Fix the width and height of vm, make agent perform more accurate

mm_agents/gpt_4v_prompt.py

@@ -31,25 +31,24 @@ for example, format as:
   "click_type": "LEFT"
 }
 ```
-- For [KEY, KEY_DOWN, KEY_UP, TYPE], you need to choose a(multiple) key(s) from the keyboard
+- For [KEY, KEY_DOWN, KEY_UP], you need to choose a(multiple) key(s) from the keyboard
+for example, format as:
+```
+{
+  "action_type": "KEY",
+  "key": "ctrl+c"
+}
+```
+- For TYPE, you need to specify the text you want to type
 for example, format as:
 ```
 {
   "action_type": "TYPE",
-  "text": [
-    "w",
-    "i",
-    "k",
-    "i",
-    "p",
-    "e",
-    "d",
-    "i",
-    "a"
-  ]
+  "text": "hello world"
 }
 ```
 
 For every step, you should only return the action_type and the parameters of your action as a dict, without any other things. You MUST wrap the dict with backticks (\`).
+You can predict multiple actions at one step, but you should only return one action for each step.
 You MUST choose and ONLY CHOOSE from the action space above, otherwise your action will be considered as invalid and you will get a penalty.
 """