Xingyao Wang 31b244f95e
[Refactor, Evaluation] Refactor and clean up evaluation harness to remove global config and use EventStreamRuntime (#3230)
* 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 2b668b1506e02145cb8f87e321aad62febca3d50.

* 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 8be4c86756f0e3fc62957b327ba2ac4999c419de.

* 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 30e2181c3fc1410e69596c2dcd06be01f1d016b3.

* disable agnostic tests in CI

* fix test

* make sure plugin arg is not passed when no plugin is specified;
remove redundant on_event function;

* move mock prompt

* rename runtime

* remove extra logging

* refactor run_controller's interface;
support multiple runtime for integration test;
filter out hostname for prompt

* uncomment other tests

* pass the right runtime to controller

* log runtime when start

* uncomment tests

* improve symbol filters

* add intergration test prompts that seemd ok

* add integration test workflow

* add python3 to default ubuntu image

* symlink python and fix permission to jupyter pip

* add retry for jupyter execute server

* fix jupyter pip install;
add post-process for jupyter pip install;
simplify init by add agent_skills path to PYTHONPATH;
add testcase to tests jupyter pip install;

* fix bug

* use ubuntu:22.04 for eventstream integration tests

* add todo

* update testcase

* remove redundant code

* fix unit test

* reduce dependency for runtime

* try making llama-index an optional dependency that's not installed by default

* remove pip install since it seemd not needed

* log ipython execution;
await write message since it returns a future

* update ipy testcase

* do not install llama-index in CI

* do not install llama-index in the app docker as well

* set sandbox container image in the integration test script

* log plugins & env var for runtime

* update conftest for sha256

* add git

* remove all non-alphanumeric chalracters

* add working ipy module tests!

* default to use host network

* remove is_async from browser to make thing a little more reliable;
retry loading browser when error;

* add sleep to wait a bit for http server

* kill http server before regenerate browsing tests

* fix browsing

* only set sandbox container image if undefined

* skip empty config value

* update evaluation to use the latest run_controller

* revert logger in execute_server to be compatible with server runtime

* revert logging level to fix jupyter

* set logger level

* revert the logging

* chmod for workspace to fix permission

* support getting timeout from action

* update test for server runtime

* try to fix file permission

* fix test_cmd_run_action_serialization_deserialization test (added timeout)

* poetry: pip 24.2, torch 2.2.2

* revert adding pip to pyproject.toml

* add build to dependencies in pyproject.toml

* forgot poetry lock --no-update

* fix a DelegatorAgent prompt_002.log (timeout)

* fix a DelegatorAgent prompt_003.log (timeout)

* couple more timeout attribs in prompt files

* some more prompt files

* prompts galore

* add clarification comment for timeout

* default timeout to config

* add assert

* update integraton tests for eventstream

* update integration tests

* fix timeout for action<->dict

* remove redundant on_event

* default to use instance image

* update run_controller interface

* add logging for copy

* refactor swe_bench for the new design

* fix action execution timeout

* updatelock

* remove build sandbox locally

* fix runtime

* use plain for-loop for single process

* remove extra print

* get swebench inference working

* print whole `test_result` dict

* got swebench patch post-process working

* update swe-bench evaluation readme

* refactor using shared reset_logger function

* move messy swebench prompt to a different file

* support the ability to specify whether to keep prompt

* support the ability to specify whether to keep prompt

* fix dockerfile

* fix import and remove unnecessary strip logic

* fix action serialization

* get agentbench running

* remove extra ls for agent bench

* fix agentbench metric

* factor out common documentation for eval

* update biocoder doc

* remove swe_env_box since it is no longer needed

* get biocoder working

* add func timeout for bird

* fix jupyter pwd with ~ as user name

* fix jupyter pwd with ~ as user name

* get bird working

* get browsing evaluation working

* make eda runnable

* fix id column

* fix eda run_infer

* unify eval output using a structured format;
make swebench coompatible with that format;
update client source code for every swebench run;
do not inject testcmd for swebench

* standardize existing benchs for the new eval output

* set update source code = true

* get gaia standardized

* fix gaia

* gorilla refactored but stuck at language.so to test

* refactor and make gpqa work

* refactor humanevalfix and get it working

* refactor logic reasoning and get it working

* refactor browser env so it works with eventstream runtime for eval

* add initial version of miniwob refactor

* fix browsergym environment

* get miniwob working!!

* allowing injecting additional dependency to OD runtime docker image

* allowing injecting additional dependency to OD runtime docker image

* support logic reasoning with pre-injected dependency

* get mint working

* update runtime build

* fix mint docker

* add test for keep_prompt;
add missing await close for some tests

* update integration tests for eventstream runtime

* fix integration tests for server runtime

* refactor ml bench and toolqa

* refactor webarena

* fix default factory

* Update run_infer.py

* add APIError to retry

* increase timeout for swebench

* make sure to hide api key when dump eval output

* update the behavior of put source code to put files instead of tarball

* add dishash to dependency

* sendintr when timeout

* fix dockerfile copy

* reduce timeout

* use dirhash to avoid repeat building for update source

* fix runtime_build testcase

* add dir_hash to docker build pipeline

* revert api error

* update poetry lock

* add retries for swebench run infer

* fix git patch

* update poetry lock

* adjust config order

* fix mount volumns

* enforce all eval to use "instance_id"

* remove file store from runtime

* make file_store public inside eventstream

* move the runtime logic inside `main` out

* support using async function for process_instance_fn

* refactor run_infer with the create_time

* fix file store

* Update evaluation/toolqa/utils.py

Co-authored-by: Graham Neubig <neubig@gmail.com>

* fix typo

---------

Co-authored-by: tobitege <tobitege@gmx.de>
Co-authored-by: super-dainiu <78588128+super-dainiu@users.noreply.github.com>
Co-authored-by: Graham Neubig <neubig@gmail.com>
2024-08-06 17:21:45 +00:00

235 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 ..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)
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
logger.debug(f'ServerRuntime `{sid}` config:\n{self.config}')
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,
) -> 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(**browser_env_config)
except BrowserInitException:
logger.warn(
'Failed to start browser environment, web browsing functionality will not work'
)
async def copy_to(self, host_src: str, sandbox_dest: str, recursive: bool = False):
self.sandbox.copy_to(host_src, sandbox_dest, recursive)
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:
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:
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')