Use event stream for the runtime (#1776)

* rebuild PR from scratch

* fix max_iter

* regenerate tests

* cut down on history

* Update opendevin/controller/agent_controller.py

* regenerate tests

* revert swe agent

* revert some codeact chagnes

* regenerate tests

* add source to dict

* only add source if not none

* try to fix coverage issue

* lock

* add gevent
This commit is contained in:
Robert Brennan 2024-05-14 09:35:25 -04:00 committed by GitHub
parent 82a798990c
commit beb74a19f6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
64 changed files with 2946 additions and 732 deletions

View File

@ -10,12 +10,10 @@ from opendevin.events.action import (
CmdRunAction,
IPythonRunCellAction,
MessageAction,
NullAction,
)
from opendevin.events.observation import (
CmdOutputObservation,
IPythonRunCellObservation,
NullObservation,
)
from opendevin.llm.llm import LLM
from opendevin.runtime.plugins import (
@ -120,18 +118,6 @@ class CodeActAgent(Agent):
JupyterRequirement(),
SWEAgentCommandsRequirement(),
]
SUPPORTED_ACTIONS = (
CmdRunAction,
IPythonRunCellAction,
MessageAction,
NullAction,
)
SUPPORTED_OBSERVATIONS = (
CmdOutputObservation,
IPythonRunCellObservation,
NullObservation,
)
messages: list[dict] = []
def __init__(
self,
@ -178,9 +164,6 @@ class CodeActAgent(Agent):
updated_info = state.updated_info
if updated_info:
for prev_action, obs in updated_info:
assert isinstance(
prev_action, self.SUPPORTED_ACTIONS
), f'{prev_action.__class__} is not supported (supported: {self.SUPPORTED_ACTIONS})'
if (
isinstance(prev_action, MessageAction)
and prev_action.source == 'user'
@ -192,16 +175,10 @@ class CodeActAgent(Agent):
# User wants to exit
return AgentFinishAction()
# handle observations
assert isinstance(
obs, self.SUPPORTED_OBSERVATIONS
), f'{obs.__class__} is not supported (supported: {self.SUPPORTED_OBSERVATIONS})'
if isinstance(obs, CmdOutputObservation):
content = 'OBSERVATION:\n' + truncate_observation(obs.content)
content += f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]]'
self.messages.append({'role': 'user', 'content': content})
elif isinstance(obs, IPythonRunCellObservation):
content = 'OBSERVATION:\n' + obs.content
# replace base64 images with a placeholder
@ -214,12 +191,7 @@ class CodeActAgent(Agent):
content = '\n'.join(splitted)
content = truncate_observation(content)
self.messages.append({'role': 'user', 'content': content})
elif isinstance(obs, NullObservation):
pass
else:
raise NotImplementedError(
f'Unknown observation type: {obs.__class__}'
)
latest_user_message = [m for m in self.messages if m['role'] == 'user'][-1]
if latest_user_message:
latest_user_message['content'] += (

View File

@ -59,7 +59,7 @@ class DummyAgent(Agent):
'observations': [NullObservation('')],
},
{
'action': ModifyTaskAction(id='0.0', state='in_progress'),
'action': ModifyTaskAction(task_id='0.0', state='in_progress'),
'observations': [NullObservation('')],
},
{
@ -96,7 +96,7 @@ class DummyAgent(Agent):
'action': CmdRunAction(command=BACKGROUND_CMD, background=True),
'observations': [
CmdOutputObservation(
'Background command started. To stop it, send a `kill` action with id 42',
'Background command started. To stop it, send a `kill` action with command_id 42',
command_id='42', # type: ignore[arg-type]
command=BACKGROUND_CMD,
),

View File

@ -1,2 +1,2 @@
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `command_id` - the ID of the background command to kill

View File

@ -35,7 +35,7 @@ Here are the possible actions:
* `command` - the command to run
* `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `command_id` - the ID of the background command to kill
* `browse` - opens a web page. Arguments:
* `url` - the URL to open
* `push` - Push a branch from the current repo to github:
@ -140,7 +140,7 @@ def get_request_action_prompt(
bg_commands_message += (
f'\n`{command_obs.command_id}`: {command_obs.command}'
)
bg_commands_message += '\nYou can end any process by sending a `kill` action with the numerical `id` above.'
bg_commands_message += '\nYou can end any process by sending a `kill` action with the numerical `command_id` above.'
user = 'opendevin' if config.run_as_devin else 'root'

View File

@ -78,7 +78,7 @@ It must be an object, and it must contain two fields:
* `command` - the command to run
* `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `command_id` - the ID of the background command to kill
* `browse` - opens a web page. Arguments:
* `url` - the URL to open
* `message` - make a plan, set a goal, or record your thoughts. Arguments:
@ -88,7 +88,7 @@ It must be an object, and it must contain two fields:
* `goal` - the goal of the task
* `subtasks` - a list of subtasks, each of which is a map with a `goal` key.
* `modify_task` - close a task. Arguments:
* `id` - the ID of the task to close
* `task_id` - the ID of the task to close
* `state` - set to 'in_progress' to start the task, 'completed' to finish it, 'verified' to assert that it was successful, 'abandoned' to give up on it permanently, or `open` to stop working on it for now.
* `finish` - if ALL of your tasks and subtasks have been verified or abandoned, and you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
@ -174,12 +174,9 @@ def parse_response(response: str) -> Action:
Returns:
- Action: A valid next action to perform from model output
"""
# attempt to load the JSON dict from the response
action_dict = json.loads(response)
if 'contents' in action_dict:
# The LLM gets confused here. Might as well be robust
action_dict['content'] = action_dict.pop('contents')
action = action_from_dict(action_dict)
return action

View File

@ -1,7 +1,6 @@
import asyncio
from typing import Optional, Type
from agenthub.codeact_agent.codeact_agent import CodeActAgent
from opendevin.controller.agent import Agent
from opendevin.controller.state.state import State
from opendevin.core.config import config
@ -27,14 +26,12 @@ from opendevin.events.event import Event
from opendevin.events.observation import (
AgentDelegateObservation,
AgentStateChangedObservation,
CmdOutputObservation,
ErrorObservation,
NullObservation,
Observation,
)
from opendevin.events.stream import EventSource, EventStream, EventStreamSubscriber
from opendevin.runtime import DockerSSHBox, Sandbox
from opendevin.runtime.runtime import Runtime
from opendevin.runtime.server.runtime import ServerRuntime
MAX_ITERATIONS = config.max_iterations
MAX_CHARS = config.llm.max_chars
@ -44,13 +41,12 @@ class AgentController:
id: str
agent: Agent
max_iterations: int
runtime: Runtime
event_stream: EventStream
state: State
agent_task: Optional[asyncio.Task] = None
delegate: 'AgentController | None' = None
_agent_state: AgentState = AgentState.LOADING
_cur_step: int = 0
_pending_action: Action | None = None
def __init__(
self,
@ -60,7 +56,6 @@ class AgentController:
max_iterations: int = MAX_ITERATIONS,
max_chars: int = MAX_CHARS,
inputs: dict | None = None,
sandbox: Optional[Sandbox] = None,
):
"""Initializes a new instance of the AgentController class.
@ -71,7 +66,6 @@ class AgentController:
max_iterations: The maximum number of iterations the agent can run.
max_chars: The maximum number of characters the agent can output.
inputs: The initial inputs to the agent.
sandbox: An optional initialized sandbox to run the agent in. If not provided, a default sandbox will be created based on config.
"""
self.id = sid
self.agent = agent
@ -81,101 +75,74 @@ class AgentController:
EventStreamSubscriber.AGENT_CONTROLLER, self.on_event
)
self.max_iterations = max_iterations
self.runtime = ServerRuntime(sandbox=sandbox, sid=self.id)
self.max_chars = max_chars
# Initialize agent-required plugins for sandbox (if any)
self.runtime.init_sandbox_plugins(agent.sandbox_plugins)
if isinstance(agent, CodeActAgent) and not isinstance(
self.runtime.sandbox, DockerSSHBox
):
logger.warning(
'CodeActAgent requires DockerSSHBox as sandbox! Using other sandbox that are not stateful (LocalBox, DockerExecBox) will not work properly.'
)
self.agent_task = asyncio.create_task(self._start_step_loop())
async def close(self):
if self.agent_task is not None:
self.agent_task.cancel()
self.event_stream.unsubscribe(EventStreamSubscriber.AGENT_CONTROLLER)
self.runtime.sandbox.close()
self.runtime.browser.close()
await self.set_agent_state_to(AgentState.STOPPED)
def update_state_for_step(self, i):
self.state.iteration = i
self.state.background_commands_obs = self.runtime.get_background_obs()
def update_state_before_step(self):
self.state.iteration += 1
def update_state_after_step(self):
self.state.updated_info = []
async def add_error_to_history(self, message: str):
await self.add_history(NullAction(), ErrorObservation(message))
async def report_error(self, message: str):
await self.event_stream.add_event(ErrorObservation(message), EventSource.AGENT)
async def add_history(
self, action: Action, observation: Observation, add_to_stream=True
):
if not isinstance(action, Action):
raise TypeError(
f'action must be an instance of Action, got {type(action).__name__} instead'
)
if not isinstance(observation, Observation):
raise TypeError(
f'observation must be an instance of Observation, got {type(observation).__name__} instead'
)
async def add_history(self, action: Action, observation: Observation):
if isinstance(action, NullAction) and isinstance(observation, NullObservation):
return
self.state.history.append((action, observation))
self.state.updated_info.append((action, observation))
if add_to_stream:
await self.event_stream.add_event(action, EventSource.AGENT)
await self.event_stream.add_event(observation, EventSource.AGENT)
async def _run(self):
if self._agent_state != AgentState.RUNNING:
raise ValueError('Task is not in running state')
for i in range(self._cur_step, self.max_iterations):
self._cur_step = i
async def _start_step_loop(self):
while True:
try:
finished = await self.step(i)
if finished:
await self.set_agent_state_to(AgentState.FINISHED)
break
except Exception:
logger.error('Error in loop', exc_info=True)
await self.set_agent_state_to(AgentState.ERROR)
await self.add_error_to_history(
'Oops! Something went wrong while completing your task. You can check the logs for more info.'
await self._step()
except asyncio.CancelledError:
logger.info('AgentController task was cancelled')
break
except Exception as e:
logger.error(f'Error while running the agent: {e}')
await self.report_error(
'There was an unexpected error while running the agent'
)
await self.set_agent_state_to(AgentState.ERROR)
break
if self._is_stuck():
logger.info('Loop detected, stopping task')
await self.set_agent_state_to(AgentState.ERROR)
await self.add_error_to_history(
'I got stuck into a loop, the task has stopped.'
)
break
await asyncio.sleep(
0.001
) # Give back control for a tick, so other async stuff can run
final_state = self.get_agent_state()
if final_state == AgentState.RUNNING:
await self.set_agent_state_to(AgentState.PAUSED)
await asyncio.sleep(0.1)
async def on_event(self, event: Event):
if isinstance(event, ChangeAgentStateAction):
await self.set_agent_state_to(event.agent_state) # type: ignore
elif isinstance(event, MessageAction) and event.source == EventSource.USER:
await self.add_history(event, NullObservation(''), add_to_stream=False)
if self.get_agent_state() != AgentState.RUNNING:
await self.set_agent_state_to(AgentState.RUNNING)
elif isinstance(event, MessageAction):
if event.source == EventSource.USER:
await self.add_history(event, NullObservation(''))
if self.get_agent_state() != AgentState.RUNNING:
await self.set_agent_state_to(AgentState.RUNNING)
elif event.source == EventSource.AGENT and event.wait_for_response:
await self.set_agent_state_to(AgentState.AWAITING_USER_INPUT)
elif isinstance(event, AgentDelegateAction):
await self.start_delegate(event)
elif isinstance(event, AddTaskAction):
self.state.root_task.add_subtask(event.parent, event.goal, event.subtasks)
elif isinstance(event, ModifyTaskAction):
self.state.root_task.set_subtask_state(event.task_id, event.state)
elif isinstance(event, AgentFinishAction):
self.state.outputs = event.outputs # type: ignore[attr-defined]
await self.set_agent_state_to(AgentState.FINISHED)
elif isinstance(event, Observation):
if self._pending_action and self._pending_action.id == event.cause:
await self.add_history(self._pending_action, event)
self._pending_action = None
elif isinstance(event, CmdOutputObservation):
await self.add_history(NullAction(), event)
async def reset_task(self):
if self.agent_task is not None:
self.agent_task.cancel()
self.state = State()
self._cur_step = 0
def reset_task(self):
self.agent.reset()
async def set_agent_state_to(self, new_state: AgentState):
@ -186,17 +153,8 @@ class AgentController:
return
self._agent_state = new_state
if new_state == AgentState.RUNNING:
self.agent_task = asyncio.create_task(self._run())
elif (
new_state == AgentState.PAUSED
or new_state == AgentState.AWAITING_USER_INPUT
):
self._cur_step += 1
if self.agent_task is not None:
self.agent_task.cancel()
elif new_state == AgentState.STOPPED or new_state == AgentState.ERROR:
await self.reset_task()
if new_state == AgentState.STOPPED or new_state == AgentState.ERROR:
self.reset_task()
await self.event_stream.add_event(
AgentStateChangedObservation('', self._agent_state), EventSource.AGENT
@ -218,64 +176,60 @@ class AgentController:
inputs=action.inputs,
)
async def step(self, i: int) -> bool:
async def _step(self):
if self.get_agent_state() != AgentState.RUNNING:
logger.debug('waiting for agent to run...')
await asyncio.sleep(1)
return
if self._pending_action:
logger.debug('waiting for pending action: ' + str(self._pending_action))
await asyncio.sleep(1)
return
logger.info(f'STEP {self.state.iteration}', extra={'msg_type': 'STEP'})
if self.state.iteration >= self.max_iterations:
await self.report_error('Agent reached maximum number of iterations')
await self.set_agent_state_to(AgentState.ERROR)
return
if self.delegate is not None:
delegate_done = await self.delegate.step(i)
delegate_done = await self.delegate._step()
if delegate_done:
outputs = self.delegate.state.outputs if self.delegate.state else {}
obs: Observation = AgentDelegateObservation(content='', outputs=outputs)
await self.add_history(NullAction(), obs)
await self.event_stream.add_event(obs, EventSource.AGENT)
self.delegate = None
self.delegateAction = None
return False
return
logger.info(f'STEP {i}', extra={'msg_type': 'STEP'})
if self.state.num_of_chars > self.max_chars:
raise MaxCharsExceedError(self.state.num_of_chars, self.max_chars)
log_obs = self.runtime.get_background_obs()
for obs in log_obs:
await self.add_history(NullAction(), obs)
logger.info(obs, extra={'msg_type': 'BACKGROUND LOG'})
self.update_state_for_step(i)
self.update_state_before_step()
action: Action = NullAction()
observation: Observation = NullObservation('')
try:
action = self.agent.step(self.state)
if action is None:
raise AgentNoActionError('No action was returned')
except (AgentMalformedActionError, AgentNoActionError, LLMOutputError) as e:
observation = ErrorObservation(str(e))
await self.report_error(str(e))
return
logger.info(action, extra={'msg_type': 'ACTION'})
self.update_state_after_step()
if isinstance(action, AgentFinishAction):
self.state.outputs = action.outputs # type: ignore[attr-defined]
logger.info(action, extra={'msg_type': 'INFO'})
if action.runnable:
self._pending_action = action
else:
await self.add_history(action, NullObservation(''))
return True
elif isinstance(action, MessageAction) and action.wait_for_response:
# FIXME: remove this once history is managed outside the agent controller
await self.add_history(action, NullObservation(''))
await self.set_agent_state_to(AgentState.AWAITING_USER_INPUT)
return False
elif isinstance(action, AgentDelegateAction):
await self.start_delegate(action)
elif isinstance(action, AddTaskAction):
self.state.root_task.add_subtask(
action.parent, action.goal, action.subtasks
)
elif isinstance(action, ModifyTaskAction):
self.state.root_task.set_subtask_state(action.id, action.state)
elif not isinstance(observation, ErrorObservation):
observation = await self.runtime.run_action(action)
if not isinstance(observation, NullObservation):
logger.info(observation, extra={'msg_type': 'OBSERVATION'})
await self.add_history(action, observation)
return False
if not isinstance(action, NullAction):
await self.event_stream.add_event(action, EventSource.AGENT)
if self._is_stuck():
await self.report_error('Agent got stuck in a loop')
await self.set_agent_state_to(AgentState.ERROR)
def get_state(self):
return self.state
@ -301,7 +255,7 @@ class AgentController:
for i in range(1, 4)
):
# same (Action, NullObservation): like 'think' the same thought over and over
logger.debug('Action, NullObservation loop detected')
logger.warning('Action, NullObservation loop detected')
return True
elif all(
isinstance(self.state.history[-i][1], ErrorObservation)
@ -309,7 +263,7 @@ class AgentController:
):
# (NullAction, ErrorObservation): errors coming from an exception
# (Action, ErrorObservation): the same action getting an error, even if not necessarily the same error
logger.debug('Action, ErrorObservation loop detected')
logger.warning('Action, ErrorObservation loop detected')
return True
return False

View File

@ -70,6 +70,7 @@ class AgentConfig(metaclass=Singleton):
class AppConfig(metaclass=Singleton):
llm: LLMConfig = field(default_factory=LLMConfig)
agent: AgentConfig = field(default_factory=AgentConfig)
runtime: str = 'server'
workspace_base: str = os.getcwd()
workspace_mount_path: str = os.getcwd()
workspace_mount_path_in_sandbox: str = '/workspace'

View File

@ -12,6 +12,7 @@ from opendevin.events.event import Event
from opendevin.events.observation import AgentStateChangedObservation
from opendevin.events.stream import EventSource, EventStream, EventStreamSubscriber
from opendevin.llm.llm import LLM
from opendevin.runtime.server.runtime import ServerRuntime
def read_task_from_file(file_path: str) -> str:
@ -82,6 +83,7 @@ async def main(task_str: str = '', exit_on_message: bool = False) -> AgentState:
max_chars=args.max_chars,
event_stream=event_stream,
)
_ = ServerRuntime(event_stream=event_stream)
await event_stream.add_event(MessageAction(content=task), EventSource.USER)
await event_stream.add_event(

View File

@ -28,7 +28,7 @@ class CmdRunAction(Action):
@dataclass
class CmdKillAction(Action):
id: int
command_id: int
thought: str = ''
action: str = ActionType.KILL
runnable: ClassVar[bool] = True

View File

@ -20,11 +20,11 @@ class AddTaskAction(Action):
@dataclass
class ModifyTaskAction(Action):
id: str
task_id: str
state: str
thought: str = ''
action: str = ActionType.MODIFY_TASK
@property
def message(self) -> str:
return f'Set task {self.id} to {self.state}'
return f'Set task {self.task_id} to {self.state}'

View File

@ -1,4 +1,12 @@
import datetime
from dataclasses import asdict, dataclass
from enum import Enum
from typing import Optional
class EventSource(str, Enum):
AGENT = 'agent'
USER = 'user'
@dataclass
@ -8,13 +16,37 @@ class Event:
def to_dict(self):
d = self.to_memory()
if self.source:
d['source'] = self.source
d['message'] = self.message
return d
@property
def message(self) -> str:
return self._message # type: ignore [attr-defined]
if hasattr(self, '_message'):
return self._message # type: ignore [attr-defined]
return ''
@property
def source(self) -> str:
return self._source # type: ignore [attr-defined]
def id(self) -> int:
if hasattr(self, '_id'):
return self._id # type: ignore [attr-defined]
return -1
@property
def timestamp(self) -> Optional[datetime.datetime]:
if hasattr(self, '_timestamp'):
return self._timestamp # type: ignore [attr-defined]
return None
@property
def source(self) -> Optional[EventSource]:
if hasattr(self, '_source'):
return self._source # type: ignore [attr-defined]
return None
@property
def cause(self) -> Optional[int]:
if hasattr(self, '_cause'):
return self._cause # type: ignore [attr-defined]
return None

View File

@ -5,7 +5,7 @@ from typing import Callable
from opendevin.core.logger import opendevin_logger as logger
from .event import Event
from .event import Event, EventSource
class EventStreamSubscriber(str, Enum):
@ -15,11 +15,6 @@ class EventStreamSubscriber(str, Enum):
MAIN = 'main'
class EventSource(str, Enum):
AGENT = 'agent'
USER = 'user'
class EventStream:
def __init__(self):
self._subscribers: dict[str, Callable] = {}
@ -28,7 +23,7 @@ class EventStream:
def subscribe(self, id: EventStreamSubscriber, callback: Callable):
if id in self._subscribers:
logger.warning('Subscriber subscribed multiple times: ' + id)
raise ValueError('Subscriber already exists: ' + id)
else:
self._subscribers[id] = callback

View File

@ -8,6 +8,8 @@ from opendevin.events.observation import (
FileWriteObservation,
Observation,
)
from opendevin.events.stream import EventStream
from opendevin.runtime import Sandbox
from opendevin.runtime.server.files import insert_lines, read_lines
from opendevin.runtime.server.runtime import ServerRuntime
@ -17,9 +19,11 @@ from .sandbox import E2BSandbox
class E2BRuntime(ServerRuntime):
def __init__(
self,
event_stream: EventStream,
sid: str = 'default',
sandbox: Sandbox | None = None,
):
super().__init__()
super().__init__(event_stream, sid, sandbox)
if not isinstance(self.sandbox, E2BSandbox):
raise ValueError('E2BRuntime requires an E2BSandbox')
self.filesystem = self.sandbox.filesystem

View File

@ -1,3 +1,4 @@
import asyncio
from abc import abstractmethod
from opendevin.core.config import config
@ -12,12 +13,14 @@ from opendevin.events.action import (
FileWriteAction,
IPythonRunCellAction,
)
from opendevin.events.event import Event
from opendevin.events.observation import (
CmdOutputObservation,
ErrorObservation,
NullObservation,
Observation,
)
from opendevin.events.stream import EventSource, EventStream, EventStreamSubscriber
from opendevin.runtime import (
DockerExecBox,
DockerSSHBox,
@ -54,8 +57,9 @@ class Runtime:
def __init__(
self,
sandbox: Sandbox | None = None,
event_stream: EventStream,
sid: str = 'default',
sandbox: Sandbox | None = None,
):
self.sid = sid
if sandbox is None:
@ -63,10 +67,25 @@ class Runtime:
else:
self.sandbox = sandbox
self.browser = BrowserEnv()
self.event_stream = event_stream
self.event_stream.subscribe(EventStreamSubscriber.RUNTIME, self.on_event)
self._bg_task = asyncio.create_task(self._start_background_observation_loop())
def close(self):
self.sandbox.close()
self.browser.close()
self._bg_task.cancel()
def init_sandbox_plugins(self, plugins: list[PluginRequirement]) -> None:
self.sandbox.init_plugins(plugins)
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]
source = event.source if event.source else EventSource.AGENT
await self.event_stream.add_event(observation, source)
async def run_action(self, action: Action) -> Observation:
"""
Run an action and return the resulting observation.
@ -75,32 +94,38 @@ class Runtime:
"""
if not action.runnable:
return NullObservation('')
action_id = action.action # type: ignore[attr-defined]
if action_id not in ACTION_TYPE_TO_CLASS:
return ErrorObservation(f'Action {action_id} does not exist.')
if not hasattr(self, action_id):
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_id} is not supported in the current runtime.'
f'Action {action_type} is not supported in the current runtime.'
)
observation = await getattr(self, action_id)(action)
observation = await getattr(self, action_type)(action)
observation._parent = action.id # type: ignore[attr-defined]
return observation
def get_background_obs(self) -> list[CmdOutputObservation]:
async def _start_background_observation_loop(self):
while True:
await self.submit_background_obs()
await asyncio.sleep(1)
async def submit_background_obs(self):
"""
Returns all observations that have accumulated in the runtime's background.
Right now, this is just background commands, but could include e.g. asyncronous
events happening in the browser.
"""
obs = []
for _id, cmd in self.sandbox.background_commands.items():
output = cmd.read_logs()
if output is not None and output != '':
obs.append(
if output:
await self.event_stream.add_event(
CmdOutputObservation(
content=output, command_id=_id, command=cmd.command
)
),
EventSource.AGENT, # FIXME: use the original action's source
)
return obs
await asyncio.sleep(1)
@abstractmethod
async def run(self, action: CmdRunAction) -> Observation:

View File

@ -25,9 +25,9 @@ class ServerRuntime(Runtime):
return self._run_command(action.command, background=action.background)
async def kill(self, action: CmdKillAction) -> Observation:
cmd = self.sandbox.kill_background(action.id)
cmd = self.sandbox.kill_background(action.command_id)
return CmdOutputObservation(
content=f'Background command with id {action.id} has been killed.',
content=f'Background command with id {action.command_id} has been killed.',
command_id=action.id,
command=cmd.command,
exit_code=0,
@ -78,7 +78,7 @@ class ServerRuntime(Runtime):
def _run_background(self, command: str) -> Observation:
bg_cmd = self.sandbox.execute_in_background(command)
content = f'Background command started. To stop it, send a `kill` action with id {bg_cmd.pid}'
content = f'Background command started. To stop it, send a `kill` action with command_id {bg_cmd.pid}'
return CmdOutputObservation(
content=content,
command_id=bg_cmd.pid,

View File

@ -1,5 +1,6 @@
from typing import Optional
from agenthub.codeact_agent.codeact_agent import CodeActAgent
from opendevin.const.guide_url import TROUBLESHOOTING_URL
from opendevin.controller import AgentController
from opendevin.controller.agent import Agent
@ -17,6 +18,10 @@ from opendevin.events.observation import (
)
from opendevin.events.stream import EventSource, EventStream, EventStreamSubscriber
from opendevin.llm.llm import LLM
from opendevin.runtime import DockerSSHBox
from opendevin.runtime.e2b.runtime import E2BRuntime
from opendevin.runtime.runtime import Runtime
from opendevin.runtime.server.runtime import ServerRuntime
from opendevin.server.session import session_manager
@ -30,14 +35,19 @@ class AgentUnit:
sid: str
event_stream: EventStream
controller: Optional[AgentController] = None
# TODO: we will add the runtime here
# runtime: Optional[Runtime] = None
runtime: Optional[Runtime] = None
def __init__(self, sid):
"""Initializes a new instance of the Session class."""
self.sid = sid
self.event_stream = EventStream()
self.event_stream.subscribe(EventStreamSubscriber.SERVER, self.on_event)
if config.runtime == 'server':
logger.info('Using server runtime')
self.runtime = ServerRuntime(self.event_stream, sid)
elif config.runtime == 'e2b':
logger.info('Using E2B runtime')
self.runtime = E2BRuntime(self.event_stream, sid)
async def send_error(self, message):
"""Sends an error message to the client.
@ -101,13 +111,20 @@ class AgentUnit:
logger.info(f'Creating agent {agent_cls} using LLM {model}')
llm = LLM(model=model, api_key=api_key, base_url=api_base)
agent = Agent.get_cls(agent_cls)(llm)
if isinstance(agent, CodeActAgent):
if not self.runtime or not isinstance(self.runtime.sandbox, DockerSSHBox):
logger.warning(
'CodeActAgent requires DockerSSHBox as sandbox! Using other sandbox that are not stateful (LocalBox, DockerExecBox) will not work properly.'
)
if self.controller is not None:
await self.controller.close()
try:
self.controller = AgentController(
sid=self.sid,
event_stream=self.event_stream,
agent=Agent.get_cls(agent_cls)(llm),
agent=agent,
max_iterations=int(max_iterations),
max_chars=int(max_chars),
)
@ -131,9 +148,7 @@ class AgentUnit:
return
async def close(self):
"""Cleanly exits an AgentUnit.
Execution awaited by the AgentManager.
"""
if self.controller is not None:
await self.controller.close()
if self.runtime is not None:
self.runtime.close()

