refactor: 简化/复用/防御 — 清理 PR #386 审计发现

简化 (S1, S2):
- src/cli/print.ts: 抽出 dispatchHeadlessCronCommand 本地 helper,把
  cron 三个入口(onFire / onFireTask agent / onFireTask 非-agent)共享的
  「dedup-claim → input-close-recheck → onSuccess」管线集中到一处,
  避免三个分支在「claim 与 dispatch 之间发生 inputClosed」的处理上漂移。
  enqueueAndRun 再抽出来,使两个非-agent 分支共用一个 onSuccess 回调。
  约 -55 行重复模板。
- src/utils/autonomyPersistence.ts: 新增 retainActiveFirst<T> 泛型
  helper —— active 记录无条件保留(不参与 cap),inactive 按 timestamp
  desc 填满剩余预算;统一 selectPersistedAutonomyRuns / Flows 的两阶段
  排序语义。
- src/utils/autonomyRuns.ts、autonomyFlows.ts: 改用 retainActiveFirst,
  删掉重复的内联两阶段排序逻辑。

复用 (R1, review #8):
- tests/mocks/file-system.ts: 新增 readTempFile / tempPathExists 两个
  Bun.file 包装,补齐 Node fs.readFileSync / existsSync 在测试里的
  Bun-only 等价物。
- src/utils/__tests__/autonomyRuns.test.ts: 把全部 Node fs/path 导入
  (existsSync, readFileSync, mkdir, writeFile, path.join/resolve)替换为
  tests/mocks/file-system 的共享 helper + node:path(带 node: 前缀)。
  不再有 6 处 mkdir + writeFile 模板,统一用 writeTempFile(自带 mkdir-p)。
  解决 review #8 (Major) 的 Bun-only 运行时契约违反。

防御 (D1, OOM 早期信号):
- src/services/compact/postCompactCleanup.ts: 在 void import().then() 末尾
  补 .catch(logError)。当前 attributionHooks 是 stub,但当真实现被恢复
  且 sweepFileContentCache 抛错时,这个 .catch 阻止它变成 unhandled
  rejection(函数返回值是 void,调用者无从观察异步失败)。
- src/utils/autonomyRuns.ts: 给 active runs 加 100 条软上限 + 一次性
  warn。selectPersistedAutonomyRuns 仍然永不淘汰 active 记录,但跨过
  阈值时 logError 一次,作为 finalize-leak 早期信号——避免 active 无限
  增长悄悄使 AUTONOMY_RUNS_MAX 失效。
This commit is contained in:
Claude
2026-04-29 13:23:41 +00:00
parent 6b7cfda9b1
commit 7a6e65caf7
7 changed files with 190 additions and 143 deletions

