fix(gateway): probe launchd domain instead of hardcoding user/<uid> (#40831)
The previous fix for #23387 changed _launchd_domain() from gui/<uid> to user/<uid> to support Background/SSH sessions on macOS 26+. However, this broke Aqua sessions where gui/<uid> is the only working domain and user/<uid> cannot bootstrap or manage the service. Now _launchd_domain() probes which domain actually contains the loaded service: 1. Try gui/<uid> first (Aqua sessions) 2. Fall back to user/<uid> (Background/SSH sessions) 3. Use launchctl managername as heuristic when neither has the service 4. Cache the result for the process lifetime Regression tests cover all four paths plus caching behavior.fix/verification-admin-route-recovery
Tranquil-Flow
Teknium
parent
2d75833abe
commit
a8f404b29f
|
|
@ -3067,12 +3067,77 @@ def get_launchd_label() -> str:
|
|||
return f"ai.hermes.gateway-{suffix}" if suffix else "ai.hermes.gateway"
|
||||
|
||||
|
||||
# Cached launchd domain result — probing is cheap but should only run once per
|
||||
# process invocation (each ``hermes gateway start/stop/status`` call).
|
||||
_resolved_launchd_domain: str | None = None
|
||||
|
||||
|
||||
def _launchd_domain() -> str:
|
||||
# The `user/<uid>` domain (vs the older `gui/<uid>`) is reachable from
|
||||
# non-Aqua/background sessions (SSH, headless, login items) and is the only
|
||||
# one that supports service management on macOS 26+. `gui/<uid>` returns
|
||||
# error 125 ("Domain does not support specified action") there. See #23387.
|
||||
return f"user/{os.getuid()}" # windows-footgun: ok — POSIX launchd (macOS) helper, never invoked on Windows
|
||||
"""Return the launchd domain that actually manages the gateway service.
|
||||
|
||||
Probes ``gui/<uid>`` first (Aqua sessions), then ``user/<uid>``
|
||||
(Background/SSH sessions). When neither domain contains a loaded
|
||||
service, falls back to ``launchctl managername`` as a heuristic.
|
||||
|
||||
The result is cached for the lifetime of the process so that repeated
|
||||
calls (``start``, ``stop``, ``restart``) use a consistent domain.
|
||||
|
||||
See #40831, #23387.
|
||||
"""
|
||||
global _resolved_launchd_domain
|
||||
if _resolved_launchd_domain is not None:
|
||||
return _resolved_launchd_domain
|
||||
|
||||
uid = os.getuid() # windows-footgun: ok — POSIX launchd (macOS) helper, never invoked on Windows
|
||||
label = get_launchd_label()
|
||||
gui_domain = f"gui/{uid}"
|
||||
user_domain = f"user/{uid}"
|
||||
|
||||
# 1. Probe gui/<uid> first — in Aqua sessions the service is loaded here.
|
||||
try:
|
||||
subprocess.run(
|
||||
["launchctl", "print", f"{gui_domain}/{label}"],
|
||||
check=True,
|
||||
timeout=5,
|
||||
capture_output=True,
|
||||
)
|
||||
_resolved_launchd_domain = gui_domain
|
||||
return gui_domain
|
||||
except (subprocess.CalledProcessError, subprocess.TimeoutExpired, FileNotFoundError):
|
||||
pass
|
||||
|
||||
# 2. Probe user/<uid> — in Background/SSH sessions this is the working domain.
|
||||
try:
|
||||
subprocess.run(
|
||||
["launchctl", "print", f"{user_domain}/{label}"],
|
||||
check=True,
|
||||
timeout=5,
|
||||
capture_output=True,
|
||||
)
|
||||
_resolved_launchd_domain = user_domain
|
||||
return user_domain
|
||||
except (subprocess.CalledProcessError, subprocess.TimeoutExpired, FileNotFoundError):