714
poetry.lock generated
View File

@ -335,17 +335,17 @@ files = [
[[package]]
name = "boto3"
version = "1.34.103"
version = "1.34.104"
description = "The AWS SDK for Python"
optional = false
python-versions = ">=3.8"
files = [
{file = "boto3-1.34.103-py3-none-any.whl", hash = "sha256:59b6499f1bb423dd99de6566a20d0a7cf1a5476824be3a792290fd86600e8365"},
{file = "boto3-1.34.103.tar.gz", hash = "sha256:58d097241f3895c4a4c80c9e606689c6e06d77f55f9f53a4cc02dee7e03938b9"},
{file = "boto3-1.34.104-py3-none-any.whl", hash = "sha256:bec91a3bca63320e5f68a25b5eaa7bab65e35bb9253a544875c2e03679f1d5fb"},
{file = "boto3-1.34.104.tar.gz", hash = "sha256:5b37c8f4ea6f408147994a6e230c49ca755da57f5964ccea8b8fd4ff5f11759e"},
]
[package.dependencies]
botocore = ">=1.34.103,<1.35.0"
botocore = ">=1.34.104,<1.35.0"
jmespath = ">=0.7.1,<2.0.0"
s3transfer = ">=0.10.0,<0.11.0"
@ -354,13 +354,13 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]
[[package]]
name = "botocore"
version = "1.34.103"
version = "1.34.104"
description = "Low-level, data-driven core of boto 3."
optional = false
python-versions = ">=3.8"
files = [
{file = "botocore-1.34.103-py3-none-any.whl", hash = "sha256:0330d139f18f78d38127e65361859e24ebd6a8bcba184f903c01bb999a3fa431"},
{file = "botocore-1.34.103.tar.gz", hash = "sha256:5f07e2c7302c0a9f469dcd08b4ddac152e9f5888b12220242c20056255010939"},
{file = "botocore-1.34.104-py3-none-any.whl", hash = "sha256:b68ed482e9b4c313129c9948af5a91d0e84840558e6d232a1a27ab0b9733e5b9"},
{file = "botocore-1.34.104.tar.gz", hash = "sha256:fe36dd3cea4160fbbe27dc1cf89cb7018234350555a26933b2977947052a346a"},
]
[package.dependencies]
@ -1539,15 +1539,78 @@ smb = ["smbprotocol"]
ssh = ["paramiko"]
tqdm = ["tqdm"]
[[package]]
name = "gevent"
version = "24.2.1"
description = "Coroutine-based network library"
optional = false
python-versions = ">=3.8"
files = [
{file = "gevent-24.2.1-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:6f947a9abc1a129858391b3d9334c45041c08a0f23d14333d5b844b6e5c17a07"},
{file = "gevent-24.2.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bde283313daf0b34a8d1bab30325f5cb0f4e11b5869dbe5bc61f8fe09a8f66f3"},
{file = "gevent-24.2.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5a1df555431f5cd5cc189a6ee3544d24f8c52f2529134685f1e878c4972ab026"},
{file = "gevent-24.2.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:14532a67f7cb29fb055a0e9b39f16b88ed22c66b96641df8c04bdc38c26b9ea5"},
{file = "gevent-24.2.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd23df885318391856415e20acfd51a985cba6919f0be78ed89f5db9ff3a31cb"},
{file = "gevent-24.2.1-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:ca80b121bbec76d7794fcb45e65a7eca660a76cc1a104ed439cdbd7df5f0b060"},
{file = "gevent-24.2.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:b9913c45d1be52d7a5db0c63977eebb51f68a2d5e6fd922d1d9b5e5fd758cc98"},
{file = "gevent-24.2.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:918cdf8751b24986f915d743225ad6b702f83e1106e08a63b736e3a4c6ead789"},
{file = "gevent-24.2.1-cp310-cp310-win_amd64.whl", hash = "sha256:3d5325ccfadfd3dcf72ff88a92fb8fc0b56cacc7225f0f4b6dcf186c1a6eeabc"},
{file = "gevent-24.2.1-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:03aa5879acd6b7076f6a2a307410fb1e0d288b84b03cdfd8c74db8b4bc882fc5"},
{file = "gevent-24.2.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f8bb35ce57a63c9a6896c71a285818a3922d8ca05d150fd1fe49a7f57287b836"},
{file = "gevent-24.2.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d7f87c2c02e03d99b95cfa6f7a776409083a9e4d468912e18c7680437b29222c"},
{file = "gevent-24.2.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:968581d1717bbcf170758580f5f97a2925854943c45a19be4d47299507db2eb7"},
{file = "gevent-24.2.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7899a38d0ae7e817e99adb217f586d0a4620e315e4de577444ebeeed2c5729be"},
{file = "gevent-24.2.1-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:f5e8e8d60e18d5f7fd49983f0c4696deeddaf6e608fbab33397671e2fcc6cc91"},
{file = "gevent-24.2.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:fbfdce91239fe306772faab57597186710d5699213f4df099d1612da7320d682"},
{file = "gevent-24.2.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:cdf66977a976d6a3cfb006afdf825d1482f84f7b81179db33941f2fc9673bb1d"},
{file = "gevent-24.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:1dffb395e500613e0452b9503153f8f7ba587c67dd4a85fc7cd7aa7430cb02cc"},
{file = "gevent-24.2.1-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:6c47ae7d1174617b3509f5d884935e788f325eb8f1a7efc95d295c68d83cce40"},
{file = "gevent-24.2.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f7cac622e11b4253ac4536a654fe221249065d9a69feb6cdcd4d9af3503602e0"},
{file = "gevent-24.2.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bf5b9c72b884c6f0c4ed26ef204ee1f768b9437330422492c319470954bc4cc7"},
{file = "gevent-24.2.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f5de3c676e57177b38857f6e3cdfbe8f38d1cd754b63200c0615eaa31f514b4f"},
{file = "gevent-24.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d4faf846ed132fd7ebfbbf4fde588a62d21faa0faa06e6f468b7faa6f436b661"},
{file = "gevent-24.2.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:368a277bd9278ddb0fde308e6a43f544222d76ed0c4166e0d9f6b036586819d9"},
{file = "gevent-24.2.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:f8a04cf0c5b7139bc6368b461257d4a757ea2fe89b3773e494d235b7dd51119f"},
{file = "gevent-24.2.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:9d8d0642c63d453179058abc4143e30718b19a85cbf58c2744c9a63f06a1d388"},
{file = "gevent-24.2.1-cp312-cp312-win_amd64.whl", hash = "sha256:94138682e68ec197db42ad7442d3cf9b328069c3ad8e4e5022e6b5cd3e7ffae5"},
{file = "gevent-24.2.1-cp38-cp38-macosx_11_0_universal2.whl", hash = "sha256:8f4b8e777d39013595a7740b4463e61b1cfe5f462f1b609b28fbc1e4c4ff01e5"},
{file = "gevent-24.2.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:141a2b24ad14f7b9576965c0c84927fc85f824a9bb19f6ec1e61e845d87c9cd8"},
{file = "gevent-24.2.1-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:9202f22ef811053077d01f43cc02b4aaf4472792f9fd0f5081b0b05c926cca19"},
{file = "gevent-24.2.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:2955eea9c44c842c626feebf4459c42ce168685aa99594e049d03bedf53c2800"},
{file = "gevent-24.2.1-cp38-cp38-win32.whl", hash = "sha256:44098038d5e2749b0784aabb27f1fcbb3f43edebedf64d0af0d26955611be8d6"},
{file = "gevent-24.2.1-cp38-cp38-win_amd64.whl", hash = "sha256:117e5837bc74a1673605fb53f8bfe22feb6e5afa411f524c835b2ddf768db0de"},
{file = "gevent-24.2.1-cp39-cp39-macosx_11_0_universal2.whl", hash = "sha256:2ae3a25ecce0a5b0cd0808ab716bfca180230112bb4bc89b46ae0061d62d4afe"},
{file = "gevent-24.2.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a7ceb59986456ce851160867ce4929edaffbd2f069ae25717150199f8e1548b8"},
{file = "gevent-24.2.1-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:2e9ac06f225b696cdedbb22f9e805e2dd87bf82e8fa5e17756f94e88a9d37cf7"},
{file = "gevent-24.2.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:90cbac1ec05b305a1b90ede61ef73126afdeb5a804ae04480d6da12c56378df1"},
{file = "gevent-24.2.1-cp39-cp39-win32.whl", hash = "sha256:782a771424fe74bc7e75c228a1da671578c2ba4ddb2ca09b8f959abdf787331e"},
{file = "gevent-24.2.1-cp39-cp39-win_amd64.whl", hash = "sha256:3adfb96637f44010be8abd1b5e73b5070f851b817a0b182e601202f20fa06533"},
{file = "gevent-24.2.1-pp310-pypy310_pp73-macosx_11_0_universal2.whl", hash = "sha256:7b00f8c9065de3ad226f7979154a7b27f3b9151c8055c162332369262fc025d8"},
{file = "gevent-24.2.1.tar.gz", hash = "sha256:432fc76f680acf7cf188c2ee0f5d3ab73b63c1f03114c7cd8a34cebbe5aa2056"},
]
[package.dependencies]
cffi = {version = ">=1.12.2", markers = "platform_python_implementation == \"CPython\" and sys_platform == \"win32\""}
greenlet = {version = ">=3.0rc3", markers = "platform_python_implementation == \"CPython\" and python_version >= \"3.11\""}
"zope.event" = "*"
"zope.interface" = "*"
[package.extras]
dnspython = ["dnspython (>=1.16.0,<2.0)", "idna"]
docs = ["furo", "repoze.sphinx.autointerface", "sphinx", "sphinxcontrib-programoutput", "zope.schema"]
monitor = ["psutil (>=5.7.0)"]
recommended = ["cffi (>=1.12.2)", "dnspython (>=1.16.0,<2.0)", "idna", "psutil (>=5.7.0)"]
test = ["cffi (>=1.12.2)", "coverage (>=5.0)", "dnspython (>=1.16.0,<2.0)", "idna", "objgraph", "psutil (>=5.7.0)", "requests"]
[[package]]
name = "google-ai-generativelanguage"
version = "0.6.2"
version = "0.6.3"
description = "Google Ai Generativelanguage API client library"
optional = false
python-versions = ">=3.7"
files = [
{file = "google-ai-generativelanguage-0.6.2.tar.gz", hash = "sha256:308791ac3b9dad015b359172970739aa3753dd542142a416d07f9fa047e22386"},
{file = "google_ai_generativelanguage-0.6.2-py3-none-any.whl", hash = "sha256:bf84c34c641570d7e8a1f2e6901e6771af1438f2ee8307d1801fd43585f9b1c6"},
{file = "google-ai-generativelanguage-0.6.3.tar.gz", hash = "sha256:10a11f1e1bb8470ff50030c1acd729b3aba7a29ade2c30cf1d1c917291366c67"},
{file = "google_ai_generativelanguage-0.6.3-py3-none-any.whl", hash = "sha256:55a6698f6c9cbbfde5f9cd288073b6941dd9e3e6dc2176dfa3197f9a4c489895"},
]
[package.dependencies]
@ -1639,16 +1702,16 @@ httplib2 = ">=0.19.0"
[[package]]
name = "google-generativeai"
version = "0.5.2"
version = "0.5.3"
description = "Google Generative AI High level API client library and tools."
optional = false
python-versions = ">=3.9"
files = [
{file = "google_generativeai-0.5.2-py3-none-any.whl", hash = "sha256:56f39485a0a673c93c21ec31c17809cc6a964193fb77b7ce809ad15d0dd72d7b"},
{file = "google_generativeai-0.5.3-py3-none-any.whl", hash = "sha256:a74509ee219601c74c0561eb4e1c9af6a88594c7dd098d30a18c6592afe62bd9"},
]
[package.dependencies]
google-ai-generativelanguage = "0.6.2"
google-ai-generativelanguage = "0.6.3"
google-api-core = "*"
google-api-python-client = "*"
google-auth = ">=2.15.0"
@ -2156,13 +2219,13 @@ files = [
[[package]]
name = "json-repair"
version = "0.19.0"
version = "0.19.1"
description = "A package to repair broken json strings"
optional = false
python-versions = ">=3.7"
files = [
{file = "json_repair-0.19.0-py3-none-any.whl", hash = "sha256:5f39beec06af677eaaf302b53477e26674b0b1f5136279742639c2dfe8253a07"},
{file = "json_repair-0.19.0.tar.gz", hash = "sha256:82b33db04ea849bde8382f94cc38f3ecb33a1d84303184847bda94c16f0ac44e"},
{file = "json_repair-0.19.1-py3-none-any.whl", hash = "sha256:ec9bf426481352390771f7814823e68975cbedcf8e09bfefdc8478e648692215"},
{file = "json_repair-0.19.1.tar.gz", hash = "sha256:b1de048af915044e5324c1d7a48cc2e083d9f3929ac453dc50972a0d47011c37"},
]
[[package]]
@ -2345,13 +2408,13 @@ types-tqdm = "*"
[[package]]
name = "litellm"
version = "1.37.5"
version = "1.37.9"
description = "Library to easily interface with LLM API providers"
optional = false
python-versions = "!=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,>=3.8"
files = [
{file = "litellm-1.37.5-py3-none-any.whl", hash = "sha256:a444dad4079d3d4c49037fe37581cd04b2135e674e9e9d1cfdbda32facd546ec"},
{file = "litellm-1.37.5.tar.gz", hash = "sha256:22d7292d2952d82992ebebc3b7dfa1a97393f603ce652f3223f2742123ba7f2b"},
{file = "litellm-1.37.9-py3-none-any.whl", hash = "sha256:f5e96df4e28e302a5df4e8f5599ac35ffbeebbacf4d68f4c609155e24ba8fa03"},
{file = "litellm-1.37.9.tar.gz", hash = "sha256:2a2fecacde1e3a414b3865c99e5be3b5cffd21433e2648f660116f1ac9333294"},
]
[package.dependencies]
@ -2367,7 +2430,7 @@ tokenizers = "*"
[package.extras]
extra-proxy = ["azure-identity (>=1.15.0,<2.0.0)", "azure-keyvault-secrets (>=4.8.0,<5.0.0)", "google-cloud-kms (>=2.21.3,<3.0.0)", "prisma (==0.11.0)", "resend (>=0.8.0,<0.9.0)"]
proxy = ["PyJWT (>=2.8.0,<3.0.0)", "apscheduler (>=3.10.4,<4.0.0)", "backoff", "cryptography (>=42.0.5,<43.0.0)", "fastapi (>=0.109.1,<0.110.0)", "fastapi-sso (>=0.10.0,<0.11.0)", "gunicorn (>=22.0.0,<23.0.0)", "orjson (>=3.9.7,<4.0.0)", "python-multipart (>=0.0.9,<0.0.10)", "pyyaml (>=6.0.1,<7.0.0)", "rq", "uvicorn (>=0.22.0,<0.23.0)"]
proxy = ["PyJWT (>=2.8.0,<3.0.0)", "apscheduler (>=3.10.4,<4.0.0)", "backoff", "cryptography (>=42.0.5,<43.0.0)", "fastapi (>=0.111.0,<0.112.0)", "fastapi-sso (>=0.10.0,<0.11.0)", "gunicorn (>=22.0.0,<23.0.0)", "orjson (>=3.9.7,<4.0.0)", "python-multipart (>=0.0.9,<0.0.10)", "pyyaml (>=6.0.1,<7.0.0)", "rq", "uvicorn (>=0.22.0,<0.23.0)"]
[[package]]
name = "llama-index"
@ -2603,13 +2666,13 @@ llama-index-llms-openai = ">=0.1.1,<0.2.0"
[[package]]
name = "llama-index-llms-openai"
version = "0.1.18"
version = "0.1.19"
description = "llama-index llms openai integration"
optional = false
python-versions = "<4.0,>=3.8.1"
files = [
{file = "llama_index_llms_openai-0.1.18-py3-none-any.whl", hash = "sha256:934cf72d10385f1c76c0183b0e94ce1850fab1026287e01b7db0a14c946dfd79"},
{file = "llama_index_llms_openai-0.1.18.tar.gz", hash = "sha256:8cb7546a1885ba558ff580b114d638569a0aed81a264961114e719bc42b37100"},
{file = "llama_index_llms_openai-0.1.19-py3-none-any.whl", hash = "sha256:2bd98ff3abbb4aa0daed1fbe01d8b69f8270ab86c53f8da51fc9f148a672264c"},
{file = "llama_index_llms_openai-0.1.19.tar.gz", hash = "sha256:f61b64a997892e424fb3cd547090d279c5b210ef15b614fc39de854d3ccaa7e7"},
]
[package.dependencies]
@ -2617,13 +2680,13 @@ llama-index-core = ">=0.10.24,<0.11.0"
[[package]]
name = "llama-index-multi-modal-llms-openai"
version = "0.1.5"
version = "0.1.6"
description = "llama-index multi-modal-llms openai integration"
optional = false
python-versions = "<4.0,>=3.8.1"
files = [
{file = "llama_index_multi_modal_llms_openai-0.1.5-py3-none-any.whl", hash = "sha256:bb332580e7e4b5f2f87488b3649d2ceb53ee82c848e59694578a982c3982ce0b"},
{file = "llama_index_multi_modal_llms_openai-0.1.5.tar.gz", hash = "sha256:9a237f4f886d1e20c27e9493e80b3e1f8753859481ff1b58fe25b7aa39b198a2"},
{file = "llama_index_multi_modal_llms_openai-0.1.6-py3-none-any.whl", hash = "sha256:0b6950a6cf98d16ade7d3b9dd0821ecfe457ca103819ae6c3e66cfc9634ca646"},
{file = "llama_index_multi_modal_llms_openai-0.1.6.tar.gz", hash = "sha256:10de75a877a444af35306385faad9b9f0624391e55309970564114a080a0578c"},
]
[package.dependencies]
@ -2743,166 +2806,149 @@ pydantic = ">=1.10"
[[package]]
name = "lxml"
version = "5.2.1"
version = "5.2.2"
description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API."
optional = false
python-versions = ">=3.6"
files = [
{file = "lxml-5.2.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:1f7785f4f789fdb522729ae465adcaa099e2a3441519df750ebdccc481d961a1"},
{file = "lxml-5.2.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:6cc6ee342fb7fa2471bd9b6d6fdfc78925a697bf5c2bcd0a302e98b0d35bfad3"},
{file = "lxml-5.2.1-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:794f04eec78f1d0e35d9e0c36cbbb22e42d370dda1609fb03bcd7aeb458c6377"},
{file = "lxml-5.2.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c817d420c60a5183953c783b0547d9eb43b7b344a2c46f69513d5952a78cddf3"},
{file = "lxml-5.2.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2213afee476546a7f37c7a9b4ad4d74b1e112a6fafffc9185d6d21f043128c81"},
{file = "lxml-5.2.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b070bbe8d3f0f6147689bed981d19bbb33070225373338df755a46893528104a"},
{file = "lxml-5.2.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e02c5175f63effbd7c5e590399c118d5db6183bbfe8e0d118bdb5c2d1b48d937"},
{file = "lxml-5.2.1-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:3dc773b2861b37b41a6136e0b72a1a44689a9c4c101e0cddb6b854016acc0aa8"},
{file = "lxml-5.2.1-cp310-cp310-manylinux_2_28_ppc64le.whl", hash = "sha256:d7520db34088c96cc0e0a3ad51a4fd5b401f279ee112aa2b7f8f976d8582606d"},
{file = "lxml-5.2.1-cp310-cp310-manylinux_2_28_s390x.whl", hash = "sha256:bcbf4af004f98793a95355980764b3d80d47117678118a44a80b721c9913436a"},
{file = "lxml-5.2.1-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:a2b44bec7adf3e9305ce6cbfa47a4395667e744097faed97abb4728748ba7d47"},
{file = "lxml-5.2.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:1c5bb205e9212d0ebddf946bc07e73fa245c864a5f90f341d11ce7b0b854475d"},
{file = "lxml-5.2.1-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:2c9d147f754b1b0e723e6afb7ba1566ecb162fe4ea657f53d2139bbf894d050a"},
{file = "lxml-5.2.1-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:3545039fa4779be2df51d6395e91a810f57122290864918b172d5dc7ca5bb433"},
{file = "lxml-5.2.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a91481dbcddf1736c98a80b122afa0f7296eeb80b72344d7f45dc9f781551f56"},
{file = "lxml-5.2.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:2ddfe41ddc81f29a4c44c8ce239eda5ade4e7fc305fb7311759dd6229a080052"},
{file = "lxml-5.2.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:a7baf9ffc238e4bf401299f50e971a45bfcc10a785522541a6e3179c83eabf0a"},
{file = "lxml-5.2.1-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:31e9a882013c2f6bd2f2c974241bf4ba68c85eba943648ce88936d23209a2e01"},
{file = "lxml-5.2.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:0a15438253b34e6362b2dc41475e7f80de76320f335e70c5528b7148cac253a1"},
{file = "lxml-5.2.1-cp310-cp310-win32.whl", hash = "sha256:6992030d43b916407c9aa52e9673612ff39a575523c5f4cf72cdef75365709a5"},
{file = "lxml-5.2.1-cp310-cp310-win_amd64.whl", hash = "sha256:da052e7962ea2d5e5ef5bc0355d55007407087392cf465b7ad84ce5f3e25fe0f"},
{file = "lxml-5.2.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:70ac664a48aa64e5e635ae5566f5227f2ab7f66a3990d67566d9907edcbbf867"},
{file = "lxml-5.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:1ae67b4e737cddc96c99461d2f75d218bdf7a0c3d3ad5604d1f5e7464a2f9ffe"},
{file = "lxml-5.2.1-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f18a5a84e16886898e51ab4b1d43acb3083c39b14c8caeb3589aabff0ee0b270"},
{file = "lxml-5.2.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c6f2c8372b98208ce609c9e1d707f6918cc118fea4e2c754c9f0812c04ca116d"},
{file = "lxml-5.2.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:394ed3924d7a01b5bd9a0d9d946136e1c2f7b3dc337196d99e61740ed4bc6fe1"},
{file = "lxml-5.2.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5d077bc40a1fe984e1a9931e801e42959a1e6598edc8a3223b061d30fbd26bbc"},
{file = "lxml-5.2.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:764b521b75701f60683500d8621841bec41a65eb739b8466000c6fdbc256c240"},
{file = "lxml-5.2.1-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:3a6b45da02336895da82b9d472cd274b22dc27a5cea1d4b793874eead23dd14f"},
{file = "lxml-5.2.1-cp311-cp311-manylinux_2_28_ppc64le.whl", hash = "sha256:5ea7b6766ac2dfe4bcac8b8595107665a18ef01f8c8343f00710b85096d1b53a"},
{file = "lxml-5.2.1-cp311-cp311-manylinux_2_28_s390x.whl", hash = "sha256:e196a4ff48310ba62e53a8e0f97ca2bca83cdd2fe2934d8b5cb0df0a841b193a"},
{file = "lxml-5.2.1-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:200e63525948e325d6a13a76ba2911f927ad399ef64f57898cf7c74e69b71095"},
{file = "lxml-5.2.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:dae0ed02f6b075426accbf6b2863c3d0a7eacc1b41fb40f2251d931e50188dad"},
{file = "lxml-5.2.1-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:ab31a88a651039a07a3ae327d68ebdd8bc589b16938c09ef3f32a4b809dc96ef"},
{file = "lxml-5.2.1-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:df2e6f546c4df14bc81f9498bbc007fbb87669f1bb707c6138878c46b06f6510"},
{file = "lxml-5.2.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:5dd1537e7cc06efd81371f5d1a992bd5ab156b2b4f88834ca852de4a8ea523fa"},
{file = "lxml-5.2.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:9b9ec9c9978b708d488bec36b9e4c94d88fd12ccac3e62134a9d17ddba910ea9"},
{file = "lxml-5.2.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:8e77c69d5892cb5ba71703c4057091e31ccf534bd7f129307a4d084d90d014b8"},
{file = "lxml-5.2.1-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:a8d5c70e04aac1eda5c829a26d1f75c6e5286c74743133d9f742cda8e53b9c2f"},
{file = "lxml-5.2.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:c94e75445b00319c1fad60f3c98b09cd63fe1134a8a953dcd48989ef42318534"},
{file = "lxml-5.2.1-cp311-cp311-win32.whl", hash = "sha256:4951e4f7a5680a2db62f7f4ab2f84617674d36d2d76a729b9a8be4b59b3659be"},
{file = "lxml-5.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:5c670c0406bdc845b474b680b9a5456c561c65cf366f8db5a60154088c92d102"},
{file = "lxml-5.2.1-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:abc25c3cab9ec7fcd299b9bcb3b8d4a1231877e425c650fa1c7576c5107ab851"},
{file = "lxml-5.2.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:6935bbf153f9a965f1e07c2649c0849d29832487c52bb4a5c5066031d8b44fd5"},
{file = "lxml-5.2.1-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d793bebb202a6000390a5390078e945bbb49855c29c7e4d56a85901326c3b5d9"},
{file = "lxml-5.2.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:afd5562927cdef7c4f5550374acbc117fd4ecc05b5007bdfa57cc5355864e0a4"},
{file = "lxml-5.2.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0e7259016bc4345a31af861fdce942b77c99049d6c2107ca07dc2bba2435c1d9"},
{file = "lxml-5.2.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:530e7c04f72002d2f334d5257c8a51bf409db0316feee7c87e4385043be136af"},
{file = "lxml-5.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:59689a75ba8d7ffca577aefd017d08d659d86ad4585ccc73e43edbfc7476781a"},
{file = "lxml-5.2.1-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:f9737bf36262046213a28e789cc82d82c6ef19c85a0cf05e75c670a33342ac2c"},
{file = "lxml-5.2.1-cp312-cp312-manylinux_2_28_ppc64le.whl", hash = "sha256:3a74c4f27167cb95c1d4af1c0b59e88b7f3e0182138db2501c353555f7ec57f4"},
{file = "lxml-5.2.1-cp312-cp312-manylinux_2_28_s390x.whl", hash = "sha256:68a2610dbe138fa8c5826b3f6d98a7cfc29707b850ddcc3e21910a6fe51f6ca0"},
{file = "lxml-5.2.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:f0a1bc63a465b6d72569a9bba9f2ef0334c4e03958e043da1920299100bc7c08"},
{file = "lxml-5.2.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:c2d35a1d047efd68027817b32ab1586c1169e60ca02c65d428ae815b593e65d4"},
{file = "lxml-5.2.1-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:79bd05260359170f78b181b59ce871673ed01ba048deef4bf49a36ab3e72e80b"},
{file = "lxml-5.2.1-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:865bad62df277c04beed9478fe665b9ef63eb28fe026d5dedcb89b537d2e2ea6"},
{file = "lxml-5.2.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:44f6c7caff88d988db017b9b0e4ab04934f11e3e72d478031efc7edcac6c622f"},
{file = "lxml-5.2.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:71e97313406ccf55d32cc98a533ee05c61e15d11b99215b237346171c179c0b0"},
{file = "lxml-5.2.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:057cdc6b86ab732cf361f8b4d8af87cf195a1f6dc5b0ff3de2dced242c2015e0"},
{file = "lxml-5.2.1-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:f3bbbc998d42f8e561f347e798b85513ba4da324c2b3f9b7969e9c45b10f6169"},
{file = "lxml-5.2.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:491755202eb21a5e350dae00c6d9a17247769c64dcf62d8c788b5c135e179dc4"},
{file = "lxml-5.2.1-cp312-cp312-win32.whl", hash = "sha256:8de8f9d6caa7f25b204fc861718815d41cbcf27ee8f028c89c882a0cf4ae4134"},
{file = "lxml-5.2.1-cp312-cp312-win_amd64.whl", hash = "sha256:f2a9efc53d5b714b8df2b4b3e992accf8ce5bbdfe544d74d5c6766c9e1146a3a"},
{file = "lxml-5.2.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:70a9768e1b9d79edca17890175ba915654ee1725975d69ab64813dd785a2bd5c"},
{file = "lxml-5.2.1-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c38d7b9a690b090de999835f0443d8aa93ce5f2064035dfc48f27f02b4afc3d0"},
{file = "lxml-5.2.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5670fb70a828663cc37552a2a85bf2ac38475572b0e9b91283dc09efb52c41d1"},
{file = "lxml-5.2.1-cp36-cp36m-manylinux_2_28_x86_64.whl", hash = "sha256:958244ad566c3ffc385f47dddde4145088a0ab893504b54b52c041987a8c1863"},
{file = "lxml-5.2.1-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:b6241d4eee5f89453307c2f2bfa03b50362052ca0af1efecf9fef9a41a22bb4f"},
{file = "lxml-5.2.1-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:2a66bf12fbd4666dd023b6f51223aed3d9f3b40fef06ce404cb75bafd3d89536"},
{file = "lxml-5.2.1-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:9123716666e25b7b71c4e1789ec829ed18663152008b58544d95b008ed9e21e9"},
{file = "lxml-5.2.1-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:0c3f67e2aeda739d1cc0b1102c9a9129f7dc83901226cc24dd72ba275ced4218"},
{file = "lxml-5.2.1-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:5d5792e9b3fb8d16a19f46aa8208987cfeafe082363ee2745ea8b643d9cc5b45"},
{file = "lxml-5.2.1-cp36-cp36m-musllinux_1_2_aarch64.whl", hash = "sha256:88e22fc0a6684337d25c994381ed8a1580a6f5ebebd5ad41f89f663ff4ec2885"},
{file = "lxml-5.2.1-cp36-cp36m-musllinux_1_2_ppc64le.whl", hash = "sha256:21c2e6b09565ba5b45ae161b438e033a86ad1736b8c838c766146eff8ceffff9"},
{file = "lxml-5.2.1-cp36-cp36m-musllinux_1_2_s390x.whl", hash = "sha256:afbbdb120d1e78d2ba8064a68058001b871154cc57787031b645c9142b937a62"},
{file = "lxml-5.2.1-cp36-cp36m-musllinux_1_2_x86_64.whl", hash = "sha256:627402ad8dea044dde2eccde4370560a2b750ef894c9578e1d4f8ffd54000461"},
{file = "lxml-5.2.1-cp36-cp36m-win32.whl", hash = "sha256:e89580a581bf478d8dcb97d9cd011d567768e8bc4095f8557b21c4d4c5fea7d0"},
{file = "lxml-5.2.1-cp36-cp36m-win_amd64.whl", hash = "sha256:59565f10607c244bc4c05c0c5fa0c190c990996e0c719d05deec7030c2aa8289"},
{file = "lxml-5.2.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:857500f88b17a6479202ff5fe5f580fc3404922cd02ab3716197adf1ef628029"},
{file = "lxml-5.2.1-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:56c22432809085b3f3ae04e6e7bdd36883d7258fcd90e53ba7b2e463efc7a6af"},
{file = "lxml-5.2.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a55ee573116ba208932e2d1a037cc4b10d2c1cb264ced2184d00b18ce585b2c0"},
{file = "lxml-5.2.1-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:6cf58416653c5901e12624e4013708b6e11142956e7f35e7a83f1ab02f3fe456"},
{file = "lxml-5.2.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:64c2baa7774bc22dd4474248ba16fe1a7f611c13ac6123408694d4cc93d66dbd"},
{file = "lxml-5.2.1-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:74b28c6334cca4dd704e8004cba1955af0b778cf449142e581e404bd211fb619"},
{file = "lxml-5.2.1-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:7221d49259aa1e5a8f00d3d28b1e0b76031655ca74bb287123ef56c3db92f213"},
{file = "lxml-5.2.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:3dbe858ee582cbb2c6294dc85f55b5f19c918c2597855e950f34b660f1a5ede6"},
{file = "lxml-5.2.1-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:04ab5415bf6c86e0518d57240a96c4d1fcfc3cb370bb2ac2a732b67f579e5a04"},
{file = "lxml-5.2.1-cp37-cp37m-musllinux_1_2_ppc64le.whl", hash = "sha256:6ab833e4735a7e5533711a6ea2df26459b96f9eec36d23f74cafe03631647c41"},
{file = "lxml-5.2.1-cp37-cp37m-musllinux_1_2_s390x.whl", hash = "sha256:f443cdef978430887ed55112b491f670bba6462cea7a7742ff8f14b7abb98d75"},
{file = "lxml-5.2.1-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:9e2addd2d1866fe112bc6f80117bcc6bc25191c5ed1bfbcf9f1386a884252ae8"},
{file = "lxml-5.2.1-cp37-cp37m-win32.whl", hash = "sha256:f51969bac61441fd31f028d7b3b45962f3ecebf691a510495e5d2cd8c8092dbd"},
{file = "lxml-5.2.1-cp37-cp37m-win_amd64.whl", hash = "sha256:b0b58fbfa1bf7367dde8a557994e3b1637294be6cf2169810375caf8571a085c"},
{file = "lxml-5.2.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:3e183c6e3298a2ed5af9d7a356ea823bccaab4ec2349dc9ed83999fd289d14d5"},
{file = "lxml-5.2.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:804f74efe22b6a227306dd890eecc4f8c59ff25ca35f1f14e7482bbce96ef10b"},
{file = "lxml-5.2.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:08802f0c56ed150cc6885ae0788a321b73505d2263ee56dad84d200cab11c07a"},
{file = "lxml-5.2.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0f8c09ed18ecb4ebf23e02b8e7a22a05d6411911e6fabef3a36e4f371f4f2585"},
{file = "lxml-5.2.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e3d30321949861404323c50aebeb1943461a67cd51d4200ab02babc58bd06a86"},
{file = "lxml-5.2.1-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:b560e3aa4b1d49e0e6c847d72665384db35b2f5d45f8e6a5c0072e0283430533"},
{file = "lxml-5.2.1-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:058a1308914f20784c9f4674036527e7c04f7be6fb60f5d61353545aa7fcb739"},
{file = "lxml-5.2.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:adfb84ca6b87e06bc6b146dc7da7623395db1e31621c4785ad0658c5028b37d7"},
{file = "lxml-5.2.1-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:417d14450f06d51f363e41cace6488519038f940676ce9664b34ebf5653433a5"},
{file = "lxml-5.2.1-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:a2dfe7e2473f9b59496247aad6e23b405ddf2e12ef0765677b0081c02d6c2c0b"},
{file = "lxml-5.2.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:bf2e2458345d9bffb0d9ec16557d8858c9c88d2d11fed53998512504cd9df49b"},
{file = "lxml-5.2.1-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:58278b29cb89f3e43ff3e0c756abbd1518f3ee6adad9e35b51fb101c1c1daaec"},
{file = "lxml-5.2.1-cp38-cp38-musllinux_1_2_ppc64le.whl", hash = "sha256:64641a6068a16201366476731301441ce93457eb8452056f570133a6ceb15fca"},
{file = "lxml-5.2.1-cp38-cp38-musllinux_1_2_s390x.whl", hash = "sha256:78bfa756eab503673991bdcf464917ef7845a964903d3302c5f68417ecdc948c"},
{file = "lxml-5.2.1-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:11a04306fcba10cd9637e669fd73aa274c1c09ca64af79c041aa820ea992b637"},
{file = "lxml-5.2.1-cp38-cp38-win32.whl", hash = "sha256:66bc5eb8a323ed9894f8fa0ee6cb3e3fb2403d99aee635078fd19a8bc7a5a5da"},
{file = "lxml-5.2.1-cp38-cp38-win_amd64.whl", hash = "sha256:9676bfc686fa6a3fa10cd4ae6b76cae8be26eb5ec6811d2a325636c460da1806"},
{file = "lxml-5.2.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:cf22b41fdae514ee2f1691b6c3cdeae666d8b7fa9434de445f12bbeee0cf48dd"},
{file = "lxml-5.2.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ec42088248c596dbd61d4ae8a5b004f97a4d91a9fd286f632e42e60b706718d7"},
{file = "lxml-5.2.1-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cd53553ddad4a9c2f1f022756ae64abe16da1feb497edf4d9f87f99ec7cf86bd"},
{file = "lxml-5.2.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:feaa45c0eae424d3e90d78823f3828e7dc42a42f21ed420db98da2c4ecf0a2cb"},
{file = "lxml-5.2.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ddc678fb4c7e30cf830a2b5a8d869538bc55b28d6c68544d09c7d0d8f17694dc"},
{file = "lxml-5.2.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:853e074d4931dbcba7480d4dcab23d5c56bd9607f92825ab80ee2bd916edea53"},
{file = "lxml-5.2.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc4691d60512798304acb9207987e7b2b7c44627ea88b9d77489bbe3e6cc3bd4"},
{file = "lxml-5.2.1-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:beb72935a941965c52990f3a32d7f07ce869fe21c6af8b34bf6a277b33a345d3"},
{file = "lxml-5.2.1-cp39-cp39-manylinux_2_28_ppc64le.whl", hash = "sha256:6588c459c5627fefa30139be4d2e28a2c2a1d0d1c265aad2ba1935a7863a4913"},
{file = "lxml-5.2.1-cp39-cp39-manylinux_2_28_s390x.whl", hash = "sha256:588008b8497667f1ddca7c99f2f85ce8511f8f7871b4a06ceede68ab62dff64b"},
{file = "lxml-5.2.1-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:b6787b643356111dfd4032b5bffe26d2f8331556ecb79e15dacb9275da02866e"},
{file = "lxml-5.2.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:7c17b64b0a6ef4e5affae6a3724010a7a66bda48a62cfe0674dabd46642e8b54"},
{file = "lxml-5.2.1-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:27aa20d45c2e0b8cd05da6d4759649170e8dfc4f4e5ef33a34d06f2d79075d57"},
