feat: act result acknowledges tools (#106)

* feat: refactor CommandResult to use Command model and add get_command_string method

* feat: update command execution in BashBackend and SliverBackend to use Command object for result creation

* feat: refactor command handling to use Command model across various components and tests

* style: format code for consistency and readability across command-related files

* style: clean up whitespace in command and command_result files for improved readability

* docs: update graph visualization

* feat: update command structure in integration tests to use Command model for improved consistency

* docs: update graph visualization

---------

Co-authored-by: GitHub Action <action@github.com>

Author: laysakura

wish-api/tests/test_placeholder.py

@@ -0,0 +1,5 @@
+"""Placeholder test file for wish-api."""
+
+def test_placeholder():
+    """Placeholder test to satisfy pytest configuration."""
+    assert True

wish-command-execution/src/wish_command_execution/backend/bash.py

@@ -132,8 +132,14 @@ async def execute_command(self, wish: Wish, command: str, cmd_num: int, log_file
             Commands are executed in the working directory /app/{run_id}/ to isolate
             command execution from the application source code.
         """
-        # Create command result
-        result = CommandResult.create(cmd_num, command, log_files, timeout_sec)
+        # Create command result with Command object
+        from wish_models.command_result.command import Command, CommandType
+        command_obj = Command(
+            command=command,
+            tool_type=CommandType.BASH,
+            tool_parameters={"timeout": timeout_sec}
+        )
+        result = CommandResult.create(cmd_num, command_obj, log_files, timeout_sec)
 
         wish.command_results.append(result)
 

wish-command-execution/src/wish_command_execution/backend/sliver.py

@@ -67,8 +67,14 @@ async def execute_command(self, wish: Wish, command: str, cmd_num: int, log_file
             log_files: The log files to write output to.
             timeout_sec: The timeout in seconds for this command.
         """
-        # Create command result
-        result = CommandResult.create(cmd_num, command, log_files, timeout_sec)
+        # Create command result with Command object
+        from wish_models.command_result.command import Command, CommandType
+        command_obj = Command(
+            command=command,
+            tool_type=CommandType.BASH,  # Sliver executes shell commands
+            tool_parameters={"timeout": timeout_sec, "session_id": self.session_id}
+        )
+        result = CommandResult.create(cmd_num, command_obj, log_files, timeout_sec)
         wish.command_results.append(result)
 
         try:

wish-command-execution/tests/backend/test_bash_backend.py

@@ -76,7 +76,7 @@ async def test_execute_command(self, mock_makedirs, mock_open, mock_popen, backe
 
         # Verify that the command result was added to the wish
         assert len(wish.command_results) == 1
-        assert wish.command_results[0].command == cmd
+        assert wish.command_results[0].command.command == cmd
         assert wish.command_results[0].num == cmd_num
 
         # Verify that the command was added to running_commands
@@ -113,7 +113,7 @@ async def test_execute_command_subprocess_error(
 
         # Verify that the command result was added to the wish
         assert len(wish.command_results) == 1
-        assert wish.command_results[0].command == cmd
+        assert wish.command_results[0].command.command == cmd
         assert wish.command_results[0].num == cmd_num
 
         # Verify that the command result was updated with the error state

wish-command-execution/tests/backend/test_sliver_backend.py

@@ -92,7 +92,7 @@ async def test_execute_command(sliver_backend, wish, log_files, mock_sliver_clie
 
     # Check that the command result was added to the wish
     assert len(wish.command_results) == 1
-    assert wish.command_results[0].command == "whoami"
+    assert wish.command_results[0].command.command == "whoami"
     assert wish.command_results[0].num == 1
 
     # Check that the log files were written to
@@ -107,7 +107,9 @@ async def test_cancel_command(sliver_backend, wish, log_files):
     """Test cancelling a command."""
     # Add a command result to the wish
     timeout_sec = 60
-    result = CommandResult.create(1, "whoami", log_files, timeout_sec)
+    from wish_models.command_result.command import Command
+    command = Command.create_bash_command("whoami")
+    result = CommandResult.create(1, command, log_files, timeout_sec)
     wish.command_results.append(result)
 
     # Cancel the command

wish-command-generation-api/src/wish_command_generation_api/nodes/network_error_handler.py

@@ -99,7 +99,7 @@ def handle_network_error(state: Annotated[GraphState, "Current state"], settings
 
         # Format the feedback as JSON string
         feedback_str = (
-            json.dumps([result.model_dump() for result in state.failed_command_results], ensure_ascii=False)
+            json.dumps([result.model_dump(mode="json") for result in state.failed_command_results], ensure_ascii=False)
             if state.failed_command_results else "[]"
         )
 

wish-command-generation-api/src/wish_command_generation_api/nodes/timeout_handler.py

@@ -107,7 +107,7 @@ def handle_timeout(state: Annotated[GraphState, "Current state"], settings_obj:
 
