feat(runtime): defer the sandbox bring-up behind a DeferredSandboxSession when create_or_reuse is called with defer=True

This commit is contained in:
Ahmed Allam 2026-10-13 13:31:53 +00:00
parent d8c00a8f4e
commit d17713ea6d
3 changed files with 575 additions and 33 deletions

View file

@ -0,0 +1,255 @@
from __future__ import annotations
import asyncio
import contextlib
import logging
from pathlib import Path
from typing import TYPE_CHECKING, Any
from agents.sandbox.session.manager import Instrumentation
from agents.sandbox.session.sandbox_session import SandboxSession
from agents.sandbox.session.sandbox_session_state import SandboxSessionState
from agents.sandbox.snapshot import NoopSnapshot
if TYPE_CHECKING:
import io
from collections.abc import Sequence
from agents.sandbox.entries import BaseEntry
from agents.sandbox.manifest import Manifest
from agents.sandbox.materialization import MaterializedFile
from agents.sandbox.session.base_sandbox_session import BaseSandboxSession
from agents.sandbox.types import ExecResult, ExposedPortEndpoint, User
logger = logging.getLogger(__name__)
class _PendingSessionState(SandboxSessionState):
type: str = "pending"
class DeferredSandboxSession(SandboxSession):
def __init__(
self,
bring_up: asyncio.Task[tuple[Any, BaseSandboxSession]],
*,
manifest: Manifest,
exposed_ports: tuple[int, ...] = (),
) -> None:
self._bring_up = bring_up
self._pending_state: SandboxSessionState = _PendingSessionState(
snapshot=NoopSnapshot(id="pending"),
manifest=manifest,
exposed_ports=exposed_ports,
)
self._pending_limits: Any = None
self._pending_archive_limits: Any = None
self._resolved: BaseSandboxSession | None = None
self._client: Any = None
self._instrumentation: Instrumentation = Instrumentation()
self._seq = 0
@property
def pending(self) -> bool:
return self._resolved is None
@property
def bring_up(self) -> asyncio.Task[tuple[Any, BaseSandboxSession]]:
return self._bring_up
async def resolve(self) -> BaseSandboxSession:
if self._resolved is not None:
return self._resolved
client, session = await asyncio.shield(self._bring_up)
self._adopt(client, session)
return session
def _adopt(self, client: Any, session: BaseSandboxSession) -> None:
if self._resolved is not None:
return
self._client = client
self._resolved = session
self._inner = session
if self._pending_limits is not None:
session._set_concurrency_limits(self._pending_limits)
if self._pending_archive_limits is not None:
session._set_archive_limits(self._pending_archive_limits)
if self._pending_state.manifest != session.state.manifest:
session.state = session.state.model_copy(
update={"manifest": self._pending_state.manifest}
)
@property
def client(self) -> Any:
return self._client
@property
def state(self) -> SandboxSessionState:
if self._resolved is None:
return self._pending_state
return self._resolved.state
@state.setter
def state(self, value: SandboxSessionState) -> None:
if self._resolved is None:
self._pending_state = value
else:
self._resolved.state = value
def _set_concurrency_limits(self, limits: Any) -> None:
if self._resolved is None:
self._pending_limits = limits
else:
self._resolved._set_concurrency_limits(limits)
def _set_archive_limits(self, limits: Any) -> None:
if self._resolved is None:
self._pending_archive_limits = limits
else:
self._resolved._set_archive_limits(limits)
def _manifest_base_dir(self) -> Path:
if self._resolved is None:
return Path.cwd()
return self._resolved._manifest_base_dir()
def normalize_path(self, path: Path | str, *, for_write: bool = False) -> Path:
if self._resolved is None:
return Path(path)
return self._resolved.normalize_path(path, for_write=for_write)
def register_persist_workspace_skip_path(self, path: Path | str) -> Path:
if self._resolved is None:
return Path(path)
return self._resolved.register_persist_workspace_skip_path(path)
def supports_pty(self) -> bool:
return self._resolved.supports_pty() if self._resolved is not None else False
async def running(self) -> bool:
if self._resolved is None:
if not self._bring_up.done():
return True
return not self._bring_up.cancelled() and self._bring_up.exception() is None
return await self._resolved.running()
