Files
OpenHands/opendevin/runtime/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

206 lines
7.4 KiB
Python

import asyncio
import atexit
import copy
import json
import os
from abc import abstractmethod
from typing import Any, Optional
from opendevin.core.config import AppConfig, SandboxConfig
from opendevin.core.logger import opendevin_logger as logger
from opendevin.events import EventStream, EventStreamSubscriber
from opendevin.events.action import (
Action,
ActionConfirmationStatus,
BrowseInteractiveAction,
BrowseURLAction,
CmdRunAction,
FileReadAction,
FileWriteAction,
IPythonRunCellAction,
)
from opendevin.events.event import Event
from opendevin.events.observation import (
CmdOutputObservation,
ErrorObservation,
NullObservation,
Observation,
RejectObservation,
)
from opendevin.events.serialization.action import ACTION_TYPE_TO_CLASS
from opendevin.runtime.plugins import JupyterRequirement, PluginRequirement
from opendevin.runtime.tools import RuntimeTool
from opendevin.storage import FileStore
def _default_env_vars(sandbox_config: SandboxConfig) -> dict[str, str]:
ret = {}
for key in os.environ:
if key.startswith('SANDBOX_ENV_'):
sandbox_key = key.removeprefix('SANDBOX_ENV_')
ret[sandbox_key] = os.environ[key]
if sandbox_config.enable_auto_lint:
ret['ENABLE_AUTO_LINT'] = 'true'
return ret
class Runtime:
"""The runtime is how the agent interacts with the external environment.
This includes a bash sandbox, a browser, and filesystem interactions.
sid is the session id, which is used to identify the current user session.
"""
sid: str
file_store: FileStore
DEFAULT_ENV_VARS: dict[str, str]
def __init__(
self,
config: AppConfig,
event_stream: EventStream,
sid: str = 'default',
plugins: list[PluginRequirement] | None = None,
):
self.sid = sid
self.event_stream = event_stream
self.event_stream.subscribe(EventStreamSubscriber.RUNTIME, self.on_event)
self.plugins = plugins if plugins is not None else []
self.config = copy.deepcopy(config)
self.DEFAULT_ENV_VARS = _default_env_vars(config.sandbox)
atexit.register(self.close_sync)
async def ainit(self, env_vars: dict[str, str] | None = None) -> None:
"""
Initialize the runtime (asynchronously).
This method should be called after the runtime's constructor.
"""
if self.DEFAULT_ENV_VARS:
logger.debug(f'Adding default env vars: {self.DEFAULT_ENV_VARS}')
await self.add_env_vars(self.DEFAULT_ENV_VARS)
if env_vars is not None:
logger.debug(f'Adding provided env vars: {env_vars}')
await self.add_env_vars(env_vars)
async def close(self) -> None:
pass
def close_sync(self) -> None:
try:
loop = asyncio.get_running_loop()
except RuntimeError:
# No running event loop, use asyncio.run()
asyncio.run(self.close())
else:
# There is a running event loop, create a task
if loop.is_running():
loop.create_task(self.close())
else:
loop.run_until_complete(self.close())
# ====================================================================
# Methods we plan to deprecate when we move to new EventStreamRuntime
# ====================================================================
def init_runtime_tools(
self,
runtime_tools: list[RuntimeTool],
runtime_tools_config: Optional[dict[RuntimeTool, Any]] = None,
is_async: bool = True,
) -> None:
# TODO: deprecate this method when we move to the new EventStreamRuntime
raise NotImplementedError('This method is not implemented in the base class.')
# ====================================================================
async def add_env_vars(self, env_vars: dict[str, str]) -> None:
# Add env vars to the IPython shell (if Jupyter is used)
if any(isinstance(plugin, JupyterRequirement) for plugin in self.plugins):
code = 'import os\n'
for key, value in env_vars.items():
# Note: json.dumps gives us nice escaping for free
code += f'os.environ["{key}"] = {json.dumps(value)}\n'
code += '\n'
obs = await self.run_ipython(IPythonRunCellAction(code))
logger.info(f'Added env vars to IPython: code={code}, obs={obs}')
# Add env vars to the Bash shell
cmd = ''
for key, value in env_vars.items():
# Note: json.dumps gives us nice escaping for free
cmd += f'export {key}={json.dumps(value)}; '
if not cmd:
return
cmd = cmd.strip()
logger.debug(f'Adding env var: {cmd}')
obs = await self.run(CmdRunAction(cmd))
if not isinstance(obs, CmdOutputObservation) or obs.exit_code != 0:
raise RuntimeError(
f'Failed to add env vars [{env_vars}] to environment: {obs.content}'
)
async def on_event(self, event: Event) -> None:
if isinstance(event, Action):
observation = await self.run_action(event)
observation._cause = event.id # type: ignore[attr-defined]
self.event_stream.add_event(observation, event.source) # type: ignore[arg-type]
async def run_action(self, action: Action) -> Observation:
"""Run an action and return the resulting observation.
If the action is not runnable in any runtime, a NullObservation is returned.
If the action is not supported by the current runtime, an ErrorObservation is returned.
"""
if not action.runnable:
return NullObservation('')
if (
hasattr(action, 'is_confirmed')
and action.is_confirmed == ActionConfirmationStatus.AWAITING_CONFIRMATION
):
return NullObservation('')
action_type = action.action # type: ignore[attr-defined]
if action_type not in ACTION_TYPE_TO_CLASS:
return ErrorObservation(f'Action {action_type} does not exist.')
if not hasattr(self, action_type):
return ErrorObservation(
f'Action {action_type} is not supported in the current runtime.'
)
if (
hasattr(action, 'is_confirmed')
and action.is_confirmed == ActionConfirmationStatus.REJECTED
):
return RejectObservation(
'Action has been rejected by the user! Waiting for further user input.'
)
observation = await getattr(self, action_type)(action)
return observation
# ====================================================================
# Implement these methods in the subclass
# ====================================================================
@abstractmethod
async def run(self, action: CmdRunAction) -> Observation:
pass
@abstractmethod
async def run_ipython(self, action: IPythonRunCellAction) -> Observation:
pass
@abstractmethod
async def read(self, action: FileReadAction) -> Observation:
pass
@abstractmethod
async def write(self, action: FileWriteAction) -> Observation:
pass
@abstractmethod
async def browse(self, action: BrowseURLAction) -> Observation:
pass
@abstractmethod
async def browse_interactive(self, action: BrowseInteractiveAction) -> Observation:
pass