Sandbox 模块¶

Sandbox模块提供了隔离环境以安全地运行代码。

公共接口¶

用户通常直接从agentscope_runtime.sandbox包导入的主要类：

BaseSandbox¶

class agentscope_runtime.sandbox.BaseSandbox(sandbox_id=None, timeout=3000, base_url=None, bearer_token=None)[source]

Bases: Sandbox

Parameters:

sandbox_id (str | None)
timeout (int)
base_url (str | None)
bearer_token (str | None)

__init__(sandbox_id=None, timeout=3000, base_url=None, bearer_token=None)[source]

Initialize the sandbox interface.

Parameters:

sandbox_id (str | None)
timeout (int)
base_url (str | None)
bearer_token (str | None)

run_ipython_cell(code)[source]

Parameters:: code (str)

run_shell_command(command)[source]

Parameters:: command (str)

BrowserSandbox¶

class agentscope_runtime.sandbox.BrowserSandbox(sandbox_id=None, timeout=3000, base_url=None, bearer_token=None)[source]

Bases: Sandbox

Parameters:

sandbox_id (str | None)
timeout (int)
base_url (str | None)
bearer_token (str | None)

__init__(sandbox_id=None, timeout=3000, base_url=None, bearer_token=None)[source]

Initialize the sandbox interface.

Parameters:

sandbox_id (str | None)
timeout (int)
base_url (str | None)
bearer_token (str | None)

property browser_ws

browser_close()[source]

browser_resize(width, height)[source]

Parameters:

width (int)
height (int)

browser_console_messages()[source]

browser_handle_dialog(accept, prompt_text='')[source]

Parameters:

accept (bool)
prompt_text (str)

browser_file_upload(paths)[source]

Parameters:: paths (list)

browser_press_key(key)[source]

Parameters:: key (str)

browser_navigate(url)[source]

Parameters:: url (str)

browser_navigate_back()[source]

browser_navigate_forward()[source]

browser_network_requests()[source]

browser_pdf_save(filename='')[source]

Parameters:: filename (str)

browser_take_screenshot(raw=False, filename='', element='', ref='')[source]

Parameters:

raw (bool)
filename (str)
element (str)
ref (str)

browser_snapshot()[source]

browser_click(element, ref)[source]

Parameters:

element (str)
ref (str)

browser_drag(start_element, start_ref, end_element, end_ref)[source]

Parameters:

start_element (str)
start_ref (str)
end_element (str)
end_ref (str)

browser_hover(element, ref)[source]

Parameters:

element (str)
ref (str)

browser_type(element, ref, text, submit=False, slowly=False)[source]

Parameters:

element (str)
ref (str)
text (str)
submit (bool)
slowly (bool)

browser_select_option(element, ref, values)[source]

Parameters:

element (str)
ref (str)
values (list)

browser_tab_list()[source]

browser_tab_new(url='')[source]

Parameters:: url (str)

browser_tab_select(index)[source]

Parameters:: index (int)

browser_tab_close(index=None)[source]

Parameters:: index (int | None)

browser_wait_for(time=None, text=None, text_gone=None)[source]

Parameters:

time (float | None)
text (str | None)
text_gone (str | None)

FilesystemSandbox¶

class agentscope_runtime.sandbox.FilesystemSandbox(sandbox_id=None, timeout=3000, base_url=None, bearer_token=None)[source]

Bases: Sandbox

Parameters:

sandbox_id (str | None)
timeout (int)
base_url (str | None)
bearer_token (str | None)

__init__(sandbox_id=None, timeout=3000, base_url=None, bearer_token=None)[source]

Initialize the sandbox interface.

Parameters:

sandbox_id (str | None)
timeout (int)
base_url (str | None)
bearer_token (str | None)

read_file(path)[source]

Parameters:: path (str)

read_multiple_files(paths)[source]

Parameters:: paths (list)

write_file(path, content)[source]

Parameters:

path (str)
content (str)

edit_file(path, edits, dry_run=False)[source]

Parameters:

path (str)
edits (list)
dry_run (bool)

create_directory(path)[source]

Parameters:: path (str)

list_directory(path)[source]

Parameters:: path (str)

directory_tree(path)[source]

Parameters:: path (str)

move_file(source, destination)[source]

Parameters:

source (str)
destination (str)

search_files(path, pattern, exclude_patterns=[])[source]

Parameters:

path (str)
pattern (str)
exclude_patterns (list)

get_file_info(path)[source]

Parameters:: path (str)

list_allowed_directories()[source]

TrainingSandbox¶

class agentscope_runtime.sandbox.TrainingSandbox(sandbox_id=None, timeout=3000, base_url=None, bearer_token=None, box_type=SandboxType.APPWORLD)[source]

Bases: Sandbox

Training Sandbox class for managing and executing training-related tasks.

This class provides methods to create, manage, and interact with training environment instances using specialized tool calls.

Parameters:

sandbox_id (str | None)
timeout (int)
base_url (str | None)
bearer_token (str | None)
box_type (SandboxType)

__init__(sandbox_id=None, timeout=3000, base_url=None, bearer_token=None, box_type=SandboxType.APPWORLD)[source]

Initialize the Training Sandbox.

Parameters:

sandbox_id (Optional[str]) – Unique identifier for the sandbox.
timeout (int) – Maximum time allowed for sandbox operations.
base_url (Optional[str]) – Base URL for sandbox API.
bearer_token (Optional[str]) – Authentication token for API access.
box_type (SandboxType)

create_instance(env_type, task_id, instance_id=None, params=None)[source]

Create a new instance of a training environment.

Parameters:

env_type (str) – Type of environment to create.
task_id (str) – Identifier for the specific task.
instance_id (str, optional) – Custom instance identifier.
params (Dict, optional) – Additional parameters for instance creation.

Returns:

The created instance details.

get_task_ids(env_type, split='train', params=None)[source]

Retrieve task identifiers for a specific environment.

Parameters:

env_type (str) – Type of environment.
split (str, optional) – Data split to retrieve tasks from. Defaults to “train”.
params (dict, optional) – Additional filtering parameters.

Returns:

List of task identifiers.

get_env_profile(env_type, split='train', params=None)[source]

Retrieve the environment profile.

Parameters:

env_type (str) – Type of environment.
split (str, optional) – Data split to retrieve profile from. Defaults to “train”.
params (dict, optional) – Additional profile retrieval parameters.

Returns:

Environment profile details.

step(instance_id, action=None, params=None)[source]

Execute a step in the training environment.

Parameters:

instance_id (str) – Identifier of the environment instance.
action (Dict, optional) – Action to be performed in the environment.
params (Dict, optional) – Additional step parameters.

Returns:

Result of the step execution.

Return type:

str

evaluate(instance_id, messages=None, params=None)[source]

Evaluate the performance of a training environment instance.

Parameters:

instance_id (str) – Identifier of the environment instance.
messages (Dict, optional) – Evaluation-related messages.
params (Dict, optional) – Additional evaluation parameters.

Returns:

Evaluation results.

release_instance(instance_id)[source]

Release a training environment instance.

Parameters:: instance_id (str) – Identifier of the instance to be released.
Returns:: Result of the instance release operation.