Mads Hvelplund
7141ccff62
* fix: resolve pre-commit check failures - Change RuntimeError to TypeError for type validation in report/writer.py - Update pyupgrade to v3.21.2 for Python 3.14 compatibility * chore: add pytest test infrastructure Mirror the layout introduced on feature/438-token_budget: pytest + pytest-asyncio dev deps, asyncio_mode auto, a tests.* mypy override, and pytest in the mypy pre-commit hook deps so the tests/ package type-checks. * feat: add --mount and large-target pre-flight for local repos (#492) Large local targets were copied into the sandbox file-by-file via the SDK LocalDir entry, which stalls on big repos and could leave /workspace empty. - --mount <path> bind-mounts a host directory read-only at /workspace/<subdir> instead of copying it, bypassing the per-file stream. - A size pre-flight (STRIX_MAX_LOCAL_COPY_MB, default 1024) fails fast with a clear message suggesting --mount when a non-mounted local target is too big. * fix: reject empty --mount paths An empty or whitespace-only --mount value resolves to the current working directory and would silently bind-mount it into the sandbox. Reject it. * fix: dedupe local targets so a dir is never both copied and mounted If the same directory is passed via --target and --mount (or as duplicate values), it previously produced two targets — copied AND bind-mounted, and the copied one could trip the size pre-flight. Dedupe by resolved path, preferring the bind mount. * fix: treat non-positive STRIX_MAX_LOCAL_COPY_MB as disabled Previously a value of 0 (or negative) made every local target count as oversized, aborting all local scans. Now <= 0 disables the pre-flight. * fix: log unreadable subtrees during size pre-flight os.walk silently swallowed directory-listing errors, so a permission-denied subtree could make a large repo under-count and slip past the pre-flight. Surface such omissions via an onerror warning. * docs: document --mount and STRIX_MAX_LOCAL_COPY_MB Add CLI reference + example for --mount, document the size pre-flight env var, note the read-only-is-not-a-hard-boundary caveat and that remote repos are not size-checked, and clarify the backends docstring on when bind mounts apply. * Update strix/interface/main.py * Update strix/runtime/docker_client.py ---------
94 lines
3.1 KiB
Python
94 lines
3.1 KiB
Python
"""Sandbox backend registry — selected via STRIX_RUNTIME_BACKEND (default: docker)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from collections.abc import Awaitable, Callable
|
|
from typing import TYPE_CHECKING, Any
|
|
|
|
|
|
if TYPE_CHECKING:
|
|
from agents.sandbox.manifest import Manifest
|
|
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
SandboxBackend = Callable[..., Awaitable[tuple[Any, Any]]]
|
|
|
|
|
|
async def _docker_backend(
|
|
*,
|
|
image: str,
|
|
manifest: Manifest,
|
|
exposed_ports: tuple[int, ...],
|
|
bind_mounts: list[dict[str, Any]] | None = None,
|
|
) -> tuple[Any, Any]:
|
|
"""Bring up a session backed by the local Docker daemon.
|
|
|
|
Uses :class:`StrixDockerSandboxClient` to inject NET_ADMIN /
|
|
NET_RAW caps + ``host.docker.internal`` host-gateway. Imports
|
|
``docker`` lazily so deployments that target a non-Docker
|
|
backend don't need the docker-py library installed.
|
|
|
|
``session.start()`` is what materializes the manifest entries
|
|
(LocalDir copies and manifest-declared volume/FUSE mounts) into the
|
|
running container — the SDK's ``client.create()`` only builds the inner
|
|
session object without applying the manifest. ``async with session:``
|
|
would call it too, but Strix manages session lifetime explicitly via
|
|
``client.delete()`` so we trigger ``start()`` ourselves.
|
|
|
|
``bind_mounts`` are host directories (e.g. large repos passed via
|
|
``--mount``) bind-mounted read-only; unlike manifest entries they are
|
|
applied by Docker at container-create time, not by ``start()``.
|
|
"""
|
|
import docker
|
|
from agents.sandbox.sandboxes.docker import DockerSandboxClientOptions
|
|
|
|
from strix.runtime.docker_client import StrixDockerSandboxClient
|
|
|
|
client = StrixDockerSandboxClient(docker.from_env())
|
|
client.strix_bind_mounts = bind_mounts or []
|
|
options = DockerSandboxClientOptions(image=image, exposed_ports=exposed_ports)
|
|
session = await client.create(options=options, manifest=manifest)
|
|
await session.start()
|
|
return client, session
|
|
|
|
|
|
_BACKENDS: dict[str, SandboxBackend] = {
|
|
"docker": _docker_backend,
|
|
}
|
|
|
|
|
|
def get_backend(name: str) -> SandboxBackend:
|
|
"""Return the backend factory for ``name`` or raise.
|
|
|
|
Args:
|
|
name: Backend identifier (e.g. ``"docker"``). Match is exact;
|
|
no fallback. Unknown values raise so config typos surface
|
|
immediately instead of silently picking a default.
|
|
"""
|
|
backend = _BACKENDS.get(name)
|
|
if backend is None:
|
|
supported = ", ".join(sorted(_BACKENDS))
|
|
raise ValueError(
|
|
f"Unknown STRIX_RUNTIME_BACKEND: {name!r} (supported: {supported})",
|
|
)
|
|
logger.debug("Selected sandbox backend: %s", name)
|
|
return backend
|
|
|
|
|
|
def register_backend(name: str, backend: SandboxBackend) -> None:
|
|
"""Register a custom backend under ``name``.
|
|
|
|
Intended for downstream users who ship their own runtime — register
|
|
before any ``session_manager.create_or_reuse`` call. Re-registering
|
|
an existing name overwrites the prior entry.
|
|
"""
|
|
_BACKENDS[name] = backend
|
|
logger.info("Registered sandbox backend: %s", name)
|
|
|
|
|
|
def supported_backends() -> list[str]:
|
|
return sorted(_BACKENDS)
|