vasyansk
fa72f1b323
The run-cancel registry is in-memory; a container restart mid-run leaves accounts/tasks persisted as 'running' with no goroutine, wedging cancel (not-in-map -> 409) and blocking remove/re-run. - startup: ResetRunningOnStartup clears stale 'running' -> 'idle' on boot - cancel handler: when no live goroutine, ClearStuckAccount + ReconcileTaskStatus reset the stuck account (and its task) instead of returning 409 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01MMHQTtnQtQqL8muAXHr9kd
45 lines
1.7 KiB
Go
45 lines
1.7 KiB
Go
package store
|
|
|
|
import "context"
|
|
|
|
// ResetRunningOnStartup clears phantom "running" statuses left behind when the
|
|
// process died mid-run (crash, container restart). A fresh process has no
|
|
// in-flight goroutines, so any persisted "running" is stale and would otherwise
|
|
// wedge the task (the run-guard refuses to start, and accounts can't be edited).
|
|
// Returns how many task and account rows were reset.
|
|
func (s *Store) ResetRunningOnStartup(ctx context.Context) (tasks int64, accounts int64, err error) {
|
|
ct, err := s.Pool.Exec(ctx, `UPDATE accounts SET status='idle' WHERE status='running'`)
|
|
if err != nil {
|
|
return 0, 0, err
|
|
}
|
|
accounts = ct.RowsAffected()
|
|
ct, err = s.Pool.Exec(ctx, `UPDATE tasks SET status='idle' WHERE status='running'`)
|
|
if err != nil {
|
|
return 0, accounts, err
|
|
}
|
|
tasks = ct.RowsAffected()
|
|
return tasks, accounts, nil
|
|
}
|
|
|
|
// ClearStuckAccount resets an account stuck in "running" (no live goroutine) to
|
|
// "idle". Returns true if a stuck row was actually cleared.
|
|
func (s *Store) ClearStuckAccount(ctx context.Context, accountID int64) (bool, error) {
|
|
ct, err := s.Pool.Exec(ctx, `UPDATE accounts SET status='idle' WHERE id=$1 AND status='running'`, accountID)
|
|
if err != nil {
|
|
return false, err
|
|
}
|
|
return ct.RowsAffected() == 1, nil
|
|
}
|
|
|
|
// ReconcileTaskStatus moves a task out of "running" once none of its accounts
|
|
// are still running — used after clearing a stuck account so the task can be
|
|
// re-run or deleted again.
|
|
func (s *Store) ReconcileTaskStatus(ctx context.Context, taskID int64) error {
|
|
_, err := s.Pool.Exec(ctx,
|
|
`UPDATE tasks SET status='idle'
|
|
WHERE id=$1 AND status='running'
|
|
AND NOT EXISTS (SELECT 1 FROM accounts WHERE task_id=$1 AND status='running')`,
|
|
taskID)
|
|
return err
|
|
}
|