fix(bootstrap): self-heal a systemd unit left on a retired plugin root

The residue an interrupted update leaves behind is invisible: the server
runs, every doctor row reads OK, and the unit quietly still names a cache
directory Claude Code deleted during the update. Nothing surfaces it until
a reboot, when the dashboard does not come back and nothing recorded why.

- fastPathOk now rejects a stale unit, so the next SessionStart repairs it
  instead of short-circuiting. `unitIsStale` is pure fs on purpose: that
  path runs on every session and may not spawn a process.
- Repairing the unit is not restarting the server. A current, healthy
  server keeps running and the corrected unit takes effect at the next
  start (`pendingSystemdRestart = systemdOwned && needsServer`), and the
  detached-spawn fallback is guarded by needsServer so a stale unit alone
  cannot start a second server onto a bound port.
- systemdOwned now also requires the unit to be ACTIVE. Installed-but-
  stopped owns nothing: skipping the stop there and asking systemd to start
  would bind an occupied port and crash-loop under Restart=always.
- /agenthub-doctor gains a systemd row naming the consequence ("will NOT
  come back after a reboot") and the fix. WARN, never FAIL — the dashboard
  in front of you works, and having no unit at all is a normal setup.

The fast-path test pins the regression against an otherwise fully healthy
install, live server included; without a live server it would have passed
against the unfixed code either way.

server/__tests__/plugin-bootstrap.test.js

@@ -129,6 +129,71 @@ describe("fast path", () => {
     );
     assert.equal(boot.fastPathOk(RT), false);
   });
+
+  it("is false when the systemd unit still names a retired plugin root", () => {
+    // The one failure a live server hides completely: everything is healthy
+    // until the next reboot, and then the dashboard never comes back because
+    // its unit points into a cache directory Claude Code has deleted. The fast
+    // path has to reject it, or no SessionStart ever repairs it.
+    //
+    // Everything else here is deliberately HEALTHY — including a live server,
+    // without which `fastPathOk` is false anyway and this test would pass
+    // against the unfixed code.
+    const ROOT = path.resolve(__dirname, "..", "..");
+    const pkg = require("../../package.json");
+    const infoPath = path.join(TMP_HOME, ".agenthub.json");
+    const prevHome = process.env.HOME;
+    // HOME first: `unitPath()` resolves against it, and computing the path
+    // before this line points every write in this test at the REAL
+    // ~/.config/systemd/user/agenthub.service — which the cleanup below then
+    // deletes. (Asked how I know.)
+    process.env.HOME = TMP_HOME;
+    const unit = require("../../scripts/systemd-service").unitPath("agenthub");
+    assert.ok(
+      unit.startsWith(TMP_HOME + path.sep),
+      `refusing to touch a unit outside the temp home: ${unit}`
+    );
+
+    const writeUnit = (workingDir) => {
+      fs.mkdirSync(path.dirname(unit), { recursive: true });
+      fs.writeFileSync(
+        unit,
+        "[Unit]\n# agenthub-managed-unit — regenerated on install, do not edit by hand\n" +
+          `[Service]\nWorkingDirectory=${workingDir}\n`,
+        "utf8"
+      );
+    };
+
+    try {
+      fs.mkdirSync(path.join(RT, "node_modules"), { recursive: true });
+      fs.writeFileSync(
+        infoPath,
+        JSON.stringify({ servers: [{ port: 4820, pid: process.pid, startedAt: "x" }] })
+      );
+      boot.writeState(
+        {
+          pluginVersion: pkg.version,
+          depsHash: boot.depsHash(),
+          pluginRoot: ROOT,
+          skillPluginsSettled: "nothing-missing",
+        },
+        RT
+      );
+
+      // Control: a unit naming THIS root is the steady state — fast path taken.
+      writeUnit(ROOT);
+      assert.equal(boot.fastPathOk(RT), true, "a current unit must not block the fast path");
+
+      // The regression: same healthy install, unit left on a retired root.
+      writeUnit("/plugins/cache/agenthub/deadbeef");
+      assert.equal(boot.fastPathOk(RT), false);
+    } finally {
+      fs.rmSync(infoPath, { force: true });
+      fs.rmSync(unit, { force: true });
+      if (prevHome === undefined) delete process.env.HOME;
+      else process.env.HOME = prevHome;
+    }
+  });
 });
 
