`disposal contains a spawn-failure rejection that races teardown` asserted one
winner of the race. A bootstrap that publishes its pre-exec failure rejects with
that failure, and a teardown that stops the bootstrap first settles as the
requested termination — the recorded failure only outranks the stop when it was
published before the stop landed. Assert the contract instead: a rejection
carries the failure, a stop carries SIGTERM, which only the Linux scope records
because the win32 job owner and the fallback launcher both reject the start.
The two terminal cases that drive a mocked PTY exit state why they pin
`internals.platform`: under the host's native scope the mocked exit races the
scope bootstrap and fails as `terminal scope exited before its bootstrap
consumed the launch request`.
Range observation waited for an active transient scope to leave `active`
before it would prove the managed range empty. systemd ends a scope only when
it observes the populated-to-empty transition, so a payload killed before the
manager placed it in the scope's cgroup leaves the unit active with an empty
cgroup forever. `waitForExit()` then polled a unit that could not change, and
`LocalSubprocessRuntime.disposeManagedProcesses()` awaited it without bound —
teardown hung for any command cancelled immediately after spawn.
Each state query now also reads the unit's process count. Once termination was
requested and the launcher has exited, a still-active unit reporting no
processes is the empty range: the launcher forked every process it will ever
fork, so nothing later joins that cgroup. The owner stops the leftover unit so
transient units cannot accumulate, and an unreported or `[not set]` count
stays unknown and keeps waiting.
The race needs a live user-systemd manager, so it stayed dormant wherever the
native scope path was unavailable and surfaced once CI routed lanes onto the
Blacksmith hosted image, whose runners accept that path. Ten repetitions of
`local.spec.ts > disposal kills still-running processes and awaits their exit`
in a Linux container with a user manager failed seven times before the change
and passed ten times after it.
Second review round (ds-review-bot v4p/v5/v6): the exit cleanup claim that
collectors unlink their spill files on dispose was wrong — completed spill
files are retained (seal() only closes, discardSpill() is the only unlink),
so the exit removal only ever applies to directories that never spilled.
Reword the JSDoc, README, and Agent Note accordingly, drop the redundant
readdirSync precheck (rmdirSync ENOTEMPTY is caught anyway), and recount the
v8-ignore window. The spawn.spec default-spill test now records the default
per-process directory it created and removes it in afterAll, so a completed
spill file is never left behind by the unit suite.
Spec files that create /tmp/dsh-* directories via mkdtemp now track and
delete them in afterEach/afterAll; module-scope fixture dirs (executor
spill dirs) are removed in afterAll. The file list came from the
observed-residue inventory on the self-hosted CI host: only specs whose
dirs actually accumulated were leak sources (issue #3134), superseding
the kept-but-unmerged CI sweep branch per the #3233 review decision.
Product per-process spill roots (dsh-subprocess-local spawn,
dsh-spill-local store) register a process-exit handler that removes the
memoized dir, so processes that used the spawn/spill path clean up on
normal exit. A SIGKILLed process cannot run in-process teardown; the
machine-side timer remains the backstop for that path.
Agent Note: .agents/notes/implemented/process/2026-08-28-test-temp-dir-self-cleanup.md
Yichen Jiang