async def start(self) -> None:
if self._resolved is None:
return
await self._resolved.start()
async def stop(self) -> None:
if self._resolved is None:
return
await self._resolved.stop()
async def shutdown(self) -> None:
if self._resolved is None:
return
await self._resolved.shutdown()
async def aclose(self) -> None:
if self._resolved is None:
return
await self._resolved.aclose()
async def _validate_manifest_application(self, *, only_ephemeral: bool = False) -> None:
session = await self.resolve()
await session._validate_manifest_application(only_ephemeral=only_ephemeral)
async def apply_manifest(self, *, only_ephemeral: bool = False) -> Any:
session = await self.resolve()
return await session.apply_manifest(only_ephemeral=only_ephemeral)
async def _apply_entry_batch(
self,
entries: Sequence[tuple[Path, BaseEntry]],
*,
base_dir: Path,
) -> list[MaterializedFile]:
del base_dir
session = await self.resolve()
return await session._apply_entry_batch(entries, base_dir=session._manifest_base_dir())
async def exec(self, *command: str | Path, **kwargs: Any) -> ExecResult:
await self.resolve()
return await super().exec(*command, **kwargs)
async def ls(self, *args: Any, **kwargs: Any) -> Any:
await self.resolve()
return await super().ls(*args, **kwargs)
async def rm(self, *args: Any, **kwargs: Any) -> Any:
await self.resolve()
return await super().rm(*args, **kwargs)
async def mkdir(self, *args: Any, **kwargs: Any) -> Any:
await self.resolve()
return await super().mkdir(*args, **kwargs)
async def read(self, path: Path, *, user: str | User | None = None) -> io.IOBase:
await self.resolve()
return await super().read(path, user=user)
async def write(self, *args: Any, **kwargs: Any) -> Any:
await self.resolve()
return await super().write(*args, **kwargs)
async def resolve_exposed_port(self, port: int) -> ExposedPortEndpoint:
await self.resolve()
return await super().resolve_exposed_port(port)
async def _resolve_exposed_port(self, port: int) -> ExposedPortEndpoint:
session = await self.resolve()
return await session._resolve_exposed_port(port)
async def pty_exec_start(self, *args: Any, **kwargs: Any) -> Any:
await self.resolve()
return await super().pty_exec_start(*args, **kwargs)
async def pty_write_stdin(self, *args: Any, **kwargs: Any) -> Any:
await self.resolve()
return await super().pty_write_stdin(*args, **kwargs)
async def pty_terminate_all(self) -> None:
if self._resolved is None:
return
await super().pty_terminate_all()
async def persist_workspace(self) -> io.IOBase:
await self.resolve()
return await super().persist_workspace()
async def hydrate_workspace(self, data: io.IOBase) -> None:
await self.resolve()
await super().hydrate_workspace(data)
async def teardown(self) -> None:
if self._resolved is None:
self._bring_up.cancel()
with contextlib.suppress(BaseException):
client, session = await self._bring_up
self._adopt(client, session)
if self._resolved is None:
return
await self._client.delete(self._resolved)
class DeferredSandboxClient:
def __init__(self, session: DeferredSandboxSession) -> None:
self._session = session
def __getattr__(self, name: str) -> Any:
client = self._session.client
if client is None:
raise AttributeError(f"sandbox client unavailable before bring-up finishes ({name})")
return getattr(client, name)
async def delete(self, session: Any) -> None:
if isinstance(session, DeferredSandboxSession):
await session.teardown()
return
real = await self._session.resolve()
await self._session.client.delete(real if session is self._session else session)

View file

@ -19,6 +19,7 @@ from strix.config import load_settings
from strix.runtime.backends import backend_supports_bind_mounts, get_backend
from strix.runtime.caido_bootstrap import bootstrap_caido
from strix.runtime.caido_handle import CaidoBootstrapHandle
from strix.runtime.deferred_session import DeferredSandboxClient, DeferredSandboxSession
if TYPE_CHECKING:
@ -262,6 +263,7 @@ async def create_or_reuse(
local_sources: list[dict[str, Any]],
extra_files: list[dict[str, Any]] | None = None,
status_sink: StatusSink | None = None,
defer: bool = False,
) -> dict[str, Any]:
"""Return the existing session bundle for ``scan_id`` or create a new one.
