memory-eternal 0.10.16 → 0.10.18

package/lib/watchdog.js

@@ -463,6 +463,39 @@ export async function waitForServedVersion(port, expect, { timeoutMs = 15000, in
   }
 }
 
+/**
+ * 等「**新实例真的接管了**」：端口服着期望版本 **且** 锁里出现一个不在 `beforePids` 里的活看门狗。
+ *
+ * 为什么不能只看版本（issue #28 的根）：升级前后版本号常常相同、或旧实例本来就是这个版本 ——
+ * 那时「端口服着 vX」与「替换还没发生」同时为真，只看版本的自检会立刻通过。实测现场：
+ * `restart` 打印「自检通过：端口 7999 正在服务 v0.10.16（等待 0s）」，紧接着 `status` 说
+ * 「锁文件里没有登记的看门狗（没有常驻实例）」—— 状态自相矛盾，面板据此给出的结论也会是错的。
+ *
+ * @returns {Promise<{ok:boolean, version:string, waitedMs:number, tookOver:boolean}>}
+ */
+export async function waitForTakeover(port, expect, {
+  env = process.env, beforePids = new Set(), timeoutMs = 25000, intervalMs = 500,
+  probe, sleep, readLock,
+} = {}) {
+  const p = Number(port) || 0
+  const want = String(expect || '')
+  const probeVersion = probe || probeServedVersion
+  const sleepFn = sleep || ((ms) => new Promise((r) => setTimeout(r, ms)))
+  const lockOf = readLock || ((e) => readWatchdogLock(e))
+  const start = Date.now()
+  let version = ''
+  for (;;) {
+    try { version = String((await probeVersion(p)) || '') } catch { version = '' }
+    let fresh = []
+    try {
+      fresh = lockOf(env).watchdogs.filter((w) => Number(w.port) === p && isPidAlive(w.pid) && !beforePids.has(Number(w.pid)))
+    } catch { fresh = [] }
+    if (version && version === want && fresh.length) return { ok: true, version, waitedMs: Date.now() - start, tookOver: true }
+    if (Date.now() - start >= Math.max(0, Number(timeoutMs) || 0)) return { ok: false, version, waitedMs: Date.now() - start, tookOver: false }
+    await sleepFn(Math.max(50, Number(intervalMs) || 500))
+  }
+}
+
 // -- 常驻实例的「版本漂移自愈」--------------------------------------------------
 //
 // 为什么需要它：常驻 web（默认 7999）**比 DSH 宿主活得久**。升级 npm 包只换磁盘上的
@@ -601,6 +634,8 @@ export async function restartResident({
   const p = Number(port) || 7999
   const expect = String(expectVersion !== undefined ? expectVersion : currentPkgVersion())
   const before = readWatchdogLock(env).watchdogs.filter((w) => Number(w.port) === p)
+  // 替换**前**就存在的 pid（看门狗 + 它拉起的 web）：自检时用来区分「还是那个旧实例」与「新实例接管了」
+  const beforePids = new Set(before.flatMap((w) => [Number(w.pid), Number(w.webPid) || 0]).filter((n) => n > 0))
   let helperPid = 0
   try {
     const child = (deps.spawnHelper || spawnReplaceHelper)({ port: p, vaultRoot, interval, maxRestart })
@@ -609,7 +644,15 @@ export async function restartResident({
     return { ok: false, stage: 'spawn-helper', expect, served: '', waitedMs: 0, helperPid: 0, before, error: String(error?.message || error) }
   }
   let check = { ok: false, version: '', waitedMs: 0 }
-  try { check = await (deps.waitForServedVersion || waitForServedVersion)(p, expect, { timeoutMs }) } catch { check = { ok: false, version: '', waitedMs: 0 } }
+  try {
+    // 只看版本会被**旧实例**骗过（版本号常常没变）→ 自检必须等到「新看门狗接管」才认成功（#28）
+    check = await (deps.waitForTakeover || waitForTakeover)(p, expect, {
+      env, beforePids, timeoutMs,
+      probe: deps.probeServedVersion,
+      sleep: deps.sleep,
+      readLock: deps.readLock,
+    })
+  } catch { check = { ok: false, version: '', waitedMs: 0 } }
   return {
     ok: Boolean(check.ok),
     stage: check.ok ? 'done' : 'verify',
@@ -618,7 +661,12 @@ export async function restartResident({
     waitedMs: Number(check.waitedMs) || 0,
     helperPid,
     before,
-    error: check.ok ? undefined : `端口 ${p} 上服务的版本是 ${check.version || '（无响应）'}，本机是 ${expect || '?'}`,
+    // 失败原因要分清两种：版本不对（旧实例还在服务）与**没人接管**（端口服务着期望版本，
+    // 但锁里没有新的活看门狗 —— 端口上那只是旧实例/孤儿）
+    error: check.ok ? undefined : (check.version === expect && !check.tookOver
+      ? `端口 ${p} 服务着 v${check.version}，但没有新看门狗接管它（端口上可能仍是替换前的旧实例或孤儿）`
