fix: anchor floor on re-enable; breaker on scheduled panic; propagate next-run err; reject negative interval; close phantom runs on startup
This commit is contained in:
@@ -6,6 +6,8 @@ import "context"
|
||||
// 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).
|
||||
// It also closes any run rows left stuck in "running" (finished_at NULL), which
|
||||
// would otherwise surface as perpetually "running" in the run-log modal.
|
||||
// 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'`)
|
||||
@@ -18,6 +20,11 @@ func (s *Store) ResetRunningOnStartup(ctx context.Context) (tasks int64, account
|
||||
return 0, accounts, err
|
||||
}
|
||||
tasks = ct.RowsAffected()
|
||||
_, err = s.Pool.Exec(ctx,
|
||||
`UPDATE runs SET status='error', finished_at=now() WHERE finished_at IS NULL`)
|
||||
if err != nil {
|
||||
return tasks, accounts, err
|
||||
}
|
||||
return tasks, accounts, nil
|
||||
}
|
||||
|
||||
|
||||
@@ -15,6 +15,7 @@ func TestResetRunningOnStartup(t *testing.T) {
|
||||
// simulate a crash mid-run
|
||||
_ = s.SetTaskStatus(ctx, taskID, "running")
|
||||
_ = s.SetAccountStatus(ctx, accID, "running")
|
||||
runID, _ := s.CreateRun(ctx, taskID, "manual") // phantom run: never finished
|
||||
|
||||
tn, an, err := s.ResetRunningOnStartup(ctx)
|
||||
if err != nil {
|
||||
@@ -31,6 +32,19 @@ func TestResetRunningOnStartup(t *testing.T) {
|
||||
if accs[0].Status == "running" {
|
||||
t.Fatal("account still running after reset")
|
||||
}
|
||||
runs, _ := s.ListRunsByTask(ctx, taskID)
|
||||
var found bool
|
||||
for _, r := range runs {
|
||||
if r.ID == runID {
|
||||
found = true
|
||||
if r.Status == "running" || r.FinishedAt == nil {
|
||||
t.Fatalf("phantom run %d still running: status=%s finished_at=%v", runID, r.Status, r.FinishedAt)
|
||||
}
|
||||
}
|
||||
}
|
||||
if !found {
|
||||
t.Fatalf("run %d not found", runID)
|
||||
}
|
||||
}
|
||||
|
||||
func TestClearStuckAccountAndReconcile(t *testing.T) {
|
||||
|
||||
@@ -56,6 +56,8 @@ func (s *Store) ListRunsByTask(ctx context.Context, taskID int64) ([]Run, error)
|
||||
|
||||
// LastFinishedRunAt returns the most recent finished run's timestamp, or nil if
|
||||
// the task has never completed a run — the baseline for the next scheduled run.
|
||||
// The same max(finished_at) rule is also inlined in ListSchedulableTasks's
|
||||
// subquery — keep the two in sync if this changes.
|
||||
func (s *Store) LastFinishedRunAt(ctx context.Context, taskID int64) (*time.Time, error) {
|
||||
var t *time.Time
|
||||
err := s.Pool.QueryRow(ctx,
|
||||
|
||||
Reference in New Issue
Block a user