|
||||
pass
|
||||
|
||||
# 3. Neither domain has the service loaded — use managername as heuristic.
|
||||
# Aqua → gui/<uid>, anything else (Background, loginwindow) → user/<uid>.
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["launchctl", "managername"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=5,
|
||||
)
|
||||
if "Aqua" in (result.stdout or ""):
|
||||
_resolved_launchd_domain = gui_domain
|
||||
return gui_domain
|
||||
except (subprocess.CalledProcessError, subprocess.TimeoutExpired, FileNotFoundError):
|
||||
pass
|
||||
|
||||
# 4. Default to user/<uid> (matches the pre-probing behavior for
|
||||
# Background/SSH sessions and is the recommended domain on macOS 26+).
|
||||
_resolved_launchd_domain = user_domain
|
||||
return user_domain
|
||||
|
||||
|
||||
# On macOS, exit code 125 ("Domain does not support specified action") and
|
||||
|
|
|
|||
|
|
@ -495,7 +495,10 @@ class TestLaunchdServiceRecovery:
|
|||
label = gateway_cli.get_launchd_label()
|
||||
domain = gateway_cli._launchd_domain()
|
||||
assert "--replace" in plist_path.read_text(encoding="utf-8")
|
||||
assert calls[:2] == [
|
||||
# The calls list includes launchctl print probes from _launchd_domain()
|
||||
# before the bootout/bootstrap calls. Filter to only bootout/bootstrap.
|
||||
service_calls = [c for c in calls if "bootout" in c or "bootstrap" in c]
|
||||
assert service_calls[:2] == [
|
||||
["launchctl", "bootout", f"{domain}/{label}"],
|
||||
["launchctl", "bootstrap", domain, str(plist_path)],
|
||||
]
|
||||
|
|
@ -679,10 +682,22 @@ class TestLaunchdServiceRecovery:
|
|||
assert "stale" in output.lower()
|
||||
assert "not loaded" in output.lower()
|
||||
|
||||
def test_launchd_domain_uses_user_domain(self):
|
||||
def test_launchd_domain_uses_user_domain(self, monkeypatch):
|
||||
# The user/<uid> domain (not gui/<uid>) is the one reachable from
|
||||
# non-Aqua/background sessions on macOS 26+ (issue #23387).
|
||||
assert gateway_cli._launchd_domain() == f"user/{os.getuid()}"
|
||||
# When gui/<uid> fails to probe and user/<uid> succeeds,
|
||||
# _launchd_domain() must return user/<uid>.
|
||||
gateway_cli._resolved_launchd_domain = None
|
||||
monkeypatch.setattr(os, "getuid", lambda: 501)
|
||||
label = gateway_cli.get_launchd_label()
|
||||
|
||||
def fake_run(cmd, check=False, **kwargs):
|
||||
if "print" in cmd and "gui/" in " ".join(cmd):
|
||||
raise subprocess.CalledProcessError(1, cmd, stderr="Domain error")
|
||||
return SimpleNamespace(returncode=0, stdout="", stderr="")
|
||||
|
||||
monkeypatch.setattr(gateway_cli.subprocess, "run", fake_run)
|
||||
assert gateway_cli._launchd_domain() == "user/501"
|
||||
|
||||
def test_launchctl_domain_unsupported_recognizes_macos26_codes(self):
|
||||
# Codes that persist after a fresh bootstrap → launchd truly unavailable.
|
||||
|
|
@ -836,6 +851,114 @@ class TestLaunchdServiceRecovery:
|
|||
assert "nohup hermes gateway run" in out
|
||||
|
||||
|
||||
class TestLaunchdDomainDetection:
|
||||
"""Regression tests for _launchd_domain() probing (#40831).
|
||||
|
||||
The function must detect which launchd domain actually contains (or can
|
||||
manage) the service, rather than hardcoding ``user/<uid>`` or ``gui/<uid>``.
|
||||
"""
|
||||
|
||||
def _reset_domain_cache(self):
|
||||
"""Clear any cached domain result between tests."""
|
||||
gateway_cli._resolved_launchd_domain = None
|
||||
|
||||
def test_prefers_gui_domain_when_service_loaded_there(self, monkeypatch):
|
||||
"""In an Aqua session where the service is loaded under gui/<uid>,
|
||||
_launchd_domain() must return ``gui/<uid>`` — not ``user/<uid>``."""
|
||||
self._reset_domain_cache()
|
||||
monkeypatch.setattr(os, "getuid", lambda: 501)
|
||||
label = gateway_cli.get_launchd_label()
|
||||
|
||||
run_calls = []
|
||||
|
||||
def fake_run(cmd, check=False, **kwargs):
|
||||
run_calls.append(cmd)
|
||||
return SimpleNamespace(returncode=0, stdout="", stderr="")
|
||||
|
||||
monkeypatch.setattr(gateway_cli.subprocess, "run", fake_run)
|
||||
|
||||
domain = gateway_cli._launchd_domain()
|
||||
assert domain == f"gui/501"
|
||||
# Should have probed gui first
|
||||
assert run_calls[0] == ["launchctl", "print", f"gui/501/{label}"]
|
||||
|
||||
def test_falls_back_to_user_domain_when_gui_fails(self, monkeypatch):
|
||||
"""In a Background/SSH session where gui/<uid> fails but user/<uid>
|
||||
works, _launchd_domain() must return ``user/<uid>``."""
