summaryrefslogtreecommitdiff
path: root/internal/scheduler/story_orchestrator_test.go
blob: bee326d7b1599311ebff00f3a1a1b6f9581cda94 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
package scheduler

import (
	"context"
	"encoding/json"
	"fmt"
	"sync"
	"testing"

	"github.com/google/uuid"
	"github.com/thepeterstone/claudomator/internal/event"
	"github.com/thepeterstone/claudomator/internal/storage"
	"github.com/thepeterstone/claudomator/internal/story"
	"github.com/thepeterstone/claudomator/internal/task"
)

// fakeStoryStore is a minimal, in-memory implementation of StoryStore for
// unit-testing StoryOrchestrator without a real SQLite database. Mirrors the
// fakeStore pattern already used by scheduler_test.go for the Phase 5
// Scheduler.
type fakeStoryStore struct {
	mu      sync.Mutex
	stories map[string]*story.Story
	tasks   map[string]*task.Task
	events  []*event.Event
}

func newFakeStoryStore() *fakeStoryStore {
	return &fakeStoryStore{
		stories: make(map[string]*story.Story),
		tasks:   make(map[string]*task.Task),
	}
}

func (f *fakeStoryStore) ListStories(_ storage.StoryFilter) ([]*story.Story, error) {
	f.mu.Lock()
	defer f.mu.Unlock()
	var out []*story.Story
	for _, s := range f.stories {
		cp := *s
		out = append(out, &cp)
	}
	return out, nil
}

func (f *fakeStoryStore) UpdateStory(st *story.Story) error {
	f.mu.Lock()
	defer f.mu.Unlock()
	if _, ok := f.stories[st.ID]; !ok {
		return fmt.Errorf("story %q not found", st.ID)
	}
	cp := *st
	f.stories[st.ID] = &cp
	return nil
}

func (f *fakeStoryStore) GetTask(id string) (*task.Task, error) {
	f.mu.Lock()
	defer f.mu.Unlock()
	t, ok := f.tasks[id]
	if !ok {
		return nil, fmt.Errorf("task %q not found", id)
	}
	cp := *t
	return &cp, nil
}

func (f *fakeStoryStore) ListDependents(taskID string) ([]*task.Task, error) {
	f.mu.Lock()
	defer f.mu.Unlock()
	var out []*task.Task
	for _, t := range f.tasks {
		for _, d := range t.DependsOn {
			if d == taskID {
				cp := *t
				out = append(out, &cp)
				break
			}
		}
	}
	return out, nil
}

func (f *fakeStoryStore) CreateTask(t *task.Task) error {
	f.mu.Lock()
	defer f.mu.Unlock()
	if _, ok := f.tasks[t.ID]; ok {
		return fmt.Errorf("task %q already exists", t.ID)
	}
	cp := *t
	f.tasks[t.ID] = &cp
	return nil
}

func (f *fakeStoryStore) UpdateTaskState(id string, newState task.State) error {
	f.mu.Lock()
	defer f.mu.Unlock()
	t, ok := f.tasks[id]
	if !ok {
		return fmt.Errorf("task %q not found", id)
	}
	t.State = newState
	return nil
}

func (f *fakeStoryStore) CreateEvent(e *event.Event) error {
	f.mu.Lock()
	defer f.mu.Unlock()
	e.ID = uuid.NewString()
	f.events = append(f.events, e)
	return nil
}

func (f *fakeStoryStore) setTaskState(id string, s task.State) {
	f.mu.Lock()
	defer f.mu.Unlock()
	if t, ok := f.tasks[id]; ok {
		t.State = s
	}
}

func (f *fakeStoryStore) setTaskSummary(id, summary string) {
	f.mu.Lock()
	defer f.mu.Unlock()
	if t, ok := f.tasks[id]; ok {
		t.Summary = summary
	}
}

func (f *fakeStoryStore) eventsOfKind(k event.Kind) []*event.Event {
	f.mu.Lock()
	defer f.mu.Unlock()
	var out []*event.Event
	for _, e := range f.events {
		if e.Kind == k {
			out = append(out, e)
		}
	}
	return out
}

func (f *fakeStoryStore) dependentsWithRole(taskID, role string) []*task.Task {
	deps, _ := f.ListDependents(taskID)
	var out []*task.Task
	for _, d := range deps {
		if d.Agent.Role == role {
			out = append(out, d)
		}
	}
	return out
}

func builderTask(id string, state task.State) *task.Task {
	return &task.Task{
		ID:            id,
		Name:          "Builder",
		Agent:         task.AgentConfig{Type: "claude", Role: "builder", Instructions: "build it"},
		RepositoryURL: "git@example.com:org/repo.git",
		State:         state,
	}
}

func newStoryWithRoot(id, rootTaskID, status string) *story.Story {
	return &story.Story{ID: id, Name: "Test Story", Status: status, RootTaskID: rootTaskID}
}