 describe("skill-plugin auto-install gate", () => {

server/__tests__/plugin-doctor-systemd.test.js

@@ -0,0 +1,121 @@
+/**
+ * @file Tests the `systemd` row of scripts/plugin-doctor.js.
+ *
+ * The row exists for a failure nothing else in the report can see: a unit still
+ * naming a retired plugin cache directory leaves a running, healthy-looking
+ * dashboard that simply does not come back after the next reboot — it starts a
+ * path Claude Code deleted during the update. Every other row would read OK.
+ *
+ * WARN and never FAIL: the dashboard in front of the user works, and plenty of
+ * machines legitimately have no unit at all.
+ * @author Nguyễn Ngọc Trí Vĩ <vinnt@smartgift.vn>
+ */
+
+const { describe, it, beforeEach, after } = require("node:test");
+const assert = require("node:assert/strict");
+const fs = require("node:fs");
+const os = require("node:os");
+const path = require("node:path");
+
+const TMP_HOME = fs.mkdtempSync(path.join(os.tmpdir(), "agenthub-doctor-systemd-"));
+const prevHome = process.env.HOME;
+// Before anything resolves a unit path: `unitPath()` reads HOME, and a path
+// computed against the real one makes these tests rewrite the developer's own
+// ~/.config/systemd/user/agenthub.service.
+process.env.HOME = TMP_HOME;
+process.env.CLAUDE_HOME = path.join(TMP_HOME, ".claude");
+
+const svc = require("../../scripts/systemd-service");
+const { diagnose } = require("../../scripts/plugin-doctor");
+
+const UNIT = svc.unitPath("agenthub");
+const PLUGIN_ROOT = path.resolve(__dirname, "..", "..");
+
+assert.ok(UNIT.startsWith(TMP_HOME + path.sep), `refusing to touch ${UNIT}`);
+
+beforeEach(() => {
+  fs.rmSync(UNIT, { force: true });
+  // Claim systemd exists and the unit is running, so each test varies exactly
+  // one thing: the unit file on disk.
+  svc.__setExecImpl((args) => ({
+    status: 0,
+    stdout: args[0] === "is-active" ? "active\n" : "",
+  }));
+});
+
+after(() => {
+  svc.__reset();
+  if (prevHome === undefined) delete process.env.HOME;
+  else process.env.HOME = prevHome;
+  delete process.env.CLAUDE_HOME;
+  fs.rmSync(TMP_HOME, { recursive: true, force: true });
+});
+
+function row() {
+  const found = diagnose().find((r) => r.label === "systemd");
+  assert.ok(found, "the doctor must always emit a systemd row");
+  return found;
+}
+
+function writeUnit(workingDir) {
+  fs.mkdirSync(path.dirname(UNIT), { recursive: true });
+  fs.writeFileSync(
+    UNIT,
+    "[Unit]\n# agenthub-managed-unit — regenerated on install, do not edit by hand\n" +
+      `[Service]\nWorkingDirectory=${workingDir}\n`,
+    "utf8"
+  );
+}
+
+const linuxOnly = { skip: process.platform !== "linux" ? "systemd is Linux-only" : false };
+
+describe("plugin-doctor: systemd row", linuxOnly, () => {
+  it("warns, never fails, when the unit names a retired plugin root", () => {
+    writeUnit("/plugins/cache/sg/agenthub/deadbeef");
+    const r = row();
+
+    assert.equal(r.level, "warn", "a working dashboard must not fail the doctor run");
+    assert.match(r.detail, /previous plugin version/i);
+    // The consequence is the whole point — a reader who does not know it will
+    // ignore the row.
+    assert.match(r.detail, /reboot/i);
+    assert.match(r.detail, /plugin-bootstrap\.js --force|new Claude Code session/);
+  });
+
+  it("passes when the unit is current and running", () => {
+    writeUnit(PLUGIN_ROOT);
+    const r = row();
+
+    assert.equal(r.level, "ok", r.detail);
+    assert.match(r.detail, /current and running/i);
+  });
+
+  it("warns when the unit is current but stopped", () => {
+    writeUnit(PLUGIN_ROOT);
+    svc.__setExecImpl((args) => ({
+      status: 3,
+      stdout: args[0] === "is-active" ? "inactive\n" : "",
+    }));
+
+    const r = row();
+    assert.equal(r.level, "warn");
+    assert.match(r.detail, /not running/i);
+  });
+
+  it("reports no unit as fine, not as a problem", () => {
+    // A plugin install without `agenthub service install` is a normal setup:
+    // the server is started per session.
+    const r = row();
+    assert.equal(r.level, "ok", r.detail);
+    assert.match(r.detail, /no unit/i);
+  });
+
+  it("warns about a unit it did not write, and never claims it is stale", () => {
+    fs.mkdirSync(path.dirname(UNIT), { recursive: true });
+    fs.writeFileSync(UNIT, "[Service]\nExecStart=/opt/someone-elses-agenthub\n", "utf8");
+
+    const r = row();
+    assert.equal(r.level, "warn");
+    assert.match(r.detail, /not written by AgentHub|left untouched/i);
+  });
+});