@ -323,41 +325,61 @@ async def create_or_reuse(
backend_name,
image,
)
report("Starting sandbox container")
client, session = await backend(
image=image,
manifest=manifest,
exposed_ports=(_CONTAINER_CAIDO_PORT,),
bind_mounts=bind_mounts,
)
if extra_file_archive is not None:
report("Placing workspace files")
try:
await stage_extra_files(session, extra_file_archive)
except BaseException:
await _discard_session(client, session)
raise
report("Setting up the proxy")
caido_endpoint = await session.resolve_exposed_port(_CONTAINER_CAIDO_PORT)
scheme = "https" if caido_endpoint.tls else "http"
host_caido_url = f"{scheme}://{caido_endpoint.host}:{caido_endpoint.port}"
logger.debug("Caido host endpoint resolved: %s", host_caido_url)
# The Caido login + project setup polls the guest for a couple of seconds
# and nothing needs the client before the first proxy tool call, so it
# runs concurrently with the rest of scan start; consumers resolve the
# handle at first use (see CaidoBootstrapHandle).
caido_client = CaidoBootstrapHandle(
asyncio.create_task(
bootstrap_caido(
session,
host_url=host_caido_url,
container_url=container_caido_url,
),
name=f"caido-bootstrap-{scan_id}",
async def _bring_up() -> tuple[Any, Any]:
report("Starting sandbox container")
client, session = await backend(
image=image,
manifest=manifest,
exposed_ports=(_CONTAINER_CAIDO_PORT,),
bind_mounts=bind_mounts,
)
if extra_file_archive is not None:
report("Placing workspace files")
try:
await stage_extra_files(session, extra_file_archive)
except BaseException:
await _discard_session(client, session)
raise
return client, session
async def _caido(session: Any) -> Any:
report("Setting up the proxy")
caido_endpoint = await session.resolve_exposed_port(_CONTAINER_CAIDO_PORT)
scheme = "https" if caido_endpoint.tls else "http"
host_caido_url = f"{scheme}://{caido_endpoint.host}:{caido_endpoint.port}"
logger.debug("Caido host endpoint resolved: %s", host_caido_url)
return await bootstrap_caido(
session,
host_url=host_caido_url,
container_url=container_caido_url,
)
if defer:
bring_up = asyncio.create_task(_bring_up(), name=f"sandbox-bring-up-{scan_id}")
deferred = DeferredSandboxSession(
bring_up,
manifest=manifest,
exposed_ports=(_CONTAINER_CAIDO_PORT,),
)
async def _caido_when_up() -> Any:
return await _caido(await deferred.resolve())
bundle = {
"client": DeferredSandboxClient(deferred),
"session": deferred,
"caido_client": CaidoBootstrapHandle(
asyncio.create_task(_caido_when_up(), name=f"caido-bootstrap-{scan_id}")
),
}
_SESSION_CACHE[scan_id] = bundle
logger.info("Sandbox session for scan %s deferred and cached", scan_id)
return bundle
client, session = await _bring_up()
caido_client = CaidoBootstrapHandle(
asyncio.create_task(_caido(session), name=f"caido-bootstrap-{scan_id}")
)
bundle = {

View file

@ -0,0 +1,265 @@
from __future__ import annotations
import asyncio
import io
from dataclasses import dataclass
from pathlib import Path
from typing import TYPE_CHECKING, Any
import pytest
from agents.run_config import SandboxRunConfig
from agents.sandbox import SandboxAgent
from agents.sandbox.capabilities import Filesystem, Shell
from agents.sandbox.runtime_session_manager import SandboxRuntimeSessionManager
from strix.runtime import session_manager
from strix.runtime.backends import _BACKENDS, _BIND_MOUNT_BACKENDS, register_backend
from strix.runtime.deferred_session import DeferredSandboxClient, DeferredSandboxSession