// TestStoryOrchestrator_SpawnsEvaluators_WhenBuilderCompletes is verification
// item (a): a builder task reaching COMPLETED for a story spawns exactly 4
// evaluator tasks with correct roles/depends_on, moves the story to
// VALIDATING.
func TestStoryOrchestrator_SpawnsEvaluators_WhenBuilderCompletes(t *testing.T) {
	store := newFakeStoryStore()
	root := builderTask("builder-1", task.StateCompleted)
	store.tasks[root.ID] = root
	st := newStoryWithRoot("story-1", root.ID, "IN_PROGRESS")
	store.stories[st.ID] = st

	pool := &fakePool{}
	orch := &StoryOrchestrator{Store: store, Pool: pool}
	orch.Tick(context.Background())

	deps, err := store.ListDependents(root.ID)
	if err != nil {
		t.Fatal(err)
	}
	if len(deps) != 4 {
		t.Fatalf("expected 4 evaluator tasks, got %d: %+v", len(deps), deps)
	}
	gotRoles := map[string]bool{}
	for _, d := range deps {
		gotRoles[d.Agent.Role] = true
		if len(d.DependsOn) != 1 || d.DependsOn[0] != root.ID {
			t.Errorf("evaluator %s: DependsOn = %+v, want [%s]", d.ID, d.DependsOn, root.ID)
		}
		if d.ParentTaskID != "" {
			t.Errorf("evaluator %s: ParentTaskID = %q, want empty (DAG sibling, not subtask)", d.ID, d.ParentTaskID)
		}
		if d.State != task.StateQueued {
			t.Errorf("evaluator %s: State = %v, want QUEUED", d.ID, d.State)
		}
	}
	for _, r := range evaluatorRoles {
		if !gotRoles[r] {
			t.Errorf("missing evaluator with role %q", r)
		}
	}
	if pool.submitCount() != 4 {
		t.Fatalf("expected 4 pool submissions, got %d", pool.submitCount())
	}

	got, err := func() (*story.Story, error) {
		stories, err := store.ListStories(storage.StoryFilter{})
		if err != nil {
			return nil, err
		}
		for _, s := range stories {
			if s.ID == st.ID {
				return s, nil
			}
		}
		return nil, fmt.Errorf("not found")
	}()
	if err != nil {
		t.Fatal(err)
	}
	if got.Status != "VALIDATING" {
		t.Errorf("story status: want VALIDATING, got %q", got.Status)
	}
}

// TestStoryOrchestrator_DoesNotDuplicateEvaluators is verification item (b):
// re-checking the same story after evaluators already exist does not spawn
// duplicates.
func TestStoryOrchestrator_DoesNotDuplicateEvaluators(t *testing.T) {
	store := newFakeStoryStore()
	root := builderTask("builder-1", task.StateCompleted)
	store.tasks[root.ID] = root
	st := newStoryWithRoot("story-1", root.ID, "IN_PROGRESS")
	store.stories[st.ID] = st

	pool := &fakePool{}
	orch := &StoryOrchestrator{Store: store, Pool: pool}
	orch.Tick(context.Background())
	orch.Tick(context.Background())
	orch.Tick(context.Background())

	deps, _ := store.ListDependents(root.ID)
	if len(deps) != 4 {
		t.Fatalf("expected exactly 4 evaluator tasks after 3 ticks, got %d", len(deps))
	}
	if pool.submitCount() != 4 {
		t.Fatalf("expected exactly 4 submissions after 3 ticks, got %d", pool.submitCount())
	}
}

// evaluatorTask builds a completed (or not) evaluator task depending on
// rootID with the given role.
func evaluatorTask(id, rootID, role string, state task.State) *task.Task {
	return &task.Task{
		ID:        id,
		Name:      role,
		Agent:     task.AgentConfig{Role: role},
		DependsOn: []string{rootID},
		State:     state,
		Summary:   "looks good",
	}
}