         # Format the feedback as JSON string
         feedback_str = (
-            json.dumps([result.model_dump() for result in state.failed_command_results], ensure_ascii=False)
+            json.dumps([result.model_dump(mode="json") for result in state.failed_command_results], ensure_ascii=False)
             if state.failed_command_results else "[]"
         )
 

wish-command-generation-api/tests/integrated/test_api_with_feedback.py

@@ -21,7 +21,11 @@ def test_lambda_handler_with_feedback(settings):
     act_result = [
         {
             "num": 1,
-            "command": "nmap -p- 10.10.10.40",
+            "command": {
+                "command": "nmap -p- 10.10.10.40",
+                "tool_type": "bash",
+                "tool_parameters": {}
+            },
             "state": "TIMEOUT",
             "exit_code": 1,
             "log_summary": "timeout",
@@ -78,7 +82,11 @@ def test_lambda_handler_with_network_error_feedback(settings):
     act_result = [
         {
             "num": 1,
-            "command": "nmap -p- 10.10.10.40",
+            "command": {
+                "command": "nmap -p- 10.10.10.40",
+                "tool_type": "bash",
+                "tool_parameters": {}
+            },
             "state": "NETWORK_ERROR",
             "exit_code": 1,
             "log_summary": "Connection closed by peer",
@@ -135,7 +143,11 @@ def test_lambda_handler_with_multiple_feedback(settings):
     act_result = [
         {
             "num": 1,
-            "command": "nmap -p1-1000 10.10.10.40",
+            "command": {
+                "command": "nmap -p1-1000 10.10.10.40",
+                "tool_type": "bash",
+                "tool_parameters": {}
+            },
             "state": "SUCCESS",
             "exit_code": 0,
             "log_summary": "Scan completed successfully",
@@ -148,7 +160,11 @@ def test_lambda_handler_with_multiple_feedback(settings):
         },
         {
             "num": 2,
-            "command": "nmap -p1001-65535 10.10.10.40",
+            "command": {
+                "command": "nmap -p1001-65535 10.10.10.40",
+                "tool_type": "bash",
+                "tool_parameters": {}
+            },
             "state": "TIMEOUT",
             "exit_code": 1,
             "log_summary": "timeout",

wish-command-generation-api/tests/integrated/test_docs_integration.py

@@ -4,6 +4,7 @@
 
 import pytest
 from wish_models.command_result import CommandResult, CommandState, LogFiles
+from wish_models.command_result.command import Command, CommandType
 from wish_models.settings import Settings
 from wish_models.utc_datetime import UtcDatetime
 
@@ -63,7 +64,11 @@ def test_command_generation_with_network_error_feedback(settings):
     act_result = [
         CommandResult(
             num=1,
-            command="smbclient -N //10.10.10.40/Users --option='client min protocol'=LANMAN1",
+            command=Command(
+                command="smbclient -N //10.10.10.40/Users --option='client min protocol'=LANMAN1",
+                tool_type=CommandType.BASH,
+                tool_parameters={}
+            ),
             state=CommandState.NETWORK_ERROR,
             exit_code=1,
             log_summary="Connection closed by peer",
@@ -118,7 +123,11 @@ def test_command_generation_with_timeout_feedback(settings):
     act_result = [
         CommandResult(
             num=1,
-            command="nmap -p- 10.10.10.40",
+            command=Command(
+                command="nmap -p- 10.10.10.40",
+                tool_type=CommandType.BASH,
+                tool_parameters={}
+            ),
             state=CommandState.TIMEOUT,
             exit_code=1,
             log_summary="timeout",

wish-command-generation-api/tests/integrated/test_graph_with_feedback.py

@@ -4,6 +4,7 @@
 
 import pytest
 from wish_models.command_result import CommandResult, CommandState, LogFiles
+from wish_models.command_result.command import Command, CommandType
 from wish_models.settings import Settings
 from wish_models.utc_datetime import UtcDatetime
 
@@ -66,7 +67,11 @@ def test_graph_with_timeout_feedback(settings):
     act_result = [
             CommandResult(
                 num=1,
-                command="nmap -p- 10.10.10.40",
+                command=Command(
+                    command="nmap -p- 10.10.10.40",
+                    tool_type=CommandType.BASH,
+                    tool_parameters={}
+                ),
                 state=CommandState.TIMEOUT,
                 exit_code=1,
                 log_summary="timeout",
@@ -126,7 +131,11 @@ def test_graph_with_network_error_feedback(settings):
     act_result = [
         CommandResult(
             num=1,
-            command="nmap -p- 10.10.10.40",
+            command=Command(
+                command="nmap -p- 10.10.10.40",
+                tool_type=CommandType.BASH,
+                tool_parameters={}
+            ),
             state=CommandState.NETWORK_ERROR,
             exit_code=1,
             log_summary="Connection closed by peer",
@@ -186,7 +195,11 @@ def test_graph_with_unknown_error_feedback(settings):
     act_result = [
         CommandResult(
             num=1,
-            command="nmap -p- 10.10.10.40",
+            command=Command(
+                command="nmap -p- 10.10.10.40",
+                tool_type=CommandType.BASH,
+                tool_parameters={}
+            ),
             state=CommandState.OTHERS,
             exit_code=1,
             log_summary="Unknown error",