Add approval continuation and multi-step tools

prompts/roles/action.md

@@ -8,9 +8,16 @@ Available tools:
   Args: {"path": "relative/path.txt"}
 - file_write: write a file inside the current workspace.
   Args: {"path": "relative/path.txt", "content": "text", "overwrite": false}
+- list_dir: list direct children of a directory inside the current workspace.
+  Args: {"path": "."}
+- search_files: search text inside files in the current workspace.
+  Args: {"query": "text to find", "path": ".", "glob": "*.py"}
 - shell_exec_safe: run a safe allowlisted shell command in the current workspace.
   Args: {"command": "pwd"}
 
 Return actions=[] when the user can be answered directly without tools.
+When tool_observations are already present, request only genuinely missing
+follow-up information. Return actions=[] when the observations are sufficient
+for the thinker to answer.
 Use only the listed tools. Keep actions minimal and directly tied to the user's
 request. Do not invent tool names.