{file = "lxml-5.2.1-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:d4f2cc7060dc3646632d7f15fe68e2fa98f58e35dd5666cd525f3b35d3fed7f8"},
{file = "lxml-5.2.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:ff46d772d5f6f73564979cd77a4fffe55c916a05f3cb70e7c9c0590059fb29ef"},
{file = "lxml-5.2.1-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:96323338e6c14e958d775700ec8a88346014a85e5de73ac7967db0367582049b"},
{file = "lxml-5.2.1-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:52421b41ac99e9d91934e4d0d0fe7da9f02bfa7536bb4431b4c05c906c8c6919"},
{file = "lxml-5.2.1-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:7a7efd5b6d3e30d81ec68ab8a88252d7c7c6f13aaa875009fe3097eb4e30b84c"},
{file = "lxml-5.2.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:0ed777c1e8c99b63037b91f9d73a6aad20fd035d77ac84afcc205225f8f41188"},
{file = "lxml-5.2.1-cp39-cp39-win32.whl", hash = "sha256:644df54d729ef810dcd0f7732e50e5ad1bd0a135278ed8d6bcb06f33b6b6f708"},
{file = "lxml-5.2.1-cp39-cp39-win_amd64.whl", hash = "sha256:9ca66b8e90daca431b7ca1408cae085d025326570e57749695d6a01454790e95"},
{file = "lxml-5.2.1-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:9b0ff53900566bc6325ecde9181d89afadc59c5ffa39bddf084aaedfe3b06a11"},
{file = "lxml-5.2.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fd6037392f2d57793ab98d9e26798f44b8b4da2f2464388588f48ac52c489ea1"},
{file = "lxml-5.2.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b9c07e7a45bb64e21df4b6aa623cb8ba214dfb47d2027d90eac197329bb5e94"},
{file = "lxml-5.2.1-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:3249cc2989d9090eeac5467e50e9ec2d40704fea9ab72f36b034ea34ee65ca98"},
{file = "lxml-5.2.1-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:f42038016852ae51b4088b2862126535cc4fc85802bfe30dea3500fdfaf1864e"},
{file = "lxml-5.2.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:533658f8fbf056b70e434dff7e7aa611bcacb33e01f75de7f821810e48d1bb66"},
{file = "lxml-5.2.1-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:622020d4521e22fb371e15f580d153134bfb68d6a429d1342a25f051ec72df1c"},
{file = "lxml-5.2.1-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:efa7b51824aa0ee957ccd5a741c73e6851de55f40d807f08069eb4c5a26b2baa"},
{file = "lxml-5.2.1-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9c6ad0fbf105f6bcc9300c00010a2ffa44ea6f555df1a2ad95c88f5656104817"},
{file = "lxml-5.2.1-pp37-pypy37_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:e233db59c8f76630c512ab4a4daf5a5986da5c3d5b44b8e9fc742f2a24dbd460"},
{file = "lxml-5.2.1-pp37-pypy37_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:6a014510830df1475176466b6087fc0c08b47a36714823e58d8b8d7709132a96"},
{file = "lxml-5.2.1-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:d38c8f50ecf57f0463399569aa388b232cf1a2ffb8f0a9a5412d0db57e054860"},
{file = "lxml-5.2.1-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:5aea8212fb823e006b995c4dda533edcf98a893d941f173f6c9506126188860d"},
{file = "lxml-5.2.1-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ff097ae562e637409b429a7ac958a20aab237a0378c42dabaa1e3abf2f896e5f"},
{file = "lxml-5.2.1-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0f5d65c39f16717a47c36c756af0fb36144069c4718824b7533f803ecdf91138"},
{file = "lxml-5.2.1-pp38-pypy38_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:3d0c3dd24bb4605439bf91068598d00c6370684f8de4a67c2992683f6c309d6b"},
{file = "lxml-5.2.1-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:e32be23d538753a8adb6c85bd539f5fd3b15cb987404327c569dfc5fd8366e85"},
{file = "lxml-5.2.1-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:cc518cea79fd1e2f6c90baafa28906d4309d24f3a63e801d855e7424c5b34144"},
{file = "lxml-5.2.1-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:a0af35bd8ebf84888373630f73f24e86bf016642fb8576fba49d3d6b560b7cbc"},
{file = "lxml-5.2.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f8aca2e3a72f37bfc7b14ba96d4056244001ddcc18382bd0daa087fd2e68a354"},
{file = "lxml-5.2.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5ca1e8188b26a819387b29c3895c47a5e618708fe6f787f3b1a471de2c4a94d9"},
{file = "lxml-5.2.1-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c8ba129e6d3b0136a0f50345b2cb3db53f6bda5dd8c7f5d83fbccba97fb5dcb5"},
{file = "lxml-5.2.1-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:e998e304036198b4f6914e6a1e2b6f925208a20e2042563d9734881150c6c246"},
{file = "lxml-5.2.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:d3be9b2076112e51b323bdf6d5a7f8a798de55fb8d95fcb64bd179460cdc0704"},
{file = "lxml-5.2.1.tar.gz", hash = "sha256:3f7765e69bbce0906a7c74d5fe46d2c7a7596147318dbc08e4a2431f3060e306"},
{file = "lxml-5.2.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:364d03207f3e603922d0d3932ef363d55bbf48e3647395765f9bfcbdf6d23632"},
{file = "lxml-5.2.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:50127c186f191b8917ea2fb8b206fbebe87fd414a6084d15568c27d0a21d60db"},
{file = "lxml-5.2.2-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:74e4f025ef3db1c6da4460dd27c118d8cd136d0391da4e387a15e48e5c975147"},
{file = "lxml-5.2.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:981a06a3076997adf7c743dcd0d7a0415582661e2517c7d961493572e909aa1d"},
{file = "lxml-5.2.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:aef5474d913d3b05e613906ba4090433c515e13ea49c837aca18bde190853dff"},
{file = "lxml-5.2.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1e275ea572389e41e8b039ac076a46cb87ee6b8542df3fff26f5baab43713bca"},
{file = "lxml-5.2.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f5b65529bb2f21ac7861a0e94fdbf5dc0daab41497d18223b46ee8515e5ad297"},
{file = "lxml-5.2.2-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:bcc98f911f10278d1daf14b87d65325851a1d29153caaf146877ec37031d5f36"},
{file = "lxml-5.2.2-cp310-cp310-manylinux_2_28_ppc64le.whl", hash = "sha256:b47633251727c8fe279f34025844b3b3a3e40cd1b198356d003aa146258d13a2"},
{file = "lxml-5.2.2-cp310-cp310-manylinux_2_28_s390x.whl", hash = "sha256:fbc9d316552f9ef7bba39f4edfad4a734d3d6f93341232a9dddadec4f15d425f"},
{file = "lxml-5.2.2-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:13e69be35391ce72712184f69000cda04fc89689429179bc4c0ae5f0b7a8c21b"},
{file = "lxml-5.2.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:3b6a30a9ab040b3f545b697cb3adbf3696c05a3a68aad172e3fd7ca73ab3c835"},
{file = "lxml-5.2.2-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:a233bb68625a85126ac9f1fc66d24337d6e8a0f9207b688eec2e7c880f012ec0"},
{file = "lxml-5.2.2-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:dfa7c241073d8f2b8e8dbc7803c434f57dbb83ae2a3d7892dd068d99e96efe2c"},
{file = "lxml-5.2.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:1a7aca7964ac4bb07680d5c9d63b9d7028cace3e2d43175cb50bba8c5ad33316"},
{file = "lxml-5.2.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:ae4073a60ab98529ab8a72ebf429f2a8cc612619a8c04e08bed27450d52103c0"},
{file = "lxml-5.2.2-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:ffb2be176fed4457e445fe540617f0252a72a8bc56208fd65a690fdb1f57660b"},
{file = "lxml-5.2.2-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:e290d79a4107d7d794634ce3e985b9ae4f920380a813717adf61804904dc4393"},
{file = "lxml-5.2.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:96e85aa09274955bb6bd483eaf5b12abadade01010478154b0ec70284c1b1526"},
{file = "lxml-5.2.2-cp310-cp310-win32.whl", hash = "sha256:f956196ef61369f1685d14dad80611488d8dc1ef00be57c0c5a03064005b0f30"},
{file = "lxml-5.2.2-cp310-cp310-win_amd64.whl", hash = "sha256:875a3f90d7eb5c5d77e529080d95140eacb3c6d13ad5b616ee8095447b1d22e7"},
{file = "lxml-5.2.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:45f9494613160d0405682f9eee781c7e6d1bf45f819654eb249f8f46a2c22545"},
{file = "lxml-5.2.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b0b3f2df149efb242cee2ffdeb6674b7f30d23c9a7af26595099afaf46ef4e88"},
{file = "lxml-5.2.2-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d28cb356f119a437cc58a13f8135ab8a4c8ece18159eb9194b0d269ec4e28083"},
{file = "lxml-5.2.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:657a972f46bbefdbba2d4f14413c0d079f9ae243bd68193cb5061b9732fa54c1"},
{file = "lxml-5.2.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b74b9ea10063efb77a965a8d5f4182806fbf59ed068b3c3fd6f30d2ac7bee734"},
{file = "lxml-5.2.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:07542787f86112d46d07d4f3c4e7c760282011b354d012dc4141cc12a68cef5f"},
{file = "lxml-5.2.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:303f540ad2dddd35b92415b74b900c749ec2010e703ab3bfd6660979d01fd4ed"},
{file = "lxml-5.2.2-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:2eb2227ce1ff998faf0cd7fe85bbf086aa41dfc5af3b1d80867ecfe75fb68df3"},
{file = "lxml-5.2.2-cp311-cp311-manylinux_2_28_ppc64le.whl", hash = "sha256:1d8a701774dfc42a2f0b8ccdfe7dbc140500d1049e0632a611985d943fcf12df"},
{file = "lxml-5.2.2-cp311-cp311-manylinux_2_28_s390x.whl", hash = "sha256:56793b7a1a091a7c286b5f4aa1fe4ae5d1446fe742d00cdf2ffb1077865db10d"},
{file = "lxml-5.2.2-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:eb00b549b13bd6d884c863554566095bf6fa9c3cecb2e7b399c4bc7904cb33b5"},
{file = "lxml-5.2.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:1a2569a1f15ae6c8c64108a2cd2b4a858fc1e13d25846be0666fc144715e32ab"},
{file = "lxml-5.2.2-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:8cf85a6e40ff1f37fe0f25719aadf443686b1ac7652593dc53c7ef9b8492b115"},
{file = "lxml-5.2.2-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:d237ba6664b8e60fd90b8549a149a74fcc675272e0e95539a00522e4ca688b04"},
{file = "lxml-5.2.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:0b3f5016e00ae7630a4b83d0868fca1e3d494c78a75b1c7252606a3a1c5fc2ad"},
{file = "lxml-5.2.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:23441e2b5339bc54dc949e9e675fa35efe858108404ef9aa92f0456929ef6fe8"},
{file = "lxml-5.2.2-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:2fb0ba3e8566548d6c8e7dd82a8229ff47bd8fb8c2da237607ac8e5a1b8312e5"},
{file = "lxml-5.2.2-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:79d1fb9252e7e2cfe4de6e9a6610c7cbb99b9708e2c3e29057f487de5a9eaefa"},
{file = "lxml-5.2.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:6dcc3d17eac1df7859ae01202e9bb11ffa8c98949dcbeb1069c8b9a75917e01b"},
{file = "lxml-5.2.2-cp311-cp311-win32.whl", hash = "sha256:4c30a2f83677876465f44c018830f608fa3c6a8a466eb223535035fbc16f3438"},
{file = "lxml-5.2.2-cp311-cp311-win_amd64.whl", hash = "sha256:49095a38eb333aaf44c06052fd2ec3b8f23e19747ca7ec6f6c954ffea6dbf7be"},
{file = "lxml-5.2.2-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:7429e7faa1a60cad26ae4227f4dd0459efde239e494c7312624ce228e04f6391"},
{file = "lxml-5.2.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:50ccb5d355961c0f12f6cf24b7187dbabd5433f29e15147a67995474f27d1776"},
{file = "lxml-5.2.2-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:dc911208b18842a3a57266d8e51fc3cfaccee90a5351b92079beed912a7914c2"},
{file = "lxml-5.2.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:33ce9e786753743159799fdf8e92a5da351158c4bfb6f2db0bf31e7892a1feb5"},
{file = "lxml-5.2.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ec87c44f619380878bd49ca109669c9f221d9ae6883a5bcb3616785fa8f94c97"},
{file = "lxml-5.2.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:08ea0f606808354eb8f2dfaac095963cb25d9d28e27edcc375d7b30ab01abbf6"},
{file = "lxml-5.2.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75a9632f1d4f698b2e6e2e1ada40e71f369b15d69baddb8968dcc8e683839b18"},
{file = "lxml-5.2.2-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:74da9f97daec6928567b48c90ea2c82a106b2d500f397eeb8941e47d30b1ca85"},
{file = "lxml-5.2.2-cp312-cp312-manylinux_2_28_ppc64le.whl", hash = "sha256:0969e92af09c5687d769731e3f39ed62427cc72176cebb54b7a9d52cc4fa3b73"},
{file = "lxml-5.2.2-cp312-cp312-manylinux_2_28_s390x.whl", hash = "sha256:9164361769b6ca7769079f4d426a41df6164879f7f3568be9086e15baca61466"},
{file = "lxml-5.2.2-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:d26a618ae1766279f2660aca0081b2220aca6bd1aa06b2cf73f07383faf48927"},
{file = "lxml-5.2.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:ab67ed772c584b7ef2379797bf14b82df9aa5f7438c5b9a09624dd834c1c1aaf"},
{file = "lxml-5.2.2-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:3d1e35572a56941b32c239774d7e9ad724074d37f90c7a7d499ab98761bd80cf"},
{file = "lxml-5.2.2-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:8268cbcd48c5375f46e000adb1390572c98879eb4f77910c6053d25cc3ac2c67"},
{file = "lxml-5.2.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e282aedd63c639c07c3857097fc0e236f984ceb4089a8b284da1c526491e3f3d"},
{file = "lxml-5.2.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6dfdc2bfe69e9adf0df4915949c22a25b39d175d599bf98e7ddf620a13678585"},
{file = "lxml-5.2.2-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:4aefd911793b5d2d7a921233a54c90329bf3d4a6817dc465f12ffdfe4fc7b8fe"},
{file = "lxml-5.2.2-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:8b8df03a9e995b6211dafa63b32f9d405881518ff1ddd775db4e7b98fb545e1c"},
{file = "lxml-5.2.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:f11ae142f3a322d44513de1018b50f474f8f736bc3cd91d969f464b5bfef8836"},
{file = "lxml-5.2.2-cp312-cp312-win32.whl", hash = "sha256:16a8326e51fcdffc886294c1e70b11ddccec836516a343f9ed0f82aac043c24a"},
{file = "lxml-5.2.2-cp312-cp312-win_amd64.whl", hash = "sha256:bbc4b80af581e18568ff07f6395c02114d05f4865c2812a1f02f2eaecf0bfd48"},
{file = "lxml-5.2.2-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:e3d9d13603410b72787579769469af730c38f2f25505573a5888a94b62b920f8"},
{file = "lxml-5.2.2-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:38b67afb0a06b8575948641c1d6d68e41b83a3abeae2ca9eed2ac59892b36706"},
{file = "lxml-5.2.2-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c689d0d5381f56de7bd6966a4541bff6e08bf8d3871bbd89a0c6ab18aa699573"},
{file = "lxml-5.2.2-cp36-cp36m-manylinux_2_28_x86_64.whl", hash = "sha256:cf2a978c795b54c539f47964ec05e35c05bd045db5ca1e8366988c7f2fe6b3ce"},
{file = "lxml-5.2.2-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:739e36ef7412b2bd940f75b278749106e6d025e40027c0b94a17ef7968d55d56"},
{file = "lxml-5.2.2-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:d8bbcd21769594dbba9c37d3c819e2d5847656ca99c747ddb31ac1701d0c0ed9"},
{file = "lxml-5.2.2-cp36-cp36m-musllinux_1_2_x86_64.whl", hash = "sha256:2304d3c93f2258ccf2cf7a6ba8c761d76ef84948d87bf9664e14d203da2cd264"},
{file = "lxml-5.2.2-cp36-cp36m-win32.whl", hash = "sha256:02437fb7308386867c8b7b0e5bc4cd4b04548b1c5d089ffb8e7b31009b961dc3"},
{file = "lxml-5.2.2-cp36-cp36m-win_amd64.whl", hash = "sha256:edcfa83e03370032a489430215c1e7783128808fd3e2e0a3225deee278585196"},
{file = "lxml-5.2.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:28bf95177400066596cdbcfc933312493799382879da504633d16cf60bba735b"},
{file = "lxml-5.2.2-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3a745cc98d504d5bd2c19b10c79c61c7c3df9222629f1b6210c0368177589fb8"},
{file = "lxml-5.2.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b336b0416828022bfd5a2e3083e7f5ba54b96242159f83c7e3eebaec752f1716"},
{file = "lxml-5.2.2-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:4bc6cb140a7a0ad1f7bc37e018d0ed690b7b6520ade518285dc3171f7a117905"},
{file = "lxml-5.2.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:57f0a0bbc9868e10ebe874e9f129d2917750adf008fe7b9c1598c0fbbfdde6a6"},
{file = "lxml-5.2.2-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:60499fe961b21264e17a471ec296dcbf4365fbea611bf9e303ab69db7159ce61"},
{file = "lxml-5.2.2-cp37-cp37m-win32.whl", hash = "sha256:d9b342c76003c6b9336a80efcc766748a333573abf9350f4094ee46b006ec18f"},
{file = "lxml-5.2.2-cp37-cp37m-win_amd64.whl", hash = "sha256:b16db2770517b8799c79aa80f4053cd6f8b716f21f8aca962725a9565ce3ee40"},
{file = "lxml-5.2.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7ed07b3062b055d7a7f9d6557a251cc655eed0b3152b76de619516621c56f5d3"},
{file = "lxml-5.2.2-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f60fdd125d85bf9c279ffb8e94c78c51b3b6a37711464e1f5f31078b45002421"},
{file = "lxml-5.2.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8a7e24cb69ee5f32e003f50e016d5fde438010c1022c96738b04fc2423e61706"},
{file = "lxml-5.2.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:23cfafd56887eaed93d07bc4547abd5e09d837a002b791e9767765492a75883f"},
{file = "lxml-5.2.2-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:19b4e485cd07b7d83e3fe3b72132e7df70bfac22b14fe4bf7a23822c3a35bff5"},
{file = "lxml-5.2.2-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:7ce7ad8abebe737ad6143d9d3bf94b88b93365ea30a5b81f6877ec9c0dee0a48"},
{file = "lxml-5.2.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:e49b052b768bb74f58c7dda4e0bdf7b79d43a9204ca584ffe1fb48a6f3c84c66"},
{file = "lxml-5.2.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:d14a0d029a4e176795cef99c056d58067c06195e0c7e2dbb293bf95c08f772a3"},
{file = "lxml-5.2.2-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:be49ad33819d7dcc28a309b86d4ed98e1a65f3075c6acd3cd4fe32103235222b"},
{file = "lxml-5.2.2-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:a6d17e0370d2516d5bb9062c7b4cb731cff921fc875644c3d751ad857ba9c5b1"},
{file = "lxml-5.2.2-cp38-cp38-win32.whl", hash = "sha256:5b8c041b6265e08eac8a724b74b655404070b636a8dd6d7a13c3adc07882ef30"},
{file = "lxml-5.2.2-cp38-cp38-win_amd64.whl", hash = "sha256:f61efaf4bed1cc0860e567d2ecb2363974d414f7f1f124b1df368bbf183453a6"},
{file = "lxml-5.2.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:fb91819461b1b56d06fa4bcf86617fac795f6a99d12239fb0c68dbeba41a0a30"},
{file = "lxml-5.2.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d4ed0c7cbecde7194cd3228c044e86bf73e30a23505af852857c09c24e77ec5d"},
{file = "lxml-5.2.2-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:54401c77a63cc7d6dc4b4e173bb484f28a5607f3df71484709fe037c92d4f0ed"},
{file = "lxml-5.2.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:625e3ef310e7fa3a761d48ca7ea1f9d8718a32b1542e727d584d82f4453d5eeb"},
{file = "lxml-5.2.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:519895c99c815a1a24a926d5b60627ce5ea48e9f639a5cd328bda0515ea0f10c"},
{file = "lxml-5.2.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c7079d5eb1c1315a858bbf180000757db8ad904a89476653232db835c3114001"},
{file = "lxml-5.2.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:343ab62e9ca78094f2306aefed67dcfad61c4683f87eee48ff2fd74902447726"},
{file = "lxml-5.2.2-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:cd9e78285da6c9ba2d5c769628f43ef66d96ac3085e59b10ad4f3707980710d3"},
{file = "lxml-5.2.2-cp39-cp39-manylinux_2_28_ppc64le.whl", hash = "sha256:546cf886f6242dff9ec206331209db9c8e1643ae642dea5fdbecae2453cb50fd"},
{file = "lxml-5.2.2-cp39-cp39-manylinux_2_28_s390x.whl", hash = "sha256:02f6a8eb6512fdc2fd4ca10a49c341c4e109aa6e9448cc4859af5b949622715a"},
{file = "lxml-5.2.2-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:339ee4a4704bc724757cd5dd9dc8cf4d00980f5d3e6e06d5847c1b594ace68ab"},
{file = "lxml-5.2.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:0a028b61a2e357ace98b1615fc03f76eb517cc028993964fe08ad514b1e8892d"},
{file = "lxml-5.2.2-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:f90e552ecbad426eab352e7b2933091f2be77115bb16f09f78404861c8322981"},
{file = "lxml-5.2.2-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:d83e2d94b69bf31ead2fa45f0acdef0757fa0458a129734f59f67f3d2eb7ef32"},
{file = "lxml-5.2.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:a02d3c48f9bb1e10c7788d92c0c7db6f2002d024ab6e74d6f45ae33e3d0288a3"},
{file = "lxml-5.2.2-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:6d68ce8e7b2075390e8ac1e1d3a99e8b6372c694bbe612632606d1d546794207"},
{file = "lxml-5.2.2-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:453d037e09a5176d92ec0fd282e934ed26d806331a8b70ab431a81e2fbabf56d"},
{file = "lxml-5.2.2-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:3b019d4ee84b683342af793b56bb35034bd749e4cbdd3d33f7d1107790f8c472"},
{file = "lxml-5.2.2-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:cb3942960f0beb9f46e2a71a3aca220d1ca32feb5a398656be934320804c0df9"},
{file = "lxml-5.2.2-cp39-cp39-win32.whl", hash = "sha256:ac6540c9fff6e3813d29d0403ee7a81897f1d8ecc09a8ff84d2eea70ede1cdbf"},
{file = "lxml-5.2.2-cp39-cp39-win_amd64.whl", hash = "sha256:610b5c77428a50269f38a534057444c249976433f40f53e3b47e68349cca1425"},
{file = "lxml-5.2.2-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:b537bd04d7ccd7c6350cdaaaad911f6312cbd61e6e6045542f781c7f8b2e99d2"},
{file = "lxml-5.2.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4820c02195d6dfb7b8508ff276752f6b2ff8b64ae5d13ebe02e7667e035000b9"},
{file = "lxml-5.2.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f2a09f6184f17a80897172863a655467da2b11151ec98ba8d7af89f17bf63dae"},
{file = "lxml-5.2.2-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:76acba4c66c47d27c8365e7c10b3d8016a7da83d3191d053a58382311a8bf4e1"},
{file = "lxml-5.2.2-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:b128092c927eaf485928cec0c28f6b8bead277e28acf56800e972aa2c2abd7a2"},
{file = "lxml-5.2.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:ae791f6bd43305aade8c0e22f816b34f3b72b6c820477aab4d18473a37e8090b"},
{file = "lxml-5.2.2-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:a2f6a1bc2460e643785a2cde17293bd7a8f990884b822f7bca47bee0a82fc66b"},
{file = "lxml-5.2.2-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8e8d351ff44c1638cb6e980623d517abd9f580d2e53bfcd18d8941c052a5a009"},
{file = "lxml-5.2.2-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bec4bd9133420c5c52d562469c754f27c5c9e36ee06abc169612c959bd7dbb07"},
{file = "lxml-5.2.2-pp37-pypy37_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:55ce6b6d803890bd3cc89975fca9de1dff39729b43b73cb15ddd933b8bc20484"},
{file = "lxml-5.2.2-pp37-pypy37_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:8ab6a358d1286498d80fe67bd3d69fcbc7d1359b45b41e74c4a26964ca99c3f8"},
{file = "lxml-5.2.2-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:06668e39e1f3c065349c51ac27ae430719d7806c026fec462e5693b08b95696b"},
{file = "lxml-5.2.2-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:9cd5323344d8ebb9fb5e96da5de5ad4ebab993bbf51674259dbe9d7a18049525"},
{file = "lxml-5.2.2-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:89feb82ca055af0fe797a2323ec9043b26bc371365847dbe83c7fd2e2f181c34"},
{file = "lxml-5.2.2-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e481bba1e11ba585fb06db666bfc23dbe181dbafc7b25776156120bf12e0d5a6"},
{file = "lxml-5.2.2-pp38-pypy38_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:9d6c6ea6a11ca0ff9cd0390b885984ed31157c168565702959c25e2191674a14"},
{file = "lxml-5.2.2-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:3d98de734abee23e61f6b8c2e08a88453ada7d6486dc7cdc82922a03968928db"},
{file = "lxml-5.2.2-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:69ab77a1373f1e7563e0fb5a29a8440367dec051da6c7405333699d07444f511"},
{file = "lxml-5.2.2-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:34e17913c431f5ae01d8658dbf792fdc457073dcdfbb31dc0cc6ab256e664a8d"},
{file = "lxml-5.2.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:05f8757b03208c3f50097761be2dea0aba02e94f0dc7023ed73a7bb14ff11eb0"},
{file = "lxml-5.2.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6a520b4f9974b0a0a6ed73c2154de57cdfd0c8800f4f15ab2b73238ffed0b36e"},
{file = "lxml-5.2.2-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:5e097646944b66207023bc3c634827de858aebc226d5d4d6d16f0b77566ea182"},
{file = "lxml-5.2.2-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:b5e4ef22ff25bfd4ede5f8fb30f7b24446345f3e79d9b7455aef2836437bc38a"},
{file = "lxml-5.2.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:ff69a9a0b4b17d78170c73abe2ab12084bdf1691550c5629ad1fe7849433f324"},
{file = "lxml-5.2.2.tar.gz", hash = "sha256:bb2dc4898180bea79863d5487e5f9c7c34297414bad54bcd0f0852aee9cfdb87"},
]
[package.extras]
@ -3752,13 +3798,13 @@ sympy = "*"
[[package]]
name = "openai"
version = "1.28.1"
version = "1.29.0"
description = "The official Python library for the openai API"
optional = false
python-versions = ">=3.7.1"
files = [
{file = "openai-1.28.1-py3-none-any.whl", hash = "sha256:943e0d0d587b9a62f99bd3acbaf479ae5362986e5fff013f57b5b7bde85cce93"},
{file = "openai-1.28.1.tar.gz", hash = "sha256:8a3adbba16882434768d76fd3129fcc9b40ace98f8d55a6ddacfc05c4096ac30"},
{file = "openai-1.29.0-py3-none-any.whl", hash = "sha256:c61cd12376c84362d406341f9e2f9a9d6b81c082b133b44484dc0f43954496b1"},
{file = "openai-1.29.0.tar.gz", hash = "sha256:d5a769f485610cff8bae14343fa45a8b1d346be3d541fa5b28ccd040dbc8baf8"},
]
[package.dependencies]
@ -5555,47 +5601,47 @@ files = [
[[package]]
name = "tiktoken"
version = "0.6.0"
version = "0.7.0"
description = "tiktoken is a fast BPE tokeniser for use with OpenAI's models"
optional = false
python-versions = ">=3.8"
files = [
{file = "tiktoken-0.6.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:277de84ccd8fa12730a6b4067456e5cf72fef6300bea61d506c09e45658d41ac"},
{file = "tiktoken-0.6.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9c44433f658064463650d61387623735641dcc4b6c999ca30bc0f8ba3fccaf5c"},
{file = "tiktoken-0.6.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:afb9a2a866ae6eef1995ab656744287a5ac95acc7e0491c33fad54d053288ad3"},
{file = "tiktoken-0.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c62c05b3109fefca26fedb2820452a050074ad8e5ad9803f4652977778177d9f"},
{file = "tiktoken-0.6.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:0ef917fad0bccda07bfbad835525bbed5f3ab97a8a3e66526e48cdc3e7beacf7"},
{file = "tiktoken-0.6.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:e095131ab6092d0769a2fda85aa260c7c383072daec599ba9d8b149d2a3f4d8b"},
{file = "tiktoken-0.6.0-cp310-cp310-win_amd64.whl", hash = "sha256:05b344c61779f815038292a19a0c6eb7098b63c8f865ff205abb9ea1b656030e"},
{file = "tiktoken-0.6.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cefb9870fb55dca9e450e54dbf61f904aab9180ff6fe568b61f4db9564e78871"},
{file = "tiktoken-0.6.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:702950d33d8cabc039845674107d2e6dcabbbb0990ef350f640661368df481bb"},
{file = "tiktoken-0.6.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e8d49d076058f23254f2aff9af603863c5c5f9ab095bc896bceed04f8f0b013a"},
{file = "tiktoken-0.6.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:430bc4e650a2d23a789dc2cdca3b9e5e7eb3cd3935168d97d43518cbb1f9a911"},
{file = "tiktoken-0.6.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:293cb8669757301a3019a12d6770bd55bec38a4d3ee9978ddbe599d68976aca7"},
{file = "tiktoken-0.6.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:7bd1a288b7903aadc054b0e16ea78e3171f70b670e7372432298c686ebf9dd47"},
{file = "tiktoken-0.6.0-cp311-cp311-win_amd64.whl", hash = "sha256:ac76e000183e3b749634968a45c7169b351e99936ef46f0d2353cd0d46c3118d"},
{file = "tiktoken-0.6.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:17cc8a4a3245ab7d935c83a2db6bb71619099d7284b884f4b2aea4c74f2f83e3"},
{file = "tiktoken-0.6.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:284aebcccffe1bba0d6571651317df6a5b376ff6cfed5aeb800c55df44c78177"},
{file = "tiktoken-0.6.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0c1a3a5d33846f8cd9dd3b7897c1d45722f48625a587f8e6f3d3e85080559be8"},
{file = "tiktoken-0.6.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6318b2bb2337f38ee954fd5efa82632c6e5ced1d52a671370fa4b2eff1355e91"},
{file = "tiktoken-0.6.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:1f5f0f2ed67ba16373f9a6013b68da298096b27cd4e1cf276d2d3868b5c7efd1"},
{file = "tiktoken-0.6.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:75af4c0b16609c2ad02581f3cdcd1fb698c7565091370bf6c0cf8624ffaba6dc"},
{file = "tiktoken-0.6.0-cp312-cp312-win_amd64.whl", hash = "sha256:45577faf9a9d383b8fd683e313cf6df88b6076c034f0a16da243bb1c139340c3"},
{file = "tiktoken-0.6.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7c1492ab90c21ca4d11cef3a236ee31a3e279bb21b3fc5b0e2210588c4209e68"},
{file = "tiktoken-0.6.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:e2b380c5b7751272015400b26144a2bab4066ebb8daae9c3cd2a92c3b508fe5a"},
{file = "tiktoken-0.6.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c9f497598b9f58c99cbc0eb764b4a92272c14d5203fc713dd650b896a03a50ad"},
{file = "tiktoken-0.6.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e65e8bd6f3f279d80f1e1fbd5f588f036b9a5fa27690b7f0cc07021f1dfa0839"},
{file = "tiktoken-0.6.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:5f1495450a54e564d236769d25bfefbf77727e232d7a8a378f97acddee08c1ae"},
{file = "tiktoken-0.6.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:6c4e4857d99f6fb4670e928250835b21b68c59250520a1941618b5b4194e20c3"},
{file = "tiktoken-0.6.0-cp38-cp38-win_amd64.whl", hash = "sha256:168d718f07a39b013032741867e789971346df8e89983fe3c0ef3fbd5a0b1cb9"},
{file = "tiktoken-0.6.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:47fdcfe11bd55376785a6aea8ad1db967db7f66ea81aed5c43fad497521819a4"},
{file = "tiktoken-0.6.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:fb7d2ccbf1a7784810aff6b80b4012fb42c6fc37eaa68cb3b553801a5cc2d1fc"},
{file = "tiktoken-0.6.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1ccb7a111ee76af5d876a729a347f8747d5ad548e1487eeea90eaf58894b3138"},
{file = "tiktoken-0.6.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b2048e1086b48e3c8c6e2ceeac866561374cd57a84622fa49a6b245ffecb7744"},
{file = "tiktoken-0.6.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:07f229a5eb250b6403a61200199cecf0aac4aa23c3ecc1c11c1ca002cbb8f159"},
{file = "tiktoken-0.6.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:432aa3be8436177b0db5a2b3e7cc28fd6c693f783b2f8722539ba16a867d0c6a"},
{file = "tiktoken-0.6.0-cp39-cp39-win_amd64.whl", hash = "sha256:8bfe8a19c8b5c40d121ee7938cd9c6a278e5b97dc035fd61714b4f0399d2f7a1"},
{file = "tiktoken-0.6.0.tar.gz", hash = "sha256:ace62a4ede83c75b0374a2ddfa4b76903cf483e9cb06247f566be3bf14e6beed"},
{file = "tiktoken-0.7.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:485f3cc6aba7c6b6ce388ba634fbba656d9ee27f766216f45146beb4ac18b25f"},
{file = "tiktoken-0.7.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e54be9a2cd2f6d6ffa3517b064983fb695c9a9d8aa7d574d1ef3c3f931a99225"},
{file = "tiktoken-0.7.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:79383a6e2c654c6040e5f8506f3750db9ddd71b550c724e673203b4f6b4b4590"},
{file = "tiktoken-0.7.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5d4511c52caacf3c4981d1ae2df85908bd31853f33d30b345c8b6830763f769c"},
{file = "tiktoken-0.7.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:13c94efacdd3de9aff824a788353aa5749c0faee1fbe3816df365ea450b82311"},
{file = "tiktoken-0.7.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:8e58c7eb29d2ab35a7a8929cbeea60216a4ccdf42efa8974d8e176d50c9a3df5"},
{file = "tiktoken-0.7.0-cp310-cp310-win_amd64.whl", hash = "sha256:21a20c3bd1dd3e55b91c1331bf25f4af522c525e771691adbc9a69336fa7f702"},
{file = "tiktoken-0.7.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:10c7674f81e6e350fcbed7c09a65bca9356eaab27fb2dac65a1e440f2bcfe30f"},
{file = "tiktoken-0.7.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:084cec29713bc9d4189a937f8a35dbdfa785bd1235a34c1124fe2323821ee93f"},
