Merge branch 'main' into fix-issue-9013

frontend/src/types/core/actions.ts

@@ -23,6 +23,7 @@ export interface CommandAction extends OpenHandsActionEvent<"run"> {
   source: "agent" | "user";
   args: {
     command: string;
+    timeout: number;
     security_risk: ActionSecurityRisk;
     confirmation_state: "confirmed" | "rejected" | "awaiting_confirmation";
     thought: string;

openhands/agenthub/codeact_agent/function_calling.py

@@ -87,18 +87,21 @@ def response_to_actions(
                     raise FunctionCallValidationError(
                         f'Missing required argument "command" in tool call {tool_call.function.name}'
                     )
+                if 'timeout' not in arguments:
+                    raise FunctionCallValidationError(
+                        f'Missing required argument "timeout" in tool call {tool_call.function.name}'
+                    )
                 # convert is_input to boolean
                 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
+                # Set hard timeout
+                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

@@ -9,10 +9,10 @@ _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 10 seconds, once that's reached, you have the option to continue or interrupt the command (see section below for details)
+* Timeout: You must specify a timeout in seconds for the command execution. A value of 10 seconds is recommended if you cannot estimate how long the command should take.
 
 ### 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 &`. 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.
+* 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 &`.
 * 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
@@ -27,7 +27,7 @@ _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 &`. For commands that need to run for a specific duration, you can set the "timeout" argument to specify a hard timeout in seconds.
+* 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 &`. You must specify a timeout in seconds for the command execution. A value of 10 seconds is recommended if you cannot estimate how long the command should take.
 * 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."""
 
@@ -67,10 +67,10 @@ def create_cmd_run_tool(
                     },
                     '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.',
+                        'description': 'Sets a hard timeout in seconds for the command execution. Select a reasonable value, and 10 is a good option if you cannot estimate a-priori how long the command should take.',
                     },
                 },
-                'required': ['command'],
+                'required': ['command', 'timeout'],
             },
         ),
     )

tests/unit/test_agents.py

@@ -132,7 +132,7 @@ def test_cmd_run_tool():
     assert CmdRunTool['type'] == 'function'
     assert CmdRunTool['function']['name'] == 'execute_bash'
     assert 'command' in CmdRunTool['function']['parameters']['properties']
-    assert CmdRunTool['function']['parameters']['required'] == ['command']
+    assert CmdRunTool['function']['parameters']['required'] == ['command', 'timeout']
 
 
 def test_ipython_tool():

tests/unit/test_function_calling.py

@@ -47,16 +47,7 @@ def create_mock_response(function_name: str, arguments: dict) -> ModelResponse:
 
 def test_execute_bash_valid():
     """Test execute_bash with valid arguments."""
-    response = create_mock_response(
-        'execute_bash', {'command': 'ls', 'is_input': 'false'}
-    )
-    actions = response_to_actions(response)
-    assert len(actions) == 1
-    assert isinstance(actions[0], CmdRunAction)
-    assert actions[0].command == 'ls'
-    assert actions[0].is_input is False
-
-    # Test with timeout parameter
+    # Test with required 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}
@@ -74,12 +65,24 @@ def test_execute_bash_valid():
 
 def test_execute_bash_missing_command():
     """Test execute_bash with missing command argument."""
-    response = create_mock_response('execute_bash', {'is_input': 'false'})
+    response = create_mock_response(
+        'execute_bash', {'is_input': 'false', 'timeout': 10}
+    )
     with pytest.raises(FunctionCallValidationError) as exc_info:
         response_to_actions(response)
     assert 'Missing required argument "command"' in str(exc_info.value)
 
 
+def test_execute_bash_missing_timeout():
+    """Test execute_bash with missing timeout argument."""
+    response = create_mock_response(
+        'execute_bash', {'command': 'ls', 'is_input': 'false'}
+    )
+    with pytest.raises(FunctionCallValidationError) as exc_info:
+        response_to_actions(response)
+    assert 'Missing required argument "timeout"' in str(exc_info.value)
+
+
 def test_execute_ipython_cell_valid():
     """Test execute_ipython_cell with valid arguments."""
     response = create_mock_response('execute_ipython_cell', {'code': "print('hello')"})