User code no longer execs in the engine. A pool of persistent worker subprocesses speaks one JSON object per line; the controller installs a proxy as the node's function, so every execution path funnels through it and the pipeline is untouched. A crash costs one subprocess, a per-node timeout is a kill, and cancelling from the canvas is that same kill. The workers run a venv of the user's own on the data volume, filled from a pip manifest versioned beside the flows. Applying it retires the workers and rebuilds, so a package lands without restarting the engine. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017MeiWk3Yq12n2pTvnQWYvt
110 lines
3.4 KiB
Python
110 lines
3.4 KiB
Python
"""Python nodes run in a worker process, and stay there when things go wrong."""
|
|
|
|
import sys
|
|
import threading
|
|
import time
|
|
from collections.abc import Iterator
|
|
|
|
import pytest
|
|
|
|
from app.flow.workers import NodeCancelled, NodeTimeout, PythonWorkerPool
|
|
|
|
|
|
@pytest.fixture
|
|
def pool() -> Iterator[PythonWorkerPool]:
|
|
# One worker: a respawn is then provably the same slot coming back.
|
|
worker_pool = PythonWorkerPool(python=sys.executable, size=1)
|
|
worker_pool.start()
|
|
yield worker_pool
|
|
worker_pool.stop()
|
|
|
|
|
|
def run(pool: PythonWorkerPool, code: str, node: str = "demo", **kwargs):
|
|
return pool.run(
|
|
"demo", node, code, kwargs, {"factor": 2}, f"demo.{node}", timeout=5
|
|
)
|
|
|
|
|
|
def test_a_node_returns_its_value_and_what_it_printed(pool, capsys):
|
|
result = run(
|
|
pool,
|
|
"def process(value, params):\n"
|
|
" print('seen', value)\n"
|
|
" return {'out': value * params['factor']}\n",
|
|
value=21,
|
|
)
|
|
assert result == {"out": 42}
|
|
# The proxy writes them to stdout, which is where the engine's tee is.
|
|
assert "seen 21" in capsys.readouterr().out
|
|
|
|
|
|
def test_a_failure_keeps_its_class_and_points_at_the_node(pool):
|
|
with pytest.raises(Exception) as caught:
|
|
run(pool, "def process(params):\n raise ValueError('bad input')\n")
|
|
|
|
# The engine renders a node error as "<class>: <message>", so both have to
|
|
# survive the trip.
|
|
assert type(caught.value).__name__ == "ValueError"
|
|
assert str(caught.value) == "bad input"
|
|
assert "<node demo." in caught.value.remote_traceback
|
|
assert "ValueError: bad input" in caught.value.remote_traceback
|
|
|
|
|
|
def test_a_node_that_kills_its_worker_is_an_ordinary_error(pool):
|
|
with pytest.raises(Exception, match="worker died"):
|
|
run(pool, "import os\n\n\ndef process(params):\n os._exit(1)\n")
|
|
|
|
assert run(pool, "def process(params):\n return {'out': 1}\n") == {"out": 1}
|
|
|
|
|
|
def test_a_node_that_runs_too_long_is_killed_and_the_pool_recovers(pool):
|
|
started = time.monotonic()
|
|
with pytest.raises(NodeTimeout):
|
|
pool.run(
|
|
"demo",
|
|
"slow",
|
|
"import time\n\n\ndef process(params):\n time.sleep(30)\n",
|
|
{},
|
|
{},
|
|
"demo.slow",
|
|
timeout=1,
|
|
)
|
|
assert time.monotonic() - started < 10
|
|
|
|
# The killed worker's slot is refilled on the next call.
|
|
assert run(pool, "def process(params):\n return {'out': 2}\n") == {"out": 2}
|
|
|
|
|
|
def test_a_running_node_can_be_cancelled(pool):
|
|
def stop_it() -> None:
|
|
for _ in range(100):
|
|
if pool.cancel("demo.slow"):
|
|
return
|
|
time.sleep(0.05)
|
|
|
|
stopper = threading.Thread(target=stop_it)
|
|
stopper.start()
|
|
try:
|
|
with pytest.raises(NodeCancelled):
|
|
pool.run(
|
|
"demo",
|
|
"slow",
|
|
"import time\n\n\ndef process(params):\n time.sleep(30)\n",
|
|
{},
|
|
{},
|
|
"demo.slow",
|
|
timeout=30,
|
|
)
|
|
finally:
|
|
stopper.join()
|
|
|
|
|
|
def test_a_result_that_is_not_json_is_refused(pool):
|
|
with pytest.raises(Exception, match="cannot be sent back as JSON"):
|
|
run(pool, "def process(params):\n return {'out': {1, 2}}\n")
|
|
|
|
|
|
def test_compiling_reports_where_the_source_is_wrong(pool):
|
|
assert pool.compile("demo", "broken", "def process(params)\n return {}\n")
|
|
assert pool.compile("demo", "fine", "def process(params):\n return {}\n") is None
|