Compare commits

...
Author SHA1 Message Date
Elliot Slusky 403dec8e98 Merge pull request #687 from Curryraj/fix/windows-daemon-detach
fix: detach the daemon from its console on Windows
2026-07-28 23:34:01 -07:00
Elliot Slusky 2c7cf6118c test: make Windows daemon test cross-platform 2026-07-28 23:27:25 -07:00
CurryrajandClaude Opus 5 2bdd860b54 test: tolerate a 503 memory backend in the route-wiring tests (#685)
``TestMemoryRoutes.test_search`` and ``test_stats`` assert the status code
is in ``(200, 500)``. That list dates from the initial commit; #527 later
made the memory routes raise 503 when the native ``openjarvis_rust``
extension is missing, so both tests now fail on any checkout where the
extension has not been built — which is every contributor who has not run
``maturin develop``.

The failure is spurious: these two tests only check that the routes are
wired up, and their own comment ("May fail if SQLite not set up, that's
ok") says an unavailable backend is tolerated. 503 is exactly that case,
and it is already asserted deliberately in ``TestMemoryRustMissing``
directly below.

Add 503 to the tolerated set via a named constant, so the reason is stated
once rather than repeated as a bare literal.

Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-07-28 23:17:25 -07:00
Jaiydaan RajandClaude Opus 5 9fc5b875d1 fix: detach the daemon from its console on Windows
``jarvis start`` spawned the server with ``start_new_session=True``. That is
POSIX-only — CPython's Windows ``_execute_child`` names the parameter
``unused_start_new_session`` and ignores it — so on Windows the server
inherited the launching console instead of detaching from it.

Closing that console, or logging off, therefore delivered CTRL_CLOSE_EVENT
to the server. Observed in the wild as the daemon dying overnight, with

    forrtl: error (200): program aborting due to window-CLOSE event

in server.log (the Fortran runtime under NumPy handles the event and
aborts). ``jarvis start`` looked like it worked: it printed a PID, wrote the
pid file and exited 0, and the server ran for as long as the console stayed
open. Registered as a log-on scheduled task, this means the machine comes
back up with no backend.

Pass DETACHED_PROCESS on Windows so the child gets no console at all, plus
CREATE_NEW_PROCESS_GROUP so a Ctrl-C in the parent console cannot reach it.
POSIX keeps start_new_session.

Verified by attaching to each spawned process with AttachConsole():
start_new_session=True attaches successfully (the child shares a console);
DETACHED_PROCESS fails with ERROR_INVALID_HANDLE (no console exists).

