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).
This commit is contained in:
2026-10-12 14:15:22 +07:00
parent 943ba03b76
commit 64173a5428
4 changed files with 47 additions and 4 deletions
+16 -2
View File
@@ -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,