// seedStoryWithEvaluators wires up a story whose builder is COMPLETED and
// whose 4 evaluators already exist (in the given state), returning the
// fakeStoryStore, story, and evaluator tasks (in evaluatorRoles order).
func seedStoryWithEvaluators(t *testing.T, evalState task.State) (*fakeStoryStore, *story.Story, []*task.Task) {
	t.Helper()
	store := newFakeStoryStore()
	root := builderTask("builder-1", task.StateCompleted)
	store.tasks[root.ID] = root
	st := newStoryWithRoot("story-1", root.ID, "VALIDATING")
	store.stories[st.ID] = st

	evaluators := make([]*task.Task, len(evaluatorRoles))
	for i, r := range evaluatorRoles {
		ev := evaluatorTask(fmt.Sprintf("eval-%d", i), root.ID, r, evalState)
		store.tasks[ev.ID] = ev
		evaluators[i] = ev
	}
	return store, st, evaluators
}

// TestStoryOrchestrator_SpawnsArbitration_WhenAllEvaluatorsComplete is
// verification item (c): all 4 evaluators reaching COMPLETED spawns exactly
// 1 arbitration task depending on all 4.
func TestStoryOrchestrator_SpawnsArbitration_WhenAllEvaluatorsComplete(t *testing.T) {
	store, _, evaluators := seedStoryWithEvaluators(t, task.StateCompleted)

	pool := &fakePool{}
	orch := &StoryOrchestrator{Store: store, Pool: pool}
	orch.Tick(context.Background())

	arbitrations := store.dependentsWithRole(evaluators[0].ID, "planner")
	if len(arbitrations) != 1 {
		t.Fatalf("expected exactly 1 arbitration task, got %d: %+v", len(arbitrations), arbitrations)
	}
	arb := arbitrations[0]
	if len(arb.DependsOn) != len(evaluators) {
		t.Fatalf("arbitration DependsOn = %+v, want all %d evaluator IDs", arb.DependsOn, len(evaluators))
	}
	for _, ev := range evaluators {
		if !dependsOnAll(arb, []string{ev.ID}) {
			t.Errorf("arbitration does not depend on evaluator %s", ev.ID)
		}
	}
	if arb.ParentTaskID != "" {
		t.Errorf("arbitration ParentTaskID = %q, want empty", arb.ParentTaskID)
	}
	if arb.State != task.StateQueued {
		t.Errorf("arbitration State = %v, want QUEUED", arb.State)
	}

	// Re-ticking must not spawn a second arbitration task.
	orch.Tick(context.Background())
	orch.Tick(context.Background())
	arbitrations = store.dependentsWithRole(evaluators[0].ID, "planner")
	if len(arbitrations) != 1 {
		t.Fatalf("expected exactly 1 arbitration task after repeated ticks, got %d", len(arbitrations))
	}
}

// TestStoryOrchestrator_DoesNotSpawnArbitration_UntilAllEvaluatorsComplete
// proves the fan-in gate: even with 3 of 4 evaluators COMPLETED, no
// arbitration task is created yet.
func TestStoryOrchestrator_DoesNotSpawnArbitration_UntilAllEvaluatorsComplete(t *testing.T) {
	store, _, evaluators := seedStoryWithEvaluators(t, task.StateCompleted)
	// Knock one evaluator back to RUNNING.
	store.setTaskState(evaluators[0].ID, task.StateRunning)

	pool := &fakePool{}
	orch := &StoryOrchestrator{Store: store, Pool: pool}
	orch.Tick(context.Background())

	arbitrations := store.dependentsWithRole(evaluators[0].ID, "planner")
	if len(arbitrations) != 0 {
		t.Fatalf("expected no arbitration task while an evaluator is incomplete, got %d", len(arbitrations))
	}
}

