From 7662484cae8e74b7d9aa383bd6cd0dad4690aadc Mon Sep 17 00:00:00 2001 From: Christophe Besson Date: Sun, 27 Sep 2026 22:20:35 +0200 Subject: fix(node): a Windows daemon that stops properly, starts honestly and runs once Found by installing the builds and driving every startup mode live: - Stop through the node's own control API first (POST /api/shutdown, loopback and per-run token): the one channel that reaches a daemon in any session without elevation -- a service node runs in session 0 -- and the one that runs its shutdown. Then Task Scheduler, then a forced stop. Nine stops in a row used to log no shutdown at all: each was a TerminateProcess. - The forced stop spares the command running it. The frozen meshbay-node.exe is the daemon and every CLI verb, so `taskkill /IM meshbay-node.exe` killed `autostart stop` and `restart-daemon` themselves: exit 1, no output, and no node after a restart. It excludes its own pid and its parent's, and /T takes a venv launcher's python child and a daemon's ffmpeg children with it. - Start and restart report the version that answered, never "started" about a node nobody asked; `service start` says so when no node answered, and where the log is. - A second instance fails before it touches anything. The daemon wrote ui-token, then failed to bind inside uvicorn's task and exited with the reason on a hidden console; the node still running then refused every stop and status, its token file naming a dead process. The control port is now bound first (exclusively on Windows, where SO_REUSEADDR would share it), and a refusal is logged and exits 2. Linux had the same order. - The daemon logs to %LOCALAPPDATA%\meshbay\state\node.log: Task Scheduler discards its stderr. Only the daemon run opens it, never a CLI verb. - Hub sign-in waits are interruptible, a stop requested before the node is up is honoured, and a hub that answers 429 or restarts leaves the node in waiting_for_hub rather than looking dead. - operator_paired is null until the roster is read, instead of a false that showed "No operator paired" about a node whose pairing was intact. The node test conftest also points HOME, USERPROFILE, LOCALAPPDATA and APPDATA at a throwaway directory for every test, and keeps log_file() away from the developer's own node: redirecting HOME alone isolates nothing on Windows, and the CLI tests had been writing invite and pairing codes into the real profile. Co-Authored-By: Claude Opus 5.5 --- packages/meshbay-node/tests/conftest.py | 42 +++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) (limited to 'packages/meshbay-node/tests/conftest.py') diff --git a/packages/meshbay-node/tests/conftest.py b/packages/meshbay-node/tests/conftest.py index 9ef23a3..32c9b3d 100644 --- a/packages/meshbay-node/tests/conftest.py +++ b/packages/meshbay-node/tests/conftest.py @@ -17,6 +17,48 @@ needs_subprocess = pytest.mark.skipif( "SelectorEventLoop for aiortc", ) +@pytest.fixture(autouse=True) +def _no_log_file_in_the_developers_profile(monkeypatch): + """A test that runs the daemon's entry point must not open its log file. + + On Windows that file is %LOCALAPPDATA%\\meshbay\\state\\node.log -- the + developer's own node's log. The first run of the suite with it appended + every later test's log lines there, through a handler left on the root + logger. A test about the log file points log_file() somewhere of its own. + """ + import logging + + from meshbay_node import platform as _plat + monkeypatch.setattr(_plat, "log_file", lambda: None) + root = logging.getLogger() + before = list(root.handlers) + yield + for h in root.handlers[:]: + if h not in before and getattr(h, "baseFilename", None): + root.removeHandler(h) + h.close() + + +@pytest.fixture(scope="session") +def _throwaway_profile(tmp_path_factory): + return tmp_path_factory.mktemp("profile") + + +@pytest.fixture(autouse=True) +def _no_test_touches_the_developers_profile(monkeypatch, _throwaway_profile): + """Every per-user location, pointed somewhere nobody lives. + + Tests redirected HOME and nothing else, which isolates nothing on Windows: + Path.home() reads USERPROFILE there and the node's own directories come from + LOCALAPPDATA. `member invite` and `operator pair`, walked by the CLI tests, + wrote their codes into the developer's real node directory and a + ~/.local/share/meshbay nobody had, on every run. A test that sets its own + HOME still can; it just no longer falls through to the real one. + """ + for var in ("HOME", "USERPROFILE", "LOCALAPPDATA", "APPDATA"): + monkeypatch.setenv(var, str(_throwaway_profile / var.lower())) + + @pytest.fixture(autouse=True) def _restore_media_tool_paths(): """Put `platform`'s resolved ffmpeg/ffprobe paths back after every test. -- cgit v1.2.3