stroblmeandClaude Opus 5
1f7c6646f1
A driver script died of one slow answer: httpx.ReadTimeout out of RunHandle.refresh() with a 30 s read timeout and no retry anywhere, which cost a sweep 78 of its 84 runs. - Split the timeout (5 s connect, 120 s read): a wrong URL fails at once, and a busy engine gets longer than the slowest thing it does on purpose (a 60 s compile, a 15 s rebuild wait). - Retry idempotent calls three times on a transport error or 502/503/504. 503 is the engine's own "ask again" — it is what RebuildBusy answers. - Submit carries a key the engine stores with the run, so a retry after a timeout returns that run instead of starting a second. A sweep keys every entry, so a half-created one recreates only what is missing. - wait() and --follow tolerate five failed polls in a row; a 404 still stops at once, because that is an answer rather than a gap. - CLI says "engine not answering" and names the run still on the engine, instead of printing a traceback. - runs: clamp the params column to 80 characters; events() takes the flow/since/until the endpoint already had; RunHandle.failures answers "what killed this run" from the run's own node rows. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
53 lines
1.6 KiB
TOML
53 lines
1.6 KiB
TOML
[project]
|
|
name = "fluksio-worker"
|
|
version = "0.1.4"
|
|
description = "Runs Fluksio nodes on a machine the engine cannot reach"
|
|
readme = "README.md"
|
|
license = "AGPL-3.0-or-later"
|
|
license-files = ["LICENSE"]
|
|
requires-python = ">=3.12"
|
|
authors = [{ name = "Fluksio", email = "stroblme@posteo.de" }]
|
|
keywords = ["automation", "workflow", "distributed", "worker", "gpu"]
|
|
classifiers = [
|
|
"Development Status :: 3 - Alpha",
|
|
"Intended Audience :: Developers",
|
|
"Intended Audience :: Science/Research",
|
|
"Operating System :: MacOS",
|
|
"Operating System :: POSIX :: Linux",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Programming Language :: Python :: 3.13",
|
|
"Topic :: Home Automation",
|
|
"Topic :: Scientific/Engineering",
|
|
"Topic :: System :: Distributed Computing",
|
|
]
|
|
dependencies = [
|
|
"websockets>=12",
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://fluksio.com"
|
|
Documentation = "https://docs.fluksio.com/code/workers/"
|
|
|
|
[project.scripts]
|
|
fluksio-worker = "fluksio_worker.agent:main"
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["fluksio_worker"]
|
|
|
|
[tool.ruff]
|
|
# The engine's config, so both distributions are linted the same way.
|
|
extend = "../backend/pyproject.toml"
|
|
|
|
[tool.ruff.lint.per-file-ignores]
|
|
# This one takes its own directory off sys.path before the rest of its imports
|
|
# run, which is the whole point of doing it there.
|
|
"fluksio_worker/worker_main.py" = ["E402"]
|
|
# Copied onto another machine it has no logger configured before it tells you
|
|
# the one dependency it is missing.
|
|
"fluksio_worker/agent.py" = ["T201"]
|