ordinary being 737492d4e1

fix(runtime): drain staged-terminal runs on shutdown before checkpointer teardown (#6620) ...

* fix(runtime): drain staged-terminal runs on shutdown before checkpointer teardown

RunManager.shutdown() selected only pending/running records, but with an event
store a run stages its terminal status in memory and keeps finalizing: journal
flush, delivery receipt, workspace scan, the duration checkpoint write and the
deferred terminal commit, all while terminal_commit_pending is set. A Gateway
shutdown landing in that window did not await the run, so langgraph_runtime
could close the checkpointer before the duration write landed - the #3373
class the drain exists to prevent.

Drain those records too, using the existing _awaits_terminal_commit state that
_renew_leases already relies on; await them without cancelling (a cancel would
skip their terminal tail) and never overwrite their staged terminal status
with interrupted.

* fix(runtime): surface shutdown terminal finalizer failures

Cover timed-out staged terminal runs for both commit barriers and terminal outcomes. Log failed finalizers with their run ID, staged status, and traceback while preserving status and completing the drain.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

2026-10-10 19:59:55 +08:00

..

deerflow

fix(runtime): drain staged-terminal runs on shutdown before checkpointer teardown (#6620)

2026-10-10 19:59:55 +08:00

pyproject.toml

feat(extensions): add host-bound Agent run control (#6190)

2026-10-03 21:16:01 +08:00