View File

@@ -2819,97 +2819,89 @@ function runHeadlessStreaming(
let cronScheduler: import('../utils/cronScheduler.js').CronScheduler | null =
null
if (cronGate.isKairosCronEnabled()) {
// Shared dedup-claim → input-close-recheck → onSuccess pipeline for the
// three cron entry points (legacy onFire, onFireTask agent, onFireTask
// non-agent). Centralizing the cancel-on-late-shutdown contract here keeps
// the three branches from drifting on what happens between claim and
// dispatch. onSuccess receives the claimed QueuedCommand and decides
// whether to enqueue it (normal path) or mark the run failed (agent path).
const dispatchHeadlessCronCommand = (params: {
basePrompt: string
sourceId: string
sourceLabel: string
logSuffix: string
onSuccess: (command: QueuedCommand) => void | Promise<void>
}): void => {
if (inputClosed) return
void (async () => {
const command = await createAutonomyQueuedPromptIfNoActiveSource({
basePrompt: params.basePrompt,
trigger: 'scheduled-task',
currentDir: cwd(),
sourceId: params.sourceId,
sourceLabel: params.sourceLabel,
workload: WORKLOAD_CRON,
shouldCreate: () => !inputClosed,
})
if (!command) return
if (inputClosed) {
await cancelQueuedAutonomyCommands({ commands: [command] })
return
}
await params.onSuccess(command)
})().catch(error => {
logError(error)
logForDebugging(
`[ScheduledTasks] failed to enqueue headless task${params.logSuffix}: ${error}`,
{ level: 'error' },
)
})
}
const enqueueAndRun = (command: QueuedCommand): void => {
enqueue({
...command,
uuid: randomUUID(),
})
void run()
}
cronScheduler = cronSchedulerModule.createCronScheduler({
onFire: prompt => {
if (inputClosed) return
void (async () => {
// Use the prompt itself as the dedup source: legacy KAIROS-style
// cron entries fire the same prompt repeatedly, and without a
// dedicated task id the prompt text is what uniquely identifies
// the entry. Without source-dedup, repeated fires would stack
// additional runs while an earlier one is still active. Match the
// onFireTask branch below to keep the two paths consistent.
const command = await createAutonomyQueuedPromptIfNoActiveSource({
basePrompt: prompt,
trigger: 'scheduled-task',
currentDir: cwd(),
sourceId: prompt,
sourceLabel: prompt,
workload: WORKLOAD_CRON,
shouldCreate: () => !inputClosed,
})
if (!command) return
if (inputClosed) {
await cancelQueuedAutonomyCommands({ commands: [command] })
return
}
enqueue({
...command,
uuid: randomUUID(),
})
void run()
})().catch(error => {
logError(error)
logForDebugging(
`[ScheduledTasks] failed to enqueue headless task: ${error}`,
{
level: 'error',
},
)
// Legacy KAIROS-style entries: the prompt text is what uniquely
// identifies the cron entry, so it doubles as both source id and
// source label for dedup.
dispatchHeadlessCronCommand({
basePrompt: prompt,
sourceId: prompt,
sourceLabel: prompt,
logSuffix: '',
onSuccess: enqueueAndRun,
})
},
onFireTask: task => {
if (inputClosed) return
void (async () => {
if (task.agentId) {
const command = await createAutonomyQueuedPromptIfNoActiveSource({
basePrompt: task.prompt,
trigger: 'scheduled-task',
currentDir: cwd(),
sourceId: task.id,
sourceLabel: task.prompt,
workload: WORKLOAD_CRON,
shouldCreate: () => !inputClosed,
})
if (!command) return
if (inputClosed) {
await cancelQueuedAutonomyCommands({ commands: [command] })
return
}
await markAutonomyRunFailed(
command.autonomy!.runId,
`No teammate runtime available for scheduled task owner ${task.agentId} in headless mode.`,
command.autonomy!.rootDir,
)
return
}
const command = await createAutonomyQueuedPromptIfNoActiveSource({
if (task.agentId) {
dispatchHeadlessCronCommand({
basePrompt: task.prompt,
trigger: 'scheduled-task',
currentDir: cwd(),
sourceId: task.id,
sourceLabel: task.prompt,
workload: WORKLOAD_CRON,
shouldCreate: () => !inputClosed,
})
if (!command) return
if (inputClosed) {
await cancelQueuedAutonomyCommands({ commands: [command] })
return
}
enqueue({
...command,
uuid: randomUUID(),
})
void run()
})().catch(error => {
logError(error)
logForDebugging(
`[ScheduledTasks] failed to enqueue headless task ${task.id}: ${error}`,
{
level: 'error',
logSuffix: ` ${task.id}`,
onSuccess: async command => {
await markAutonomyRunFailed(
command.autonomy!.runId,
`No teammate runtime available for scheduled task owner ${task.agentId} in headless mode.`,
command.autonomy!.rootDir,
)
},
)
})
return
}
dispatchHeadlessCronCommand({
basePrompt: task.prompt,
sourceId: task.id,
sourceLabel: task.prompt,
logSuffix: ` ${task.id}`,
onSuccess: enqueueAndRun,
})
},
isLoading: () => running || inputClosed,