fix: a run started a moment ago is never judged dead — another dashboard's tmux list may predate it

Only the process that starts a pane writes it into its own cached tmux list
(noteSession); a second dashboard on the same database (a dev server) holds
a member list up to 15 s old, so its heal beat ended a Codex pane seconds
after it started and the proxy gateway answered 401. reconcileOrphans and
healRunId skip a run younger than 20 s (dashboard-runs.isYoungRun).
Tests: dashboard-runs (young vs old).

server/__tests__/dashboard-runs.test.js

@@ -22,8 +22,17 @@ before(() => {
 });
 after(() => fs.rmSync(ROOT, { recursive: true, force: true }));
 
+// Long enough ago that no reconcile treats the run as just started.
 const start = (id, extra = {}) =>
-  runs.recordRun({ id, mode: "interactive", cwd: "/r", status: "running", laneId: 4, ...extra });
+  runs.recordRun({
+    id,
+    mode: "interactive",
+    cwd: "/r",
+    status: "running",
+    laneId: 4,
+    startedAt: Date.parse("2026-01-01T00:00:00Z"),
+    ...extra,
+  });
 
 describe("dashboard-runs", () => {
   it("keeps the previous run of a pane as history when the pane starts again", () => {
@@ -77,6 +86,14 @@ describe("dashboard-runs", () => {
     assert.ok(runs.getRun("agenthub-lane-11"), "another tool's row stays");
   });
 
+  it("never ends a run started a moment ago: another process's tmux list may predate it", () => {
+    start("agenthub-lane-30", { laneId: 30, startedAt: Date.now() - 2000 });
+    start("agenthub-lane-31", { laneId: 31, startedAt: Date.now() - 60_000 });
+    runs.reconcileOrphans(() => false);
+    assert.equal(runs.getRun("agenthub-lane-30").status, "running");
+    assert.equal(runs.getRun("agenthub-lane-31").status, "abandoned");
+  });
+
   it("flags as abandoned only the running rows whose pane is gone", () => {
     start("agenthub-lane-5", { laneId: 5 });
     start("agenthub-lane-6", { laneId: 6 });

server/__tests__/s3-unseen-member-runs.test.js

@@ -31,7 +31,15 @@ const { healAllRunIds } = require("../routes/lanes");
 after(() => fs.rmSync(ROOT, { recursive: true, force: true }));
 
 const start = (id, laneId, cwd) =>
-  runs.recordRun({ id, mode: "interactive", cwd, status: "running", laneId, sessionId: `s-${id}` });
+  runs.recordRun({
+    id,
+    mode: "interactive",
+    cwd,
+    status: "running",
+    laneId,
+    sessionId: `s-${id}`,
+    startedAt: Date.parse("2026-01-01T00:00:00Z"),
+  });
 
 describe("a server without S3 on an S3 machine's database", () => {
   it("never ends a member's run, and still ends its own", () => {

server/lib/dashboard-runs.js

@@ -258,8 +258,21 @@ function claimToolSessions(sessionId = null) {
 }
 
 const runningStmt = db.prepare(
-  "SELECT id, tool, session_id, cwd FROM dashboard_runs WHERE status IN ('running', 'spawning')"
+  "SELECT id, tool, session_id, cwd, started_at FROM dashboard_runs WHERE status IN ('running', 'spawning')"
 );
+
+/**
+ * How long a new run is never judged dead. A tmux list is a cached answer —
+ * a member's may be up to 15 s old (tmux.js MEMBER_LIST_MAX_AGE_MS) — and only
+ * the process that started a pane writes it into its own cache, so another
+ * dashboard on the same database (a dev server) ended a pane it had simply
+ * not listed yet: the proxy gateway then answered 401 to a live Codex.
+ */
+const YOUNG_RUN_MS = 20_000;
+function isYoungRun(startedAt, now = Date.now()) {
+  const t = Date.parse(startedAt || "");
+  return Number.isFinite(t) && now - t < YOUNG_RUN_MS;
+}
 const endStmt = db.prepare(`
   UPDATE dashboard_runs
   SET status = @status,
@@ -300,7 +313,7 @@ function reconcileOrphans(isAlive = () => false) {
     let changes = 0;
     const { unseenMemberFolder } = require("./linux-accounts");
     for (const row of runningStmt.all()) {
-      if (isAlive(row.id) || unseenMemberFolder(row.cwd)) continue;
+      if (isAlive(row.id) || unseenMemberFolder(row.cwd) || isYoungRun(row.started_at)) continue;
       const interrupted =
         row.tool !== "shell" &&
         !!row.session_id &&
@@ -368,6 +381,7 @@ module.exports = {
   getRun,
   forgetShellRun,
   reconcileOrphans,
+  isYoungRun,
   listInterrupted,
   dismissInterrupted,
   proxyForSession,

server/routes/lanes.js

@@ -128,6 +128,10 @@ function healRunId(lane, live = null) {
   if (require("../lib/linux-accounts").unseenMemberFolder(lane.cwd)) return lane;
   if (live) {
     if (live.has(lane.run_id)) return lane;
+    // Started a moment ago: a cached list may not show it yet (dashboard-runs.js).
+    const dashboardRuns = require("../lib/dashboard-runs");
+    const row = dashboardRuns.getRun(lane.run_id);
+    if (row && row.status === "running" && dashboardRuns.isYoungRun(row.started_at)) return lane;
   } else {
     const run = runs.getRun(lane.run_id);
     if (run && run.status === "running") return lane;