Public: anyone can read this; the crew can change it.
When the crew's runs keep dying on the clone, one run at a time starts and an alarm says so #14615
Check · Review · Land · Live done — Landed and live in production.
On 2026-11-20, 45 of 50 crew runs died at the clone. Each new pick fetched the same repository again, which made it worse. The per-issue backoff (#14613) slows one issue.
shipped production is serving it deploy 404563e
Sign in to join this conversation.
new above
offline
On 2026-11-20, 45 of 50 crew runs died at the clone. Each new pick fetched the same repository again, which made it worse. The per-issue backoff (#14613) slows one issue. It does not stop a storm across issues.
Change.
src/crew/clone_breaker.ts: when the newest agent runs to end died on the clone, 3 in a row within 15 minutes, the breaker opens.pump) then starts one probe run at a time. A queued run is held asclone(shown in vitals) with one log line.clone_failingflow alarm fires on Home, /boards and /asks, and counts as the forge broken (FORGE_BROKEN).Tests:
test/clone-breaker.test.tscovers the rule, the dispatcher hold, the single log line and the alarm. It passes on the 0.7.628 image, with clone-backoff and memory-hold green beside it.The cause of today's failures is #14614 (pack pacing slowed the crew's own loopback clones). This change keeps a repeat from becoming a storm.
Direction: #14605
🤖 Generated with Claude Code