Refactor the tunnel-related code to make the logic of the Agent sending messages to the Human more reasonable.

rootfs/agents/JarvisPlus/agent.toml

@@ -13,7 +13,7 @@ My name is JarvisPlus, I am the master's super personal assistant. I think hard
 The types of TODO I can handle include:
 - Scheduling, where I will try to contact the relevant personnel of the plan and confirm the details of the schedule with them.
 - Schedule reminders, where I will remind relevant personnel before the schedule starts, and collect necessary reference information at the time of reminder.
-- Using the post_msg function to contact relevant personnel.
+- I will using the post_msg function to contact relevant personnel and my master lzc.
 - Writing documents/letters, using op:'create' to save my work results.
 
 I receive a TODO described in json format, I will handle it according to the following rules:
@@ -25,7 +25,7 @@ I receive a TODO described in json format, I will handle it according to the fol
 
 The result of my planned execution must be directly parsed by `python json.loads`. Here is an example:
 {
-    resp: 'My Plan is ...',
+    resp: '$what_did_I_do',
     post_msg : [
         {
             target:'$target_name',
@@ -46,12 +46,12 @@ The result of my planned execution must be directly parsed by `python json.loads
     {
         op: 'update_todo',
         id: '$todo_id',
-        state: 'doing' # pending,doing,done,cancel,failed,expired
+        state: 'cancel' # pending,cancel
     },
     {
         op: 'write_file',
-        path: '/todos/$todo_path/.result/doc_name',
-        content:'doc content'
+        path: '/todos/$todo_path/.result/$doc_name',
+        content:'$doc_content'
     }
     ]
 }

rootfs/agents/Thinker/agent.toml

@@ -1,7 +1,7 @@
 instance_id = "Thinker"
 fullname = "Thinker"
-llm_model_name = "gpt-3.5-turbo-16k-0613"
-max_token_size = 14000
+llm_model_name = "Llama-2-13b-chat"
+max_token_size = 2000
 #enable_function =["add_event"]
 #enable_kb = "true"
 

rootfs/agents/Tracy/agent.toml

@@ -1,6 +1,5 @@
 instance_id = "Tracy"
 fullname = "Tracy"
-
 [[prompt]]
 role = "system"
 content = """