if TYPE_CHECKING:
from collections.abc import Iterator
@dataclass
class _RuntimeSettings:
backend: str
@dataclass
class _Settings:
runtime: _RuntimeSettings
@dataclass
class _Endpoint:
host: str = "127.0.0.1"
port: int = 8080
tls: bool = False
@dataclass
class _ExecResult:
exit_code: int = 0
stdout: bytes = b""
stderr: bytes = b""
def ok(self) -> bool:
return self.exit_code == 0
class _State:
def __init__(self) -> None:
self.manifest: Any = None
self.session_id = "00000000-0000-4000-8000-000000000001"
def model_copy(self, *, update: dict[str, Any]) -> _State:
copy = _State()
copy.manifest = update.get("manifest", self.manifest)
return copy
class _Session:
def __init__(self) -> None:
self.state = _State()
self.execs: list[tuple[str, ...]] = []
self.writes: list[tuple[Path, bytes]] = []
self.limits: list[Any] = []
def _set_concurrency_limits(self, limits: Any) -> None:
self.limits.append(limits)
def _set_archive_limits(self, limits: Any) -> None:
self.limits.append(limits)
async def running(self) -> bool:
return True
async def resolve_exposed_port(self, _port: int) -> _Endpoint:
return _Endpoint()
async def exec(self, *argv: str, timeout: float | None = None, **_kw: Any) -> _ExecResult:
del timeout
self.execs.append(argv)
return _ExecResult()
async def write(self, path: Path, data: io.IOBase, **_kw: Any) -> None:
self.writes.append((path, data.read()))
class _Client:
def __init__(self) -> None:
self.deleted: list[Any] = []
async def delete(self, session: Any) -> None:
self.deleted.append(session)
async def _no_caido(*_args: Any, **_kwargs: Any) -> None:
return None
class _Backend:
def __init__(self, *, fail: bool = False) -> None:
self.gate = asyncio.Event()
self.calls = 0
self.fail = fail
self.client = _Client()
self.session = _Session()
async def __call__(self, **_kwargs: Any) -> tuple[Any, Any]:
self.calls += 1
await self.gate.wait()
if self.fail:
raise RuntimeError("bring-up exploded")
return self.client, self.session
@pytest.fixture
def backend(monkeypatch: pytest.MonkeyPatch, request: pytest.FixtureRequest) -> Iterator[_Backend]:
name = f"deferred-{request.node.name}"
fake = _Backend(fail="fail" in request.node.name)
register_backend(name, fake, supports_bind_mounts=True)
monkeypatch.setattr(session_manager, "bootstrap_caido", _no_caido)
monkeypatch.setattr(
session_manager, "load_settings", lambda: _Settings(runtime=_RuntimeSettings(backend=name))
)
yield fake
_BACKENDS.pop(name, None)
_BIND_MOUNT_BACKENDS.discard(name)
async def _create(scan_id: str, **kwargs: Any) -> dict[str, Any]:
return await session_manager.create_or_reuse(
scan_id, image="img", local_sources=[], defer=True, **kwargs
)
@pytest.mark.asyncio
async def test_deferred_bundle_returns_before_the_backend_finishes(backend: _Backend) -> None:
scan_id = "deferred-returns"
try:
bundle = await asyncio.wait_for(_create(scan_id), timeout=1)
session = bundle["session"]
assert isinstance(session, DeferredSandboxSession)
assert isinstance(bundle["client"], DeferredSandboxClient)
assert session.pending
await asyncio.sleep(0)
assert backend.calls == 1
assert await session.running()
assert session.state.manifest.environment.value["PYTHONUNBUFFERED"] == "1"
again = await session_manager.create_or_reuse(scan_id, image="img", local_sources=[])
assert again is bundle
assert backend.calls == 1
finally:
await session_manager.cleanup(scan_id)
@pytest.mark.asyncio
async def test_first_io_resolves_the_sandbox_then_delegates(backend: _Backend) -> None:
