fix(subprocess): honor Windows termination semantics

This commit is contained in:
imccyu
2026-07-18 16:25:51 +08:00
parent d36dc6ece9
commit 64f64724e5
8 changed files with 48 additions and 38 deletions

View File

@@ -20,13 +20,13 @@ Exit waits over a `ChildProcess`: resolve once the child exits by any code or si
### `disposeChildProcess(child, graces)`
The three-tier dispose ladder. Resolves only once the child has ACTUALLY exited — quiescence reached, not merely requested (see [defensive patterns](../../../docs/defensive-patterns.md)):
The platform-aware dispose ladder resolves only once the child has ACTUALLY exited — quiescence reached, not merely requested (see [defensive patterns](../../../docs/defensive-patterns.md)):
1. stdin EOF (when stdin is piped), then wait `graces.disposeEofGraceMs` — a cooperative child quiesces on its own, its flushes and nested-subprocess teardown intact;
2. `SIGTERM`, then wait `graces.disposeGraceMs`;
3. `SIGKILL`, then await the now-certain exit — a child that ignores EOF and traps `SIGTERM` cannot wedge dispose forever.
2. on POSIX, `SIGTERM`, then wait `graces.disposeGraceMs`;
3. force termination and await exit — `SIGKILL` on POSIX and Node's `TerminateProcess` mapping on Windows.
The two graces (`DisposeLadderGraces`) come from the consuming plugin's `disposeEofGraceMs`/`disposeGraceMs` Config fields; the EOF window is deliberately a separate — usually wider — grace than the signal tier, since a cooperative child's EOF teardown may itself await a signal-trapping grandchild plus a final flush.
The two graces (`DisposeLadderGraces`) come from the consuming plugin's `disposeEofGraceMs`/`disposeGraceMs` Config fields; `disposeGraceMs` is unused on Windows because Node maps `SIGTERM` and `SIGKILL` to the same forced termination. The EOF window is deliberately separate and usually wider, since cooperative teardown may await a signal-trapping grandchild plus a final flush.
### `createIsolatedConfigDir(prefix, pinnedPath?)`
@@ -37,7 +37,7 @@ A per-run isolated config directory for an external CLI child (the target of `CL
## Testing
`tests/subagent-subprocess.spec.ts`: the env scrub and config-dir helpers run against the real process env and real filesystem (the rm-failure path injects its rejection at the fs boundary — a real recursive-rm failure is not portably provokable, and root ignores permission bits); the exit waits and the dispose ladder run against a scriptable fake child, driving each escalation tier deterministically. The [ACP backend suite](../subagent-acp/README.md) exercises the same ladder against real subprocesses (EOF-cooperative, EOF-ignoring, and SIGTERM-trapping children) end to end.
`tests/subagent-subprocess.spec.ts`: the env scrub and config-dir helpers run against the real process env and real filesystem (the rm-failure path injects its rejection at the fs boundary — a real recursive-rm failure is not portably provokable, and root ignores permission bits); the exit waits and platform termination paths run against a scriptable fake child. The [ACP backend suite](../subagent-acp/README.md) exercises them against real subprocesses end to end.
## Model Experience

View File

@@ -98,33 +98,42 @@ export interface DisposeLadderGraces {
/**
* Tier-1 window (ms): after stdin EOF, how long the child gets to quiesce
* ON ITS OWN — flush durable state, tear down its own nested subprocesses —
* before the parent escalates to `SIGTERM`. A separate (usually WIDER)
* before the parent escalates to platform termination. A separate (usually WIDER)
* grace than {@link DisposeLadderGraces.disposeGraceMs}: a cooperative
* child's EOF-driven teardown may itself be waiting on a signal-trapping
* grandchild plus a final flush, needing more than one signal-grace of
* headroom.
*/
disposeEofGraceMs: number
/** Tier-2 window (ms): between `SIGTERM` and the `SIGKILL` escalation. */
/** POSIX tier-2 window (ms): between `SIGTERM` and the `SIGKILL` escalation. */
disposeGraceMs: number
}
/**
* Tear a child process down to quiescence, resolving only after exit: close stdin and allow
* cooperative flush, then send `SIGTERM`, then `SIGKILL` and await the forced exit.
* cooperative flush, then use the host's graceful and forced termination semantics. POSIX
* sends `SIGTERM` before `SIGKILL`; Windows skips directly to forced termination because Node
* maps both signals to `TerminateProcess`.
*
* @param child - the child process to tear down.
* @param graces - the two grace periods, from the consuming plugin's Config.
* @param platform - the host platform, injectable for unit coverage.
*/
export async function disposeChildProcess(child: ChildProcess, graces: DisposeLadderGraces): Promise<void> {
export async function disposeChildProcess(
child: ChildProcess,
graces: DisposeLadderGraces,
platform: NodeJS.Platform = process.platform,
): Promise<void> {
// Already gone: nothing to reap.
if (child.exitCode !== null || child.signalCode !== null) return
// 1. Close stdin and allow cooperative teardown and durable-state flush.
child.stdin?.end()
if (await exitsWithin(child, graces.disposeEofGraceMs)) return
// 2. SIGTERM, escalating if the child still does not exit within the grace.
child.kill('SIGTERM')
if (await exitsWithin(child, graces.disposeGraceMs)) return
// 2. POSIX gets a catchable graceful signal; Windows signals all force-terminate.
if (platform !== 'win32') {
child.kill('SIGTERM')
if (await exitsWithin(child, graces.disposeGraceMs)) return
}
// 3. Force-kill and await the (now-certain) exit.
child.kill('SIGKILL')
await waitForExit(child)

View File

@@ -229,7 +229,7 @@ describe('disposeChildProcess', () => {
it('tier 2: a child that ignores EOF but honors SIGTERM dies on the middle rung', async () => {
const fake = new FakeChild({ diesOn: 'SIGTERM', delayMs: 5 })
await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 })
await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 }, 'linux')
expect(fake.stdinEnded).toBe(true)
expect(fake.kills).toEqual(['SIGTERM'])
expect(fake.signalCode).toBe('SIGTERM')
@@ -237,7 +237,7 @@ describe('disposeChildProcess', () => {
it('tier 3: a SIGTERM-trapping child is SIGKILLed, and dispose resolves only after the exit', async () => {
const fake = new FakeChild({ delayMs: 5 }) // only SIGKILL fells it
await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 20 })
await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 20 }, 'linux')
expect(fake.kills).toEqual(['SIGTERM', 'SIGKILL'])
// Quiescence, not a request: at resolution the child has ACTUALLY exited
// (the exit event landed, despite the scripted post-SIGKILL delay).
@@ -246,9 +246,16 @@ describe('disposeChildProcess', () => {
it('walks the ladder for a child spawned without a stdin pipe', async () => {
const fake = new FakeChild({ stdin: false, diesOn: 'SIGTERM', delayMs: 5 })
await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 })
await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 }, 'linux')
expect(fake.kills).toEqual(['SIGTERM'])
})
it('skips the redundant SIGTERM tier on Windows and awaits forced exit', async () => {
const fake = new FakeChild({ diesOn: 'SIGTERM', delayMs: 5 })
await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 }, 'win32')
expect(fake.kills).toEqual(['SIGKILL'])
expect(fake.signalCode).toBe('SIGKILL')
})
})
describe('createIsolatedConfigDir', () => {