Xingyao Wang 1c7cdbefdd
feat(CodeActAgent): Support Agent-User Interaction during Task Execution and the Full Integration of CodeActAgent (#1290)
* initialize plugin definition

* initialize plugin definition

* simplify mixin

* further improve plugin mixin

* add cache dir for pip

* support clean up cache

* add script for setup jupyter and execution server

* integrate JupyterRequirement to ssh_box

* source bashrc at the end of plugin load

* add execute_cli that accept code via stdin

* make JUPYTER_EXEC_SERVER_PORT configurable via env var

* increase background cmd sleep time

* Update opendevin/sandbox/plugins/mixin.py

Co-authored-by: Robert Brennan <accounts@rbren.io>

* add mixin to base class

* make jupyter requirement a dataclass

* source plugins only when >0 requirements

* add `sandbox_plugins` for each agent & have controller take care of it

* update build.sh to make logs available in /opendevin/logs

* switch to use config for lib and cache dir

* Add SANDBOX_WORKSPACE_DIR into config

* Add SANDBOX_WORKSPACE_DIR into config

* fix occurence of /workspace

* fix permission issue with /workspace

* use python to implement execute_cli to avoid stdin escape issue

* add IPythonRunCellAction and get it working

* wait until jupyter is avaialble

* support plugin via copying instead of mounting

* add agent talk action

* support follow-up user language feedback

* add __str__ for action to be printed better

* only print PLAN at the beginning

* wip: update codeact agent

* get rid the initial messate

* update codeact agent to handle null action;
add thought to bash

* dispatch thought for RUN action as well

* fix weird behavior of pxssh where the output would not flush correctly

* make ssh box can handle exit_code properly as well

* add initial version of swe-agent plugin;

* rename swe cursors

* split setup script into two and create two requirements

* print SWE-agent command documentation

* update swe-agent to default to no custom docs

* add initial version of swe-agent plugin;

* rename swe cursors

* split setup script into two and create two requirements

* print SWE-agent command documentation

* update swe-agent to default to no custom docs

* update dockerfile with dependency from swe-agent

* make env setup a separate script for .bashrc source

* add wip prompt

* fix mount_dir for ssh_box

* update prompt

* fix mount_dir for ssh_box

* default to use host network

* default to use host network

* move prompt to a separate file

* fix swe-tool plugins;
add missing _split_string

* remove hostname from sshbox

* update the prompt with edit functionality

* fix swe-tool plugins;
add missing _split_string

* add awaiting into status bar

* fix the bug of additional send event

* remove some print action

* move logic to config.py

* remove debugging comments

* make host network as default

* make WORKSPACE_MOUNT_PATH as abspath

* implement execute_cli via file cp

* Revert "implement execute_cli via file cp"

This reverts commit 06f0155bc17d1f99097e71b83b2143f6e8092654.

* add codeact dependencies to default container

* add IPythonRunCellObservation

* add back cache dir and default to /tmp

* make USE_HOST_NETWORK a bool

* revert use host network to false

* add temporarily fix for IPython RUN action

* update prompt

* revert USE_HOST_NETWORK to true since it is not affecting anything

* attempt to fix lint

* remove newline

* fix jupyter execution server

* add `thought` to most action class

* fix unit tests for current action abstraction

* support user exit

* update test cases with the latest action format (added 'thought')