|
||||
self._reset_domain_cache()
|
||||
monkeypatch.setattr(os, "getuid", lambda: 501)
|
||||
label = gateway_cli.get_launchd_label()
|
||||
|
||||
run_calls = []
|
||||
|
||||
def fake_run(cmd, check=False, **kwargs):
|
||||
run_calls.append(cmd)
|
||||
if "print" in cmd and "gui/" in " ".join(cmd):
|
||||
raise subprocess.CalledProcessError(1, cmd, stderr="Domain error")
|
||||
return SimpleNamespace(returncode=0, stdout="", stderr="")
|
||||
|
||||
monkeypatch.setattr(gateway_cli.subprocess, "run", fake_run)
|
||||
|
||||
domain = gateway_cli._launchd_domain()
|
||||
assert domain == f"user/501"
|
||||
# Should have tried gui first, then user
|
||||
assert len(run_calls) >= 2
|
||||
|
||||
def test_uses_managername_heuristic_when_both_probe_fail(self, monkeypatch):
|
||||
"""When neither domain contains a loaded service, use
|
||||
``launchctl managername`` as a tiebreaker: Aqua -> gui, else -> user."""
|
||||
self._reset_domain_cache()
|
||||
monkeypatch.setattr(os, "getuid", lambda: 501)
|
||||
label = gateway_cli.get_launchd_label()
|
||||
|
||||
def fake_run(cmd, check=False, **kwargs):
|
||||
if "print" in cmd:
|
||||
raise subprocess.CalledProcessError(1, cmd, stderr="not found")
|
||||
if "managername" in cmd:
|
||||
return SimpleNamespace(returncode=0, stdout="Aqua\n", stderr="")
|
||||
return SimpleNamespace(returncode=0, stdout="", stderr="")
|
||||
|
||||
monkeypatch.setattr(gateway_cli.subprocess, "run", fake_run)
|
||||
|
||||
domain = gateway_cli._launchd_domain()
|
||||
assert domain == f"gui/501"
|
||||
|
||||
def test_managername_background_selects_user_domain(self, monkeypatch):
|
||||
"""When managername is Background (non-Aqua), use user/<uid>."""
|
||||
self._reset_domain_cache()
|
||||
monkeypatch.setattr(os, "getuid", lambda: 501)
|
||||
|
||||
def fake_run(cmd, check=False, **kwargs):
|
||||
if "print" in cmd:
|
||||
raise subprocess.CalledProcessError(1, cmd, stderr="not found")
|
||||
if "managername" in cmd:
|
||||
return SimpleNamespace(returncode=0, stdout="Background\n", stderr="")
|
||||
return SimpleNamespace(returncode=0, stdout="", stderr="")
|
||||
|
||||
monkeypatch.setattr(gateway_cli.subprocess, "run", fake_run)
|
||||
|
||||
domain = gateway_cli._launchd_domain()
|
||||
assert domain == f"user/501"
|
||||
|
||||
def test_caches_result_across_calls(self, monkeypatch):
|
||||
"""Domain detection should run once and cache the result."""
|
||||
self._reset_domain_cache()
|
||||
monkeypatch.setattr(os, "getuid", lambda: 501)
|
||||
|
||||
run_count = [0]
|
||||
|
||||
def fake_run(cmd, check=False, **kwargs):
|
||||
run_count[0] += 1
|
||||
return SimpleNamespace(returncode=0, stdout="", stderr="")
|
||||
|
||||
monkeypatch.setattr(gateway_cli.subprocess, "run", fake_run)
|
||||
|
||||
d1 = gateway_cli._launchd_domain()
|
||||
d2 = gateway_cli._launchd_domain()
|
||||
assert d1 == d2
|
||||
assert run_count[0] == 1 # Only probed once
|
||||
|
||||
|
||||
class TestGatewayServiceDetection:
|
||||
def test_supports_systemd_services_requires_systemctl_binary(self, monkeypatch):
|
||||
monkeypatch.setattr(gateway_cli, "is_linux", lambda: True)
|
||||
|
|
|
|||
Loading…
Reference in New Issue