Files
OpenHands/opendevin/runtime/server/runtime.py
Xingyao Wang bd68249fba [Arch] Test EventStreamRuntime to ensure its feature parity with ServerRuntime (#3157)
* Remove global config from memory

* Remove runtime global config

* Remove from storage

* Remove global config

* Fix event stream tests

* Fix sandbox issue

* Change config

* Removed transferred tests

* Add swe env box

* Fixes on testing

* Fixed some tests

* Merge with stashed changes

* Fix typing

* Fix ipython test

* Revive function

* Make temp_dir fixture

* Remove test to avoid circular import

* fix eventstream filestore for test_runtime

* fix parse arg issue that cause integration test to fail

* support swebench pull from custom namespace

* add back simple tests for runtime

* move multi-line bash tests to test_runtime;
support multi-line bash for esruntime;

* add testcase to handle PS2 prompt

* use bashlex for bash parsing to handle multi-line commands;
add testcases for multi-line commands

* revert ghcr runtime change

* Apply stash

* fix run as other user;
make test async;

* fix test runtime for run as od

* add run-as-devin to all the runtime tests

* handle the case when username is root

* move all run-as-devin tests from sandbox;
only tests a few cases on different user to save time;

* move over multi-line echo related tests to test_runtime

* fix user-specific jupyter by fixing the pypoetry virtualenv folder

* make plugin's init async;
chdir at initialization of jupyter plugin;
move ipy simple testcase to test runtime;

* support agentskills import in
move tests for jupyter pwd tests;
overload `add_env_vars` for EventStreamRuntime to update env var also in Jupyter;
make agentskills read env var lazily, in case env var is updated;

* fix ServerRuntime agentskills issue

* move agnostic image test to test_runtime

* merge runtime tests in CI

* fix enable auto lint as env var

* update warning message

* update warning message

* test for different container images

* change parsing output as debug

* add exception handling for update_pwd_decorator

* fix unit test indentation

* add plugins as default input to Runtime class;
remove init_sandbox_plugins;
implement add_env_var (include jupyter) in the base class;

* fix server runtime auto lint

* Revert "add exception handling for update_pwd_decorator"

This reverts commit 2b668b1506.

* tries to print debugging info for agentskills

* explictly setting uid (try fix permission issue)

* Revert "tries to print debugging info for agentskills"

This reverts commit 8be4c86756.

* set sandbox user id during testing to hopefully fix the permission issue

* add browser tools for server runtime

* try to debug for old pwd

* update debug cmd

* only test agnostic runtime when TEST_RUNTIME is Server

* fix temp dir mkdir

* load TEST_RUNTIME at the beginning

* remove ipython tests

* only log to file when DEBUG

* default logging to project root

* temporarily remove log to file

* fix LLM logger dir

* fix logger

* make set pwd an optional aux action

* fix prev pwd

* fix infinity recursion

* simplify

* do not import the whole od library to avoid logger folder by jupyter

* fix browsing

* increase timeout

* attempt to fix agentskills yet again

* clean up in testcases, since CI maybe run as non-root

* add _cause attribute for event.id

* remove parent

* add a bunch of debugging statement again for CI :(

* fix temp_dir fixture

* change all temp dir to follow pytest's tmp_path_factory

* remove extra bracket

* clean up error printing a bit

* jupyter chdir to self.config.workspace_mount_path_in_sandbox on initialization

* jupyter chdir to self.config.workspace_mount_path_in_sandbox on initialization

* add typing for tmp dir fixture

* clear the directory before running the test to avoid weird CI temp dir

* remove agnostic test case for server runtime

* Revert "remove agnostic test case for server runtime"

This reverts commit 30e2181c3f.

