Add timeout parameter to bash tool for hard timeout control (#8106)

Co-authored-by: openhands <openhands@all-hands.dev>
Co-authored-by: Xingyao Wang <xingyao@all-hands.dev>

openhands/agenthub/codeact_agent/function_calling.py

@@ -93,6 +93,15 @@ def response_to_actions(
                 is_input = arguments.get('is_input', 'false') == 'true'
                 action = CmdRunAction(command=arguments['command'], is_input=is_input)
 
+                # Set hard timeout if provided
+                if 'timeout' in arguments:
+                    try:
+                        action.set_hard_timeout(float(arguments['timeout']))
+                    except ValueError as e:
+                        raise FunctionCallValidationError(
+                            f"Invalid float passed to 'timeout' argument: {arguments['timeout']}"
+                        ) from e
+
             # ================================================
             # IPythonTool (Jupyter)
             # ================================================

openhands/agenthub/codeact_agent/tools/bash.py

@@ -7,10 +7,10 @@ _DETAILED_BASH_DESCRIPTION = """Execute a bash command in the terminal within a
 ### Command Execution
 * One command at a time: You can only execute one bash command at a time. If you need to run multiple commands sequentially, use `&&` or `;` to chain them together.
 * Persistent session: Commands execute in a persistent shell session where environment variables, virtual environments, and working directory persist between commands.
-* Timeout: Commands have a soft timeout of 120 seconds, once that's reached, you have the option to continue or interrupt the command (see section below for details)
+* Timeout: Commands have a soft timeout of 10 seconds, once that's reached, you have the option to continue or interrupt the command (see section below for details)
 
 ### Running and Interacting with Processes
-* Long running commands: For commands that may run indefinitely, run them in the background and redirect output to a file, e.g. `python3 app.py > server.log 2>&1 &`.
+* Long running commands: For commands that may run indefinitely, run them in the background and redirect output to a file, e.g. `python3 app.py > server.log 2>&1 &`. For commands that need to run for a specific duration, like "sleep", you can set the "timeout" argument to specify a hard timeout in seconds.
 * Interact with running process: If a bash command returns exit code `-1`, this means the process is not yet finished. By setting `is_input` to `true`, you can:
   - Send empty `command` to retrieve additional logs
   - Send text (set `command` to the text) to STDIN of the running process
@@ -25,7 +25,7 @@ _DETAILED_BASH_DESCRIPTION = """Execute a bash command in the terminal within a
 """
 
 _SHORT_BASH_DESCRIPTION = """Execute a bash command in the terminal.
-* Long running commands: For commands that may run indefinitely, it should be run in the background and the output should be redirected to a file, e.g. command = `python3 app.py > server.log 2>&1 &`.
+* Long running commands: For commands that may run indefinitely, it should be run in the background and the output should be redirected to a file, e.g. command = `python3 app.py > server.log 2>&1 &`. For commands that need to run for a specific duration, you can set the "timeout" argument to specify a hard timeout in seconds.
 * Interact with running process: If a bash command returns exit code `-1`, this means the process is not yet finished. By setting `is_input` to `true`, the assistant can interact with the running process and send empty `command` to retrieve any additional logs, or send additional text (set `command` to the text) to STDIN of the running process, or send command like `C-c` (Ctrl+C), `C-d` (Ctrl+D), `C-z` (Ctrl+Z) to interrupt the process.
 * One command at a time: You can only execute one bash command at a time. If you need to run multiple commands sequentially, you can use `&&` or `;` to chain them together."""
 
@@ -63,6 +63,10 @@ def create_cmd_run_tool(
                         ),
                         'enum': ['true', 'false'],
                     },
+                    'timeout': {
+                        'type': 'number',
+                        'description': 'Optional. Sets a hard timeout in seconds for the command execution. If not provided, the command will use the default soft timeout behavior.',
+                    },
                 },
                 'required': ['command'],
             },

tests/unit/test_function_calling.py

@@ -1,6 +1,7 @@
 """Test function calling module."""
 
 import json
+from unittest.mock import patch
 
 import pytest
 from litellm import ModelResponse
@@ -56,6 +57,21 @@ def test_execute_bash_valid():
     assert actions[0].command == 'ls'
     assert actions[0].is_input is False
 
+    # Test with timeout parameter
+    with patch.object(CmdRunAction, 'set_hard_timeout') as mock_set_hard_timeout:
+        response_with_timeout = create_mock_response(
+            'execute_bash', {'command': 'ls', 'is_input': 'false', 'timeout': 30}
+        )
+        actions_with_timeout = response_to_actions(response_with_timeout)
+
+        # Verify set_hard_timeout was called with the correct value
+        mock_set_hard_timeout.assert_called_once_with(30.0)
+
+        assert len(actions_with_timeout) == 1
+        assert isinstance(actions_with_timeout[0], CmdRunAction)
+        assert actions_with_timeout[0].command == 'ls'
+        assert actions_with_timeout[0].is_input is False
+
 
 def test_execute_bash_missing_command():
     """Test execute_bash with missing command argument."""