strix/tests/test_deferred_session.py

283 lines
9 KiB
Python

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 _settle() -> None:
for _ in range(10):
await asyncio.sleep(0)
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 _settle()
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
backend.gate.set()
await _settle()
assert backend.client.deleted == [backend.session]
@pytest.mark.asyncio
async def test_cleanup_while_pending_ignores_a_failed_late_bring_up(backend: _Backend) -> None:
scan_id = "deferred-cancel-fail"
await _create(scan_id)
await asyncio.wait_for(session_manager.cleanup(scan_id), timeout=1)
backend.gate.set()
await _settle()
assert backend.client.deleted == []
@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)