You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit b7b14bf
Browse filesBrowse the repository at this point in the historyBrowse files
fix(server): remote task followers read only their own task
RemoteDelegation.start resumes every open remote task at once, and each
follower read its parent's whole subagent list to find one task, then held
it across a wait of up to ten minutes. A parent with 1,441 tasks (35 MB of
payload) and 122 open ones made every restart decode ~170k records and hold
8 GB, so the server ran out of heap seconds after starting and crash-looped.
getThreadRecords now takes a subagentIds filter. Followers, and task_status
waits that re-read on every parent subagent.updated, read just their task.
Against a copy of the affected database the startup fan-out drops from 8.2 GB
retained over 21.6 s to 8 MB over 61 ms.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
"Start one child agent with only `task`. No parent history. Separate checkout or PR per child: `isolation:'worktree'`. Keep `taskId` for `task_status` and `task_cancel`. `target.environmentId` runs it on a linked machine, in the project with this repository unless `target.projectId` names one.",
76
+
"Start one child agent with only `task`. No parent history. Separate checkout or PR per child: `isolation:'worktree'`. Keep `taskId` for `task_status` and `task_cancel`.",
0 commit comments