Retry transient requests after one and three minutes and coordinate provider recovery across processes with bounded probe intervals. Preserve completed results when recovery bookkeeping fails, keep concurrent failure accounting accurate, and expose retry state in the UI.
Persist manual requests until exchange confirmation, preserve stop protection, and reconcile fills before settling plans. Tighten model stream, crawler, skill, research accounting, and frontend race handling, with regression coverage. Keep queued analyses pending until a fresh account snapshot is available.
eezd