// TestStoryOrchestrator_EmitsEvalVerdict_OncePerEvaluator proves
// maybeEmitVerdict fires exactly once per completed evaluator, attached to
// the story's ID, even across repeated ticks.
func TestStoryOrchestrator_EmitsEvalVerdict_OncePerEvaluator(t *testing.T) {
	store, st, evaluators := seedStoryWithEvaluators(t, task.StateCompleted)

	pool := &fakePool{}
	orch := &StoryOrchestrator{Store: store, Pool: pool}
	orch.Tick(context.Background())
	orch.Tick(context.Background())
	orch.Tick(context.Background())

	verdicts := store.eventsOfKind(event.KindEvalVerdict)
	if len(verdicts) != len(evaluators) {
		t.Fatalf("expected exactly %d eval_verdict events, got %d", len(evaluators), len(verdicts))
	}
	seenTaskIDs := map[string]bool{}
	for _, e := range verdicts {
		if e.TaskID != st.ID {
			t.Errorf("eval_verdict event attached to %q, want story ID %q", e.TaskID, st.ID)
		}
		var payload struct {
			TaskID  string `json:"task_id"`
			Role    string `json:"role"`
			Summary string `json:"summary"`
		}
		if err := json.Unmarshal(e.Payload, &payload); err != nil {
			t.Fatalf("unmarshal payload: %v", err)
		}
		seenTaskIDs[payload.TaskID] = true
		if payload.Role == "" {
			t.Errorf("payload missing role: %+v", payload)
		}
		if payload.Summary != "looks good" {
			t.Errorf("payload summary = %q, want %q", payload.Summary, "looks good")
		}
	}
	for _, ev := range evaluators {
		if !seenTaskIDs[ev.ID] {
			t.Errorf("no eval_verdict event found for evaluator %s", ev.ID)
		}
	}
}

// TestStoryOrchestrator_ArbitrationCompletes_EmitsDecisionAndReviewReady is
// verification item (d): arbitration reaching COMPLETED emits
// KindArbitrationDecided and moves the story to REVIEW_READY.
func TestStoryOrchestrator_ArbitrationCompletes_EmitsDecisionAndReviewReady(t *testing.T) {
	store, st, evaluators := seedStoryWithEvaluators(t, task.StateCompleted)

	pool := &fakePool{}
	orch := &StoryOrchestrator{Store: store, Pool: pool}
	// Tick 1: spawns the arbitration task.
	orch.Tick(context.Background())

	arbitrations := store.dependentsWithRole(evaluators[0].ID, "planner")
	if len(arbitrations) != 1 {
		t.Fatalf("expected 1 arbitration task, got %d", len(arbitrations))
	}
	arb := arbitrations[0]
	store.setTaskState(arb.ID, task.StateCompleted)
	store.setTaskSummary(arb.ID, "ship it")

	// Tick 2: arbitration is now COMPLETED.
	orch.Tick(context.Background())

	decided := store.eventsOfKind(event.KindArbitrationDecided)
	if len(decided) != 1 {
		t.Fatalf("expected exactly 1 arbitration_decided event, got %d", len(decided))
	}
	if decided[0].TaskID != st.ID {
		t.Errorf("arbitration_decided attached to %q, want story ID %q", decided[0].TaskID, st.ID)
	}
	var payload struct {
		TaskID  string `json:"task_id"`
		Summary string `json:"summary"`
	}
	if err := json.Unmarshal(decided[0].Payload, &payload); err != nil {
		t.Fatalf("unmarshal payload: %v", err)
	}
	if payload.TaskID != arb.ID || payload.Summary != "ship it" {
		t.Errorf("unexpected payload: %+v", payload)
	}

	stories, _ := store.ListStories(storage.StoryFilter{})
	var got *story.Story
	for _, s := range stories {
		if s.ID == st.ID {
			got = s
		}
	}
	if got == nil {
		t.Fatal("story not found")
	}
	if got.Status != "REVIEW_READY" {
		t.Errorf("story status: want REVIEW_READY, got %q", got.Status)
	}

	// Tick 3+: must not re-emit or re-decide.
	orch.Tick(context.Background())
	orch.Tick(context.Background())
	decided = store.eventsOfKind(event.KindArbitrationDecided)
	if len(decided) != 1 {
		t.Fatalf("expected still exactly 1 arbitration_decided event after repeated ticks, got %d", len(decided))
	}
}

