
+      
+#       created_time timestamptz default current_timestamp,
+#       updated_time timestamptz default current_timestamp,
+#       description	text
+#     );
+
+#     create table wine_food (
+#       wine_id uuid references wine(wine_id),
+#       food_id uuid references food(food_id),
+#       constraint wine_food_id primary key (wine_id, food_id),
+
+#       created_time timestamptz default current_timestamp,
+#       updated_time timestamptz default current_timestamp
+#     );
+
+#     CREATE TABLE retailer_wine (
+#       retailer_id uuid references retailer(retailer_id),
+#       wine_id uuid references wine(wine_id),
+#       constraint retailer_wine_id primary key (retailer_id, wine_id),
+#       price NUMERIC(10, 2),
+#       currency varchar(3) not null,
+      
+#       created_time timestamptz default current_timestamp,
+#       updated_time timestamptz default current_timestamp
+#     );
+
+#     CREATE TABLE retailer_food (
+#       retailer_id uuid references retailer(retailer_id),
+#       food_id uuid references food(food_id),
+#       constraint retailer_food_id primary key (retailer_id, food_id),
+#       price NUMERIC(10, 2),
+#       currency varchar(3) not null,
+      
+#       created_time timestamptz default current_timestamp,
+#       updated_time timestamptz default current_timestamp
+#     );
+#     """
+
+#   # println("\n--- SQLLLM query() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+#   # println("---")
+#   # error("SQLLLM query() end")
+
+#   initialstate["context"]["table_schema"] = table_schema
+
+#   transitionargs = (
+#                   executeSQL=executeSQL,
+#                   decisionMaker=decisionMaker, 
+#                   evaluator=evaluator, 
+#                   reflector=reflector,
+#                   text2textInstructLLM=text2textInstructLLM,
+#                   querySQLVectorDB=similarSQLVectorDB,
+#                   insertSQLVectorDB=insertSQLVectorDB,
+#                   llmFormatName=llmFormatName
+#                   )
+
+#   earlystop(state) = state["reward"] >= 8 ? true : false
+  
+#   root, _, resultState, highValueState = 
+#     LLMMCTS.runMCTS(initialstate, transition, transitionargs;
+#                   horizontalSampleExpansionPhase=1, 
+#                   horizontalSampleSimulationPhase=1,
+#                   maxSimulationDepth=1,
+#                   maxiterations=1, 
+#                   explorationweight=1.0,
+#                   earlystop=earlystop,
+#                   saveSimulatedNode=true,
+#                   multithread=false)
+  
+#   # error("SQLLLM query() end")
+  
+#   # compare all high value state answer then select the best one
+#   if length(highValueState) > 1
+#     selected = compareState(query, highValueState, text2textInstructLLM, llmFormatName)
+#     resultState = highValueState[selected]
+#   end
+
+#   max_ind =
+#     if length(resultState["action_history"]) == 0
+#       0
+#     else
+#       k = keys(resultState["action_history"])
+#       maximum(parse.(Int, k))
+#     end
+#   latest_action = resultState["action_history"]["$max_ind"]
+  
+#   #CHANGE add to vectorDB only if the answer is achieved and the state is terminal 
+#   sql = latest_action["action_input"]
+#   if insertSQLVectorDB !== nothing && resultState["isterminal"] == true &&
+#     resultState["accepted_as_answer"] == "yes"
+#     insertSQLVectorDB(resultState["question"], sql)
+#   end
+
+#   println("\n--- SQLLLM query() ", @__FILE__, ":", @__LINE__, " $(Dates.now())")
+#   # pprintln(resultState)
+#   println("---\n")
+  
+#   return (result_str=latest_action["action_result"], result_raw=resultState["result_raw"])
+# end
 
 
 """ Make a new state.
diff --git a/src/llmfunction.jl b/src/llmfunction.jl
index 0cf8f60..93cca1a 100644
--- a/src/llmfunction.jl
+++ b/src/llmfunction.jl
@@ -497,7 +497,7 @@ function SQLexecution(executeSQL::Function, sql::T
     else
       sql = sql * ";"
     end
-    result = executeSQL(sql)
+    result = executeSQL(sql)  #BUG sometime return table, sometime error
     df = DataFrame(result)
     tablesize = size(df)
     row, column = tablesize