feat: 增强任务步骤注入与a11y状态表达，提升树形交互稳定性

- 打通 metadata.steps 传递链路，将任务步骤注入 agent 预测上下文

- 优化 a11y tree 线性化输出：使用中心坐标并新增 states 列（expanded/collapsed/selected 等）

- 放宽可保留节点条件，保留无文本输入类控件（edit/textfield/searchbox 等）

- 强化输出约束：单轮仅允许动作代码或 WAIT/DONE/FAIL，禁止动作与 DONE 同轮返回

- 补充 avogadro 示例步骤：展开 aromatics 并选择 benzene.cjson

mm_agents/prompts.py

@@ -15,6 +15,8 @@ When you think you have to wait for some time, return ```WAIT```;
 When you think the task can not be done, return ```FAIL```, don't easily say ```FAIL```, try your best to do the task;
 When you think the task is done, return ```DONE```.
 
+IMPORTANT: You must return EITHER a python code block OR a special code (WAIT/DONE/FAIL) in each response, NEVER BOTH. Do NOT include ```DONE``` in the same response as a ```python``` code block. After executing an action, wait for the next observation to verify the result before returning ```DONE```.
+
 My computer's password is '{{CLIENT_PASSWORD}}', feel free to use it when you need sudo rights.
 First give the current screenshot and previous things we did a short reflection, then RETURN ME THE CODE OR SPECIAL CODE I ASKED FOR. NEVER EVER RETURN ME ANYTHING ELSE.
 """.strip()
@@ -36,6 +38,8 @@ When you think you have to wait for some time, return ```WAIT```;
 When you think the task can not be done, return ```FAIL```, don't easily say ```FAIL```, try your best to do the task;
 When you think the task is done, return ```DONE```.
 
+IMPORTANT: You must return EITHER a python code block OR a special code (WAIT/DONE/FAIL) in each response, NEVER BOTH. Do NOT include ```DONE``` in the same response as a ```python``` code block. After executing an action, wait for the next observation to verify the result before returning ```DONE```.
+
 My computer's password is '{{CLIENT_PASSWORD}}', feel free to use it when you need sudo rights.
 Our past communication is great, and what you have done is very helpful. I will now give you another task to complete.
 First take a deep breath, think step by step, give the current screenshot a thinking, then RETURN ME THE CODE OR SPECIAL CODE I ASKED FOR. NEVER EVER RETURN ME ANYTHING ELSE.
@@ -550,6 +554,8 @@ When you think you have to wait for some time, return ```WAIT```;
 When you think the task can not be done, return ```FAIL```, don't easily say ```FAIL```, try your best to do the task;
 When you think the task is done, return ```DONE```.
 
+IMPORTANT: You must return EITHER a python code block OR a special code (WAIT/DONE/FAIL) in each response, NEVER BOTH. Do NOT include ```DONE``` in the same response as a ```python``` code block. After executing an action, wait for the next observation to verify the result before returning ```DONE```.
+
 My computer's password is '{{CLIENT_PASSWORD}}', feel free to use it when you need sudo rights.
 First give the current screenshot and previous things we did a short reflection, then RETURN ME THE CODE OR SPECIAL CODE I ASKED FOR. NEVER EVER RETURN ME ANYTHING ELSE.
 """.strip()
@@ -817,6 +823,8 @@ When you think you have to wait for some time, return ```WAIT```;
 When you think the task can not be done, return ```FAIL```, don't easily say ```FAIL```, try your best to do the task;
 When you think the task is done, return ```DONE```.
 
+IMPORTANT: You must return EITHER a python code block OR a special code (WAIT/DONE/FAIL) in each response, NEVER BOTH. Do NOT include ```DONE``` in the same response as a ```python``` code block. After executing an action, wait for the next observation to verify the result before returning ```DONE```.
+
 My computer's password is '{{CLIENT_PASSWORD}}', feel free to use it when you need sudo rights.
 First give the current screenshot and previous things we did a short reflection, then RETURN ME THE CODE OR SPECIAL CODE I ASKED FOR. NEVER EVER RETURN ME ANYTHING ELSE.
 """.strip()