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:
@@ -48,6 +48,8 @@ The hooks themselves run in the agent's session workspace: for the agent-scoped
|
||||
|
||||
A tool call's payload carries the real `tool_name` (the same value the matcher tests) and Codex's `tool_input: { command }` shape (the `command` arg when present, else `''`). The matcher subject is the tool name (`PreToolUse`/`PostToolUse`) or the session source (`SessionStart`); `UserPromptSubmit`/`Stop` ignore matchers.
|
||||
|
||||
`SessionStart` — the one emit point — runs detached; each run chain is tracked, and disposing the bridge aborts a still-running hook process, then drains the continuation before the dispose resolves (`createDetachedRuns` in `dsh-hook-protocol`).
|
||||
|
||||
## Context source
|
||||
|
||||
Injected context carries an explicit `{ kind: 'plugin', plugin: 'hooks-codex' }` source (`agent.inject()` would otherwise default it to `{ kind: 'user' }`).
|
||||
|
||||
@@ -24,6 +24,7 @@ import type { PostToolDecision, PreToolDecision, ToolExecution, ToolExecutionRes
|
||||
import {
|
||||
appendHookInvoked,
|
||||
appendHookResult,
|
||||
createDetachedRuns,
|
||||
DEFAULT_HOOK_TIMEOUT_MS,
|
||||
DEFAULT_STDERR_SUMMARY_MAX_CHARS,
|
||||
matchesMatcher,
|
||||
@@ -97,6 +98,12 @@ export function apply(ctx: Context, config: Config): void {
|
||||
|
||||
const model = config.model ?? ''
|
||||
|
||||
// SessionStart is the one emit-shaped (detached) point Codex has: track its
|
||||
// run chains so disposal aborts a still-running hook process and drains the
|
||||
// continuation (docs/defensive-patterns.md: dispose must reach quiescence).
|
||||
const detached = createDetachedRuns()
|
||||
ctx.effect(() => () => detached.drain(), 'hooks-codex: drain detached hook runs')
|
||||
|
||||
async function runPoint(
|
||||
point: string,
|
||||
matchQuery: string,
|
||||
@@ -189,12 +196,12 @@ export function apply(ctx: Context, config: Config): void {
|
||||
// the model (a slow hook can miss the first request). Gating is a deferred
|
||||
// loop-level change; the contract is "injected as soon as the hook resolves".
|
||||
ctx.on('agent/session-start', (agent, source) => {
|
||||
void runPoint('SessionStart', source, { ...base(agent, 'SessionStart', model), source }, { agent, plainStdoutAsContext: true })
|
||||
detached.track(runPoint('SessionStart', source, { ...base(agent, 'SessionStart', model), source }, { agent, plainStdoutAsContext: true, signal: detached.signal })
|
||||
.then((merged) => {
|
||||
const context = contextFrom(merged)
|
||||
if (context) agent.inject(context.content, { source: context.source })
|
||||
})
|
||||
.catch((error: unknown) => { ctx.logger.warn(`hooks-codex: SessionStart hook failed: ${String(error)}`) })
|
||||
.catch((error: unknown) => { ctx.logger.warn(`hooks-codex: SessionStart hook failed: ${String(error)}`) }))
|
||||
})
|
||||
|
||||
// UserPromptSubmit → PromptDecision. Codex can only BLOCK (no allow/ask).
|
||||
|
||||
@@ -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')
|
||||
|
||||
Reference in New Issue
Block a user