Files
app/backend/fluksio/__init__.py
T
stroblme 34243e6902 SDK: artifacts work outside a node, run --follow prints status and queue waits, fluksio cancel
save_artifact/load_artifact outside a node use the worker's own store code in
$FLUKSIO_ARTIFACT_DIR or <tmp>/fluksio-artifacts, so a node can be called by
hand. --follow prints status changes and each node's resource wait; the
placer's waiting snapshot now carries the run. fluksio cancel <run>...
2026-10-28 08:07:35 +01:00

101 lines
3.5 KiB
Python

"""The Fluksio engine, and the decorators that declare flows in your own code.
Two audiences, one import name. In a research repository, ``from fluksio
import Port, node, Flow`` is the authoring API: it says which of your existing
functions are nodes and which nodes make up a flow, and ``fluksio sync``
uploads what it finds. Those names come from :mod:`fluksio.sdk`, which imports
nothing but the standard library. ``FLOWS`` and ``build`` come with them, so a
test can check the declarations without an engine.
Inside a node, ``import fluksio`` is not this package at all: the worker
installs a reporter of its own under that name before any node code runs, so
what a node gets is :mod:`fluksio_worker.worker_main`'s ``emit`` and
``save_artifact`` — and inert copies of the decorators, since a module the
node imports may well declare them at its top. Everywhere else the functions
below stand in, so a node called directly — in a test, in a notebook — behaves
like the real one: ``emit`` does nothing and the artifact helpers use a local
directory.
Nothing is imported from the rest of the package here. Every ``from fluksio.x
import y`` in the engine passes through this module, and an import cycle or a
second of start-up cost would both begin here.
"""
import logging
import os
from importlib.metadata import PackageNotFoundError
from importlib.metadata import version as _version
from typing import Any
from fluksio.sdk import FLOWS, Flow, Port, build, node, use
try:
__version__ = _version("fluksio")
except PackageNotFoundError: # pragma: no cover - a checkout that was never installed
__version__ = "0.0.0+unknown"
__all__ = [
"FLOWS",
"Flow",
"Port",
"build",
"emit",
"load_artifact",
"node",
"save_artifact",
"use",
]
logger = logging.getLogger(__name__)
def emit(**ports: Any) -> None:
"""Publish values on a node's declared output ports, mid-run.
Outside a node there is nowhere to publish to, and this does nothing on
purpose: a node function called directly — in a test, in a notebook, under
a debugger — is ordinary Python, and having it die on a progress report
would defeat the point of the code staying yours.
"""
logger.debug("fluksio.emit(%s) outside a node", ", ".join(ports))
def _local_store() -> Any:
"""The worker's own artifact code, pointed at a directory of this machine.
``$FLUKSIO_ARTIFACT_DIR`` when it is set, which is how a worker finds the
engine's store, and a directory in the temporary location otherwise. The
references that come out are the ones a node gets inside the engine, so
what a node returns can be handed to the next one by hand.
"""
import tempfile
from pathlib import Path
from fluksio_worker.worker_main import ARTIFACT_DIR_ENV, _Reporter
os.environ.setdefault(
ARTIFACT_DIR_ENV, str(Path(tempfile.gettempdir()) / "fluksio-artifacts")
)
return _Reporter("fluksio")
def save_artifact(
source: Any,
name: str = "",
media_type: str = "application/octet-stream",
volatile: bool = False,
) -> dict[str, Any]:
"""Put bytes or a file in the artifact store and return a reference to them.
Outside a node the store is a local directory, see :func:`_local_store`.
"""
reference: dict[str, Any] = _local_store().save_artifact(
source, name, media_type, volatile
)
return reference
def load_artifact(ref: dict[str, Any]) -> str:
"""Fetch what an artifact reference points at, and return a path to it."""
return str(_local_store().load_artifact(ref))