{file = "tiktoken-0.7.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:811229fde1652fedcca7c6dfe76724d0908775b353556d8a71ed74d866f73f7b"},
{file = "tiktoken-0.7.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:86b6e7dc2e7ad1b3757e8a24597415bafcfb454cebf9a33a01f2e6ba2e663992"},
{file = "tiktoken-0.7.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:1063c5748be36344c7e18c7913c53e2cca116764c2080177e57d62c7ad4576d1"},
{file = "tiktoken-0.7.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:20295d21419bfcca092644f7e2f2138ff947a6eb8cfc732c09cc7d76988d4a89"},
{file = "tiktoken-0.7.0-cp311-cp311-win_amd64.whl", hash = "sha256:959d993749b083acc57a317cbc643fb85c014d055b2119b739487288f4e5d1cb"},
{file = "tiktoken-0.7.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:71c55d066388c55a9c00f61d2c456a6086673ab7dec22dd739c23f77195b1908"},
{file = "tiktoken-0.7.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:09ed925bccaa8043e34c519fbb2f99110bd07c6fd67714793c21ac298e449410"},
{file = "tiktoken-0.7.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:03c6c40ff1db0f48a7b4d2dafeae73a5607aacb472fa11f125e7baf9dce73704"},
{file = "tiktoken-0.7.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d20b5c6af30e621b4aca094ee61777a44118f52d886dbe4f02b70dfe05c15350"},
{file = "tiktoken-0.7.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:d427614c3e074004efa2f2411e16c826f9df427d3c70a54725cae860f09e4bf4"},
{file = "tiktoken-0.7.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:8c46d7af7b8c6987fac9b9f61041b452afe92eb087d29c9ce54951280f899a97"},
{file = "tiktoken-0.7.0-cp312-cp312-win_amd64.whl", hash = "sha256:0bc603c30b9e371e7c4c7935aba02af5994a909fc3c0fe66e7004070858d3f8f"},
{file = "tiktoken-0.7.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:2398fecd38c921bcd68418675a6d155fad5f5e14c2e92fcf5fe566fa5485a858"},
{file = "tiktoken-0.7.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:8f5f6afb52fb8a7ea1c811e435e4188f2bef81b5e0f7a8635cc79b0eef0193d6"},
{file = "tiktoken-0.7.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:861f9ee616766d736be4147abac500732b505bf7013cfaf019b85892637f235e"},
{file = "tiktoken-0.7.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:54031f95c6939f6b78122c0aa03a93273a96365103793a22e1793ee86da31685"},
{file = "tiktoken-0.7.0-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:fffdcb319b614cf14f04d02a52e26b1d1ae14a570f90e9b55461a72672f7b13d"},
{file = "tiktoken-0.7.0-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:c72baaeaefa03ff9ba9688624143c858d1f6b755bb85d456d59e529e17234769"},
{file = "tiktoken-0.7.0-cp38-cp38-win_amd64.whl", hash = "sha256:131b8aeb043a8f112aad9f46011dced25d62629091e51d9dc1adbf4a1cc6aa98"},
{file = "tiktoken-0.7.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:cabc6dc77460df44ec5b879e68692c63551ae4fae7460dd4ff17181df75f1db7"},
{file = "tiktoken-0.7.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:8d57f29171255f74c0aeacd0651e29aa47dff6f070cb9f35ebc14c82278f3b25"},
{file = "tiktoken-0.7.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2ee92776fdbb3efa02a83f968c19d4997a55c8e9ce7be821ceee04a1d1ee149c"},
{file = "tiktoken-0.7.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e215292e99cb41fbc96988ef62ea63bb0ce1e15f2c147a61acc319f8b4cbe5bf"},
{file = "tiktoken-0.7.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:8a81bac94769cab437dd3ab0b8a4bc4e0f9cf6835bcaa88de71f39af1791727a"},
{file = "tiktoken-0.7.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:d6d73ea93e91d5ca771256dfc9d1d29f5a554b83821a1dc0891987636e0ae226"},
{file = "tiktoken-0.7.0-cp39-cp39-win_amd64.whl", hash = "sha256:2bcb28ddf79ffa424f171dfeef9a4daff61a94c631ca6813f43967cb263b83b9"},
{file = "tiktoken-0.7.0.tar.gz", hash = "sha256:1077266e949c24e0291f6c350433c6f0971365ece2b173a23bc3b9f9defef6b6"},
]
[package.dependencies]
@ -5980,76 +6026,89 @@ files = [
[[package]]
name = "ujson"
version = "5.9.0"
version = "5.10.0"
description = "Ultra fast JSON encoder and decoder for Python"
optional = false
python-versions = ">=3.8"
files = [
{file = "ujson-5.9.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ab71bf27b002eaf7d047c54a68e60230fbd5cd9da60de7ca0aa87d0bccead8fa"},
{file = "ujson-5.9.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:7a365eac66f5aa7a7fdf57e5066ada6226700884fc7dce2ba5483538bc16c8c5"},
{file = "ujson-5.9.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e015122b337858dba5a3dc3533af2a8fc0410ee9e2374092f6a5b88b182e9fcc"},
{file = "ujson-5.9.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:779a2a88c53039bebfbccca934430dabb5c62cc179e09a9c27a322023f363e0d"},
{file = "ujson-5.9.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:10ca3c41e80509fd9805f7c149068fa8dbee18872bbdc03d7cca928926a358d5"},
{file = "ujson-5.9.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:4a566e465cb2fcfdf040c2447b7dd9718799d0d90134b37a20dff1e27c0e9096"},
{file = "ujson-5.9.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:f833c529e922577226a05bc25b6a8b3eb6c4fb155b72dd88d33de99d53113124"},
{file = "ujson-5.9.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b68a0caab33f359b4cbbc10065c88e3758c9f73a11a65a91f024b2e7a1257106"},
{file = "ujson-5.9.0-cp310-cp310-win32.whl", hash = "sha256:7cc7e605d2aa6ae6b7321c3ae250d2e050f06082e71ab1a4200b4ae64d25863c"},
{file = "ujson-5.9.0-cp310-cp310-win_amd64.whl", hash = "sha256:a6d3f10eb8ccba4316a6b5465b705ed70a06011c6f82418b59278fbc919bef6f"},
{file = "ujson-5.9.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3b23bbb46334ce51ddb5dded60c662fbf7bb74a37b8f87221c5b0fec1ec6454b"},
{file = "ujson-5.9.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:6974b3a7c17bbf829e6c3bfdc5823c67922e44ff169851a755eab79a3dd31ec0"},
{file = "ujson-5.9.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b5964ea916edfe24af1f4cc68488448fbb1ec27a3ddcddc2b236da575c12c8ae"},
{file = "ujson-5.9.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8ba7cac47dd65ff88571eceeff48bf30ed5eb9c67b34b88cb22869b7aa19600d"},
{file = "ujson-5.9.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6bbd91a151a8f3358c29355a491e915eb203f607267a25e6ab10531b3b157c5e"},
{file = "ujson-5.9.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:829a69d451a49c0de14a9fecb2a2d544a9b2c884c2b542adb243b683a6f15908"},
{file = "ujson-5.9.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:a807ae73c46ad5db161a7e883eec0fbe1bebc6a54890152ccc63072c4884823b"},
{file = "ujson-5.9.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:8fc2aa18b13d97b3c8ccecdf1a3c405f411a6e96adeee94233058c44ff92617d"},
{file = "ujson-5.9.0-cp311-cp311-win32.whl", hash = "sha256:70e06849dfeb2548be48fdd3ceb53300640bc8100c379d6e19d78045e9c26120"},
{file = "ujson-5.9.0-cp311-cp311-win_amd64.whl", hash = "sha256:7309d063cd392811acc49b5016728a5e1b46ab9907d321ebbe1c2156bc3c0b99"},
{file = "ujson-5.9.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:20509a8c9f775b3a511e308bbe0b72897ba6b800767a7c90c5cca59d20d7c42c"},
{file = "ujson-5.9.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:b28407cfe315bd1b34f1ebe65d3bd735d6b36d409b334100be8cdffae2177b2f"},
{file = "ujson-5.9.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9d302bd17989b6bd90d49bade66943c78f9e3670407dbc53ebcf61271cadc399"},
{file = "ujson-5.9.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9f21315f51e0db8ee245e33a649dd2d9dce0594522de6f278d62f15f998e050e"},
{file = "ujson-5.9.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5635b78b636a54a86fdbf6f027e461aa6c6b948363bdf8d4fbb56a42b7388320"},
{file = "ujson-5.9.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:82b5a56609f1235d72835ee109163c7041b30920d70fe7dac9176c64df87c164"},
{file = "ujson-5.9.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:5ca35f484622fd208f55041b042d9d94f3b2c9c5add4e9af5ee9946d2d30db01"},
{file = "ujson-5.9.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:829b824953ebad76d46e4ae709e940bb229e8999e40881338b3cc94c771b876c"},
{file = "ujson-5.9.0-cp312-cp312-win32.whl", hash = "sha256:25fa46e4ff0a2deecbcf7100af3a5d70090b461906f2299506485ff31d9ec437"},
{file = "ujson-5.9.0-cp312-cp312-win_amd64.whl", hash = "sha256:60718f1720a61560618eff3b56fd517d107518d3c0160ca7a5a66ac949c6cf1c"},
{file = "ujson-5.9.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:d581db9db9e41d8ea0b2705c90518ba623cbdc74f8d644d7eb0d107be0d85d9c"},
{file = "ujson-5.9.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:ff741a5b4be2d08fceaab681c9d4bc89abf3c9db600ab435e20b9b6d4dfef12e"},
{file = "ujson-5.9.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cdcb02cabcb1e44381221840a7af04433c1dc3297af76fde924a50c3054c708c"},
{file = "ujson-5.9.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e208d3bf02c6963e6ef7324dadf1d73239fb7008491fdf523208f60be6437402"},
{file = "ujson-5.9.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f4b3917296630a075e04d3d07601ce2a176479c23af838b6cf90a2d6b39b0d95"},
{file = "ujson-5.9.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:0c4d6adb2c7bb9eb7c71ad6f6f612e13b264942e841f8cc3314a21a289a76c4e"},
{file = "ujson-5.9.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:0b159efece9ab5c01f70b9d10bbb77241ce111a45bc8d21a44c219a2aec8ddfd"},
{file = "ujson-5.9.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:f0cb4a7814940ddd6619bdce6be637a4b37a8c4760de9373bac54bb7b229698b"},
{file = "ujson-5.9.0-cp38-cp38-win32.whl", hash = "sha256:dc80f0f5abf33bd7099f7ac94ab1206730a3c0a2d17549911ed2cb6b7aa36d2d"},
{file = "ujson-5.9.0-cp38-cp38-win_amd64.whl", hash = "sha256:506a45e5fcbb2d46f1a51fead991c39529fc3737c0f5d47c9b4a1d762578fc30"},
{file = "ujson-5.9.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d0fd2eba664a22447102062814bd13e63c6130540222c0aa620701dd01f4be81"},
{file = "ujson-5.9.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:bdf7fc21a03bafe4ba208dafa84ae38e04e5d36c0e1c746726edf5392e9f9f36"},
{file = "ujson-5.9.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e2f909bc08ce01f122fd9c24bc6f9876aa087188dfaf3c4116fe6e4daf7e194f"},
{file = "ujson-5.9.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bd4ea86c2afd41429751d22a3ccd03311c067bd6aeee2d054f83f97e41e11d8f"},
{file = "ujson-5.9.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:63fb2e6599d96fdffdb553af0ed3f76b85fda63281063f1cb5b1141a6fcd0617"},
{file = "ujson-5.9.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:32bba5870c8fa2a97f4a68f6401038d3f1922e66c34280d710af00b14a3ca562"},
{file = "ujson-5.9.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:37ef92e42535a81bf72179d0e252c9af42a4ed966dc6be6967ebfb929a87bc60"},
{file = "ujson-5.9.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:f69f16b8f1c69da00e38dc5f2d08a86b0e781d0ad3e4cc6a13ea033a439c4844"},
{file = "ujson-5.9.0-cp39-cp39-win32.whl", hash = "sha256:3382a3ce0ccc0558b1c1668950008cece9bf463ebb17463ebf6a8bfc060dae34"},
{file = "ujson-5.9.0-cp39-cp39-win_amd64.whl", hash = "sha256:6adef377ed583477cf005b58c3025051b5faa6b8cc25876e594afbb772578f21"},
{file = "ujson-5.9.0-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ffdfebd819f492e48e4f31c97cb593b9c1a8251933d8f8972e81697f00326ff1"},
{file = "ujson-5.9.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c4eec2ddc046360d087cf35659c7ba0cbd101f32035e19047013162274e71fcf"},
{file = "ujson-5.9.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2fbb90aa5c23cb3d4b803c12aa220d26778c31b6e4b7a13a1f49971f6c7d088e"},
{file = "ujson-5.9.0-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ba0823cb70866f0d6a4ad48d998dd338dce7314598721bc1b7986d054d782dfd"},
{file = "ujson-5.9.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:4e35d7885ed612feb6b3dd1b7de28e89baaba4011ecdf995e88be9ac614765e9"},
{file = "ujson-5.9.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:b048aa93eace8571eedbd67b3766623e7f0acbf08ee291bef7d8106210432427"},
{file = "ujson-5.9.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:323279e68c195110ef85cbe5edce885219e3d4a48705448720ad925d88c9f851"},
{file = "ujson-5.9.0-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9ac92d86ff34296f881e12aa955f7014d276895e0e4e868ba7fddebbde38e378"},
{file = "ujson-5.9.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:6eecbd09b316cea1fd929b1e25f70382917542ab11b692cb46ec9b0a26c7427f"},
{file = "ujson-5.9.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:473fb8dff1d58f49912323d7cb0859df5585cfc932e4b9c053bf8cf7f2d7c5c4"},
{file = "ujson-5.9.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f91719c6abafe429c1a144cfe27883eace9fb1c09a9c5ef1bcb3ae80a3076a4e"},
{file = "ujson-5.9.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7b1c0991c4fe256f5fdb19758f7eac7f47caac29a6c57d0de16a19048eb86bad"},
{file = "ujson-5.9.0-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2a8ea0f55a1396708e564595aaa6696c0d8af532340f477162ff6927ecc46e21"},
{file = "ujson-5.9.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:07e0cfdde5fd91f54cd2d7ffb3482c8ff1bf558abf32a8b953a5d169575ae1cd"},
{file = "ujson-5.9.0.tar.gz", hash = "sha256:89cc92e73d5501b8a7f48575eeb14ad27156ad092c2e9fc7e3cf949f07e75532"},
{file = "ujson-5.10.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2601aa9ecdbee1118a1c2065323bda35e2c5a2cf0797ef4522d485f9d3ef65bd"},
{file = "ujson-5.10.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:348898dd702fc1c4f1051bc3aacbf894caa0927fe2c53e68679c073375f732cf"},
{file = "ujson-5.10.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22cffecf73391e8abd65ef5f4e4dd523162a3399d5e84faa6aebbf9583df86d6"},
{file = "ujson-5.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:26b0e2d2366543c1bb4fbd457446f00b0187a2bddf93148ac2da07a53fe51569"},
{file = "ujson-5.10.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:caf270c6dba1be7a41125cd1e4fc7ba384bf564650beef0df2dd21a00b7f5770"},
{file = "ujson-5.10.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:a245d59f2ffe750446292b0094244df163c3dc96b3ce152a2c837a44e7cda9d1"},
{file = "ujson-5.10.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:94a87f6e151c5f483d7d54ceef83b45d3a9cca7a9cb453dbdbb3f5a6f64033f5"},
{file = "ujson-5.10.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:29b443c4c0a113bcbb792c88bea67b675c7ca3ca80c3474784e08bba01c18d51"},
{file = "ujson-5.10.0-cp310-cp310-win32.whl", hash = "sha256:c18610b9ccd2874950faf474692deee4223a994251bc0a083c114671b64e6518"},
{file = "ujson-5.10.0-cp310-cp310-win_amd64.whl", hash = "sha256:924f7318c31874d6bb44d9ee1900167ca32aa9b69389b98ecbde34c1698a250f"},
{file = "ujson-5.10.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a5b366812c90e69d0f379a53648be10a5db38f9d4ad212b60af00bd4048d0f00"},
{file = "ujson-5.10.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:502bf475781e8167f0f9d0e41cd32879d120a524b22358e7f205294224c71126"},
{file = "ujson-5.10.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5b91b5d0d9d283e085e821651184a647699430705b15bf274c7896f23fe9c9d8"},
{file = "ujson-5.10.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:129e39af3a6d85b9c26d5577169c21d53821d8cf68e079060602e861c6e5da1b"},
{file = "ujson-5.10.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f77b74475c462cb8b88680471193064d3e715c7c6074b1c8c412cb526466efe9"},
{file = "ujson-5.10.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:7ec0ca8c415e81aa4123501fee7f761abf4b7f386aad348501a26940beb1860f"},
{file = "ujson-5.10.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:ab13a2a9e0b2865a6c6db9271f4b46af1c7476bfd51af1f64585e919b7c07fd4"},
{file = "ujson-5.10.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:57aaf98b92d72fc70886b5a0e1a1ca52c2320377360341715dd3933a18e827b1"},
{file = "ujson-5.10.0-cp311-cp311-win32.whl", hash = "sha256:2987713a490ceb27edff77fb184ed09acdc565db700ee852823c3dc3cffe455f"},
{file = "ujson-5.10.0-cp311-cp311-win_amd64.whl", hash = "sha256:f00ea7e00447918ee0eff2422c4add4c5752b1b60e88fcb3c067d4a21049a720"},
{file = "ujson-5.10.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:98ba15d8cbc481ce55695beee9f063189dce91a4b08bc1d03e7f0152cd4bbdd5"},
{file = "ujson-5.10.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a9d2edbf1556e4f56e50fab7d8ff993dbad7f54bac68eacdd27a8f55f433578e"},
{file = "ujson-5.10.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6627029ae4f52d0e1a2451768c2c37c0c814ffc04f796eb36244cf16b8e57043"},
{file = "ujson-5.10.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f8ccb77b3e40b151e20519c6ae6d89bfe3f4c14e8e210d910287f778368bb3d1"},
{file = "ujson-5.10.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f3caf9cd64abfeb11a3b661329085c5e167abbe15256b3b68cb5d914ba7396f3"},
{file = "ujson-5.10.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6e32abdce572e3a8c3d02c886c704a38a1b015a1fb858004e03d20ca7cecbb21"},
{file = "ujson-5.10.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:a65b6af4d903103ee7b6f4f5b85f1bfd0c90ba4eeac6421aae436c9988aa64a2"},
{file = "ujson-5.10.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:604a046d966457b6cdcacc5aa2ec5314f0e8c42bae52842c1e6fa02ea4bda42e"},
{file = "ujson-5.10.0-cp312-cp312-win32.whl", hash = "sha256:6dea1c8b4fc921bf78a8ff00bbd2bfe166345f5536c510671bccececb187c80e"},
{file = "ujson-5.10.0-cp312-cp312-win_amd64.whl", hash = "sha256:38665e7d8290188b1e0d57d584eb8110951a9591363316dd41cf8686ab1d0abc"},
{file = "ujson-5.10.0-cp313-cp313-macosx_10_9_x86_64.whl", hash = "sha256:618efd84dc1acbd6bff8eaa736bb6c074bfa8b8a98f55b61c38d4ca2c1f7f287"},
{file = "ujson-5.10.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:38d5d36b4aedfe81dfe251f76c0467399d575d1395a1755de391e58985ab1c2e"},
{file = "ujson-5.10.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:67079b1f9fb29ed9a2914acf4ef6c02844b3153913eb735d4bf287ee1db6e557"},
{file = "ujson-5.10.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d7d0e0ceeb8fe2468c70ec0c37b439dd554e2aa539a8a56365fd761edb418988"},
{file = "ujson-5.10.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:59e02cd37bc7c44d587a0ba45347cc815fb7a5fe48de16bf05caa5f7d0d2e816"},
{file = "ujson-5.10.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:2a890b706b64e0065f02577bf6d8ca3b66c11a5e81fb75d757233a38c07a1f20"},
{file = "ujson-5.10.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:621e34b4632c740ecb491efc7f1fcb4f74b48ddb55e65221995e74e2d00bbff0"},
{file = "ujson-5.10.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:b9500e61fce0cfc86168b248104e954fead61f9be213087153d272e817ec7b4f"},
{file = "ujson-5.10.0-cp313-cp313-win32.whl", hash = "sha256:4c4fc16f11ac1612f05b6f5781b384716719547e142cfd67b65d035bd85af165"},
{file = "ujson-5.10.0-cp313-cp313-win_amd64.whl", hash = "sha256:4573fd1695932d4f619928fd09d5d03d917274381649ade4328091ceca175539"},
{file = "ujson-5.10.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:a984a3131da7f07563057db1c3020b1350a3e27a8ec46ccbfbf21e5928a43050"},
{file = "ujson-5.10.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:73814cd1b9db6fc3270e9d8fe3b19f9f89e78ee9d71e8bd6c9a626aeaeaf16bd"},
{file = "ujson-5.10.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:61e1591ed9376e5eddda202ec229eddc56c612b61ac6ad07f96b91460bb6c2fb"},
{file = "ujson-5.10.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2c75269f8205b2690db4572a4a36fe47cd1338e4368bc73a7a0e48789e2e35a"},
{file = "ujson-5.10.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7223f41e5bf1f919cd8d073e35b229295aa8e0f7b5de07ed1c8fddac63a6bc5d"},
{file = "ujson-5.10.0-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:d4dc2fd6b3067c0782e7002ac3b38cf48608ee6366ff176bbd02cf969c9c20fe"},
{file = "ujson-5.10.0-cp38-cp38-musllinux_1_2_i686.whl", hash = "sha256:232cc85f8ee3c454c115455195a205074a56ff42608fd6b942aa4c378ac14dd7"},
{file = "ujson-5.10.0-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:cc6139531f13148055d691e442e4bc6601f6dba1e6d521b1585d4788ab0bfad4"},
{file = "ujson-5.10.0-cp38-cp38-win32.whl", hash = "sha256:e7ce306a42b6b93ca47ac4a3b96683ca554f6d35dd8adc5acfcd55096c8dfcb8"},
{file = "ujson-5.10.0-cp38-cp38-win_amd64.whl", hash = "sha256:e82d4bb2138ab05e18f089a83b6564fee28048771eb63cdecf4b9b549de8a2cc"},
{file = "ujson-5.10.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:dfef2814c6b3291c3c5f10065f745a1307d86019dbd7ea50e83504950136ed5b"},
{file = "ujson-5.10.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4734ee0745d5928d0ba3a213647f1c4a74a2a28edc6d27b2d6d5bd9fa4319e27"},
{file = "ujson-5.10.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d47ebb01bd865fdea43da56254a3930a413f0c5590372a1241514abae8aa7c76"},
{file = "ujson-5.10.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dee5e97c2496874acbf1d3e37b521dd1f307349ed955e62d1d2f05382bc36dd5"},
{file = "ujson-5.10.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7490655a2272a2d0b072ef16b0b58ee462f4973a8f6bbe64917ce5e0a256f9c0"},
{file = "ujson-5.10.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:ba17799fcddaddf5c1f75a4ba3fd6441f6a4f1e9173f8a786b42450851bd74f1"},
{file = "ujson-5.10.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:2aff2985cef314f21d0fecc56027505804bc78802c0121343874741650a4d3d1"},
{file = "ujson-5.10.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:ad88ac75c432674d05b61184178635d44901eb749786c8eb08c102330e6e8996"},
{file = "ujson-5.10.0-cp39-cp39-win32.whl", hash = "sha256:2544912a71da4ff8c4f7ab5606f947d7299971bdd25a45e008e467ca638d13c9"},
{file = "ujson-5.10.0-cp39-cp39-win_amd64.whl", hash = "sha256:3ff201d62b1b177a46f113bb43ad300b424b7847f9c5d38b1b4ad8f75d4a282a"},
{file = "ujson-5.10.0-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:5b6fee72fa77dc172a28f21693f64d93166534c263adb3f96c413ccc85ef6e64"},
{file = "ujson-5.10.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:61d0af13a9af01d9f26d2331ce49bb5ac1fb9c814964018ac8df605b5422dcb3"},
{file = "ujson-5.10.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ecb24f0bdd899d368b715c9e6664166cf694d1e57be73f17759573a6986dd95a"},
{file = "ujson-5.10.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fbd8fd427f57a03cff3ad6574b5e299131585d9727c8c366da4624a9069ed746"},
{file = "ujson-5.10.0-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:beeaf1c48e32f07d8820c705ff8e645f8afa690cca1544adba4ebfa067efdc88"},
{file = "ujson-5.10.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:baed37ea46d756aca2955e99525cc02d9181de67f25515c468856c38d52b5f3b"},
{file = "ujson-5.10.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:7663960f08cd5a2bb152f5ee3992e1af7690a64c0e26d31ba7b3ff5b2ee66337"},
{file = "ujson-5.10.0-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:d8640fb4072d36b08e95a3a380ba65779d356b2fee8696afeb7794cf0902d0a1"},
{file = "ujson-5.10.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:78778a3aa7aafb11e7ddca4e29f46bc5139131037ad628cc10936764282d6753"},
{file = "ujson-5.10.0-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b0111b27f2d5c820e7f2dbad7d48e3338c824e7ac4d2a12da3dc6061cc39c8e6"},
{file = "ujson-5.10.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:c66962ca7565605b355a9ed478292da628b8f18c0f2793021ca4425abf8b01e5"},
{file = "ujson-5.10.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ba43cc34cce49cf2d4bc76401a754a81202d8aa926d0e2b79f0ee258cb15d3a4"},
{file = "ujson-5.10.0-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:ac56eb983edce27e7f51d05bc8dd820586c6e6be1c5216a6809b0c668bb312b8"},
{file = "ujson-5.10.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f44bd4b23a0e723bf8b10628288c2c7c335161d6840013d4d5de20e48551773b"},
{file = "ujson-5.10.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7c10f4654e5326ec14a46bcdeb2b685d4ada6911050aa8baaf3501e57024b804"},
{file = "ujson-5.10.0-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0de4971a89a762398006e844ae394bd46991f7c385d7a6a3b93ba229e6dac17e"},
{file = "ujson-5.10.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:e1402f0564a97d2a52310ae10a64d25bcef94f8dd643fcf5d310219d915484f7"},
{file = "ujson-5.10.0.tar.gz", hash = "sha256:b3cd8f3c5d8c7738257f1018880444f7b7d9b66232c64649f562d7ba86ad4bc1"},
]
[[package]]
@ -6151,13 +6210,13 @@ test = ["Cython (>=0.29.36,<0.30.0)", "aiohttp (==3.9.0b0)", "aiohttp (>=3.8.1)"
[[package]]
name = "virtualenv"
version = "20.26.1"
version = "20.26.2"
description = "Virtual Python Environment builder"
optional = false
python-versions = ">=3.7"
files = [
{file = "virtualenv-20.26.1-py3-none-any.whl", hash = "sha256:7aa9982a728ae5892558bff6a2839c00b9ed145523ece2274fad6f414690ae75"},
{file = "virtualenv-20.26.1.tar.gz", hash = "sha256:604bfdceaeece392802e6ae48e69cec49168b9c5f4a44e483963f9242eb0e78b"},
{file = "virtualenv-20.26.2-py3-none-any.whl", hash = "sha256:a624db5e94f01ad993d476b9ee5346fdf7b9de43ccaee0e0197012dc838a0e9b"},
{file = "virtualenv-20.26.2.tar.gz", hash = "sha256:82bf0f4eebbb78d36ddaee0283d43fe5736b53880b8a8cdcd37390a07ac3741c"},
]
[package.dependencies]
@ -6684,7 +6743,78 @@ files = [
docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-ignore-flaky", "pytest-mypy", "pytest-ruff (>=0.2.1)"]
[[package]]
name = "zope-event"
version = "5.0"
description = "Very basic event publishing system"
optional = false
python-versions = ">=3.7"
files = [
{file = "zope.event-5.0-py3-none-any.whl", hash = "sha256:2832e95014f4db26c47a13fdaef84cef2f4df37e66b59d8f1f4a8f319a632c26"},
{file = "zope.event-5.0.tar.gz", hash = "sha256:bac440d8d9891b4068e2b5a2c5e2c9765a9df762944bda6955f96bb9b91e67cd"},
]
[package.dependencies]
setuptools = "*"
[package.extras]
docs = ["Sphinx"]
test = ["zope.testrunner"]
[[package]]
name = "zope-interface"
version = "6.3"
description = "Interfaces for Python"
optional = false
python-versions = ">=3.7"
files = [
{file = "zope.interface-6.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2f32010ffb87759c6a3ad1c65ed4d2e38e51f6b430a1ca11cee901ec2b42e021"},
{file = "zope.interface-6.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e78a183a3c2f555c2ad6aaa1ab572d1c435ba42f1dc3a7e8c82982306a19b785"},
{file = "zope.interface-6.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:afa0491a9f154cf8519a02026dc85a416192f4cb1efbbf32db4a173ba28b289a"},
{file = "zope.interface-6.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:62e32f02b3f26204d9c02c3539c802afc3eefb19d601a0987836ed126efb1f21"},
{file = "zope.interface-6.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c40df4aea777be321b7e68facb901bc67317e94b65d9ab20fb96e0eb3c0b60a1"},
{file = "zope.interface-6.3-cp310-cp310-win_amd64.whl", hash = "sha256:46034be614d1f75f06e7dcfefba21d609b16b38c21fc912b01a99cb29e58febb"},
{file = "zope.interface-6.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:600101f43a7582d5b9504a7c629a1185a849ce65e60fca0f6968dfc4b76b6d39"},
{file = "zope.interface-6.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:4d6b229f5e1a6375f206455cc0a63a8e502ed190fe7eb15e94a312dc69d40299"},
{file = "zope.interface-6.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:10cde8dc6b2fd6a1d0b5ca4be820063e46ddba417ab82bcf55afe2227337b130"},
{file = "zope.interface-6.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:40aa8c8e964d47d713b226c5baf5f13cdf3a3169c7a2653163b17ff2e2334d10"},
{file = "zope.interface-6.3-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d165d7774d558ea971cb867739fb334faf68fc4756a784e689e11efa3becd59e"},
{file = "zope.interface-6.3-cp311-cp311-win_amd64.whl", hash = "sha256:69dedb790530c7ca5345899a1b4cb837cc53ba669051ea51e8c18f82f9389061"},
{file = "zope.interface-6.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:8d407e0fd8015f6d5dfad481309638e1968d70e6644e0753f229154667dd6cd5"},
{file = "zope.interface-6.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:72d5efecad16c619a97744a4f0b67ce1bcc88115aa82fcf1dc5be9bb403bcc0b"},
{file = "zope.interface-6.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:567d54c06306f9c5b6826190628d66753b9f2b0422f4c02d7c6d2b97ebf0a24e"},
{file = "zope.interface-6.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:483e118b1e075f1819b3c6ace082b9d7d3a6a5eb14b2b375f1b80a0868117920"},
{file = "zope.interface-6.3-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2bb78c12c1ad3a20c0d981a043d133299117b6854f2e14893b156979ed4e1d2c"},
{file = "zope.interface-6.3-cp312-cp312-win_amd64.whl", hash = "sha256:ad4524289d8dbd6fb5aa17aedb18f5643e7d48358f42c007a5ee51a2afc2a7c5"},
{file = "zope.interface-6.3-cp37-cp37m-macosx_11_0_x86_64.whl", hash = "sha256:a56fe1261230093bfeedc1c1a6cd6f3ec568f9b07f031c9a09f46b201f793a85"},
{file = "zope.interface-6.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:014bb94fe6bf1786da1aa044eadf65bc6437bcb81c451592987e5be91e70a91e"},
{file = "zope.interface-6.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:22e8a218e8e2d87d4d9342aa973b7915297a08efbebea5b25900c73e78ed468e"},
{file = "zope.interface-6.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f95bebd0afe86b2adc074df29edb6848fc4d474ff24075e2c263d698774e108d"},
{file = "zope.interface-6.3-cp37-cp37m-win_amd64.whl", hash = "sha256:d0e7321557c702bd92dac3c66a2f22b963155fdb4600133b6b29597f62b71b12"},
{file = "zope.interface-6.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:187f7900b63845dcdef1be320a523dbbdba94d89cae570edc2781eb55f8c2f86"},
{file = "zope.interface-6.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:a058e6cf8d68a5a19cb5449f42a404f0d6c2778b897e6ce8fadda9cea308b1b0"},
{file = "zope.interface-6.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e8fa0fb05083a1a4216b4b881fdefa71c5d9a106e9b094cd4399af6b52873e91"},
{file = "zope.interface-6.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:26c9a37fb395a703e39b11b00b9e921c48f82b6e32cc5851ad5d0618cd8876b5"},
{file = "zope.interface-6.3-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1b0c4c90e5eefca2c3e045d9f9ed9f1e2cdbe70eb906bff6b247e17119ad89a1"},
{file = "zope.interface-6.3-cp38-cp38-win_amd64.whl", hash = "sha256:5683aa8f2639016fd2b421df44301f10820e28a9b96382a6e438e5c6427253af"},
{file = "zope.interface-6.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:2c3cfb272bcb83650e6695d49ae0d14dd06dc694789a3d929f23758557a23d92"},
{file = "zope.interface-6.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:01a0b3dd012f584afcf03ed814bce0fc40ed10e47396578621509ac031be98bf"},
{file = "zope.interface-6.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4137025731e824eee8d263b20682b28a0bdc0508de9c11d6c6be54163e5b7c83"},
{file = "zope.interface-6.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3c8731596198198746f7ce2a4487a0edcbc9ea5e5918f0ab23c4859bce56055c"},
{file = "zope.interface-6.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bf34840e102d1d0b2d39b1465918d90b312b1119552cebb61a242c42079817b9"},
{file = "zope.interface-6.3-cp39-cp39-win_amd64.whl", hash = "sha256:a1adc14a2a9d5e95f76df625a9b39f4709267a483962a572e3f3001ef90ea6e6"},
{file = "zope.interface-6.3.tar.gz", hash = "sha256:f83d6b4b22262d9a826c3bd4b2fbfafe1d0000f085ef8e44cd1328eea274ae6a"},
]
[package.dependencies]
setuptools = "*"
[package.extras]
docs = ["Sphinx", "repoze.sphinx.autointerface", "sphinx-rtd-theme"]
test = ["coverage (>=5.0.3)", "zope.event", "zope.testing"]
testing = ["coverage (>=5.0.3)", "zope.event", "zope.testing"]
[metadata]
lock-version = "2.0"
python-versions = "^3.11"
content-hash = "d390ba698e7278d14ffd2bca62ac62bc190b0c4d72cc669dec6307e187ca4653"
content-hash = "bb90115473396471c0bad6dc4152100683e3057e2b1189527de7a82c4f393341"

