PassthroughSandbox

Run commands and agent-written programs inside an operating-system boundary. See the guide.

class zett_agent.sandbox.passthrough.PassthroughSandbox(policy=None, *, memory_strategy=MemoryStrategy.AUTO)

Run commands with no isolation, behind the same interface as a real sandbox.

The policy is not enforced: the process can read and write whatever the user can and can use the network. What it still gives is everything the Sandbox interface promises around the process: the filtered environment, the time limit, the output cap, and stopping the whole process tree. That keeps a host's code identical on every platform, with isolated telling the truth about the boundary.

It is what create_sandbox() returns on a platform with no backend, which is Windows today, and it warns when it does. It is never chosen in place of a backend that exists but cannot run.

示例

Run with no isolation, deliberately:

sandbox = PassthroughSandbox()
result = await sandbox.run("echo hello")
assert not result.isolated

警告

This is not a sandbox. A command run through it has the full authority of the host process.

参数:

• policy (SandboxPolicy | None)

• memory_strategy (MemoryStrategy | str)

name: ClassVar[str] = 'passthrough'

Short stable name of the backend, reported in results.

isolated: ClassVar[bool] = False

Whether this backend enforces a boundary. False only for the backend that runs commands as they are.

check()

Always available.

返回类型:

None