+      : `端口 ${p} 上服务的版本是 ${check.version || '（无响应）'}，本机是 ${expect || '?'}`),
+    tookOver: Boolean(check.tookOver),
   }
 }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "memory-eternal",
-  "version": "0.10.16",
+  "version": "0.10.18",
   "description": "记忆核心（Memory Eternal）：自研的 DeepSeek Harness 记忆插件，不移植任何既有记忆框架——对话结束后自动沉淀知识卡到本地 Markdown Vault（自研去重、自研 CJK 检索、可 git 管理），设置页提供图形化知识库（统计 / 搜索 / 知识图谱 + 侧边栏一键弹窗），Agent 通过 memory_recall 工具按需召回历史上下文。零人工干预。",
   "license": "MIT",
   "repository": {
@@ -64,7 +64,7 @@
     "prepublishOnly": "node build.mjs",
     "release": "node scripts/release.mjs",
     "release:dry": "node scripts/release.mjs --dry-run",
-    "test": "node build.mjs && node tests/vault.test.mjs && node tests/capture.test.mjs && node tests/capture-route.test.mjs && node tests/stall.test.mjs && node tests/vault-path.test.mjs && node tests/vault-resolve.test.mjs && node tests/minhash.test.mjs && node tests/settings-save.test.mjs && node tests/config-coverage.test.mjs && node tests/config-sync.test.mjs && node tests/config-merge.test.mjs && node tests/sse.test.mjs && node tests/api.test.mjs && node tests/import-roundtrip.test.mjs && node tests/graph-perf.test.mjs && node tests/settings-compat.test.mjs && node tests/node-bin.test.mjs && node tests/watchdog-lock.test.mjs && node tests/markdown.test.mjs && node tests/feedback.test.mjs && node tests/graph-lod.test.mjs && node tests/ssr.test.mjs && node tests/web-assets.test.mjs && node tests/manifests.test.mjs && node tests/two-store.test.mjs && node tests/noise-gate.test.mjs && node tests/e2e-recall.test.mjs && node tests/issue-fixes.test.mjs && node tests/issue-fixes-2.test.mjs && node tests/issue-fixes-3.test.mjs && node tests/watchdog-orphans.test.mjs && node tests/watchdog-restart.test.mjs && node tests/readme-i18n.test.mjs && node tests/issue-fixes-4.test.mjs && node tests/host-drain.test.mjs && node tests/e2e-host-drain.mjs && node tests/issue-fixes-5.test.mjs && node tests/issue-fixes-6.test.mjs && node tests/capture-json-repair.test.mjs && node tests/csrf-origin.test.mjs && node tests/watchdog-orphan-web.test.mjs"
+    "test": "node build.mjs && node tests/vault.test.mjs && node tests/capture.test.mjs && node tests/capture-route.test.mjs && node tests/stall.test.mjs && node tests/vault-path.test.mjs && node tests/vault-resolve.test.mjs && node tests/minhash.test.mjs && node tests/settings-save.test.mjs && node tests/config-coverage.test.mjs && node tests/config-sync.test.mjs && node tests/config-merge.test.mjs && node tests/sse.test.mjs && node tests/api.test.mjs && node tests/import-roundtrip.test.mjs && node tests/graph-perf.test.mjs && node tests/settings-compat.test.mjs && node tests/node-bin.test.mjs && node tests/watchdog-lock.test.mjs && node tests/markdown.test.mjs && node tests/feedback.test.mjs && node tests/graph-lod.test.mjs && node tests/ssr.test.mjs && node tests/web-assets.test.mjs && node tests/manifests.test.mjs && node tests/two-store.test.mjs && node tests/noise-gate.test.mjs && node tests/e2e-recall.test.mjs && node tests/issue-fixes.test.mjs && node tests/issue-fixes-2.test.mjs && node tests/issue-fixes-3.test.mjs && node tests/watchdog-orphans.test.mjs && node tests/watchdog-restart.test.mjs && node tests/readme-i18n.test.mjs && node tests/issue-fixes-4.test.mjs && node tests/host-drain.test.mjs && node tests/e2e-host-drain.mjs && node tests/issue-fixes-5.test.mjs && node tests/issue-fixes-6.test.mjs && node tests/capture-json-repair.test.mjs && node tests/csrf-origin.test.mjs && node tests/watchdog-orphan-web.test.mjs && node tests/config-validate.test.mjs"
   },
   "dependencies": {
     "@deepseek-ai/schemastery": "^3.18.1"