Compare commits

..
Author SHA1 Message Date
ChuckBuilds cf521bdfd8 fix(startup): warn when an installed systemd unit has drifted from the repo's
Nothing re-applies systemd units after the first install. `git pull` -- which
is what the web UI's update button runs -- brings a new template into the
checkout, but no code in web_interface/ or src/ copies it to
/etc/systemd/system, and nothing anywhere runs `systemctl daemon-reload`. The
unit that actually runs is whatever first_time_install.sh wrote on day one.

So every hardening added to a unit is inert on existing installs, silently.
Measured on a live rig:

    installed  /etc/systemd/system/ledmatrix.service   2026-08-06
    template   systemd/ledmatrix.service               2026-08-19
    contents                                           differ

with the practical result that the MemoryMax=85% the repo's template specifies
was not being enforced at all -- `systemctl show` reported
MemoryMax=infinity. Anyone reading the template would reasonably believe the
service was capped.

Startup now compares each installed unit against its substituted template and
warns when they differ, naming install_service.sh as the remedy.

A warning, not an error, and deliberately not a silent rewrite: editing files
under /etc and restarting services is the installer's job, not something a
display process should do to a machine while it is booting. Making it fatal
would also brick every development checkout whose unit is legitimately absent
or hand-edited.

Comparison ignores comments, blank lines and ordering. The template carries
explanatory comments the installed copy will not have, and systemd does not
care about order within a section, so a literal comparison would warn on every
boot and be ignored within a week.

Mutation-checked three ways: never reporting drift fails, making it fatal
fails, and -- after the first attempt missed it -- comparing raw text now fails
too. That last gap is worth noting: the comment-insensitivity tests originally
exercised the helper directly, so a comparison that stopped calling the helper
passed them all. The test that catches it goes through _validate_systemd_units.