* disable agnostic tests in CI

* fix test

---------

Co-authored-by: Graham Neubig <neubig@gmail.com>
2024-07-31 04:30:59 +08:00

236 lines
9.1 KiB
Python

from typing import Any, Optional
from opendevin.core.config import AppConfig
from opendevin.core.exceptions import BrowserInitException
from opendevin.core.logger import opendevin_logger as logger
from opendevin.events.action import (
BrowseInteractiveAction,
BrowseURLAction,
CmdRunAction,
FileReadAction,
FileWriteAction,
IPythonRunCellAction,
)
from opendevin.events.observation import (
CmdOutputObservation,
ErrorObservation,
IPythonRunCellObservation,
Observation,
)
from opendevin.events.stream import EventStream
from opendevin.runtime import (
DockerSSHBox,
E2BBox,
LocalBox,
Sandbox,
)
from opendevin.runtime.browser.browser_env import BrowserEnv
from opendevin.runtime.plugins import JupyterRequirement, PluginRequirement
from opendevin.runtime.runtime import Runtime
from opendevin.runtime.tools import RuntimeTool
from opendevin.storage.local import LocalFileStore
from ..browser import browse
from .files import read_file, write_file
class ServerRuntime(Runtime):
def __init__(
self,
config: AppConfig,
event_stream: EventStream,
sid: str = 'default',
plugins: list[PluginRequirement] | None = None,
sandbox: Sandbox | None = None,
):
super().__init__(config, event_stream, sid, plugins)
self.file_store = LocalFileStore(config.workspace_base)
if sandbox is None:
self.sandbox = self.create_sandbox(sid, config.sandbox.box_type)
self._is_external_sandbox = False
else:
self.sandbox = sandbox
self._is_external_sandbox = True
self.browser: BrowserEnv | None = None
def create_sandbox(self, sid: str = 'default', box_type: str = 'ssh') -> Sandbox:
if box_type == 'local':
return LocalBox(
config=self.config.sandbox, workspace_base=self.config.workspace_base
)
elif box_type == 'ssh':
return DockerSSHBox(
config=self.config.sandbox,
persist_sandbox=self.config.persist_sandbox,
workspace_mount_path=self.config.workspace_mount_path,
sandbox_workspace_dir=self.config.workspace_mount_path_in_sandbox,
cache_dir=self.config.cache_dir,
run_as_devin=self.config.run_as_devin,
ssh_hostname=self.config.ssh_hostname,
ssh_password=self.config.ssh_password,
ssh_port=self.config.ssh_port,
sid=sid,
)
elif box_type == 'e2b':
return E2BBox(
config=self.config.sandbox,
e2b_api_key=self.config.e2b_api_key,
)
else:
raise ValueError(f'Invalid sandbox type: {box_type}')
async def ainit(self, env_vars: dict[str, str] | None = None):
# init sandbox plugins
self.sandbox.init_plugins(self.plugins)
# MUST call super().ainit() to initialize both default env vars
# AND the ones in env vars!
await super().ainit(env_vars)
if any(isinstance(plugin, JupyterRequirement) for plugin in self.plugins):
obs = await self.run_ipython(
IPythonRunCellAction(
code=f'import os; os.chdir("{self.config.workspace_mount_path_in_sandbox}")'
)
)
logger.info(
f'Switch to working directory {self.config.workspace_mount_path_in_sandbox} in IPython. Output: {obs.content}'
)
async def close(self):
if hasattr(self, '_is_external_sandbox') and not self._is_external_sandbox:
self.sandbox.close()
if hasattr(self, 'browser') and self.browser is not None:
self.browser.close()
def init_runtime_tools(
self,
runtime_tools: list[RuntimeTool],
runtime_tools_config: Optional[dict[RuntimeTool, Any]] = None,
is_async: bool = True,
) -> None:
# if browser in runtime_tools, init it
if RuntimeTool.BROWSER in runtime_tools:
if runtime_tools_config is None:
runtime_tools_config = {}
browser_env_config = runtime_tools_config.get(RuntimeTool.BROWSER, {})
try:
self.browser = BrowserEnv(is_async=is_async, **browser_env_config)
except BrowserInitException:
logger.warn(
'Failed to start browser environment, web browsing functionality will not work'
)
async def run(self, action: CmdRunAction) -> Observation:
return self._run_command(action.command)
async def run_ipython(self, action: IPythonRunCellAction) -> Observation:
self._run_command(
f"cat > /tmp/opendevin_jupyter_temp.py <<'EOL'\n{action.code}\nEOL"
)
# run the code
obs = self._run_command('cat /tmp/opendevin_jupyter_temp.py | execute_cli')
output = obs.content
if 'pip install' in action.code:
print(output)
package_names = action.code.split(' ', 2)[-1]
is_single_package = ' ' not in package_names
if 'Successfully installed' in output:
restart_kernel = 'import IPython\nIPython.Application.instance().kernel.do_shutdown(True)'
if (
'Note: you may need to restart the kernel to use updated packages.'
in output
):
self._run_command(
(
"cat > /tmp/opendevin_jupyter_temp.py <<'EOL'\n"
f'{restart_kernel}\n'
'EOL'
)
)
obs = self._run_command(
'cat /tmp/opendevin_jupyter_temp.py | execute_cli'
)
output = '[Package installed successfully]'
if "{'status': 'ok', 'restart': True}" != obs.content.strip():
print(obs.content)
output += (
'\n[But failed to restart the kernel to load the package]'
)
else:
output += (
'\n[Kernel restarted successfully to load the package]'
)
# re-init the kernel after restart
if action.kernel_init_code:
self._run_command(
(
f"cat > /tmp/opendevin_jupyter_init.py <<'EOL'\n"
f'{action.kernel_init_code}\n'
'EOL'
),
)
obs = self._run_command(
'cat /tmp/opendevin_jupyter_init.py | execute_cli',
)
elif (
is_single_package
and f'Requirement already satisfied: {package_names}' in output
):
output = '[Package already installed]'
return IPythonRunCellObservation(content=output, code=action.code)
async def read(self, action: FileReadAction) -> Observation:
# TODO: use self.file_store
working_dir = self.sandbox.get_working_directory()
return await read_file(
action.path,
working_dir,
self.config.workspace_base,
self.config.workspace_mount_path_in_sandbox,
action.start,
action.end,
)
async def write(self, action: FileWriteAction) -> Observation:
# TODO: use self.file_store
working_dir = self.sandbox.get_working_directory()
return await write_file(
action.path,
working_dir,
self.config.workspace_base,
self.config.workspace_mount_path_in_sandbox,
action.content,
action.start,
action.end,
)
async def browse(self, action: BrowseURLAction) -> Observation:
return await browse(action, self.browser)
async def browse_interactive(self, action: BrowseInteractiveAction) -> Observation:
return await browse(action, self.browser)
def _run_command(self, command: str) -> Observation:
try:
exit_code, output = self.sandbox.execute(command)
if 'pip install' in command:
package_names = command.split(' ', 2)[-1]
is_single_package = ' ' not in package_names
print(output)
if 'Successfully installed' in output:
output = '[Package installed successfully]'
elif (
is_single_package
and f'Requirement already satisfied: {package_names}' in output
):
output = '[Package already installed]'
return CmdOutputObservation(
command_id=-1, content=str(output), command=command, exit_code=exit_code
)
except UnicodeDecodeError:
return ErrorObservation('Command output could not be decoded as utf-8')