server/__tests__/systemd-service.test.js

@@ -134,6 +134,53 @@ describe("systemd-service — restartUserService", linuxOnly, () => {
   });
 });
 
+describe("systemd-service — unitIsStale", linuxOnly, () => {
+  it("is true when the unit names a plugin root that is no longer the current one", () => {
+    // Invisible while the server runs, fatal at the next reboot: the unit
+    // starts a path Claude Code garbage-collected after the update.
+    svc.writeUserService({ ...UNIT, workingDir: "/plugin/root/old" });
+    assert.equal(svc.unitIsStale("agenthub", "/plugin/root/new"), true);
+  });
+
+  it("is false for a unit already naming the current root", () => {
+    svc.writeUserService(UNIT);
+    assert.equal(svc.unitIsStale("agenthub", "/plugin/root/new"), false);
+  });
+
+  it("is false when there is no unit, and for one we do not own", () => {
+    assert.equal(svc.unitIsStale("agenthub", "/plugin/root/new"), false);
+
+    fs.mkdirSync(path.dirname(svc.unitPath("agenthub")), { recursive: true });
+    fs.writeFileSync(svc.unitPath("agenthub"), "[Service]\nWorkingDirectory=/opt/mine\n", "utf8");
+    assert.equal(
+      svc.unitIsStale("agenthub", "/plugin/root/new"),
+      false,
+      "a foreign unit is not ours to call stale, or to rewrite"
+    );
+  });
+
+  it("spawns nothing — the bootstrap fast path runs it on every SessionStart", () => {
+    svc.writeUserService(UNIT);
+    calls = [];
+
+    svc.unitIsStale("agenthub", "/plugin/root/new");
+    assert.deepEqual(calls, []);
+  });
+});
+
+describe("systemd-service — unitIsActive", linuxOnly, () => {
+  it("is true only for `active`", () => {
+    svc.__setExecImpl((args) => ({ status: 0, stdout: args[0] === "is-active" ? "active\n" : "" }));
+    assert.equal(svc.unitIsActive("agenthub"), true);
+
+    svc.__setExecImpl((args) => ({
+      status: 3,
+      stdout: args[0] === "is-active" ? "inactive\n" : "",
+    }));
+    assert.equal(svc.unitIsActive("agenthub"), false);
+  });
+});
+
 describe("systemd-service — unitIsOurs", linuxOnly, () => {
   it("is false when no unit exists at all", () => {
     fs.rmSync(svc.unitPath("agenthub"), { force: true });