Fail the batch job when recording its end fails, and reconcile orphans
CI / ci (push) Successful in 2m55s
CI / ci (pull_request) Successful in 3m1s

finishBatch now returns its error, and treats a batch that is no longer
running as one, so a batch job never ends succeeded with its batch still
running. A batch left pending or running with its job ended (process
stopped, or the final status write failed) is failed inside startBatch,
before the active batch is read, so it never blocks a manual or
replenish batch. This replaces the boot-only FailInterruptedBatches.

Document suggestions.name in the architecture schema summary.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-06 23:59:40 -04:00
co-authored by Claude Opus 5.5
parent 4e2773703b
commit a6643aaa94
8 changed files with 88 additions and 51 deletions
+8 -5
View File
@@ -50,7 +50,8 @@ func (r batchResult) PublicJSON() ([]byte, error) { return json.Marshal(r) }
// batch, as does suggest_side_quests failing, with no Side quest made up
// instead. Each round's grounded Side quests are stored before the next
// round starts, so the deck fills as the batch goes. The batch ends done
// or failed; Side quests stored before a failure stay in the deck.
// or failed; Side quests stored before a failure stay in the deck. When
// recording the batch's end fails, so does the job.
func (s *Service) runBatch(ctx context.Context, p BatchJob, publish func(batchResult) error) (batchResult, error) {
n, err := db.New(s.st.Writer).StartSuggestionBatch(ctx, db.StartSuggestionBatchParams{
UpdatedAt: store.Now().String(),
@@ -65,12 +66,14 @@ func (s *Service) runBatch(ctx context.Context, p BatchJob, publish func(batchRe
res, err := s.fill(ctx, p.BatchID, publish)
write := context.WithoutCancel(ctx)
if err == nil {
s.finishBatch(write, p.BatchID, BatchDone)
if err := s.finishBatch(write, p.BatchID, BatchDone); err != nil {
return batchResult{}, err
}
return res, nil
}
s.finishBatch(write, p.BatchID, BatchFailed)
finishErr := s.finishBatch(write, p.BatchID, BatchFailed)
if ctx.Err() != nil {
return batchResult{}, ctx.Err()
return batchResult{}, errors.Join(ctx.Err(), finishErr)
}
var failure *jobs.Failure
if errors.As(err, &failure) {
@@ -78,7 +81,7 @@ func (s *Service) runBatch(ctx context.Context, p BatchJob, publish func(batchRe
// search provider's response.
s.logger.InfoContext(ctx, "suggestion batch failed", "batch_id", p.BatchID, "reason", failure.Code)
}
return batchResult{}, err
return batchResult{}, errors.Join(err, finishErr)
}
// fill does runBatch's work, returning a *jobs.Failure for a failure the