Fix runWave swallowing parent cancellation (D39.17 errata): return parent.Err() when no worker errored, so a Ctrl-C resume surfaces context.Canceled instead of a nil-deref panic or false exit-0 partial success; regression-pinned

backend/internal/pipeline/waverun.go

@@ -183,6 +183,15 @@ func (r *Runner) translateBookWaves(ctx context.Context, chunks []Chunk, stickyS
 // race-clean. Results are written by the callback into a caller-owned slice indexed by i, so the result
 // ORDER is deterministic (item index) regardless of completion order — the golden capture sorts the wire/log
 // side-effects separately. workers ≤ 0 is treated as 1 (LoadPipeline already clamps).
+//
+// PARENT CANCELLATION (Ctrl-C / SIGTERM — the CLI wires a signal.NotifyContext) is surfaced as an error too,
+// NOT a silent nil: the feeder drops the remaining items on ctx.Done(), and a worker need not observe the
+// cancellation to return (a $0 resume worker resolves entirely through its own opContext store reads, never
+// touching the cancellable ctx), so firstErr can stay nil while items are left UNDONE. Returning nil then
+// would let the caller index uninitialised result slots — a nil-deref on the edit-wave `*oc` assembly, or a
+// draft-only run reporting empty translations as exit-0 success. So after the workers drain, a still-nil
+// firstErr defers to parent.Err(): nil on a clean run, context.Canceled on an interrupted one (the durable
+// store stays correct — the undone items were never checkpointed, so a re-run resumes them).
 func (r *Runner) runWave(parent context.Context, workers, n int, work func(ctx context.Context, i int) error) error {
 	if workers < 1 {
 		workers = 1
@@ -224,8 +233,13 @@ func (r *Runner) runWave(parent context.Context, workers, n int, work func(ctx c
 	}
 	close(idxCh)
 	wg.Wait()
+	if firstErr != nil {
 		return firstErr
 	}
+	// No worker failed, but the PARENT may have been cancelled (Ctrl-C), which the feeder honoured by
+	// dropping items — surface that as an error so the driver never assembles a partial result as success.
+	return parent.Err()
+}
 
 // stageSeqResult is the outcome of running one chunk/unit through an ORDERED list of stages (one wave):
 // the per-stage results, the final OK stage's text, and the terminal flag state.

backend/internal/pipeline/waverun_test.go

@@ -133,6 +133,25 @@ func TestWaveMultiChunkEditUnit(t *testing.T) {
 	}
 }
 
+// TestRunWaveSurfacesParentCancellation pins the cancellation contract: when the PARENT context is
+// cancelled (a Ctrl-C / SIGTERM during a live run — main.go wires a signal.NotifyContext), runWave must
+// surface that as an ERROR, never a silent nil. The feeder drops the remaining items on ctx.Done(), and a
+// $0 resume worker never touches the cancellable ctx (its store ops use their own opContext), so firstErr
+// stays nil — without a parent.Err() check runWave returns nil with items UNDONE, and the driver then
+// indexes uninitialised result slots (an edit pipeline nil-derefs *oc; a draft-only run reports empty
+// translations as exit-0 success). A cancelled parent → a non-nil error is the fix's whole point.
+func TestRunWaveSurfacesParentCancellation(t *testing.T) {
+	r := &Runner{} // runWave touches no Runner field
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel() // the operator hit Ctrl-C before/at the wave boundary
+	// Workers return nil (a $0 resume worker never observes the cancellable ctx) — so firstErr stays nil
+	// and ONLY a parent-cancellation check can turn this into the error the driver needs.
+	err := r.runWave(ctx, 2, 8, func(context.Context, int) error { return nil })
+	if err == nil {
+		t.Fatal("runWave returned nil on a cancelled parent ctx — items are left undone and the driver indexes uninitialised result slots (nil-deref panic on an edit pipeline / silent exit-0 partial success on draft-only)")
+	}
+}
+
 // TestWaveParallelWorkersMoneyConserved runs the wave driver with several parallel workers over a book of
 // many chunks and asserts the money invariant survives concurrency: committed spend == the sum of the
 // settled checkpoints (the single-writer store serializes Reserve/Settle), and the per-unit result is