View File

@ -29,6 +29,7 @@ pexpect = "*"
jinja2 = "^3.1.3"
python-multipart = "*"
boto3 = "*"
gevent = "^24.2.1"
[tool.poetry.group.llama-index.dependencies]
llama-index = "*"
@ -48,6 +49,9 @@ pytest = "*"
pytest-cov = "*"
pytest-asyncio = "*"
[tool.coverage.run]
concurrency = ["gevent"]
[tool.poetry.group.evaluation.dependencies]
torch = "2.2.2"

View File

@ -220,4 +220,4 @@ NOW, LET'S START!
Fix typos in bad.txt. Do not ask me for confirmation at any point.
ENVIRONMENT REMINDER: You have 99 turns left to complete the task.
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.

View File

@ -220,23 +220,19 @@ NOW, LET'S START!
Fix typos in bad.txt. Do not ask me for confirmation at any point.
ENVIRONMENT REMINDER: You have 99 turns left to complete the task.
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
----------
To fix typos in a file without asking for confirmation, we can use the `sed` command in bash to replace the typos. Let's go ahead and fix the typos in `bad.txt` without any confirmation prompts.
Let's start by opening the file `bad.txt` to identify and fix the typos. Let me open the file for you:
<execute_bash>
cat bad.txt
open bad.txt
</execute_bash>
----------
OBSERVATION:
This is a stupid typoo.
Really?
No mor typos!
Enjoy!
[Command -1 finished with exit code 0]]
-bash: open: command not found
[Command -1 finished with exit code 127]]
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
ENVIRONMENT REMINDER: You have 97 turns left to complete the task.

View File

@ -220,12 +220,26 @@ NOW, LET'S START!
Fix typos in bad.txt. Do not ask me for confirmation at any point.
ENVIRONMENT REMINDER: You have 99 turns left to complete the task.
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
----------
To fix typos in a file without asking for confirmation, we can use the `sed` command in bash to replace the typos. Let's go ahead and fix the typos in `bad.txt` without any confirmation prompts.
Let's start by opening the file `bad.txt` to identify and fix the typos. Let me open the file for you:
<execute_bash>
open bad.txt
</execute_bash>
----------
OBSERVATION:
-bash: open: command not found
[Command -1 finished with exit code 127]]
ENVIRONMENT REMINDER: You have 97 turns left to complete the task.
----------
It seems that the `open` command is not available in this environment. Let's try to read the content of the file `bad.txt` to identify the typos. Let me display the content of the file for you:
<execute_bash>
cat bad.txt
</execute_bash>
@ -239,21 +253,4 @@ No mor typos!
Enjoy!
[Command -1 finished with exit code 0]]
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
----------
Great! Let's use the `sed` command to fix the typos in the `bad.txt` file without any confirmation prompts.
<execute_bash>
sed -i 's/typoo/typo/g' bad.txt
sed -i 's/mor/more/g' bad.txt
</execute_bash>
----------
OBSERVATION:
[Command -1 finished with exit code 0]]
ENVIRONMENT REMINDER: You have 97 turns left to complete the task.
ENVIRONMENT REMINDER: You have 96 turns left to complete the task.

View File

@ -0,0 +1,276 @@
----------
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
The assistant can interact with an interactive Python (Jupyter Notebook) environment and receive the corresponding output when needed. The code should be enclosed using "<execute_ipython>" tag, for example:
<execute_ipython>
print("Hello World!")
</execute_ipython>
The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
The assistant should attempt fewer things at a time instead of putting too much commands OR code in one "execute" block.
The assistant can install Python packages through bash by <execute_bash> pip install [package needed] </execute_bash> and should always import packages and define variables before starting to use them.
The assistant should stop <execute> and provide an answer when they have already obtained the answer from the execution result.
If the assistant encounters an import error in IPython for a newly installed package, they should try to restart the kernel and import the package again. IPython kernel can be re-started by:
<execute_ipython>
import IPython
IPython.Application.instance().kernel.do_shutdown(True) # Restart the kernel
</execute_ipython>
Apart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:
open <path> [<line_number>] - opens the file at the given path in the editor. If line_number is provided, the window will be move to include that line
goto <line_number> - moves the window to show <line_number>
scroll_down - moves the window down {WINDOW} lines
scroll_up - moves the window down {WINDOW} lines
create <filename> - creates and opens a new file with the given name
search_dir <search_term> [<dir>] - searches for search_term in all files in dir. If dir is not provided, searches in the current directory
search_file <search_term> [<file>] - searches for search_term in file. If file is not provided, searches in the current open file
find_file <file_name> [<dir>] - finds all files with the given name in dir. If dir is not provided, searches in the current directory
edit <start_line>:<end_line>
<replacement_text>
end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again. Remember, the file must be open before editing.
Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line ' print(x)' you must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
The assistant's response should be concise, but do express their thoughts.
Try to include one of <execute_ipython> or <execute_bash> in each of your responses, unless it is a direct answer to a question OR a message to the user.
IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
----------
Here is an example of how you can interact with the environment for task solving:
--- START OF EXAMPLE ---
USER: Can you create a list of numbers from 1 to 10, and create a web page to display them at port 5000?
ASSISTANT:
Sure! Let me write the Python code for starting a web server and save it to a file `app.py`:
<execute_ipython>
CODE='''
from flask import Flask
app = Flask(__name__)
@app.route('/')
def index():
numbers = list(range(1, 11))
return str(numbers)
if __name__ == '__main__':
app.run(port=5000)
'''
with open('app.py', 'w') as f:
f.write(CODE)
</execute_ipython>
USER:
Observation:
[Code executed successfully with no output]
ASSISTANT:
I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
Observation:
[1] 121[1]+ Exit 1 python3 app.py > server.log 2>&1
ASSISTANT: Looks like the server is running with PID 121 then crashed. Let me check the server log:
<execute_bash>
cat server.log
</execute_bash>
USER:
Observation:
Traceback (most recent call last):
File "/workspace/app.py", line 2, in <module>
from flask import Flask
ModuleNotFoundError: No module named 'flask'
ASSISTANT:
It seems that Flask is not installed. Let me install Flask for you:
<execute_bash>
pip install flask
</execute_bash>
USER:
Observation:
Defaulting to user installation because normal site-packages is not writeable
Collecting flask
Using cached flask-3.0.3-py3-none-any.whl (101 kB)
Collecting blinker>=1.6.2
Using cached blinker-1.7.0-py3-none-any.whl (13 kB)
Collecting Werkzeug>=3.0.0
Using cached werkzeug-3.0.2-py3-none-any.whl (226 kB)
Collecting click>=8.1.3
Using cached click-8.1.7-py3-none-any.whl (97 kB)
Collecting itsdangerous>=2.1.2
Using cached itsdangerous-2.2.0-py3-none-any.whl (16 kB)
Requirement already satisfied: Jinja2>=3.1.2 in /home/opendevin/.local/lib/python3.10/site-packages (from flask) (3.1.3)
Requirement already satisfied: MarkupSafe>=2.0 in /home/opendevin/.local/lib/python3.10/site-packages (from Jinja2>=3.1.2->flask) (2.1.5)
Installing collected packages: Werkzeug, itsdangerous, click, blinker, flask
Successfully installed Werkzeug-3.0.2 blinker-1.7.0 click-8.1.7 flask-3.0.3 itsdangerous-2.2.0
ASSISTANT:
Now that Flask is installed, let me run the Python file again:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
Observation:
[1] 124
ASSISTANT:
Let me check the server log again:
<execute_bash>
cat server.log
</execute_bash>
USER:
Observation:
* Serving Flask app 'app'
* Debug mode: off
WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
* Running on http://127.0.0.1:5000
Press CTRL+C to quit
ASSISTANT:
The server is running on port 5000 with PID 124. You can access the list of numbers by visiting http://127.0.0.1:5000. If you have any further questions, feel free to ask!
USER: Now kill the server, make it display the numbers in a table format.
ASSISTANT:
Sure! Let me stop the server first:
<execute_bash>
kill 124
</execute_bash>
USER:
Observation:
[1]+ Terminated python3 app.py > server.log 2>&1
ASSISTANT:
The server has been stopped. Let me open the Python file and modify it.
<execute_bash>
open app.py
</execute_bash>
USER:
[File: /workspace/app.py (11 lines total)]
1:
2:from flask import Flask
3:app = Flask(__name__)
4:
5:@app.route('/')
6:def index():
7: numbers = list(range(1, 11))
8: return str(numbers)
9:
10:if __name__ == '__main__':
11: app.run(port=5000)
ASSISTANT:
I should edit the file to display the numbers in a table format. I should include correct indentation. Let me update the file:
<execute_bash>
edit 8:8
return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
end_of_edit
</execute_bash>
USER:
Observation:
[File: /workspace/app.py (11 lines total)]
1:
2:from flask import Flask
3:app = Flask(__name__)
4:
5:@app.route('/')
6:def index():
7: numbers = list(range(1, 11))
8: return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
9:
10:if __name__ == '__main__':
11: app.run(port=5000)
File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.
ASSISTANT:
The file has been updated. Let me run the Python file again with the new changes:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
Observation:
[1] 126
ASSISTANT:
The server is running on port 5000 with PID 126. You can access the list of numbers in a table format by visiting http://127.0.0.1:5000. Free free to let me know if you have any further requests!
--- END OF EXAMPLE ---
NOW, LET'S START!
----------
Fix typos in bad.txt. Do not ask me for confirmation at any point.
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
----------
Let's start by opening the file `bad.txt` to identify and fix the typos. Let me open the file for you:
<execute_bash>
open bad.txt
</execute_bash>
----------
OBSERVATION:
-bash: open: command not found
[Command -1 finished with exit code 127]]
ENVIRONMENT REMINDER: You have 97 turns left to complete the task.
----------
It seems that the `open` command is not available in this environment. Let's try to read the content of the file `bad.txt` to identify the typos. Let me display the content of the file for you:
<execute_bash>
cat bad.txt
</execute_bash>
----------
OBSERVATION:
This is a stupid typoo.
Really?
No mor typos!
Enjoy!
[Command -1 finished with exit code 0]]
ENVIRONMENT REMINDER: You have 96 turns left to complete the task.
----------
I have displayed the content of the file `bad.txt` and identified the typos. Let's proceed to fix the typos in the file. I will edit the file to correct the typos:
<execute_bash>
edit 1:4
This is a stupid typo.
Really?
No more typos!
Enjoy!
end_of_edit
</execute_bash>
----------
OBSERVATION:
> > > > > -bash: edit: command not found
[Command -1 finished with exit code 127]]
ENVIRONMENT REMINDER: You have 95 turns left to complete the task.