// TestStoryOrchestrator_DoesNothing_WhenBuilderNotComplete proves the
// orchestrator is inert for a story whose builder task hasn't reached
// COMPLETED yet and isn't auto-acceptable either (still RUNNING — not
// READY, so autoAccept has nothing to do).
func TestStoryOrchestrator_DoesNothing_WhenBuilderNotComplete(t *testing.T) {
	store := newFakeStoryStore()
	root := builderTask("builder-1", task.StateRunning)
	store.tasks[root.ID] = root
	st := newStoryWithRoot("story-1", root.ID, "IN_PROGRESS")
	store.stories[st.ID] = st

	pool := &fakePool{}
	orch := &StoryOrchestrator{Store: store, Pool: pool}
	orch.Tick(context.Background())

	deps, _ := store.ListDependents(root.ID)
	if len(deps) != 0 {
		t.Fatalf("expected no evaluator tasks while builder is RUNNING, got %d", len(deps))
	}
	if pool.submitCount() != 0 {
		t.Fatalf("expected no submissions, got %d", pool.submitCount())
	}
	got, err := store.GetTask(root.ID)
	if err != nil {
		t.Fatal(err)
	}
	if got.State != task.StateRunning {
		t.Errorf("builder state must be untouched: want RUNNING, got %v", got.State)
	}
}

// TestStoryOrchestrator_AutoAcceptsReadyBuilder is the core regression test
// for the auto-accept fix: a builder task sitting at READY (execution
// succeeded, awaiting what would otherwise be a manual
// POST /api/tasks/{id}/accept) is transitioned to COMPLETED by the
// orchestrator itself — with no external accept call — and, because that
// unblocks Stage 1 in the same tick, the 4 evaluators are spawned
// immediately too.
func TestStoryOrchestrator_AutoAcceptsReadyBuilder(t *testing.T) {
	store := newFakeStoryStore()
	root := builderTask("builder-1", task.StateReady)
	store.tasks[root.ID] = root
	st := newStoryWithRoot("story-1", root.ID, "IN_PROGRESS")
	store.stories[st.ID] = st

	pool := &fakePool{}
	orch := &StoryOrchestrator{Store: store, Pool: pool}
	orch.Tick(context.Background())

	got, err := store.GetTask(root.ID)
	if err != nil {
		t.Fatal(err)
	}
	if got.State != task.StateCompleted {
		t.Fatalf("builder should be auto-accepted to COMPLETED, got %v", got.State)
	}

	deps, _ := store.ListDependents(root.ID)
	if len(deps) != 4 {
		t.Fatalf("expected 4 evaluator tasks spawned in the same tick the builder auto-accepts, got %d", len(deps))
	}
}

// TestStoryOrchestrator_AutoAcceptsReadyEvaluators proves READY evaluator
// tasks are auto-accepted to COMPLETED by the orchestrator, with no external
// accept call, and that doing so unblocks arbitration spawning.
func TestStoryOrchestrator_AutoAcceptsReadyEvaluators(t *testing.T) {
	store, _, evaluators := seedStoryWithEvaluators(t, task.StateReady)

	pool := &fakePool{}
	orch := &StoryOrchestrator{Store: store, Pool: pool}
	orch.Tick(context.Background())

	for _, ev := range evaluators {
		got, err := store.GetTask(ev.ID)
		if err != nil {
			t.Fatal(err)
		}
		if got.State != task.StateCompleted {
			t.Errorf("evaluator %s should be auto-accepted to COMPLETED, got %v", ev.ID, got.State)
		}
	}

	arbitrations := store.dependentsWithRole(evaluators[0].ID, "planner")
	if len(arbitrations) != 1 {
		t.Fatalf("expected arbitration spawned once all evaluators auto-accept, got %d", len(arbitrations))
	}
}

// TestStoryOrchestrator_AutoAcceptsReadyArbitration proves a READY
// arbitration task is auto-accepted to COMPLETED by the orchestrator, with
// no external accept call, and that this in turn triggers
// finalizeArbitration (KindArbitrationDecided + REVIEW_READY) in the same
// tick.
func TestStoryOrchestrator_AutoAcceptsReadyArbitration(t *testing.T) {
	store, st, evaluators := seedStoryWithEvaluators(t, task.StateCompleted)

	pool := &fakePool{}
	orch := &StoryOrchestrator{Store: store, Pool: pool}
	// Tick 1: spawns the arbitration task (starts at QUEUED).
	orch.Tick(context.Background())

	arbitrations := store.dependentsWithRole(evaluators[0].ID, "planner")
	if len(arbitrations) != 1 {
		t.Fatalf("expected 1 arbitration task, got %d", len(arbitrations))
	}
	arb := arbitrations[0]
	// Simulate the arbitration's execution succeeding (RUNNING -> READY),
	// exactly as executor.Pool.handleRunResult would do for any top-level
	// task — without ever calling POST /api/tasks/{id}/accept.
	store.setTaskState(arb.ID, task.StateReady)
	store.setTaskSummary(arb.ID, "approved")

