diff --git a/src/interface.jl b/src/interface.jl
index 4bd6edf..4888be2 100755
--- a/src/interface.jl
+++ b/src/interface.jl
@@ -373,7 +373,7 @@ function actor_mistral_openorca(a::agentReflex)
     {context}
     <|im_end|>
     {shorttermMemory}
-    Thought $mark: 
+    Thought: 
   """
   
   prompt = replace(prompt, "{role}" => a.roles[a.role])
@@ -780,9 +780,10 @@ function actor(a::agentReflex)
       respond = split(respond, "Obs")[1]
       respond_actor_raw = respond
       @show respond_actor_raw
-      
-      ind = findfirst(":", respond)[end]
-      respond = respond[ind+1:end]
+      if occursin("Thought", respond)
+        ind = findfirst(":", respond)[end]
+        respond = respond[ind+1:end]
+      end
       respond = "Thought: " * respond
       
       # some time LLM not generate a number after headers but I want it
@@ -825,7 +826,6 @@ function actor(a::agentReflex)
         respond = toolinput
         msgToUser = respond
         actorState = toolname
-        a.step += 1
         break
       else  # function call
         f = a.tools[Symbol(toolname)][:func]
diff --git a/src/type.jl b/src/type.jl
index ebd5085..70e5744 100644
--- a/src/type.jl
+++ b/src/type.jl
@@ -110,7 +110,7 @@ function agentReflex(
     :actor=> 
       """
       Use the following format:
-      Thought: think about what to do according to step {step} of the plan? (pay attention to correct numeral calculation and commonsense).
+      Thought: ask yourself do you have all the info you need and what to do according to step {step} of the plan (pay attention to correct numeral calculation and commonsense).
       Act: the action to take that match your thought, should be one of [{toolnames}]
       ActInput: the input to the action (pay attention to the tool's input)
       Obs: the result of the action