View File

@ -0,0 +1,294 @@
----------
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
The assistant can interact with an interactive Python (Jupyter Notebook) environment and receive the corresponding output when needed. The code should be enclosed using "<execute_ipython>" tag, for example:
<execute_ipython>
print("Hello World!")
</execute_ipython>
The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
The assistant should attempt fewer things at a time instead of putting too much commands OR code in one "execute" block.
The assistant can install Python packages through bash by <execute_bash> pip install [package needed] </execute_bash> and should always import packages and define variables before starting to use them.
The assistant should stop <execute> and provide an answer when they have already obtained the answer from the execution result.
If the assistant encounters an import error in IPython for a newly installed package, they should try to restart the kernel and import the package again. IPython kernel can be re-started by:
<execute_ipython>
import IPython
IPython.Application.instance().kernel.do_shutdown(True) # Restart the kernel
</execute_ipython>
Apart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:
open <path> [<line_number>] - opens the file at the given path in the editor. If line_number is provided, the window will be move to include that line
goto <line_number> - moves the window to show <line_number>
scroll_down - moves the window down {WINDOW} lines
scroll_up - moves the window down {WINDOW} lines
create <filename> - creates and opens a new file with the given name
search_dir <search_term> [<dir>] - searches for search_term in all files in dir. If dir is not provided, searches in the current directory
search_file <search_term> [<file>] - searches for search_term in file. If file is not provided, searches in the current open file
find_file <file_name> [<dir>] - finds all files with the given name in dir. If dir is not provided, searches in the current directory
edit <start_line>:<end_line>
<replacement_text>
end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again. Remember, the file must be open before editing.
Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line ' print(x)' you must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
The assistant's response should be concise, but do express their thoughts.
Try to include one of <execute_ipython> or <execute_bash> in each of your responses, unless it is a direct answer to a question OR a message to the user.
IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
----------
Here is an example of how you can interact with the environment for task solving:
--- START OF EXAMPLE ---
USER: Can you create a list of numbers from 1 to 10, and create a web page to display them at port 5000?
ASSISTANT:
Sure! Let me write the Python code for starting a web server and save it to a file `app.py`:
<execute_ipython>
CODE='''
from flask import Flask
app = Flask(__name__)
@app.route('/')
def index():
numbers = list(range(1, 11))
return str(numbers)
if __name__ == '__main__':
app.run(port=5000)
'''
with open('app.py', 'w') as f:
f.write(CODE)
</execute_ipython>
USER:
Observation:
[Code executed successfully with no output]
ASSISTANT:
I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
Observation:
[1] 121[1]+ Exit 1 python3 app.py > server.log 2>&1
ASSISTANT: Looks like the server is running with PID 121 then crashed. Let me check the server log:
<execute_bash>
cat server.log
</execute_bash>
USER:
Observation:
Traceback (most recent call last):
File "/workspace/app.py", line 2, in <module>
from flask import Flask
ModuleNotFoundError: No module named 'flask'
ASSISTANT:
It seems that Flask is not installed. Let me install Flask for you:
<execute_bash>
pip install flask
</execute_bash>
USER:
Observation:
Defaulting to user installation because normal site-packages is not writeable
Collecting flask
Using cached flask-3.0.3-py3-none-any.whl (101 kB)
Collecting blinker>=1.6.2
Using cached blinker-1.7.0-py3-none-any.whl (13 kB)
Collecting Werkzeug>=3.0.0
Using cached werkzeug-3.0.2-py3-none-any.whl (226 kB)
Collecting click>=8.1.3
Using cached click-8.1.7-py3-none-any.whl (97 kB)
Collecting itsdangerous>=2.1.2
Using cached itsdangerous-2.2.0-py3-none-any.whl (16 kB)
Requirement already satisfied: Jinja2>=3.1.2 in /home/opendevin/.local/lib/python3.10/site-packages (from flask) (3.1.3)
Requirement already satisfied: MarkupSafe>=2.0 in /home/opendevin/.local/lib/python3.10/site-packages (from Jinja2>=3.1.2->flask) (2.1.5)
Installing collected packages: Werkzeug, itsdangerous, click, blinker, flask
Successfully installed Werkzeug-3.0.2 blinker-1.7.0 click-8.1.7 flask-3.0.3 itsdangerous-2.2.0
ASSISTANT:
Now that Flask is installed, let me run the Python file again:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
Observation:
[1] 124
ASSISTANT:
Let me check the server log again:
<execute_bash>
cat server.log
</execute_bash>
USER:
Observation:
* Serving Flask app 'app'
* Debug mode: off
WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
* Running on http://127.0.0.1:5000
Press CTRL+C to quit
ASSISTANT:
The server is running on port 5000 with PID 124. You can access the list of numbers by visiting http://127.0.0.1:5000. If you have any further questions, feel free to ask!
USER: Now kill the server, make it display the numbers in a table format.
ASSISTANT:
Sure! Let me stop the server first:
<execute_bash>
kill 124
</execute_bash>
USER:
Observation:
[1]+ Terminated python3 app.py > server.log 2>&1
ASSISTANT:
The server has been stopped. Let me open the Python file and modify it.
<execute_bash>
open app.py
</execute_bash>
USER:
[File: /workspace/app.py (11 lines total)]
1:
2:from flask import Flask
3:app = Flask(__name__)
4:
5:@app.route('/')
6:def index():
7: numbers = list(range(1, 11))
8: return str(numbers)
9:
10:if __name__ == '__main__':
11: app.run(port=5000)
ASSISTANT:
I should edit the file to display the numbers in a table format. I should include correct indentation. Let me update the file:
<execute_bash>
edit 8:8
return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
end_of_edit
</execute_bash>
USER:
Observation:
[File: /workspace/app.py (11 lines total)]
1:
2:from flask import Flask
3:app = Flask(__name__)
4:
5:@app.route('/')
6:def index():
7: numbers = list(range(1, 11))
8: return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
9:
10:if __name__ == '__main__':
11: app.run(port=5000)
File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.
ASSISTANT:
The file has been updated. Let me run the Python file again with the new changes:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
Observation:
[1] 126
ASSISTANT:
The server is running on port 5000 with PID 126. You can access the list of numbers in a table format by visiting http://127.0.0.1:5000. Free free to let me know if you have any further requests!
--- END OF EXAMPLE ---
NOW, LET'S START!
----------
Fix typos in bad.txt. Do not ask me for confirmation at any point.
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
----------
Let's start by opening the file `bad.txt` to identify and fix the typos. Let me open the file for you:
<execute_bash>
open bad.txt
</execute_bash>
----------
OBSERVATION:
-bash: open: command not found
[Command -1 finished with exit code 127]]
ENVIRONMENT REMINDER: You have 97 turns left to complete the task.
----------
It seems that the `open` command is not available in this environment. Let's try to read the content of the file `bad.txt` to identify the typos. Let me display the content of the file for you:
<execute_bash>
cat bad.txt
</execute_bash>
----------
OBSERVATION:
This is a stupid typoo.
Really?
No mor typos!
Enjoy!
[Command -1 finished with exit code 0]]
ENVIRONMENT REMINDER: You have 96 turns left to complete the task.
----------
I have displayed the content of the file `bad.txt` and identified the typos. Let's proceed to fix the typos in the file. I will edit the file to correct the typos:
<execute_bash>
edit 1:4
This is a stupid typo.
Really?
No more typos!
Enjoy!
end_of_edit
</execute_bash>
----------
OBSERVATION:
> > > > > -bash: edit: command not found
[Command -1 finished with exit code 127]]
ENVIRONMENT REMINDER: You have 95 turns left to complete the task.
----------
It seems that the `edit` command is not available in this environment as well. Let's try a different approach to fix the typos in the file `bad.txt`. I will overwrite the content of the file with the corrected text:
<execute_bash>
echo "This is a stupid typo.
Really?
No more typos!
Enjoy!" > bad.txt
</execute_bash>
----------
OBSERVATION:
> > >
[Command -1 finished with exit code 0]]
ENVIRONMENT REMINDER: You have 94 turns left to complete the task.

View File

@ -1,4 +1,3 @@
To fix typos in a file without asking for confirmation, we can use the `sed` command in bash to replace the typos. Let's go ahead and fix the typos in `bad.txt` without any confirmation prompts.
Let's start by opening the file `bad.txt` to identify and fix the typos. Let me open the file for you:
<execute_bash>
cat bad.txt
open bad.txt

View File

@ -1,5 +1,3 @@
Great! Let's use the `sed` command to fix the typos in the `bad.txt` file without any confirmation prompts.
It seems that the `open` command is not available in this environment. Let's try to read the content of the file `bad.txt` to identify the typos. Let me display the content of the file for you:
<execute_bash>
sed -i 's/typoo/typo/g' bad.txt
sed -i 's/mor/more/g' bad.txt
cat bad.txt

View File

@ -1 +1,8 @@
The typos in the `bad.txt` file have been successfully fixed. If you need further assistance or have any more tasks, feel free to let me know!
I have displayed the content of the file `bad.txt` and identified the typos. Let's proceed to fix the typos in the file. I will edit the file to correct the typos:
<execute_bash>
edit 1:4
This is a stupid typo.
Really?
No more typos!
Enjoy!
end_of_edit

View File

@ -0,0 +1,6 @@
It seems that the `edit` command is not available in this environment as well. Let's try a different approach to fix the typos in the file `bad.txt`. I will overwrite the content of the file with the corrected text:
<execute_bash>
echo "This is a stupid typo.
Really?
No more typos!
Enjoy!" > bad.txt

View File

@ -0,0 +1 @@
The typos in the file `bad.txt` have been successfully fixed by overwriting the content with the corrected text. If you need any further assistance or have any more tasks, feel free to let me know!

View File

@ -220,4 +220,4 @@ NOW, LET'S START!
Use Jupyter IPython to write a text file containing 'hello world' to '/workspace/test.txt'. Do not ask me for confirmation at any point.
ENVIRONMENT REMINDER: You have 99 turns left to complete the task.
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.

View File

@ -220,7 +220,7 @@ NOW, LET'S START!
Use Jupyter IPython to write a text file containing 'hello world' to '/workspace/test.txt'. Do not ask me for confirmation at any point.
ENVIRONMENT REMINDER: You have 99 turns left to complete the task.
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
----------
@ -234,6 +234,6 @@ with open('/workspace/test.txt', 'w') as f:
----------
OBSERVATION:
[Code executed successfully with no output]
-bash: execute_cli: command not found
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
ENVIRONMENT REMINDER: You have 97 turns left to complete the task.

View File

@ -0,0 +1,255 @@
----------
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
The assistant can interact with an interactive Python (Jupyter Notebook) environment and receive the corresponding output when needed. The code should be enclosed using "<execute_ipython>" tag, for example:
<execute_ipython>
print("Hello World!")
</execute_ipython>
The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
The assistant should attempt fewer things at a time instead of putting too much commands OR code in one "execute" block.
The assistant can install Python packages through bash by <execute_bash> pip install [package needed] </execute_bash> and should always import packages and define variables before starting to use them.
The assistant should stop <execute> and provide an answer when they have already obtained the answer from the execution result.
If the assistant encounters an import error in IPython for a newly installed package, they should try to restart the kernel and import the package again. IPython kernel can be re-started by:
<execute_ipython>
import IPython
IPython.Application.instance().kernel.do_shutdown(True) # Restart the kernel
</execute_ipython>
Apart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:
open <path> [<line_number>] - opens the file at the given path in the editor. If line_number is provided, the window will be move to include that line
goto <line_number> - moves the window to show <line_number>
scroll_down - moves the window down {WINDOW} lines
scroll_up - moves the window down {WINDOW} lines
create <filename> - creates and opens a new file with the given name
search_dir <search_term> [<dir>] - searches for search_term in all files in dir. If dir is not provided, searches in the current directory
search_file <search_term> [<file>] - searches for search_term in file. If file is not provided, searches in the current open file
find_file <file_name> [<dir>] - finds all files with the given name in dir. If dir is not provided, searches in the current directory
edit <start_line>:<end_line>
<replacement_text>
end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again. Remember, the file must be open before editing.
Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line ' print(x)' you must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
The assistant's response should be concise, but do express their thoughts.
Try to include one of <execute_ipython> or <execute_bash> in each of your responses, unless it is a direct answer to a question OR a message to the user.
IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
----------
Here is an example of how you can interact with the environment for task solving:
--- START OF EXAMPLE ---
USER: Can you create a list of numbers from 1 to 10, and create a web page to display them at port 5000?
ASSISTANT:
Sure! Let me write the Python code for starting a web server and save it to a file `app.py`:
<execute_ipython>
CODE='''
from flask import Flask
app = Flask(__name__)
@app.route('/')
def index():
numbers = list(range(1, 11))
return str(numbers)
if __name__ == '__main__':
app.run(port=5000)
'''
with open('app.py', 'w') as f:
f.write(CODE)
</execute_ipython>
USER:
Observation:
[Code executed successfully with no output]
ASSISTANT:
I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
Observation:
[1] 121[1]+ Exit 1 python3 app.py > server.log 2>&1
ASSISTANT: Looks like the server is running with PID 121 then crashed. Let me check the server log:
<execute_bash>
cat server.log
</execute_bash>
USER:
Observation:
Traceback (most recent call last):
File "/workspace/app.py", line 2, in <module>
from flask import Flask
ModuleNotFoundError: No module named 'flask'
ASSISTANT:
It seems that Flask is not installed. Let me install Flask for you:
<execute_bash>
pip install flask
</execute_bash>
USER:
Observation:
Defaulting to user installation because normal site-packages is not writeable
Collecting flask
Using cached flask-3.0.3-py3-none-any.whl (101 kB)
Collecting blinker>=1.6.2
Using cached blinker-1.7.0-py3-none-any.whl (13 kB)
Collecting Werkzeug>=3.0.0
Using cached werkzeug-3.0.2-py3-none-any.whl (226 kB)
Collecting click>=8.1.3
Using cached click-8.1.7-py3-none-any.whl (97 kB)
Collecting itsdangerous>=2.1.2
Using cached itsdangerous-2.2.0-py3-none-any.whl (16 kB)
Requirement already satisfied: Jinja2>=3.1.2 in /home/opendevin/.local/lib/python3.10/site-packages (from flask) (3.1.3)
Requirement already satisfied: MarkupSafe>=2.0 in /home/opendevin/.local/lib/python3.10/site-packages (from Jinja2>=3.1.2->flask) (2.1.5)
Installing collected packages: Werkzeug, itsdangerous, click, blinker, flask
Successfully installed Werkzeug-3.0.2 blinker-1.7.0 click-8.1.7 flask-3.0.3 itsdangerous-2.2.0
ASSISTANT:
Now that Flask is installed, let me run the Python file again:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
Observation:
[1] 124
ASSISTANT:
Let me check the server log again:
<execute_bash>
cat server.log
</execute_bash>
USER:
Observation:
* Serving Flask app 'app'
* Debug mode: off
WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
* Running on http://127.0.0.1:5000
Press CTRL+C to quit
ASSISTANT:
The server is running on port 5000 with PID 124. You can access the list of numbers by visiting http://127.0.0.1:5000. If you have any further questions, feel free to ask!
USER: Now kill the server, make it display the numbers in a table format.
ASSISTANT:
Sure! Let me stop the server first:
<execute_bash>
kill 124
</execute_bash>
USER:
Observation:
[1]+ Terminated python3 app.py > server.log 2>&1
ASSISTANT:
The server has been stopped. Let me open the Python file and modify it.
<execute_bash>
open app.py
</execute_bash>
USER:
[File: /workspace/app.py (11 lines total)]
1:
2:from flask import Flask
3:app = Flask(__name__)
4:
5:@app.route('/')
6:def index():
7: numbers = list(range(1, 11))
8: return str(numbers)
9:
10:if __name__ == '__main__':
11: app.run(port=5000)
ASSISTANT:
I should edit the file to display the numbers in a table format. I should include correct indentation. Let me update the file:
<execute_bash>
edit 8:8
return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
end_of_edit
</execute_bash>
USER:
Observation:
[File: /workspace/app.py (11 lines total)]
1:
2:from flask import Flask
3:app = Flask(__name__)
4:
5:@app.route('/')
6:def index():
7: numbers = list(range(1, 11))
8: return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
9:
10:if __name__ == '__main__':
11: app.run(port=5000)
File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.
ASSISTANT:
The file has been updated. Let me run the Python file again with the new changes:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
Observation:
[1] 126
ASSISTANT:
The server is running on port 5000 with PID 126. You can access the list of numbers in a table format by visiting http://127.0.0.1:5000. Free free to let me know if you have any further requests!
--- END OF EXAMPLE ---
NOW, LET'S START!
----------
Use Jupyter IPython to write a text file containing 'hello world' to '/workspace/test.txt'. Do not ask me for confirmation at any point.
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
----------
To write 'hello world' to a text file named 'test.txt' in the '/workspace' directory without asking for confirmation, I will execute the following Python code:
<execute_ipython>
with open('/workspace/test.txt', 'w') as f:
f.write('hello world')
</execute_ipython>
----------
OBSERVATION:
-bash: execute_cli: command not found
ENVIRONMENT REMINDER: You have 97 turns left to complete the task.
----------
It seems there was an issue with the execution. Let me try running the code again to write 'hello world' to the text file 'test.txt' in the '/workspace' directory:
<execute_ipython>
with open('/workspace/test.txt', 'w') as f:
f.write('hello world')
</execute_ipython>
----------
OBSERVATION:
-bash: execute_cli: command not found
ENVIRONMENT REMINDER: You have 96 turns left to complete the task.

View File

@ -0,0 +1,271 @@
----------
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
The assistant can interact with an interactive Python (Jupyter Notebook) environment and receive the corresponding output when needed. The code should be enclosed using "<execute_ipython>" tag, for example:
<execute_ipython>
print("Hello World!")
</execute_ipython>
The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
The assistant should attempt fewer things at a time instead of putting too much commands OR code in one "execute" block.
The assistant can install Python packages through bash by <execute_bash> pip install [package needed] </execute_bash> and should always import packages and define variables before starting to use them.
The assistant should stop <execute> and provide an answer when they have already obtained the answer from the execution result.
If the assistant encounters an import error in IPython for a newly installed package, they should try to restart the kernel and import the package again. IPython kernel can be re-started by:
<execute_ipython>
import IPython
IPython.Application.instance().kernel.do_shutdown(True) # Restart the kernel
</execute_ipython>
Apart from the standard bash commands, you can also use the following special commands in <execute_bash> environment:
open <path> [<line_number>] - opens the file at the given path in the editor. If line_number is provided, the window will be move to include that line
goto <line_number> - moves the window to show <line_number>
scroll_down - moves the window down {WINDOW} lines
scroll_up - moves the window down {WINDOW} lines
create <filename> - creates and opens a new file with the given name
search_dir <search_term> [<dir>] - searches for search_term in all files in dir. If dir is not provided, searches in the current directory
search_file <search_term> [<file>] - searches for search_term in file. If file is not provided, searches in the current open file
find_file <file_name> [<dir>] - finds all files with the given name in dir. If dir is not provided, searches in the current directory
edit <start_line>:<end_line>
<replacement_text>
end_of_edit - replaces lines <start_line> through <end_line> (inclusive) with the given text in the open file. The replacement text is terminated by a line with only end_of_edit on it. All of the <replacement text> will be entered, so make sure your indentation is formatted properly. Python files will be checked for syntax errors after the edit. If the system detects a syntax error, the edit will not be executed. Simply try to edit the file again, but make sure to read the error message and modify the edit command you issue accordingly. Issuing the same command a second time will just lead to the same error message again. Remember, the file must be open before editing.
Please note that THE EDIT COMMAND REQUIRES PROPER INDENTATION. If you'd like to add the line ' print(x)' you must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
The assistant's response should be concise, but do express their thoughts.
Try to include one of <execute_ipython> or <execute_bash> in each of your responses, unless it is a direct answer to a question OR a message to the user.
IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
----------
Here is an example of how you can interact with the environment for task solving:
--- START OF EXAMPLE ---
USER: Can you create a list of numbers from 1 to 10, and create a web page to display them at port 5000?
ASSISTANT:
Sure! Let me write the Python code for starting a web server and save it to a file `app.py`:
<execute_ipython>
CODE='''
from flask import Flask
app = Flask(__name__)
@app.route('/')
def index():
numbers = list(range(1, 11))
return str(numbers)
if __name__ == '__main__':
app.run(port=5000)
'''
with open('app.py', 'w') as f:
f.write(CODE)
</execute_ipython>
USER:
Observation:
[Code executed successfully with no output]
ASSISTANT:
I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
Observation:
[1] 121[1]+ Exit 1 python3 app.py > server.log 2>&1
ASSISTANT: Looks like the server is running with PID 121 then crashed. Let me check the server log:
<execute_bash>
cat server.log
</execute_bash>
USER:
Observation:
Traceback (most recent call last):
File "/workspace/app.py", line 2, in <module>
from flask import Flask
ModuleNotFoundError: No module named 'flask'
ASSISTANT:
It seems that Flask is not installed. Let me install Flask for you:
<execute_bash>
pip install flask
</execute_bash>
USER:
Observation:
Defaulting to user installation because normal site-packages is not writeable
Collecting flask
Using cached flask-3.0.3-py3-none-any.whl (101 kB)
Collecting blinker>=1.6.2
Using cached blinker-1.7.0-py3-none-any.whl (13 kB)
Collecting Werkzeug>=3.0.0
Using cached werkzeug-3.0.2-py3-none-any.whl (226 kB)
Collecting click>=8.1.3
Using cached click-8.1.7-py3-none-any.whl (97 kB)
Collecting itsdangerous>=2.1.2
Using cached itsdangerous-2.2.0-py3-none-any.whl (16 kB)
Requirement already satisfied: Jinja2>=3.1.2 in /home/opendevin/.local/lib/python3.10/site-packages (from flask) (3.1.3)
Requirement already satisfied: MarkupSafe>=2.0 in /home/opendevin/.local/lib/python3.10/site-packages (from Jinja2>=3.1.2->flask) (2.1.5)
Installing collected packages: Werkzeug, itsdangerous, click, blinker, flask
Successfully installed Werkzeug-3.0.2 blinker-1.7.0 click-8.1.7 flask-3.0.3 itsdangerous-2.2.0
ASSISTANT:
Now that Flask is installed, let me run the Python file again:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
Observation:
[1] 124
ASSISTANT:
Let me check the server log again:
<execute_bash>
cat server.log
</execute_bash>
USER:
Observation:
* Serving Flask app 'app'
* Debug mode: off
WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
* Running on http://127.0.0.1:5000
Press CTRL+C to quit
ASSISTANT:
The server is running on port 5000 with PID 124. You can access the list of numbers by visiting http://127.0.0.1:5000. If you have any further questions, feel free to ask!
USER: Now kill the server, make it display the numbers in a table format.
ASSISTANT:
Sure! Let me stop the server first:
<execute_bash>
kill 124
</execute_bash>
USER:
Observation:
[1]+ Terminated python3 app.py > server.log 2>&1
ASSISTANT:
The server has been stopped. Let me open the Python file and modify it.
<execute_bash>
open app.py
</execute_bash>
USER:
[File: /workspace/app.py (11 lines total)]
1:
2:from flask import Flask
3:app = Flask(__name__)
4:
5:@app.route('/')
6:def index():
7: numbers = list(range(1, 11))
8: return str(numbers)
9:
10:if __name__ == '__main__':
11: app.run(port=5000)
ASSISTANT:
I should edit the file to display the numbers in a table format. I should include correct indentation. Let me update the file:
<execute_bash>
edit 8:8
return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
end_of_edit
</execute_bash>
USER:
Observation:
[File: /workspace/app.py (11 lines total)]
1:
2:from flask import Flask
3:app = Flask(__name__)
4:
5:@app.route('/')
6:def index():
7: numbers = list(range(1, 11))
8: return '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
9:
10:if __name__ == '__main__':
11: app.run(port=5000)
File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.
ASSISTANT:
The file has been updated. Let me run the Python file again with the new changes:
<execute_bash>
python3 app.py > server.log 2>&1 &
</execute_bash>
USER:
Observation:
[1] 126
ASSISTANT:
The server is running on port 5000 with PID 126. You can access the list of numbers in a table format by visiting http://127.0.0.1:5000. Free free to let me know if you have any further requests!
--- END OF EXAMPLE ---
NOW, LET'S START!
----------
Use Jupyter IPython to write a text file containing 'hello world' to '/workspace/test.txt'. Do not ask me for confirmation at any point.
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
----------
To write 'hello world' to a text file named 'test.txt' in the '/workspace' directory without asking for confirmation, I will execute the following Python code:
<execute_ipython>
with open('/workspace/test.txt', 'w') as f:
f.write('hello world')
</execute_ipython>
----------
OBSERVATION:
-bash: execute_cli: command not found
ENVIRONMENT REMINDER: You have 97 turns left to complete the task.
----------
It seems there was an issue with the execution. Let me try running the code again to write 'hello world' to the text file 'test.txt' in the '/workspace' directory:
<execute_ipython>
with open('/workspace/test.txt', 'w') as f:
f.write('hello world')
</execute_ipython>
----------
OBSERVATION:
-bash: execute_cli: command not found
ENVIRONMENT REMINDER: You have 96 turns left to complete the task.
----------
It seems there is still an issue with the execution. Let me try a different approach to write 'hello world' to the text file 'test.txt' in the '/workspace' directory:
<execute_bash>
echo "hello world" > /workspace/test.txt
</execute_bash>
----------
OBSERVATION:
[Command -1 finished with exit code 0]]
ENVIRONMENT REMINDER: You have 95 turns left to complete the task.

View File

@ -1 +1,5 @@
The text file 'test.txt' containing 'hello world' has been successfully created in the '/workspace' directory. If you need any further assistance or have any more tasks in mind, feel free to let me know!
It seems there was an issue with the execution. Let me try running the code again to write 'hello world' to the text file 'test.txt' in the '/workspace' directory:
<execute_ipython>
with open('/workspace/test.txt', 'w') as f:
f.write('hello world')

View File

@ -0,0 +1,4 @@
It seems there is still an issue with the execution. Let me try a different approach to write 'hello world' to the text file 'test.txt' in the '/workspace' directory:
<execute_bash>
echo "hello world" > /workspace/test.txt

View File

@ -0,0 +1 @@
The text 'hello world' has been successfully written to the file 'test.txt' in the '/workspace' directory. If you need any further assistance or have any more tasks in mind, feel free to let me know!