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-28 13:17:06 +08:00
3 changed files with 102 additions and 4 deletions
+16 -2
View File
@@ -81,14 +81,28 @@ def start(
if agent_name:
cmd.extend(["--agent", agent_name])
# Start as background process
# Start as background process, fully detached from the launching terminal.
#
# ``start_new_session`` is POSIX-only: CPython's Windows ``_execute_child``
# names the parameter ``unused_start_new_session`` and ignores it. Relying
# on it there leaves the server sharing its parent's console, so closing
# that console — or logging off — delivers CTRL_CLOSE_EVENT and kills the
# daemon. DETACHED_PROCESS gives it no console at all; the new process
# group additionally stops a Ctrl-C in the parent reaching it.
DEFAULT_CONFIG_DIR.mkdir(parents=True, exist_ok=True)
log_fh = open(_LOG_FILE, "a") # noqa: SIM115
spawn_kwargs: dict = {}
if sys.platform == "win32":
spawn_kwargs["creationflags"] = (
subprocess.DETACHED_PROCESS | subprocess.CREATE_NEW_PROCESS_GROUP
)
else:
spawn_kwargs["start_new_session"] = True
proc = subprocess.Popen(
cmd,
stdout=log_fh,
stderr=log_fh,
start_new_session=True,
**spawn_kwargs,
)
_write_pid(proc.pid)
+78
View File
@@ -2,6 +2,7 @@
from __future__ import annotations
import subprocess
from pathlib import Path
from unittest.mock import MagicMock, patch
@@ -79,3 +80,80 @@ class TestDaemonCommands:
result = CliRunner().invoke(cli, ["start"])
assert result.exit_code != 0
assert "already running" in result.output
class TestDaemonDetachment:
"""The spawned server must outlive the console that started it.
``start_new_session`` is POSIX-only — CPython's Windows ``_execute_child``
names the parameter ``unused_start_new_session``. Relying on it there leaves
the server sharing its parent's console, so closing that console (or logging
off) delivers CTRL_CLOSE_EVENT and kills the daemon.
"""
@staticmethod
def _spawn_kwargs(platform: str) -> dict:
"""Return the kwargs ``start`` passes to Popen when spawning the server.
``load_config`` is stubbed because it shells out for GPU detection —
patching Popen wholesale would otherwise break config loading before
the spawn is reached.
"""
with (
patch("openjarvis.cli.daemon_cmd._read_pid", return_value=None),
patch("openjarvis.cli.daemon_cmd._write_pid"),
patch("openjarvis.cli.daemon_cmd.load_config"),
patch("openjarvis.cli.daemon_cmd.sys.platform", platform),
patch("openjarvis.cli.daemon_cmd.subprocess.Popen") as popen,
patch("builtins.open", MagicMock()),
):
popen.return_value = MagicMock(pid=4321)
result = CliRunner().invoke(cli, ["start"])
assert result.exit_code == 0, result.output
spawns = [
c for c in popen.call_args_list if c.args and "serve" in c.args[0]
]
assert spawns, f"start did not spawn the server: {popen.call_args_list}"
return spawns[-1].kwargs
def test_windows_spawn_is_detached_from_the_console(self) -> None:
# These constants are only exported by ``subprocess`` on Windows.
# Supply their documented values so the simulated Windows branch is
# still exercised by the POSIX test job.
detached_process = getattr(subprocess, "DETACHED_PROCESS", 0x00000008)
create_new_process_group = getattr(
subprocess, "CREATE_NEW_PROCESS_GROUP", 0x00000200
)
with (
patch.object(
subprocess,
"DETACHED_PROCESS",
detached_process,
create=True,
),
patch.object(
subprocess,
"CREATE_NEW_PROCESS_GROUP",
create_new_process_group,
create=True,
),
):
kwargs = self._spawn_kwargs("win32")
flags = kwargs.get("creationflags", 0)
assert flags & detached_process, (
"server must be spawned with DETACHED_PROCESS on Windows, otherwise "
"closing the launching console kills it"
)
assert flags & create_new_process_group, (
"server must be in its own process group so Ctrl-C in the parent "
"console does not propagate to it"
)
assert not kwargs.get("start_new_session"), (
"start_new_session is ignored on Windows; it must not be relied on"
)
def test_posix_spawn_still_uses_start_new_session(self) -> None:
kwargs = self._spawn_kwargs("linux")
assert kwargs.get("start_new_session") is True
assert "creationflags" not in kwargs or kwargs["creationflags"] == 0
+8 -2
View File
@@ -37,16 +37,22 @@ class TestAgentRoutes:
class TestMemoryRoutes:
# 503 is the documented response when the native ``openjarvis_rust``
# extension is absent from the venv (see TestMemoryRustMissing below).
# These tests are only asserting "the route is wired up", so a backend
# that cannot be built is tolerated the same way a 500 is.
_BACKEND_OPTIONAL = (200, 500, 503)
def test_search(self):
client = TestClient(_make_app())
resp = client.post("/v1/memory/search", json={"query": "test"})
# May fail if SQLite not set up, that's ok
assert resp.status_code in (200, 500)
assert resp.status_code in self._BACKEND_OPTIONAL
def test_stats(self):
client = TestClient(_make_app())
resp = client.get("/v1/memory/stats")
assert resp.status_code in (200, 500)
assert resp.status_code in self._BACKEND_OPTIONAL
class TestMemoryRustMissing: