[fix] restart gap

This commit is contained in:
Azamat 2026-04-02 23:39:25 +03:00
parent 770af1fe76
commit 50af62b3fb
10 changed files with 348 additions and 4 deletions

View file

@ -11,6 +11,7 @@ from adapter.config.model import AppConfig
from adapter.docker.runtime import DockerSandboxRuntime
from adapter.observability.factory import build_observability
from adapter.observability.runtime import ObservabilityRuntime
from adapter.sandbox.reconciliation import SandboxSessionReconciler
from repository.sandbox_lock import ProcessLocalSandboxLifecycleLocker
from repository.sandbox_session import InMemorySandboxSessionRepository
from usecase.interface import Clock
@ -34,6 +35,7 @@ class AppContainer:
observability: ObservabilityRuntime
repositories: AppRepositories
usecases: AppUsecases
sandbox_reconciler: SandboxSessionReconciler = field(repr=False)
_docker_client: DockerClient = field(repr=False)
_is_shutdown: bool = field(default=False, init=False, repr=False)
@ -80,6 +82,11 @@ def build_container(
sandbox_repository = InMemorySandboxSessionRepository()
sandbox_locker = ProcessLocalSandboxLifecycleLocker()
sandbox_runtime = DockerSandboxRuntime(app_config.sandbox, docker_client)
sandbox_reconciler = SandboxSessionReconciler(
state_source=sandbox_runtime,
registry=sandbox_repository,
logger=observability.logger,
)
repositories = AppRepositories(sandbox_session=sandbox_repository)
usecases = AppUsecases(
@ -105,5 +112,6 @@ def build_container(
observability=observability,
repositories=repositories,
usecases=usecases,
sandbox_reconciler=sandbox_reconciler,
_docker_client=docker_client,
)

View file

@ -11,6 +11,8 @@ from domain.error import SandboxError, SandboxStartError
from domain.sandbox import SandboxSession, SandboxStatus
from usecase.interface import SandboxRuntime
SANDBOX_LABELS = ('session_id', 'chat_id', 'expires_at')
class DockerSandboxRuntime(SandboxRuntime):
def __init__(
@ -69,6 +71,23 @@ class DockerSandboxRuntime(SandboxRuntime):
except DockerException as exc:
raise SandboxError('sandbox_stop_failed') from exc
def list_active_sessions(self) -> list[SandboxSession]:
try:
containers = self._client.containers.list(
filters={'label': list(SANDBOX_LABELS)}
)
except DockerException as exc:
raise SandboxError('sandbox_list_failed') from exc
sessions: list[SandboxSession] = []
for container in containers:
session = self._session_from_container(container)
if session is None:
continue
sessions.append(session)
return sessions
def _labels(
self,
session_id: UUID,
@ -120,5 +139,50 @@ class DockerSandboxRuntime(SandboxRuntime):
raise ValueError('invalid host path')
return host_path
def _session_from_container(self, container: object) -> SandboxSession | None:
container_id = str(getattr(container, 'id', '')).strip()
labels = getattr(container, 'labels', None)
if not container_id or not isinstance(labels, dict):
return None
try:
session_id = UUID(labels['session_id'])
chat_id = UUID(labels['chat_id'])
created_at = self._container_created_at(container)
expires_at = _parse_datetime(labels['expires_at'])
except (KeyError, TypeError, ValueError):
return None
return SandboxSession(
session_id=session_id,
chat_id=chat_id,
container_id=container_id,
status=SandboxStatus.RUNNING,
created_at=created_at,
expires_at=expires_at,
)
def _container_created_at(self, container: object) -> datetime:
attrs = getattr(container, 'attrs', None)
if not isinstance(attrs, dict):
reload_container = getattr(container, 'reload', None)
if callable(reload_container):
reload_container()
attrs = getattr(container, 'attrs', None)
if not isinstance(attrs, dict):
raise ValueError('invalid container attrs')
raw_created_at = attrs.get('Created')
if not isinstance(raw_created_at, str):
raise ValueError('invalid created_at')
return _parse_datetime(raw_created_at)
def _host_path(self, path_value: str) -> Path:
return Path(path_value).expanduser().resolve(strict=False)
def _parse_datetime(value: str) -> datetime:
normalized = f'{value[:-1]}+00:00' if value.endswith('Z') else value
return datetime.fromisoformat(normalized)

View file

@ -56,6 +56,8 @@ def _build_startup_handler(
if task is not None and not task.done():
return
await asyncio.to_thread(container.sandbox_reconciler.execute)
stop_event = asyncio.Event()
setattr(app.state, APP_CLEANUP_STOP_STATE, stop_event)
setattr(

View file

View file

@ -0,0 +1,39 @@
from dataclasses import dataclass
from typing import Protocol
from uuid import UUID
from domain.sandbox import SandboxSession
from usecase.interface import Logger
class SandboxSessionStateSource(Protocol):
def list_active_sessions(self) -> list[SandboxSession]: ...
class SandboxSessionRegistry(Protocol):
def replace_all(self, sessions: list[SandboxSession]) -> None: ...
@dataclass(frozen=True, slots=True)
class SandboxSessionReconciler:
state_source: SandboxSessionStateSource
registry: SandboxSessionRegistry
logger: Logger
def execute(self) -> list[SandboxSession]:
sessions_by_chat_id: dict[UUID, SandboxSession] = {}
for session in sorted(
self.state_source.list_active_sessions(),
key=lambda item: item.created_at,
):
sessions_by_chat_id[session.chat_id] = session
sessions = list(sessions_by_chat_id.values())
self.registry.replace_all(sessions)
self.logger.info(
'sandbox_reconciled',
attrs={
'session_count': len(sessions),
},
)
return sessions