	// Tick 2: orchestrator must auto-accept READY -> COMPLETED itself.
	orch.Tick(context.Background())

	got, err := store.GetTask(arb.ID)
	if err != nil {
		t.Fatal(err)
	}
	if got.State != task.StateCompleted {
		t.Fatalf("arbitration should be auto-accepted to COMPLETED, got %v", got.State)
	}

	decided := store.eventsOfKind(event.KindArbitrationDecided)
	if len(decided) != 1 {
		t.Fatalf("expected exactly 1 arbitration_decided event after auto-accept, got %d", len(decided))
	}

	stories, _ := store.ListStories(storage.StoryFilter{})
	for _, s := range stories {
		if s.ID == st.ID && s.Status != "REVIEW_READY" {
			t.Errorf("story status: want REVIEW_READY after arbitration auto-accepts, got %q", s.Status)
		}
	}
}

// TestStoryOrchestrator_AutoAccept_DoesNotTouchUnrelatedReadyTask proves the
// auto-accept behavior is scoped to a story's own pipeline tasks (root task
// + its role-matched evaluator/arbitration dependents) and does not sweep up
// an unrelated READY task that merely happens to exist in the store.
func TestStoryOrchestrator_AutoAccept_DoesNotTouchUnrelatedReadyTask(t *testing.T) {
	store := newFakeStoryStore()
	root := builderTask("builder-1", task.StateCompleted)
	store.tasks[root.ID] = root
	st := newStoryWithRoot("story-1", root.ID, "IN_PROGRESS")
	store.stories[st.ID] = st

	unrelated := &task.Task{ID: "unrelated-1", Name: "unrelated", Agent: task.AgentConfig{Type: "claude"}, State: task.StateReady}
	store.tasks[unrelated.ID] = unrelated

	pool := &fakePool{}
	orch := &StoryOrchestrator{Store: store, Pool: pool}
	orch.Tick(context.Background())

	got, err := store.GetTask(unrelated.ID)
	if err != nil {
		t.Fatal(err)
	}
	if got.State != task.StateReady {
		t.Errorf("unrelated task must not be auto-accepted: want READY, got %v", got.State)
	}
}

// TestStoryOrchestrator_SkipsStoriesWithNoRootTask proves a story with no
// root_task_id set is left completely untouched.
func TestStoryOrchestrator_SkipsStoriesWithNoRootTask(t *testing.T) {
	store := newFakeStoryStore()
	st := &story.Story{ID: "story-1", Name: "no root yet", Status: "DISCOVERY"}
	store.stories[st.ID] = st

	pool := &fakePool{}
	orch := &StoryOrchestrator{Store: store, Pool: pool}
	orch.Tick(context.Background()) // must not panic or error despite no root task existing

	if pool.submitCount() != 0 {
		t.Fatalf("expected no submissions, got %d", pool.submitCount())
	}
}

// TestStoryOrchestrator_SkipsTerminalStories proves DONE/CANCELLED stories
// are never revisited, even if (hypothetically) their root task is
// COMPLETED and evaluators don't yet exist.
func TestStoryOrchestrator_SkipsTerminalStories(t *testing.T) {
	for _, status := range []string{"DONE", "CANCELLED"} {
		t.Run(status, func(t *testing.T) {
			store := newFakeStoryStore()
			root := builderTask("builder-1", task.StateCompleted)
			store.tasks[root.ID] = root
			st := newStoryWithRoot("story-1", root.ID, status)
			store.stories[st.ID] = st

			pool := &fakePool{}
			orch := &StoryOrchestrator{Store: store, Pool: pool}
			orch.Tick(context.Background())

			deps, _ := store.ListDependents(root.ID)
			if len(deps) != 0 {
				t.Fatalf("status %s: expected no evaluator tasks spawned, got %d", status, len(deps))
			}
		})
	}
}