View File

@ -220,4 +220,4 @@ NOW, LET'S START!
Write a shell script 'hello.sh' that prints 'hello'. Do not ask me for confirmation at any point.
ENVIRONMENT REMINDER: You have 99 turns left to complete the task.
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.

View File

@ -220,12 +220,11 @@ NOW, LET'S START!
Write a shell script 'hello.sh' that prints 'hello'. Do not ask me for confirmation at any point.
ENVIRONMENT REMINDER: You have 99 turns left to complete the task.
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
----------
I will create a shell script named 'hello.sh' that prints 'hello' without asking for confirmation. Let's proceed with creating the script:
I will create a shell script named 'hello.sh' that prints 'hello' without asking for confirmation. Let me write the script for you:
<execute_bash>
echo "echo 'hello'" > hello.sh
</execute_bash>
@ -236,4 +235,4 @@ OBSERVATION:
[Command -1 finished with exit code 0]]
ENVIRONMENT REMINDER: You have 98 turns left to complete the task.
ENVIRONMENT REMINDER: You have 97 turns left to complete the task.

View File

@ -1,4 +1,3 @@
I will create a shell script named 'hello.sh' that prints 'hello' without asking for confirmation. Let's proceed with creating the script:
I will create a shell script named 'hello.sh' that prints 'hello' without asking for confirmation. Let me write the script for you:
<execute_bash>
echo "echo 'hello'" > hello.sh

View File

@ -1 +1 @@
The shell script 'hello.sh' has been successfully created. You can run this script to print 'hello'. If you have any more tasks or questions, feel free to let me know!
The shell script 'hello.sh' has been successfully created. You can run it to print 'hello'. If you have any more tasks or questions, feel free to ask!

View File

@ -350,7 +350,7 @@ Here are the possible actions:
* `command` - the command to run
* `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `command_id` - the ID of the background command to kill
* `browse` - opens a web page. Arguments:
* `url` - the URL to open
* `push` - Push a branch from the current repo to github:

View File

@ -366,7 +366,7 @@ Here are the possible actions:
* `command` - the command to run
* `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `command_id` - the ID of the background command to kill
* `browse` - opens a web page. Arguments:
* `url` - the URL to open
* `push` - Push a branch from the current repo to github:

View File

@ -383,7 +383,7 @@ Here are the possible actions:
* `command` - the command to run
* `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `command_id` - the ID of the background command to kill
* `browse` - opens a web page. Arguments:
* `url` - the URL to open
* `push` - Push a branch from the current repo to github:

View File

@ -350,7 +350,7 @@ Here are the possible actions:
* `command` - the command to run
* `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `command_id` - the ID of the background command to kill
* `browse` - opens a web page. Arguments:
* `url` - the URL to open
* `push` - Push a branch from the current repo to github:

View File

@ -367,7 +367,7 @@ Here are the possible actions:
* `command` - the command to run
* `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `command_id` - the ID of the background command to kill
* `browse` - opens a web page. Arguments:
* `url` - the URL to open
* `push` - Push a branch from the current repo to github:

View File

@ -80,7 +80,7 @@ It must be an object, and it must contain two fields:
* `command` - the command to run
* `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `command_id` - the ID of the background command to kill
* `browse` - opens a web page. Arguments:
* `url` - the URL to open
* `message` - make a plan, set a goal, or record your thoughts. Arguments:
@ -90,7 +90,7 @@ It must be an object, and it must contain two fields:
* `goal` - the goal of the task
* `subtasks` - a list of subtasks, each of which is a map with a `goal` key.
* `modify_task` - close a task. Arguments:
* `id` - the ID of the task to close
* `task_id` - the ID of the task to close
* `state` - set to 'in_progress' to start the task, 'completed' to finish it, 'verified' to assert that it was successful, 'abandoned' to give up on it permanently, or `open` to stop working on it for now.
* `finish` - if ALL of your tasks and subtasks have been verified or abandoned, and you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
@ -101,4 +101,3 @@ actions are all `message` actions, you should consider taking a different action
What is your next thought or action? Again, you must reply with JSON, and only with JSON.
Look at your last thought in the history above. What does it suggest? Don't think anymore--take action.

View File

@ -96,7 +96,7 @@ It must be an object, and it must contain two fields:
* `command` - the command to run
* `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `command_id` - the ID of the background command to kill
* `browse` - opens a web page. Arguments:
* `url` - the URL to open
* `message` - make a plan, set a goal, or record your thoughts. Arguments:
@ -106,7 +106,7 @@ It must be an object, and it must contain two fields:
* `goal` - the goal of the task
* `subtasks` - a list of subtasks, each of which is a map with a `goal` key.
* `modify_task` - close a task. Arguments:
* `id` - the ID of the task to close
* `task_id` - the ID of the task to close
* `state` - set to 'in_progress' to start the task, 'completed' to finish it, 'verified' to assert that it was successful, 'abandoned' to give up on it permanently, or `open` to stop working on it for now.
* `finish` - if ALL of your tasks and subtasks have been verified or abandoned, and you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.

View File

@ -113,7 +113,7 @@ It must be an object, and it must contain two fields:
* `command` - the command to run
* `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `command_id` - the ID of the background command to kill
* `browse` - opens a web page. Arguments:
* `url` - the URL to open
* `message` - make a plan, set a goal, or record your thoughts. Arguments:
@ -123,7 +123,7 @@ It must be an object, and it must contain two fields:
* `goal` - the goal of the task
* `subtasks` - a list of subtasks, each of which is a map with a `goal` key.
* `modify_task` - close a task. Arguments:
* `id` - the ID of the task to close
* `task_id` - the ID of the task to close
* `state` - set to 'in_progress' to start the task, 'completed' to finish it, 'verified' to assert that it was successful, 'abandoned' to give up on it permanently, or `open` to stop working on it for now.
* `finish` - if ALL of your tasks and subtasks have been verified or abandoned, and you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.

View File

@ -80,7 +80,7 @@ It must be an object, and it must contain two fields:
* `command` - the command to run
* `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `command_id` - the ID of the background command to kill
* `browse` - opens a web page. Arguments:
* `url` - the URL to open
* `message` - make a plan, set a goal, or record your thoughts. Arguments:
@ -90,7 +90,7 @@ It must be an object, and it must contain two fields:
* `goal` - the goal of the task
* `subtasks` - a list of subtasks, each of which is a map with a `goal` key.
* `modify_task` - close a task. Arguments:
* `id` - the ID of the task to close
* `task_id` - the ID of the task to close
* `state` - set to 'in_progress' to start the task, 'completed' to finish it, 'verified' to assert that it was successful, 'abandoned' to give up on it permanently, or `open` to stop working on it for now.
* `finish` - if ALL of your tasks and subtasks have been verified or abandoned, and you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
@ -101,4 +101,3 @@ actions are all `message` actions, you should consider taking a different action
What is your next thought or action? Again, you must reply with JSON, and only with JSON.
Look at your last thought in the history above. What does it suggest? Don't think anymore--take action.

View File

@ -19,14 +19,7 @@ track of your progress. Here's a JSON representation of your plan:
"id": "",
"goal": "",
"state": "open",
"subtasks": [
{
"id": "0",
"goal": "Create a shell script 'hello.sh' that prints 'hello'",
"state": "open",
"subtasks": []
}
]
"subtasks": []
}
@ -67,13 +60,21 @@ ten actions--more happened before that.
}
},
{
"action": "add_task",
"action": "write",
"args": {
"parent": "",
"goal": "Create a shell script 'hello.sh' that prints 'hello'",
"subtasks": [],
"path": "hello.sh",
"content": "#!/bin/bash\n\necho 'hello'",
"start": 0,
"end": -1,
"thought": ""
}
},
{
"observation": "write",
"content": "",
"extras": {
"path": "hello.sh"
}
}
]
@ -96,7 +97,7 @@ It must be an object, and it must contain two fields:
* `command` - the command to run
* `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `command_id` - the ID of the background command to kill
* `browse` - opens a web page. Arguments:
* `url` - the URL to open
* `message` - make a plan, set a goal, or record your thoughts. Arguments:
@ -106,7 +107,7 @@ It must be an object, and it must contain two fields:
* `goal` - the goal of the task
* `subtasks` - a list of subtasks, each of which is a map with a `goal` key.
* `modify_task` - close a task. Arguments:
* `id` - the ID of the task to close
* `task_id` - the ID of the task to close
* `state` - set to 'in_progress' to start the task, 'completed' to finish it, 'verified' to assert that it was successful, 'abandoned' to give up on it permanently, or `open` to stop working on it for now.
* `finish` - if ALL of your tasks and subtasks have been verified or abandoned, and you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
@ -116,4 +117,4 @@ actions are all `message` actions, you should consider taking a different action
What is your next thought or action? Again, you must reply with JSON, and only with JSON.
You should think about the next action to take.
You just changed a file. You should think about how it affects your plan.

View File

@ -1,136 +0,0 @@
----------
# Task
You're a diligent software engineer AI. You can't see, draw, or interact with a
browser, but you can read and write files, and you can run commands, and you can think.
You've been given the following task:
Write a shell script 'hello.sh' that prints 'hello'. Do not ask me for confirmation at any point.
## Plan
As you complete this task, you're building a plan and keeping
track of your progress. Here's a JSON representation of your plan:
{
"id": "",
"goal": "",
"state": "open",
"subtasks": [
{
"id": "0",
"goal": "Create a shell script 'hello.sh' that prints 'hello'",
"state": "open",
"subtasks": []
}
]
}
You're not currently working on any tasks. Your next action MUST be to mark a task as in_progress.
You're responsible for managing this plan and the status of tasks in
it, by using the `add_task` and `modify_task` actions described below.
If the History below contradicts the state of any of these tasks, you
MUST modify the task using the `modify_task` action described below.
Be sure NOT to duplicate any tasks. Do NOT use the `add_task` action for
a task that's already represented. Every task must be represented only once.
Tasks that are sequential MUST be siblings. They must be added in order
to their parent task.
If you mark a task as 'completed', 'verified', or 'abandoned',
all non-abandoned subtasks will be marked the same way.
So before closing a task this way, you MUST not only be sure that it has
been completed successfully--you must ALSO be sure that all its subtasks
are ready to be marked the same way.
If, and only if, ALL tasks have already been marked verified,
you MUST respond with the `finish` action.
## History
Here is a recent history of actions you've taken in service of this plan,
as well as observations you've made. This only includes the MOST RECENT
ten actions--more happened before that.
[
{
"action": "message",
"args": {
"content": "Write a shell script 'hello.sh' that prints 'hello'. Do not ask me for confirmation at any point.",
"wait_for_response": false
}
},
{
"action": "add_task",
"args": {
"parent": "",
"goal": "Create a shell script 'hello.sh' that prints 'hello'",
"subtasks": [],
"thought": ""
}
},
{
"action": "write",
"args": {
"path": "hello.sh",
"content": "echo 'hello'",
"start": 0,
"end": -1,
"thought": ""
}
},
{
"observation": "write",
"content": "",
"extras": {
"path": "hello.sh"
}
}
]
Your most recent action is at the bottom of that history.
## Action
What is your next thought or action? Your response must be in JSON format.
It must be an object, and it must contain two fields:
* `action`, which is one of the actions below
* `args`, which is a map of key-value pairs, specifying the arguments for that action
* `read` - reads the content of a file. Arguments:
* `path` - the path of the file to read
* `write` - writes the content to a file. Arguments:
* `path` - the path of the file to write
* `content` - the content to write to the file
* `run` - runs a command on the command line in a Linux shell. Arguments:
* `command` - the command to run
* `background` - if true, run the command in the background, so that other commands can be run concurrently. Useful for e.g. starting a server. You won't be able to see the logs. You don't need to end the command with `&`, just set this to true.
* `kill` - kills a background command
* `id` - the ID of the background command to kill
* `browse` - opens a web page. Arguments:
* `url` - the URL to open
* `message` - make a plan, set a goal, or record your thoughts. Arguments:
* `content` - the message to record
* `add_task` - add a task to your plan. Arguments:
* `parent` - the ID of the parent task (leave empty if it should go at the top level)
* `goal` - the goal of the task
* `subtasks` - a list of subtasks, each of which is a map with a `goal` key.
* `modify_task` - close a task. Arguments:
* `id` - the ID of the task to close
* `state` - set to 'in_progress' to start the task, 'completed' to finish it, 'verified' to assert that it was successful, 'abandoned' to give up on it permanently, or `open` to stop working on it for now.
* `finish` - if ALL of your tasks and subtasks have been verified or abandoned, and you're absolutely certain that you've completed your task and have tested your work, use the finish action to stop working.
You MUST take time to think in between read, write, run, browse, and recall actions--do this with the `message` action.
You should never act twice in a row without thinking. But if your last several
actions are all `message` actions, you should consider taking a different action.
What is your next thought or action? Again, you must reply with JSON, and only with JSON.
You just changed a file. You should think about how it affects your plan.

View File

@ -1,8 +1,7 @@
{
"action": "add_task",
"action": "write",
"args": {
"goal": "Create a shell script 'hello.sh' that prints 'hello'",
"parent": "",
"subtasks": []
"path": "hello.sh",
"content": "#!/bin/bash\n\necho 'hello'"
}
}

View File

@ -1,7 +1,3 @@
{
"action": "write",
"args": {
"path": "hello.sh",
"content": "echo 'hello'"
}
"action": "finish"
}

View File

@ -1,7 +0,0 @@
{
"action": "modify_task",
"args": {
"id": "0",
"state": "completed"
}
}

View File

@ -0,0 +1,199 @@
----------
SYSTEM INFO:
You am an autonomous coding agent, here to provide solutions for coding issues.
You have been designed to assist you with a wide range of programming tasks, from code editing and debugging to testing and deployment.
You have access to a variety of tools and commands that you can use to help you solve problems efficiently.
INSTRUCTIONS:
Now, you're going to solve this issue on your own. You can use any bash commands or custom commands you wish to complete your task. Edit all the files you need to and run any checks or tests that you want.
Remember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME. You should always wait for feedback after every command.
When you're satisfied with all of the changes you've made, you can indicate that you are done by running the exit command.
Note however that you cannot use any interactive session commands (e.g. python, vim, node) in this environment, but you can write scripts and run them. E.g. you can write a python script and then run it with `python <script_name>.py`.
NOTE ABOUT THE write COMMAND: Indentation really matters! When editing a file, make sure to insert appropriate indentation before each line!
IMPORTANT TIPS:
1. Reproduce the bug: Always start by trying to replicate the bug that the issue discusses. If the issue includes code for reproducing the bug, we recommend that you re-implement that in your environment and run it to ensure you can reproduce the bug. Then, start trying to fix it. When you think you've fixed the bug, re-run the bug reproduction script to make sure that the issue has indeed been resolved.
If the bug reproduction script does not print anything when it successfully runs, we recommend adding a print("Script completed successfully, no errors.") command at the end of the file, so that you can be sure the script ran fine all the way through.
2. Try different commands: If you run a command and it doesn't work, try running a different command. A command that did not work once will not work the second time unless you modify it.
3. Navigate large files: If you open a file and need to get to an area around a specific line that is not in the first 100 lines, say line 583, you would use the 'read' command like this: 'read <file> 583'. This is a much faster way to read through the file.
4. Handle input files: If the bug reproduction script requires inputting/reading a specific file, such as 'buggy-input.png', and you'd like to understand how to input that file, conduct a search in the existing repository code to see whether someone else has already done that. Do this by running the command: 'search_dir "buggy-input.png"'. If that doesn't work, use the Linux 'find' command.
5. Understand your context: Always make sure to look at the currently open file and the current working directory. The currently open file might be in a different directory than the working directory.
6. Verify your edits: When editing files, it is easy to accidentally specify a wrong line number or to write code with incorrect indentation. Always check the code after you issue an edit to make sure that it reflects what you wanted to accomplish. If it didn't, issue another command to fix it.
7. Thoroughly test your solution: After making any changes to fix a bug, be sure to thoroughly test your solution to ensure the bug has been resolved. Re-run the bug reproduction script and verify that the issue has been addressed.
DOCUMENTATION:
It is recommend that you use the commands provided for interacting with files and your directory because they have been specially built for you.
They will make it much easier for you to look at files and make changes. Using these commands will help you be better at your task.
You can open an file by using either the read or write operations.
- If a file already exists you should read it before making any changes. Use the `edit` command to make changes once you have read it.
- If you are creating a new file use the write command. Use the `edit` command to make changes once you have created the new file.
Commands:
exit - Executed when task is complete
read <file_name> [<start_line>] [<end_line>] - Shows a given file's contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. By default the whole file will be read.
write <file> <changes> [<start_line>] [<end_line>] - Modifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.
browse <url> - Returns the text version of any url, this can be useful to look up documentation or finding issues on github
scroll_up - Takes no arguments. This will scroll up and show you the 100 lines above your current lines
scroll_down - Takes no arguments. This will scroll down and show you the 100 lines below your current lines
edit <start_line> <end_line> <changes> - This will modify lines in the currently open file. use start_line and end_line to designate which lines to change and then write the multiline changes. Set end_line to -1 to denote the end of the file
goto <line_num> - This will take you directly to a line and show you the 100 lines below it.
<bash_command> <args> - You can use any bash command you need (cd, ls, rm, grep, dir, mv, wget, git, zip, etc.) with their arguments included
pip install <package> - You can use this to import python packages. Make sure you include the correct package name when using this command.
ls - Use the ls command to view all the files in your current directory, this is a good starting point.
NOT ALLOWED - You cannot use interactive commands like python or node
Custom bash commands:
None
The following commands require an open file to be used: edit, scroll_up, scroll_down, goto
To modify the current file use 'edit'. To move through the current file use 'goto' or 'scroll_up'/'scroll_down'
when using write and edit do not surround the code with any "" just write the code.
----------
These are your past 4 actions:
===== Previous Actions =====
Memory 0:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the code to the 'hello.sh' script that will print 'hello' without asking for confirmation. This involves editing the existing script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 1:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the code to the 'hello.sh' script that will print 'hello' without asking for confirmation. Since the script is already created and made executable, I should simply edit the script to include the command to print 'hello'.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 2:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the code to the 'hello.sh' script that will print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 3:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the command in the 'hello.sh' script to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
======= End Actions =======
Use these memories to provide additional context to the problem you are solving.
Remember that you have already completed these steps so you do not need to perform them again.
----------
RESPONSE FORMAT:
This is the format of the response you will make in order to solve the current issue.
You will be given multiple iterations to complete this task so break it into steps and solve them one by one.
Your output must contain the following:
- First, thoughts about what your next action should be and plan it out.
- You will have a memory of your thoughts so you can use this to remember things for the next step.
- Use your thoughts to think about what you are currently doing, what you have done on prior steps and how that relates to solving the problem.
- Second, create a piece of code that will execute your next action based on the thoughts you have.
- Remember that you can only have one action for each thought, do not include multiple actions.
Your code MUST be surrounded in triple back ticks EXACTLY like this:
```
<code>
```
Notes:
- Adhere to the format so that the program loop continues smoothly, it is very important to only give one command per output.
- DO NOT give more than one command within the triple backticks. This will just throw an error and nothing will happen as a result.
- Do not give multiple code blocks, if you do only the second one will be captured and run, this might give an error if the first one was necessary.
- To execute multiple commands you should write them down in your thoughts section so you can remember it on the next step and execute them then.
- The only commands you are not capable of executing are interactive commands like `python` or `node` by themselves.
- If you think that you have completed the task that has been given to you based on your previous actions and outputs then use ``` exit ``` as the command to let the system know that you are done.
- DO NOT make any copies of your previous memories those will be provided to you at each step, making copies just wastes time and energy. Think smarter not harder.
- The write and edit commands requires proper indentation in the content section ex. `write hw.py def hello():
print('Hello World')` this is how you would have to format your write command.
- The white spaces matter as the code changes will be added to the code so they must have proper syntax.
This is a template using the format described above
Items in <> are suggestions for you, fill them out based on the context of the problem you are solving.
[ FORMAT ]
Thoughts:
<Provide clear and concise thoughts on the next step to take, highlighting any important details or context that should be remembered.>
<You can use multiple lines to express your thoughts>
Action:
```
<command> <params>
```
[ END FORMAT ]
Do not provide anything extra just your thought and action.
You are currently trying to complete this task:
Write a shell script 'hello.sh' that prints 'hello'. Do not ask me for confirmation at any point.
CURRENT WORKSPACE:
Open File: hello.sh on line 0
You can use these commands with the current file:
Navigation: `scroll_up`, `scroll_down`, and `goto <line>`
Modification: `edit <start_line> <end_line> <changes>`
Keep all of the guidelines above in mind when you are thinking and making code.
Please come up with a thought and action based on your current task and latest steps.
Make sure that you do not repeat the same actions, there will not be any changes in result if you do not changes anything.
Be very strict about the formatting that you use and make sure you follow the guidelines.
NEVER output multiple commands. ONLY take ONE STEP at a time.
When you have completed your task run the "exit" command.
Begin with your thought about the next step and then come up with an action to perform your thought.

View File

@ -0,0 +1,291 @@
----------
SYSTEM INFO:
You am an autonomous coding agent, here to provide solutions for coding issues.
You have been designed to assist you with a wide range of programming tasks, from code editing and debugging to testing and deployment.
You have access to a variety of tools and commands that you can use to help you solve problems efficiently.
INSTRUCTIONS:
Now, you're going to solve this issue on your own. You can use any bash commands or custom commands you wish to complete your task. Edit all the files you need to and run any checks or tests that you want.
Remember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME. You should always wait for feedback after every command.
When you're satisfied with all of the changes you've made, you can indicate that you are done by running the exit command.
Note however that you cannot use any interactive session commands (e.g. python, vim, node) in this environment, but you can write scripts and run them. E.g. you can write a python script and then run it with `python <script_name>.py`.
NOTE ABOUT THE write COMMAND: Indentation really matters! When editing a file, make sure to insert appropriate indentation before each line!
IMPORTANT TIPS:
1. Reproduce the bug: Always start by trying to replicate the bug that the issue discusses. If the issue includes code for reproducing the bug, we recommend that you re-implement that in your environment and run it to ensure you can reproduce the bug. Then, start trying to fix it. When you think you've fixed the bug, re-run the bug reproduction script to make sure that the issue has indeed been resolved.
If the bug reproduction script does not print anything when it successfully runs, we recommend adding a print("Script completed successfully, no errors.") command at the end of the file, so that you can be sure the script ran fine all the way through.
2. Try different commands: If you run a command and it doesn't work, try running a different command. A command that did not work once will not work the second time unless you modify it.
3. Navigate large files: If you open a file and need to get to an area around a specific line that is not in the first 100 lines, say line 583, you would use the 'read' command like this: 'read <file> 583'. This is a much faster way to read through the file.
4. Handle input files: If the bug reproduction script requires inputting/reading a specific file, such as 'buggy-input.png', and you'd like to understand how to input that file, conduct a search in the existing repository code to see whether someone else has already done that. Do this by running the command: 'search_dir "buggy-input.png"'. If that doesn't work, use the Linux 'find' command.
5. Understand your context: Always make sure to look at the currently open file and the current working directory. The currently open file might be in a different directory than the working directory.
6. Verify your edits: When editing files, it is easy to accidentally specify a wrong line number or to write code with incorrect indentation. Always check the code after you issue an edit to make sure that it reflects what you wanted to accomplish. If it didn't, issue another command to fix it.
7. Thoroughly test your solution: After making any changes to fix a bug, be sure to thoroughly test your solution to ensure the bug has been resolved. Re-run the bug reproduction script and verify that the issue has been addressed.
DOCUMENTATION:
It is recommend that you use the commands provided for interacting with files and your directory because they have been specially built for you.
They will make it much easier for you to look at files and make changes. Using these commands will help you be better at your task.
You can open an file by using either the read or write operations.
- If a file already exists you should read it before making any changes. Use the `edit` command to make changes once you have read it.
- If you are creating a new file use the write command. Use the `edit` command to make changes once you have created the new file.
Commands:
exit - Executed when task is complete
read <file_name> [<start_line>] [<end_line>] - Shows a given file's contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. By default the whole file will be read.
write <file> <changes> [<start_line>] [<end_line>] - Modifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.
browse <url> - Returns the text version of any url, this can be useful to look up documentation or finding issues on github
scroll_up - Takes no arguments. This will scroll up and show you the 100 lines above your current lines
scroll_down - Takes no arguments. This will scroll down and show you the 100 lines below your current lines
edit <start_line> <end_line> <changes> - This will modify lines in the currently open file. use start_line and end_line to designate which lines to change and then write the multiline changes. Set end_line to -1 to denote the end of the file
goto <line_num> - This will take you directly to a line and show you the 100 lines below it.
<bash_command> <args> - You can use any bash command you need (cd, ls, rm, grep, dir, mv, wget, git, zip, etc.) with their arguments included
pip install <package> - You can use this to import python packages. Make sure you include the correct package name when using this command.
ls - Use the ls command to view all the files in your current directory, this is a good starting point.
NOT ALLOWED - You cannot use interactive commands like python or node
Custom bash commands:
None
The following commands require an open file to be used: edit, scroll_up, scroll_down, goto
To modify the current file use 'edit'. To move through the current file use 'goto' or 'scroll_up'/'scroll_down'
when using write and edit do not surround the code with any "" just write the code.
----------
These are your past 4 actions:
===== Previous Actions =====
Memory 0:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the code to the 'hello.sh' script that will print 'hello' without asking for confirmation. This involves editing the existing script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 1:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the code to the 'hello.sh' script that will print 'hello' without asking for confirmation. Since the script is already created and made executable, I should simply edit the script to include the command to print 'hello'.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 2:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the code to the 'hello.sh' script that will print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 3:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the command in the 'hello.sh' script to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
======= End Actions =======
Use these memories to provide additional context to the problem you are solving.
Remember that you have already completed these steps so you do not need to perform them again.
----------
RESPONSE FORMAT:
This is the format of the response you will make in order to solve the current issue.
You will be given multiple iterations to complete this task so break it into steps and solve them one by one.
Your output must contain the following:
- First, thoughts about what your next action should be and plan it out.
- You will have a memory of your thoughts so you can use this to remember things for the next step.
- Use your thoughts to think about what you are currently doing, what you have done on prior steps and how that relates to solving the problem.
- Second, create a piece of code that will execute your next action based on the thoughts you have.
- Remember that you can only have one action for each thought, do not include multiple actions.
Your code MUST be surrounded in triple back ticks EXACTLY like this:
```
<code>
```
Notes:
- Adhere to the format so that the program loop continues smoothly, it is very important to only give one command per output.
- DO NOT give more than one command within the triple backticks. This will just throw an error and nothing will happen as a result.
- Do not give multiple code blocks, if you do only the second one will be captured and run, this might give an error if the first one was necessary.
- To execute multiple commands you should write them down in your thoughts section so you can remember it on the next step and execute them then.
- The only commands you are not capable of executing are interactive commands like `python` or `node` by themselves.
- If you think that you have completed the task that has been given to you based on your previous actions and outputs then use ``` exit ``` as the command to let the system know that you are done.
- DO NOT make any copies of your previous memories those will be provided to you at each step, making copies just wastes time and energy. Think smarter not harder.
- The write and edit commands requires proper indentation in the content section ex. `write hw.py def hello():
print('Hello World')` this is how you would have to format your write command.
- The white spaces matter as the code changes will be added to the code so they must have proper syntax.
This is a template using the format described above
Items in <> are suggestions for you, fill them out based on the context of the problem you are solving.
[ FORMAT ]
Thoughts:
<Provide clear and concise thoughts on the next step to take, highlighting any important details or context that should be remembered.>
<You can use multiple lines to express your thoughts>
Action:
```
<command> <params>
```
[ END FORMAT ]
Do not provide anything extra just your thought and action.
You are currently trying to complete this task:
Write a shell script 'hello.sh' that prints 'hello'. Do not ask me for confirmation at any point.
CURRENT WORKSPACE:
Open File: hello.sh on line 0
You can use these commands with the current file:
Navigation: `scroll_up`, `scroll_down`, and `goto <line>`
Modification: `edit <start_line> <end_line> <changes>`
Keep all of the guidelines above in mind when you are thinking and making code.
Please come up with a thought and action based on your current task and latest steps.
Make sure that you do not repeat the same actions, there will not be any changes in result if you do not changes anything.
Be very strict about the formatting that you use and make sure you follow the guidelines.
NEVER output multiple commands. ONLY take ONE STEP at a time.
When you have completed your task run the "exit" command.
Begin with your thought about the next step and then come up with an action to perform your thought.
----------
You did not include any action to take in your most recent output:
===== Output ======
Thoughts:
I need to add the command in the 'hello.sh' script to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
I will edit the 'hello.sh' script to include the command to print 'hello' without asking for confirmation.
==== End Output ===
Remember these are the custom commands you can use:
DOCUMENTATION:
It is recommend that you use the commands provided for interacting with files and your directory because they have been specially built for you.
They will make it much easier for you to look at files and make changes. Using these commands will help you be better at your task.
You can open an file by using either the read or write operations.
- If a file already exists you should read it before making any changes. Use the `edit` command to make changes once you have read it.
- If you are creating a new file use the write command. Use the `edit` command to make changes once you have created the new file.
Commands:
exit - Executed when task is complete
read <file_name> [<start_line>] [<end_line>] - Shows a given file's contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. By default the whole file will be read.
write <file> <changes> [<start_line>] [<end_line>] - Modifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.
browse <url> - Returns the text version of any url, this can be useful to look up documentation or finding issues on github
scroll_up - Takes no arguments. This will scroll up and show you the 100 lines above your current lines
scroll_down - Takes no arguments. This will scroll down and show you the 100 lines below your current lines
edit <start_line> <end_line> <changes> - This will modify lines in the currently open file. use start_line and end_line to designate which lines to change and then write the multiline changes. Set end_line to -1 to denote the end of the file
goto <line_num> - This will take you directly to a line and show you the 100 lines below it.
<bash_command> <args> - You can use any bash command you need (cd, ls, rm, grep, dir, mv, wget, git, zip, etc.) with their arguments included
pip install <package> - You can use this to import python packages. Make sure you include the correct package name when using this command.
ls - Use the ls command to view all the files in your current directory, this is a good starting point.
NOT ALLOWED - You cannot use interactive commands like python or node
Custom bash commands:
None
The following commands require an open file to be used: edit, scroll_up, scroll_down, goto
To modify the current file use 'edit'. To move through the current file use 'goto' or 'scroll_up'/'scroll_down'
when using write and edit do not surround the code with any "" just write the code.
Lets try that again, it is very important that you adhere to the output format
This time, be sure to use the exact format below, replacing anything in <> with the appropriate value(s):
RESPONSE FORMAT:
This is the format of the response you will make in order to solve the current issue.
You will be given multiple iterations to complete this task so break it into steps and solve them one by one.
Your output must contain the following:
- First, thoughts about what your next action should be and plan it out.
- You will have a memory of your thoughts so you can use this to remember things for the next step.
- Use your thoughts to think about what you are currently doing, what you have done on prior steps and how that relates to solving the problem.
- Second, create a piece of code that will execute your next action based on the thoughts you have.
- Remember that you can only have one action for each thought, do not include multiple actions.
Your code MUST be surrounded in triple back ticks EXACTLY like this:
```
<code>
```
Notes:
- Adhere to the format so that the program loop continues smoothly, it is very important to only give one command per output.
- DO NOT give more than one command within the triple backticks. This will just throw an error and nothing will happen as a result.
- Do not give multiple code blocks, if you do only the second one will be captured and run, this might give an error if the first one was necessary.
- To execute multiple commands you should write them down in your thoughts section so you can remember it on the next step and execute them then.
- The only commands you are not capable of executing are interactive commands like `python` or `node` by themselves.
- If you think that you have completed the task that has been given to you based on your previous actions and outputs then use ``` exit ``` as the command to let the system know that you are done.
- DO NOT make any copies of your previous memories those will be provided to you at each step, making copies just wastes time and energy. Think smarter not harder.
- The write and edit commands requires proper indentation in the content section ex. `write hw.py def hello():
print('Hello World')` this is how you would have to format your write command.
- The white spaces matter as the code changes will be added to the code so they must have proper syntax.
This is a template using the format described above
Items in <> are suggestions for you, fill them out based on the context of the problem you are solving.
[ FORMAT ]
Thoughts:
<Provide clear and concise thoughts on the next step to take, highlighting any important details or context that should be remembered.>
<You can use multiple lines to express your thoughts>
Action:
```
<command> <params>
```
[ END FORMAT ]
Do not provide anything extra just your thought and action.
It is crucial you use the format provided as the output will be parsed automatically.

