fix(hooks): drain detached hook runs on bridge dispose

The emit-shaped hook points (SessionStart, SubagentStart, SubagentStop)
run fire-and-forget: no seam awaits the run chain, so disposing a bridge
could strand a live hook process and let a late continuation inject into
a disposed context. The floating continuation also made the coverage
gate racy: the only coverage of the SubagentStart continuation's
no-context branch arm rode on an un-awaited .then, and on a loaded CI
runner the fork's per-file coverage snapshot beat it — master run
28798191671 failed the 100% branch gate on hooks-claude/src/index.ts at
99.03% (uncovered line 336) with the identical tree passing the PR run
three minutes earlier.

New shared primitive createDetachedRuns() in dsh-hook-protocol: a bridge
tracks each detached run chain, passes the tracker's abort signal to
runHook, and registers drain() as its effect disposer — drain aborts
still-running hook processes (a kill via the bash seam, not a wait out
to the 10-minute default hook timeout), then resolves once every chain
has settled. fiber.dispose() resolving now means the bridge's detached
work is quiescent (docs/defensive-patterns.md).

The subagent marker test disposes the bridge as its sync point, so the
formerly racy branch arm is executed deterministically before the file's
coverage snapshot; new tests pin abort-on-dispose promptness for both
bridges and the tracker's settle/drain contract in hook-protocol.
This commit is contained in:
Tianyi Cui
2026-07-06 23:27:54 +08:00
parent 0606cd559c
commit 9ca31ab193
11 changed files with 260 additions and 19 deletions

View File

@@ -1,5 +1,5 @@
import { afterEach, describe, expect, it } from 'vitest'
import { mkdtempSync, rmSync, writeFileSync, chmodSync } from 'node:fs'
import { afterEach, describe, expect, it, vi } from 'vitest'
import { chmodSync, existsSync, mkdtempSync, rmSync, writeFileSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { Context } from 'cordis'
@@ -62,6 +62,15 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
}
function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] }
/** Poll `predicate` until true or the deadline passes (detached hook effects can't be awaited directly). */
async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise<void> {
const deadline = Date.now() + timeout
while (!predicate()) {
if (Date.now() > deadline) throw new Error('waitFor: condition not met before deadline')
await new Promise(r => setTimeout(r, interval))
}
}
describe('hooks-codex bridge', () => {
it('a PreToolUse hook (exit 2) denies a tool the regex matcher matches as a substring', async () => {
const dir = configDir()
@@ -159,6 +168,35 @@ describe('hooks-codex bridge', () => {
expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) // no hook ran
})
it('disposing the bridge aborts a still-running SessionStart hook and drains to quiescence', async () => {
const dir = configDir()
const marker = join(dir, 'started')
// Touch the marker FIRST so the test can tell "the hook is genuinely
// mid-run", then sleep far past the suite timeout: dispose resolving at all
// proves the drain KILLED the process (the tracker's abort signal wired
// through this bridge's runPoint) instead of awaiting its exit.
const slow = script(dir, 'slow.sh', `#!/usr/bin/env bash\ntouch "${marker}"\nsleep 30\n`)
writeHooks(dir, { SessionStart: [{ hooks: [{ type: 'command', command: slow }] }] })
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' })
ctx.llm.registerAdapter(['mock'], new MockAdapter([]))
const warn = vi.fn()
ctx.logger.warn = warn as never
ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) // fires agent/session-start
await waitFor(() => existsSync(marker))
await fiber.dispose()
// The aborted run resolves as a non-blocking error (runHook never rejects),
// so the drained continuation must NOT have logged a failure.
expect(warn).not.toHaveBeenCalledWith(expect.stringContaining('SessionStart hook failed'))
})
it('has the namespace-plugin export shape (no stray default) so the Loader keeps name/inject/apply', () => {
expect('default' in HooksCodex).toBe(false)
expect(HooksCodex.name).toBe('hooks-codex')