// TestStoryOrchestrator_EndToEnd drives a story through the full chain —
// builder complete -> evaluators -> arbitration -> REVIEW_READY — using only
// the fake store/pool, proving the whole ceremony holds together end to end
// at the orchestrator level (verification item 5, the higher-level test).
//
// Every task in the chain is driven to READY (never directly to COMPLETED),
// mirroring exactly what executor.Pool.handleRunResult does for a real
// top-level task whose execution succeeds — proving the orchestrator's own
// auto-accept (not an external POST /api/tasks/{id}/accept call, which this
// test never makes) is what carries each task the rest of the way to
// COMPLETED and advances the story. The only accept call anywhere in this
// flow is the story-level one, which isn't part of this test — it's covered
// separately in internal/api's story accept-gate tests.
func TestStoryOrchestrator_EndToEnd(t *testing.T) {
	store := newFakeStoryStore()
	root := builderTask("builder-1", task.StatePending)
	store.tasks[root.ID] = root
	st := newStoryWithRoot("story-1", root.ID, "IN_PROGRESS")
	store.stories[st.ID] = st

	pool := &fakePool{}
	orch := &StoryOrchestrator{Store: store, Pool: pool}

	// Before the builder completes, nothing happens.
	orch.Tick(context.Background())
	if deps, _ := store.ListDependents(root.ID); len(deps) != 0 {
		t.Fatalf("expected no evaluators before builder completes, got %d", len(deps))
	}

	// Builder's execution succeeds (RUNNING -> READY, exactly like
	// handleRunResult) — no POST /api/tasks/{id}/accept call here.
	store.setTaskState(root.ID, task.StateReady)
	orch.Tick(context.Background())

	rootAfter, err := store.GetTask(root.ID)
	if err != nil {
		t.Fatal(err)
	}
	if rootAfter.State != task.StateCompleted {
		t.Fatalf("builder should be auto-accepted to COMPLETED without an accept call, got %v", rootAfter.State)
	}

	deps, _ := store.ListDependents(root.ID)
	if len(deps) != 4 {
		t.Fatalf("expected 4 evaluators, got %d", len(deps))
	}
	statusOf := func() string {
		stories, _ := store.ListStories(storage.StoryFilter{})
		for _, s := range stories {
			if s.ID == st.ID {
				return s.Status
			}
		}
		return ""
	}
	if statusOf() != "VALIDATING" {
		t.Fatalf("expected VALIDATING after evaluators spawn, got %q", statusOf())
	}

	// Evaluators' executions succeed one by one (READY, not COMPLETED);
	// arbitration must not spawn early.
	for i, d := range deps {
		store.setTaskState(d.ID, task.StateReady)
		store.setTaskSummary(d.ID, fmt.Sprintf("verdict %d", i))
		orch.Tick(context.Background())
		arbs := store.dependentsWithRole(deps[0].ID, "planner")
		if i < len(deps)-1 && len(arbs) != 0 {
			t.Fatalf("arbitration spawned too early, after %d/%d evaluators complete", i+1, len(deps))
		}
	}

	for _, d := range deps {
		got, err := store.GetTask(d.ID)
		if err != nil {
			t.Fatal(err)
		}
		if got.State != task.StateCompleted {
			t.Errorf("evaluator %s should be auto-accepted to COMPLETED, got %v", d.ID, got.State)
		}
	}

	arbs := store.dependentsWithRole(deps[0].ID, "planner")
	if len(arbs) != 1 {
		t.Fatalf("expected exactly 1 arbitration task, got %d", len(arbs))
	}
	arb := arbs[0]

	verdicts := store.eventsOfKind(event.KindEvalVerdict)
	if len(verdicts) != 4 {
		t.Fatalf("expected 4 eval_verdict events, got %d", len(verdicts))
	}

	// Arbitration's execution succeeds (READY, not COMPLETED).
	store.setTaskState(arb.ID, task.StateReady)
	store.setTaskSummary(arb.ID, "approved")
	orch.Tick(context.Background())

	arbAfter, err := store.GetTask(arb.ID)
	if err != nil {
		t.Fatal(err)
	}
	if arbAfter.State != task.StateCompleted {
		t.Fatalf("arbitration should be auto-accepted to COMPLETED, got %v", arbAfter.State)
	}

	if statusOf() != "REVIEW_READY" {
		t.Fatalf("expected REVIEW_READY after arbitration completes, got %q", statusOf())
	}
	decided := store.eventsOfKind(event.KindArbitrationDecided)
	if len(decided) != 1 {
		t.Fatalf("expected exactly 1 arbitration_decided event, got %d", len(decided))
	}
}