29 startup-validator tests pass.
2026-08-20 00:48:06 -04:00
9 changed files with 206 additions and 48 deletions
Executable → Regular
View File
View File
View File
+68
View File
@@ -62,6 +62,9 @@ class StartupValidator:
# Validate plugins if plugin manager is available # Validate plugins if plugin manager is available
if self.plugin_manager: if self.plugin_manager:
self._validate_plugins() self._validate_plugins()
# Warn when the running systemd unit no longer matches the repo's
self._validate_systemd_units()
is_valid = len(self.errors) == 0 is_valid = len(self.errors) == 0
@@ -74,6 +77,71 @@ class StartupValidator:
return (is_valid, self.errors.copy(), self.warnings.copy()) return (is_valid, self.errors.copy(), self.warnings.copy())
#: Units this project installs, and where each is installed to.
_UNITS = (
("systemd/ledmatrix.service", "/etc/systemd/system/ledmatrix.service"),
("systemd/ledmatrix-web.service", "/etc/systemd/system/ledmatrix-web.service"),
)
def _validate_systemd_units(self) -> None:
"""Warn when an installed unit has drifted from the repo's template.
Nothing re-applies these after the first install. `git pull` -- which is
what the web UI's update button runs -- brings a new template into the
checkout, but nothing copies it to /etc/systemd/system and nothing runs
`systemctl daemon-reload`, so the unit that actually runs is whatever
first_time_install.sh wrote on day one.
That makes every hardening added to a unit inert on existing installs.
Measured on one rig: the installed unit was thirteen days older than the
repo's and differed in content, so a MemoryMax the repo had specified
was not being enforced at all -- `systemctl show` reported
MemoryMax=infinity.
A warning rather than an error, and certainly not a silent rewrite:
editing files under /etc and restarting services is the installer's job,
not something a display process should do to a machine while it boots.
The remedy is to re-run scripts/install/install_service.sh.
"""
try:
project_root = Path(__file__).resolve().parent.parent
for template_rel, installed_path in self._UNITS:
template = project_root / template_rel
installed = Path(installed_path)
if not template.is_file() or not installed.is_file():
continue
# The template carries placeholders the installer substitutes,
# so compare the substituted form rather than the raw file.
expected = template.read_text(encoding="utf-8")
expected = expected.replace("__PROJECT_ROOT_DIR__", str(project_root))
expected = expected.replace("__USER__", "root")
try:
actual = installed.read_text(encoding="utf-8")
except PermissionError:
continue
if self._unit_body(expected) != self._unit_body(actual):
self.warnings.append(
f"{installed.name} differs from {template_rel}; the "
"installed unit is not refreshed by an update, so "
"settings added to the template are not in effect. "
"Re-run scripts/install/install_service.sh to apply them."
)
except OSError as e:
self.logger.debug("Could not compare systemd units: %s", e)
@staticmethod
def _unit_body(text: str) -> str:
"""A unit's meaningful lines: no comments, no blanks, no ordering noise."""
lines = []
for line in text.splitlines():
line = line.strip()
if line and not line.startswith("#"):
lines.append(line)
return "\n".join(sorted(lines))
def _validate_config(self) -> None: def _validate_config(self) -> None:
"""Validate configuration files.""" """Validate configuration files."""
try: try:
Executable → Regular
View File
Executable → Regular
View File
+3 -37
View File
@@ -58,7 +58,7 @@ def repos(tmp_path):
def test_branch_with_upstream_uses_a_plain_pull(repos): def test_branch_with_upstream_uses_a_plain_pull(repos):
args, note, error = resolve_pull_command(str(repos)) args, note, error = resolve_pull_command(str(repos))
assert error is None assert error is None
assert args == ['git', 'pull', '--rebase', '--autostash'] assert args == ['git', 'pull', '--rebase']
assert note == '' assert note == ''
@@ -73,7 +73,7 @@ def test_branch_without_upstream_falls_back_to_origin_branch(repos):
args, note, error = resolve_pull_command(str(repos)) args, note, error = resolve_pull_command(str(repos))
assert error is None assert error is None
assert args == ['git', 'pull', '--rebase', '--autostash', 'origin', 'audit'] assert args == ['git', 'pull', '--rebase', 'origin', 'audit']
assert 'audit' in note assert 'audit' in note
@@ -155,7 +155,7 @@ def test_switching_attaches_tracking_so_pull_needs_no_fallback(repos):
args, note, error = resolve_pull_command(str(repos)) args, note, error = resolve_pull_command(str(repos))
assert error is None assert error is None
assert args == ['git', 'pull', '--rebase', '--autostash'] assert args == ['git', 'pull', '--rebase']
assert note == '' assert note == ''
@@ -200,37 +200,3 @@ def test_stash_option_lets_the_switch_through_and_keeps_the_work(repos):
assert _git('branch', '--show-current', cwd=repos).stdout.strip() == 'other' assert _git('branch', '--show-current', cwd=repos).stdout.strip() == 'other'
# The edit is not lost — it is on the stash. # The edit is not lost — it is on the stash.
assert 'switch to other' in _git('stash', 'list', cwd=repos).stdout assert 'switch to other' in _git('stash', 'list', cwd=repos).stdout
class TestInstallerDoesNotBlockTheUpdateButton:
"""first_time_install.sh chmods scripts that git tracked as 644.
With core.fileMode true -- the default on Linux -- that leaves five
permanently modified tracked files on every machine that ran the
installer, and `git pull --rebase` refuses to start:
error: cannot pull with rebase: You have unstaged changes.
Tracking them as executable makes the installer's chmod a no-op.
"""
CHMODDED = [
'first_time_install.sh',
'start_display.sh',
'stop_display.sh',
'scripts/install/install_service.sh',
'scripts/install/install_web_service.sh',
]
def test_scripts_the_installer_chmods_are_tracked_executable(self):
import subprocess
from pathlib import Path
root = Path(__file__).resolve().parent.parent
out = subprocess.run(['git', 'ls-files', '-s', *self.CHMODDED],
capture_output=True, text=True, cwd=str(root)).stdout
modes = {line.split()[3]: line.split()[0] for line in out.strip().split('\n') if line}
non_exec = sorted(f for f, m in modes.items() if m != '100755')
assert not non_exec, (
f"{non_exec} are chmodded by the installer but tracked non-executable, "
"so every install leaves the working tree dirty and the update "
"button cannot pull")
+133
View File
@@ -0,0 +1,133 @@
"""An installed unit that no longer matches the repo's must be reported.
Nothing re-applies systemd units after the first install. `git pull` -- what
the web UI's update button runs -- brings a new template into the checkout, but
no code in web_interface/ or src/ copies it to /etc/systemd/system or runs
`systemctl daemon-reload`. The unit that actually runs is whatever
first_time_install.sh wrote on day one.
So every hardening added to a unit is inert on existing installs. Measured on a