View File

@ -0,0 +1,199 @@
----------
SYSTEM INFO:
You am an autonomous coding agent, here to provide solutions for coding issues.
You have been designed to assist you with a wide range of programming tasks, from code editing and debugging to testing and deployment.
You have access to a variety of tools and commands that you can use to help you solve problems efficiently.
INSTRUCTIONS:
Now, you're going to solve this issue on your own. You can use any bash commands or custom commands you wish to complete your task. Edit all the files you need to and run any checks or tests that you want.
Remember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME. You should always wait for feedback after every command.
When you're satisfied with all of the changes you've made, you can indicate that you are done by running the exit command.
Note however that you cannot use any interactive session commands (e.g. python, vim, node) in this environment, but you can write scripts and run them. E.g. you can write a python script and then run it with `python <script_name>.py`.
NOTE ABOUT THE write COMMAND: Indentation really matters! When editing a file, make sure to insert appropriate indentation before each line!
IMPORTANT TIPS:
1. Reproduce the bug: Always start by trying to replicate the bug that the issue discusses. If the issue includes code for reproducing the bug, we recommend that you re-implement that in your environment and run it to ensure you can reproduce the bug. Then, start trying to fix it. When you think you've fixed the bug, re-run the bug reproduction script to make sure that the issue has indeed been resolved.
If the bug reproduction script does not print anything when it successfully runs, we recommend adding a print("Script completed successfully, no errors.") command at the end of the file, so that you can be sure the script ran fine all the way through.
2. Try different commands: If you run a command and it doesn't work, try running a different command. A command that did not work once will not work the second time unless you modify it.
3. Navigate large files: If you open a file and need to get to an area around a specific line that is not in the first 100 lines, say line 583, you would use the 'read' command like this: 'read <file> 583'. This is a much faster way to read through the file.
4. Handle input files: If the bug reproduction script requires inputting/reading a specific file, such as 'buggy-input.png', and you'd like to understand how to input that file, conduct a search in the existing repository code to see whether someone else has already done that. Do this by running the command: 'search_dir "buggy-input.png"'. If that doesn't work, use the Linux 'find' command.
5. Understand your context: Always make sure to look at the currently open file and the current working directory. The currently open file might be in a different directory than the working directory.
6. Verify your edits: When editing files, it is easy to accidentally specify a wrong line number or to write code with incorrect indentation. Always check the code after you issue an edit to make sure that it reflects what you wanted to accomplish. If it didn't, issue another command to fix it.
7. Thoroughly test your solution: After making any changes to fix a bug, be sure to thoroughly test your solution to ensure the bug has been resolved. Re-run the bug reproduction script and verify that the issue has been addressed.
DOCUMENTATION:
It is recommend that you use the commands provided for interacting with files and your directory because they have been specially built for you.
They will make it much easier for you to look at files and make changes. Using these commands will help you be better at your task.
You can open an file by using either the read or write operations.
- If a file already exists you should read it before making any changes. Use the `edit` command to make changes once you have read it.
- If you are creating a new file use the write command. Use the `edit` command to make changes once you have created the new file.
Commands:
exit - Executed when task is complete
read <file_name> [<start_line>] [<end_line>] - Shows a given file's contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. By default the whole file will be read.
write <file> <changes> [<start_line>] [<end_line>] - Modifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.
browse <url> - Returns the text version of any url, this can be useful to look up documentation or finding issues on github
scroll_up - Takes no arguments. This will scroll up and show you the 100 lines above your current lines
scroll_down - Takes no arguments. This will scroll down and show you the 100 lines below your current lines
edit <start_line> <end_line> <changes> - This will modify lines in the currently open file. use start_line and end_line to designate which lines to change and then write the multiline changes. Set end_line to -1 to denote the end of the file
goto <line_num> - This will take you directly to a line and show you the 100 lines below it.
<bash_command> <args> - You can use any bash command you need (cd, ls, rm, grep, dir, mv, wget, git, zip, etc.) with their arguments included
pip install <package> - You can use this to import python packages. Make sure you include the correct package name when using this command.
ls - Use the ls command to view all the files in your current directory, this is a good starting point.
NOT ALLOWED - You cannot use interactive commands like python or node
Custom bash commands:
None
The following commands require an open file to be used: edit, scroll_up, scroll_down, goto
To modify the current file use 'edit'. To move through the current file use 'goto' or 'scroll_up'/'scroll_down'
when using write and edit do not surround the code with any "" just write the code.
----------
These are your past 4 actions:
===== Previous Actions =====
Memory 0:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the code to the 'hello.sh' script that will print 'hello' without asking for confirmation. Since the script is already created and made executable, I should simply edit the script to include the command to print 'hello'.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 1:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the code to the 'hello.sh' script that will print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 2:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the command in the 'hello.sh' script to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 3:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to edit the 'hello.sh' script to include the command to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
======= End Actions =======
Use these memories to provide additional context to the problem you are solving.
Remember that you have already completed these steps so you do not need to perform them again.
----------
RESPONSE FORMAT:
This is the format of the response you will make in order to solve the current issue.
You will be given multiple iterations to complete this task so break it into steps and solve them one by one.
Your output must contain the following:
- First, thoughts about what your next action should be and plan it out.
- You will have a memory of your thoughts so you can use this to remember things for the next step.
- Use your thoughts to think about what you are currently doing, what you have done on prior steps and how that relates to solving the problem.
- Second, create a piece of code that will execute your next action based on the thoughts you have.
- Remember that you can only have one action for each thought, do not include multiple actions.
Your code MUST be surrounded in triple back ticks EXACTLY like this:
```
<code>
```
Notes:
- Adhere to the format so that the program loop continues smoothly, it is very important to only give one command per output.
- DO NOT give more than one command within the triple backticks. This will just throw an error and nothing will happen as a result.
- Do not give multiple code blocks, if you do only the second one will be captured and run, this might give an error if the first one was necessary.
- To execute multiple commands you should write them down in your thoughts section so you can remember it on the next step and execute them then.
- The only commands you are not capable of executing are interactive commands like `python` or `node` by themselves.
- If you think that you have completed the task that has been given to you based on your previous actions and outputs then use ``` exit ``` as the command to let the system know that you are done.
- DO NOT make any copies of your previous memories those will be provided to you at each step, making copies just wastes time and energy. Think smarter not harder.
- The write and edit commands requires proper indentation in the content section ex. `write hw.py def hello():
print('Hello World')` this is how you would have to format your write command.
- The white spaces matter as the code changes will be added to the code so they must have proper syntax.
This is a template using the format described above
Items in <> are suggestions for you, fill them out based on the context of the problem you are solving.
[ FORMAT ]
Thoughts:
<Provide clear and concise thoughts on the next step to take, highlighting any important details or context that should be remembered.>
<You can use multiple lines to express your thoughts>
Action:
```
<command> <params>
```
[ END FORMAT ]
Do not provide anything extra just your thought and action.
You are currently trying to complete this task:
Write a shell script 'hello.sh' that prints 'hello'. Do not ask me for confirmation at any point.
CURRENT WORKSPACE:
Open File: hello.sh on line 0
You can use these commands with the current file:
Navigation: `scroll_up`, `scroll_down`, and `goto <line>`
Modification: `edit <start_line> <end_line> <changes>`
Keep all of the guidelines above in mind when you are thinking and making code.
Please come up with a thought and action based on your current task and latest steps.
Make sure that you do not repeat the same actions, there will not be any changes in result if you do not changes anything.
Be very strict about the formatting that you use and make sure you follow the guidelines.
NEVER output multiple commands. ONLY take ONE STEP at a time.
When you have completed your task run the "exit" command.
Begin with your thought about the next step and then come up with an action to perform your thought.

View File

@ -0,0 +1,199 @@
----------
SYSTEM INFO:
You am an autonomous coding agent, here to provide solutions for coding issues.
You have been designed to assist you with a wide range of programming tasks, from code editing and debugging to testing and deployment.
You have access to a variety of tools and commands that you can use to help you solve problems efficiently.
INSTRUCTIONS:
Now, you're going to solve this issue on your own. You can use any bash commands or custom commands you wish to complete your task. Edit all the files you need to and run any checks or tests that you want.
Remember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME. You should always wait for feedback after every command.
When you're satisfied with all of the changes you've made, you can indicate that you are done by running the exit command.
Note however that you cannot use any interactive session commands (e.g. python, vim, node) in this environment, but you can write scripts and run them. E.g. you can write a python script and then run it with `python <script_name>.py`.
NOTE ABOUT THE write COMMAND: Indentation really matters! When editing a file, make sure to insert appropriate indentation before each line!
IMPORTANT TIPS:
1. Reproduce the bug: Always start by trying to replicate the bug that the issue discusses. If the issue includes code for reproducing the bug, we recommend that you re-implement that in your environment and run it to ensure you can reproduce the bug. Then, start trying to fix it. When you think you've fixed the bug, re-run the bug reproduction script to make sure that the issue has indeed been resolved.
If the bug reproduction script does not print anything when it successfully runs, we recommend adding a print("Script completed successfully, no errors.") command at the end of the file, so that you can be sure the script ran fine all the way through.
2. Try different commands: If you run a command and it doesn't work, try running a different command. A command that did not work once will not work the second time unless you modify it.
3. Navigate large files: If you open a file and need to get to an area around a specific line that is not in the first 100 lines, say line 583, you would use the 'read' command like this: 'read <file> 583'. This is a much faster way to read through the file.
4. Handle input files: If the bug reproduction script requires inputting/reading a specific file, such as 'buggy-input.png', and you'd like to understand how to input that file, conduct a search in the existing repository code to see whether someone else has already done that. Do this by running the command: 'search_dir "buggy-input.png"'. If that doesn't work, use the Linux 'find' command.
5. Understand your context: Always make sure to look at the currently open file and the current working directory. The currently open file might be in a different directory than the working directory.
6. Verify your edits: When editing files, it is easy to accidentally specify a wrong line number or to write code with incorrect indentation. Always check the code after you issue an edit to make sure that it reflects what you wanted to accomplish. If it didn't, issue another command to fix it.
7. Thoroughly test your solution: After making any changes to fix a bug, be sure to thoroughly test your solution to ensure the bug has been resolved. Re-run the bug reproduction script and verify that the issue has been addressed.
DOCUMENTATION:
It is recommend that you use the commands provided for interacting with files and your directory because they have been specially built for you.
They will make it much easier for you to look at files and make changes. Using these commands will help you be better at your task.
You can open an file by using either the read or write operations.
- If a file already exists you should read it before making any changes. Use the `edit` command to make changes once you have read it.
- If you are creating a new file use the write command. Use the `edit` command to make changes once you have created the new file.
Commands:
exit - Executed when task is complete
read <file_name> [<start_line>] [<end_line>] - Shows a given file's contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. By default the whole file will be read.
write <file> <changes> [<start_line>] [<end_line>] - Modifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.
browse <url> - Returns the text version of any url, this can be useful to look up documentation or finding issues on github
scroll_up - Takes no arguments. This will scroll up and show you the 100 lines above your current lines
scroll_down - Takes no arguments. This will scroll down and show you the 100 lines below your current lines
edit <start_line> <end_line> <changes> - This will modify lines in the currently open file. use start_line and end_line to designate which lines to change and then write the multiline changes. Set end_line to -1 to denote the end of the file
goto <line_num> - This will take you directly to a line and show you the 100 lines below it.
<bash_command> <args> - You can use any bash command you need (cd, ls, rm, grep, dir, mv, wget, git, zip, etc.) with their arguments included
pip install <package> - You can use this to import python packages. Make sure you include the correct package name when using this command.
ls - Use the ls command to view all the files in your current directory, this is a good starting point.
NOT ALLOWED - You cannot use interactive commands like python or node
Custom bash commands:
None
The following commands require an open file to be used: edit, scroll_up, scroll_down, goto
To modify the current file use 'edit'. To move through the current file use 'goto' or 'scroll_up'/'scroll_down'
when using write and edit do not surround the code with any "" just write the code.
----------
These are your past 4 actions:
===== Previous Actions =====
Memory 0:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the code to the 'hello.sh' script that will print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 1:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the command in the 'hello.sh' script to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 2:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to edit the 'hello.sh' script to include the command to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 3:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the command in the 'hello.sh' script to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
======= End Actions =======
Use these memories to provide additional context to the problem you are solving.
Remember that you have already completed these steps so you do not need to perform them again.
----------
RESPONSE FORMAT:
This is the format of the response you will make in order to solve the current issue.
You will be given multiple iterations to complete this task so break it into steps and solve them one by one.
Your output must contain the following:
- First, thoughts about what your next action should be and plan it out.
- You will have a memory of your thoughts so you can use this to remember things for the next step.
- Use your thoughts to think about what you are currently doing, what you have done on prior steps and how that relates to solving the problem.
- Second, create a piece of code that will execute your next action based on the thoughts you have.
- Remember that you can only have one action for each thought, do not include multiple actions.
Your code MUST be surrounded in triple back ticks EXACTLY like this:
```
<code>
```
Notes:
- Adhere to the format so that the program loop continues smoothly, it is very important to only give one command per output.
- DO NOT give more than one command within the triple backticks. This will just throw an error and nothing will happen as a result.
- Do not give multiple code blocks, if you do only the second one will be captured and run, this might give an error if the first one was necessary.
- To execute multiple commands you should write them down in your thoughts section so you can remember it on the next step and execute them then.
- The only commands you are not capable of executing are interactive commands like `python` or `node` by themselves.
- If you think that you have completed the task that has been given to you based on your previous actions and outputs then use ``` exit ``` as the command to let the system know that you are done.
- DO NOT make any copies of your previous memories those will be provided to you at each step, making copies just wastes time and energy. Think smarter not harder.
- The write and edit commands requires proper indentation in the content section ex. `write hw.py def hello():
print('Hello World')` this is how you would have to format your write command.
- The white spaces matter as the code changes will be added to the code so they must have proper syntax.
This is a template using the format described above
Items in <> are suggestions for you, fill them out based on the context of the problem you are solving.
[ FORMAT ]
Thoughts:
<Provide clear and concise thoughts on the next step to take, highlighting any important details or context that should be remembered.>
<You can use multiple lines to express your thoughts>
Action:
```
<command> <params>
```
[ END FORMAT ]
Do not provide anything extra just your thought and action.
You are currently trying to complete this task:
Write a shell script 'hello.sh' that prints 'hello'. Do not ask me for confirmation at any point.
CURRENT WORKSPACE:
Open File: hello.sh on line 0
You can use these commands with the current file:
Navigation: `scroll_up`, `scroll_down`, and `goto <line>`
Modification: `edit <start_line> <end_line> <changes>`
Keep all of the guidelines above in mind when you are thinking and making code.
Please come up with a thought and action based on your current task and latest steps.
Make sure that you do not repeat the same actions, there will not be any changes in result if you do not changes anything.
Be very strict about the formatting that you use and make sure you follow the guidelines.
NEVER output multiple commands. ONLY take ONE STEP at a time.
When you have completed your task run the "exit" command.
Begin with your thought about the next step and then come up with an action to perform your thought.

View File

@ -0,0 +1,199 @@
----------
SYSTEM INFO:
You am an autonomous coding agent, here to provide solutions for coding issues.
You have been designed to assist you with a wide range of programming tasks, from code editing and debugging to testing and deployment.
You have access to a variety of tools and commands that you can use to help you solve problems efficiently.
INSTRUCTIONS:
Now, you're going to solve this issue on your own. You can use any bash commands or custom commands you wish to complete your task. Edit all the files you need to and run any checks or tests that you want.
Remember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME. You should always wait for feedback after every command.
When you're satisfied with all of the changes you've made, you can indicate that you are done by running the exit command.
Note however that you cannot use any interactive session commands (e.g. python, vim, node) in this environment, but you can write scripts and run them. E.g. you can write a python script and then run it with `python <script_name>.py`.
NOTE ABOUT THE write COMMAND: Indentation really matters! When editing a file, make sure to insert appropriate indentation before each line!
IMPORTANT TIPS:
1. Reproduce the bug: Always start by trying to replicate the bug that the issue discusses. If the issue includes code for reproducing the bug, we recommend that you re-implement that in your environment and run it to ensure you can reproduce the bug. Then, start trying to fix it. When you think you've fixed the bug, re-run the bug reproduction script to make sure that the issue has indeed been resolved.
If the bug reproduction script does not print anything when it successfully runs, we recommend adding a print("Script completed successfully, no errors.") command at the end of the file, so that you can be sure the script ran fine all the way through.
2. Try different commands: If you run a command and it doesn't work, try running a different command. A command that did not work once will not work the second time unless you modify it.
3. Navigate large files: If you open a file and need to get to an area around a specific line that is not in the first 100 lines, say line 583, you would use the 'read' command like this: 'read <file> 583'. This is a much faster way to read through the file.
4. Handle input files: If the bug reproduction script requires inputting/reading a specific file, such as 'buggy-input.png', and you'd like to understand how to input that file, conduct a search in the existing repository code to see whether someone else has already done that. Do this by running the command: 'search_dir "buggy-input.png"'. If that doesn't work, use the Linux 'find' command.
5. Understand your context: Always make sure to look at the currently open file and the current working directory. The currently open file might be in a different directory than the working directory.
6. Verify your edits: When editing files, it is easy to accidentally specify a wrong line number or to write code with incorrect indentation. Always check the code after you issue an edit to make sure that it reflects what you wanted to accomplish. If it didn't, issue another command to fix it.
7. Thoroughly test your solution: After making any changes to fix a bug, be sure to thoroughly test your solution to ensure the bug has been resolved. Re-run the bug reproduction script and verify that the issue has been addressed.
DOCUMENTATION:
It is recommend that you use the commands provided for interacting with files and your directory because they have been specially built for you.
They will make it much easier for you to look at files and make changes. Using these commands will help you be better at your task.
You can open an file by using either the read or write operations.
- If a file already exists you should read it before making any changes. Use the `edit` command to make changes once you have read it.
- If you are creating a new file use the write command. Use the `edit` command to make changes once you have created the new file.
Commands:
exit - Executed when task is complete
read <file_name> [<start_line>] [<end_line>] - Shows a given file's contents starting from <start_line> up to <end_line>. Default: start_line = 0, end_line = -1. By default the whole file will be read.
write <file> <changes> [<start_line>] [<end_line>] - Modifies a <file> by replacing the current lines between <start_line> and <end_line> with <changes>. Default start_line = 0 and end_line = -1. Calling this with no line args will replace the whole file.
browse <url> - Returns the text version of any url, this can be useful to look up documentation or finding issues on github
scroll_up - Takes no arguments. This will scroll up and show you the 100 lines above your current lines
scroll_down - Takes no arguments. This will scroll down and show you the 100 lines below your current lines
edit <start_line> <end_line> <changes> - This will modify lines in the currently open file. use start_line and end_line to designate which lines to change and then write the multiline changes. Set end_line to -1 to denote the end of the file
goto <line_num> - This will take you directly to a line and show you the 100 lines below it.
<bash_command> <args> - You can use any bash command you need (cd, ls, rm, grep, dir, mv, wget, git, zip, etc.) with their arguments included
pip install <package> - You can use this to import python packages. Make sure you include the correct package name when using this command.
ls - Use the ls command to view all the files in your current directory, this is a good starting point.
NOT ALLOWED - You cannot use interactive commands like python or node
Custom bash commands:
None
The following commands require an open file to be used: edit, scroll_up, scroll_down, goto
To modify the current file use 'edit'. To move through the current file use 'goto' or 'scroll_up'/'scroll_down'
when using write and edit do not surround the code with any "" just write the code.
----------
These are your past 4 actions:
===== Previous Actions =====
Memory 0:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the command in the 'hello.sh' script to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 1:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to edit the 'hello.sh' script to include the command to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 2:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the command in the 'hello.sh' script to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
Memory 3:
Previous Action:
action: write
args:
path: hello.sh
start: 0
end: -1
thought: Thoughts:
I need to add the command in the 'hello.sh' script to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
Output from Action:
observation: write
content:
extras:
path: hello.sh
======= End Actions =======
Use these memories to provide additional context to the problem you are solving.
Remember that you have already completed these steps so you do not need to perform them again.
----------
RESPONSE FORMAT:
This is the format of the response you will make in order to solve the current issue.
You will be given multiple iterations to complete this task so break it into steps and solve them one by one.
Your output must contain the following:
- First, thoughts about what your next action should be and plan it out.
- You will have a memory of your thoughts so you can use this to remember things for the next step.
- Use your thoughts to think about what you are currently doing, what you have done on prior steps and how that relates to solving the problem.
- Second, create a piece of code that will execute your next action based on the thoughts you have.
- Remember that you can only have one action for each thought, do not include multiple actions.
Your code MUST be surrounded in triple back ticks EXACTLY like this:
```
<code>
```
Notes:
- Adhere to the format so that the program loop continues smoothly, it is very important to only give one command per output.
- DO NOT give more than one command within the triple backticks. This will just throw an error and nothing will happen as a result.
- Do not give multiple code blocks, if you do only the second one will be captured and run, this might give an error if the first one was necessary.
- To execute multiple commands you should write them down in your thoughts section so you can remember it on the next step and execute them then.
- The only commands you are not capable of executing are interactive commands like `python` or `node` by themselves.
- If you think that you have completed the task that has been given to you based on your previous actions and outputs then use ``` exit ``` as the command to let the system know that you are done.
- DO NOT make any copies of your previous memories those will be provided to you at each step, making copies just wastes time and energy. Think smarter not harder.
- The write and edit commands requires proper indentation in the content section ex. `write hw.py def hello():
print('Hello World')` this is how you would have to format your write command.
- The white spaces matter as the code changes will be added to the code so they must have proper syntax.
This is a template using the format described above
Items in <> are suggestions for you, fill them out based on the context of the problem you are solving.
[ FORMAT ]
Thoughts:
<Provide clear and concise thoughts on the next step to take, highlighting any important details or context that should be remembered.>
<You can use multiple lines to express your thoughts>
Action:
```
<command> <params>
```
[ END FORMAT ]
Do not provide anything extra just your thought and action.
You are currently trying to complete this task:
Write a shell script 'hello.sh' that prints 'hello'. Do not ask me for confirmation at any point.
CURRENT WORKSPACE:
Open File: hello.sh on line 0
You can use these commands with the current file:
Navigation: `scroll_up`, `scroll_down`, and `goto <line>`
Modification: `edit <start_line> <end_line> <changes>`
Keep all of the guidelines above in mind when you are thinking and making code.
Please come up with a thought and action based on your current task and latest steps.
Make sure that you do not repeat the same actions, there will not be any changes in result if you do not changes anything.
Be very strict about the formatting that you use and make sure you follow the guidelines.
NEVER output multiple commands. ONLY take ONE STEP at a time.
When you have completed your task run the "exit" command.
Begin with your thought about the next step and then come up with an action to perform your thought.

View File

@ -0,0 +1,5 @@
Thoughts:
I need to add the command in the 'hello.sh' script to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
I will edit the 'hello.sh' script to include the command to print 'hello' without asking for confirmation.

View File

@ -0,0 +1,7 @@
Thoughts:
I need to edit the 'hello.sh' script to include the command to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
```
edit 0 -1 "echo 'hello'"
```

View File

@ -0,0 +1,7 @@
Thoughts:
I need to add the command in the 'hello.sh' script to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
```
edit 0 -1 "echo 'hello'"
```

View File

@ -0,0 +1,7 @@
Thoughts:
I need to add the command in the 'hello.sh' script to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
```
edit 0 -1 "echo 'hello'"
```

View File

@ -0,0 +1,9 @@
Thoughts:
I need to add the command in the 'hello.sh' script to print 'hello' without asking for confirmation. Since the script is already created, made executable, and the initial content was added, I should now insert the command to print 'hello' into the script.
Action:
I will add the command to print 'hello' into the 'hello.sh' script.
```
edit 0 -1 "echo 'hello'"
```

View File

@ -64,7 +64,10 @@ def test_agent_reject_action_serialization_deserialization():
def test_cmd_kill_action_serialization_deserialization():
original_action_dict = {'action': 'kill', 'args': {'id': '1337', 'thought': ''}}
original_action_dict = {
'action': 'kill',
'args': {'command_id': '1337', 'thought': ''},
}
serialization_deserialization(original_action_dict, CmdKillAction)
@ -122,6 +125,6 @@ def test_add_task_action_serialization_deserialization():
def test_modify_task_action_serialization_deserialization():
original_action_dict = {
'action': 'modify_task',
'args': {'id': 1, 'state': 'Test state.', 'thought': ''},
'args': {'task_id': 1, 'state': 'Test state.', 'thought': ''},
}
serialization_deserialization(original_action_dict, ModifyTaskAction)