scan_id = "deferred-io"
try:
bundle = await _create(scan_id)
session = bundle["session"]
session._set_concurrency_limits("limits")
exec_task = asyncio.create_task(session.exec("echo", "hi"))
await asyncio.sleep(0.05)
assert not exec_task.done()
backend.gate.set()
result = await asyncio.wait_for(exec_task, timeout=1)
assert result.ok()
assert backend.session.execs == [("echo", "hi")]
assert not session.pending
assert backend.session.limits == ["limits"]
assert backend.session.state.manifest is session.state.manifest
await session.write(Path("/workspace/x"), io.BytesIO(b"data"))
assert backend.session.writes == [(Path("/workspace/x"), b"data")]
finally:
await session_manager.cleanup(scan_id)
assert backend.client.deleted == [backend.session]
@pytest.mark.asyncio
async def test_failed_bring_up_surfaces_on_first_io(backend: _Backend) -> None:
scan_id = "deferred-fail"
try:
bundle = await _create(scan_id)
session = bundle["session"]
backend.gate.set()
with pytest.raises(RuntimeError, match="bring-up exploded"):
await asyncio.wait_for(session.exec("true"), timeout=1)
assert not await session.running()
with pytest.raises(RuntimeError, match="bring-up exploded"):
await bundle["caido_client"].get()
finally:
await session_manager.cleanup(scan_id)
assert backend.client.deleted == []
@pytest.mark.asyncio
async def test_cleanup_while_pending_cancels_the_bring_up(backend: _Backend) -> None:
scan_id = "deferred-cancel"
bundle = await _create(scan_id)
session = bundle["session"]
await asyncio.wait_for(session_manager.cleanup(scan_id), timeout=1)
assert session.bring_up.cancelled()
assert backend.client.deleted == []
assert session_manager._SESSION_CACHE.get(scan_id) is None
@pytest.mark.asyncio
async def test_extra_files_are_staged_inside_the_deferred_bring_up(backend: _Backend) -> None:
scan_id = "deferred-extra"
try:
bundle = await _create(
scan_id,
extra_files=[{"workspace_path": "/workspace/.strix/notes.md", "content": "hi"}],
)
assert backend.session.writes == []
backend.gate.set()
await asyncio.wait_for(bundle["session"].resolve(), timeout=1)
assert len(backend.session.writes) == 1
assert backend.session.execs
finally:
await session_manager.cleanup(scan_id)
@pytest.mark.asyncio
async def test_default_path_still_blocks_until_the_sandbox_is_up(backend: _Backend) -> None:
scan_id = "deferred-off"
backend.gate.set()
try:
bundle = await session_manager.create_or_reuse(scan_id, image="img", local_sources=[])
assert bundle["session"] is backend.session
assert bundle["client"] is backend.client
finally:
await session_manager.cleanup(scan_id)
assert backend.client.deleted == [backend.session]
@pytest.mark.asyncio
async def test_sdk_session_prep_does_not_wait_for_the_bring_up(backend: _Backend) -> None:
scan_id = "deferred-sdk-prep"
try:
bundle = await _create(scan_id)
agent = SandboxAgent(
name="root", instructions="x", tools=[], capabilities=[Filesystem(), Shell()]
)
manager = SandboxRuntimeSessionManager(
starting_agent=agent,
sandbox_config=SandboxRunConfig(client=bundle["client"], session=bundle["session"]),
run_state=None,
)
session = await asyncio.wait_for(
manager.ensure_session(
agent=agent, capabilities=list(agent.capabilities), is_resumed_state=False
),
timeout=1,
)
assert session is bundle["session"]
assert session.pending
backend.gate.set()
await asyncio.wait_for(session.resolve(), timeout=1)
assert not session.pending
finally:
await session_manager.cleanup(scan_id)