live rig: the installed unit was dated 2026-08-06 and the repo's 2026-08-19,
and they differed -- with the result that a MemoryMax=85% present in the repo's
template was not being enforced at all. `systemctl show` reported
MemoryMax=infinity.
This is a warning, not an error, and deliberately not a silent rewrite:
editing files under /etc and restarting services is the installer's job, not
something a display process should do to a machine while it boots.
"""
import logging
from pathlib import Path
from unittest.mock import MagicMock
import pytest
from src.startup_validator import StartupValidator
@pytest.fixture
def validator():
v = StartupValidator(config_manager=MagicMock())
v.logger = logging.getLogger("test")
v.warnings = []
v.errors = []
return v
def test_a_matching_unit_produces_no_warning(validator, tmp_path):
"""The installed unit, substituted exactly as the installer would."""
project_root = Path("src/startup_validator.py").resolve().parent.parent
template_rel = "systemd/ledmatrix.service"
template = project_root / template_rel
if not template.is_file():
pytest.skip("repo unit template not present")
installed = tmp_path / "ledmatrix.service"
installed.write_text(
template.read_text(encoding="utf-8")
.replace("__PROJECT_ROOT_DIR__", str(project_root))
.replace("__USER__", "root"),
encoding="utf-8")
validator._UNITS = ((template_rel, str(installed)),)
validator._validate_systemd_units()
assert not validator.warnings, f"a matching unit warned: {validator.warnings}"
assert not validator.errors
def test_comments_and_blank_lines_are_not_drift():
"""Otherwise every comment the repo adds would look like a changed unit."""
a = "[Service]\n# explains a setting\nExecStart=/x\nRestart=always\n"
b = "[Service]\nExecStart=/x\n\nRestart=always\n"
assert StartupValidator._unit_body(a) == StartupValidator._unit_body(b)
def test_a_changed_directive_is_drift():
a = "[Service]\nExecStart=/x\nMemoryMax=85%\n"
b = "[Service]\nExecStart=/x\n"
assert StartupValidator._unit_body(a) != StartupValidator._unit_body(b)
def test_reordered_directives_are_not_drift():
"""systemd does not care about order within a section, so neither should this."""
a = "[Service]\nExecStart=/x\nRestart=always\n"
b = "[Service]\nRestart=always\nExecStart=/x\n"
assert StartupValidator._unit_body(a) == StartupValidator._unit_body(b)
def test_cosmetic_differences_do_not_warn(validator, tmp_path):
"""Through the real comparison, not the helper.
The repo's template carries explanatory comments the installed copy may not
have, and the installer does not preserve ordering or blank lines. If those
counted as drift, every boot would warn and the warning would be ignored.
Asserting this on _unit_body alone would not catch a comparison that stopped
calling it -- which is exactly what a careless edit does.
"""
project_root = Path("src/startup_validator.py").resolve().parent.parent
template_rel = "systemd/ledmatrix.service"
template = project_root / template_rel
if not template.is_file():
pytest.skip("repo unit template not present")
substituted = (template.read_text(encoding="utf-8")
.replace("__PROJECT_ROOT_DIR__", str(project_root))
.replace("__USER__", "root"))
# Same directives, stripped of comments and blank lines and reordered.
directives = sorted(line.strip() for line in substituted.splitlines()
if line.strip() and not line.strip().startswith("#"))
installed = tmp_path / "ledmatrix.service"
installed.write_text("\n".join(reversed(directives)) + "\n", encoding="utf-8")
validator._UNITS = ((template_rel, str(installed)),)
validator._validate_systemd_units()
assert not validator.warnings, (
f"cosmetic-only difference reported as drift: {validator.warnings}")
def test_drift_is_reported_as_a_warning(validator, tmp_path):
"""The whole point: a real difference must surface, and only as a warning."""
installed = tmp_path / "ledmatrix.service"
installed.write_text("[Service]\nExecStart=/usr/bin/python3 /x/run.py\n")
project_root = Path("src/startup_validator.py").resolve().parent.parent
template_rel = "systemd/ledmatrix.service"
template = project_root / template_rel
if not template.is_file():
pytest.skip("repo unit template not present")
validator._UNITS = ((template_rel, str(installed)),)
validator._validate_systemd_units()
assert validator.warnings, "a differing unit produced no warning"
assert "install_service.sh" in validator.warnings[0], (
"the warning does not tell the user how to fix it")
assert not validator.errors, "drift must not be fatal at startup"
def test_a_missing_installed_unit_is_silent(validator, tmp_path):
"""Development checkouts have no /etc/systemd unit; that is not drift."""
validator._UNITS = (("systemd/ledmatrix.service", str(tmp_path / "absent.service")),)
validator._validate_systemd_units()
assert not validator.warnings
assert not validator.errors
+2 -11
View File
@@ -1657,22 +1657,13 @@ def resolve_pull_command(project_dir):
backup, or following an install guide that names one. The update button backup, or following an install guide that names one. The update button
then reports a failure the user cannot act on. then reports a failure the user cannot act on.
``--autostash`` is passed for the same reason. Rebase refuses to start
when any tracked file is modified, and on these installs something always
is: first_time_install.sh chmods five scripts that git tracked as 644, so
every machine that ran the installer carries five permanent mode changes
and the update button reports "cannot pull with rebase: You have unstaged
changes". Those modes are corrected in this commit, but a user cannot pull
the correction while the pull is what is blocked, and any other local edit
would reproduce it anyway. Autostash reapplies the changes afterwards.
Returns ``(args, note, error)``. When ``origin/<branch>`` exists the pull Returns ``(args, note, error)``. When ``origin/<branch>`` exists the pull
is made explicit against it, so the update proceeds and the branch is is made explicit against it, so the update proceeds and the branch is
given tracking information afterwards. given tracking information afterwards.
""" """
upstream = _git_upstream(project_dir) upstream = _git_upstream(project_dir)
if upstream: if upstream:
return ['git', 'pull', '--rebase', '--autostash'], '', None return ['git', 'pull', '--rebase'], '', None
branch = _git_current_branch(project_dir) branch = _git_current_branch(project_dir)
if not branch: if not branch:
@@ -1682,7 +1673,7 @@ def resolve_pull_command(project_dir):
) )
if _git_remote_branch_exists(project_dir, branch): if _git_remote_branch_exists(project_dir, branch):
return ( return (
['git', 'pull', '--rebase', '--autostash', 'origin', branch], ['git', 'pull', '--rebase', 'origin', branch],
f"Branch '{branch}' had no upstream; pulled from origin/{branch} and set it as the upstream.", f"Branch '{branch}' had no upstream; pulled from origin/{branch} and set it as the upstream.",
None, None,
) )