* fix integration test for CodeActAGent by mocking stdin

* only mock stdin for tests with user_responses.log

* remove -exec integration test for CodeActAgent since it is not supported

* remove specific stop word

* fix comments

* improve clarity of prompt

* fix py lint

* fix integration tests

* sandbox might failed in chown due to mounting, but it won't be fatal

* update debug instruction for sshbox

* fix typo

* get RUN_AS_DEVIN and network=host working with app sandbox

* get RUN_AS_DEVIN and network=host working with app sandbox

* attempt to fix the workspace base permission

* sandbox might failed in chown due to mounting, but it won't be fatal

* update sshbox instruction

* remove default user id since it will be passed in the instruction

* revert permission fix since it should be resolved by correct SANDBOX_USER_ID

* the permission issue can be fixed by simply provide correct env var

* remove log

* set sandbox user id to getuid by default

* move logging to initializer

* make the uid consistent across host, app container, and sandbox

* remove hostname as it causes sudo issue

* fix permission of entrypoint script

* make the uvicron app run as host user uid for jupyter plugin

* add warning message

* update dev md for instruction of running unit tests

* add back unit tests

* revert back to the original sandbox implementation to fix testcases

* revert use host network

* get docker socket gid and usermod instead of chmod 777

* allow unit test workflow to find docker.sock

* make sandbox test working via patch

* fix arg parser that's broken for some reason

* try to fix app build disk space issue

* fix integration test

* Revert "fix arg parser that's broken for some reason"

This reverts commit 6cc89611337bb74555fd16b4be78681fb7e36573.

* update Development.md

* cleanup intergration tests & add exception for CodeAct+execbox

* fix config

* implement user_message action

* fix doc

* fix event dict error

* fix frontend lint

* revert accidentally changes to integration tests

* revert accidentally changes to integration tests

---------

Co-authored-by: Robert Brennan <accounts@rbren.io>
Co-authored-by: Robert Brennan <contact@rbren.io>
2024-05-01 08:40:00 -04:00

97 lines
2.8 KiB
Python

import os
import pathlib
from dataclasses import dataclass
from typing import TYPE_CHECKING
from opendevin import config
from opendevin.schema import ActionType, ConfigType
from .base import ExecutableAction
if TYPE_CHECKING:
from opendevin.controller import AgentController
from opendevin.observation import CmdOutputObservation, Observation
from opendevin.observation import IPythonRunCellObservation
@dataclass
class CmdRunAction(ExecutableAction):
command: str
background: bool = False
thought: str = ''
action: str = ActionType.RUN
async def run(self, controller: 'AgentController') -> 'Observation':
return controller.action_manager.run_command(self.command, self.background)
@property
def message(self) -> str:
return f'Running command: {self.command}'
def __str__(self) -> str:
ret = '**CmdRunAction**\n'
if self.thought:
ret += f'THOUGHT:{self.thought}\n'
ret += f'COMMAND:\n{self.command}'
return ret
@dataclass
class CmdKillAction(ExecutableAction):
id: int
thought: str = ''
action: str = ActionType.KILL
async def run(self, controller: 'AgentController') -> 'CmdOutputObservation':
return controller.action_manager.kill_command(self.id)
@property
def message(self) -> str:
return f'Killing command: {self.id}'
def __str__(self) -> str:
return f'**CmdKillAction**\n{self.id}'
@dataclass
class IPythonRunCellAction(ExecutableAction):
code: str
thought: str = ''
action: str = ActionType.RUN_IPYTHON
async def run(self, controller: 'AgentController') -> 'IPythonRunCellObservation':
# echo "import math" | execute_cli
# write code to a temporary file and pass it to `execute_cli` via stdin
tmp_filepath = os.path.join(
config.get(ConfigType.WORKSPACE_BASE),
'.tmp', '.ipython_execution_tmp.py'
)
pathlib.Path(os.path.dirname(tmp_filepath)).mkdir(parents=True, exist_ok=True)
with open(tmp_filepath, 'w') as tmp_file:
tmp_file.write(self.code)
tmp_filepath_inside_sandbox = os.path.join(
config.get(ConfigType.WORKSPACE_MOUNT_PATH_IN_SANDBOX),
'.tmp', '.ipython_execution_tmp.py'
)
obs = controller.action_manager.run_command(
f'execute_cli < {tmp_filepath_inside_sandbox}',
background=False
)
return IPythonRunCellObservation(
content=obs.content,
code=self.code
)
def __str__(self) -> str:
ret = '**IPythonRunCellAction**\n'
if self.thought:
ret += f'THOUGHT:{self.thought}\n'
ret += f'CODE:\n{self.code}'
return ret
@property
def message(self) -> str:
return f'Running Python code interactively: {self.code}'