package scheduler

import (
	"context"
	"encoding/json"
	"fmt"
	"strings"
	"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

	// executions and activeRoleConfigs back the Phase 8 retro stage's
	// context-gathering (ListExecutions/GetActiveRoleConfig) — keyed the
	// same way the real storage.DB is (by task ID / role name).
	executions        map[string][]*storage.Execution
	activeRoleConfigs map[string]*storage.RoleConfigRow
}

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()
	e.Seq = int64(len(f.events)) + 1
	f.events = append(f.events, e)
	return nil
}

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

func (f *fakeStoryStore) ListExecutions(taskID string) ([]*storage.Execution, error) {
	f.mu.Lock()
	defer f.mu.Unlock()
	return f.executions[taskID], nil
}

func (f *fakeStoryStore) GetActiveRoleConfig(roleName string) (*storage.RoleConfigRow, error) {
	f.mu.Lock()
	defer f.mu.Unlock()
	row, ok := f.activeRoleConfigs[roleName]
	if !ok {
		return nil, fmt.Errorf("no active role config for %q", roleName)
	}
	return row, nil
}

func (f *fakeStoryStore) ListEvents(taskID string, sinceSeq int64) ([]*event.Event, error) {
	f.mu.Lock()
	defer f.mu.Unlock()
	var out []*event.Event
	for _, e := range f.events {
		if e.TaskID == taskID && e.Seq > sinceSeq {
			out = append(out, e)
		}
	}
	return out, 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_ArbitrationRejects_SetsStoryNeedsFix proves that
// when the arbitration task reports a structured approved=false verdict
// (via a KindVerdictReported event, the same one AgentChannel.ReportVerdict
// records), finalizeArbitration routes the story to NEEDS_FIX instead of
// unconditionally REVIEW_READY.
func TestStoryOrchestrator_ArbitrationRejects_SetsStoryNeedsFix(t *testing.T) {
	store, st, evaluators := seedStoryWithEvaluators(t, task.StateCompleted)

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

	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 agent calling report_verdict with a rejection
	// before finishing, the same event storeChannel.ReportVerdict records.
	payload, _ := json.Marshal(struct {
		Approved  bool   `json:"approved"`
		Reasoning string `json:"reasoning"`
	}{Approved: false, Reasoning: "breaks the running-log panel styling"})
	if err := store.CreateEvent(&event.Event{
		TaskID:  arb.ID,
		Kind:    event.KindVerdictReported,
		Actor:   event.ActorAgent,
		Payload: payload,
	}); err != nil {
		t.Fatalf("seed verdict event: %v", err)
	}

	store.setTaskState(arb.ID, task.StateCompleted)
	store.setTaskSummary(arb.ID, "found a real problem")

	orch.Tick(context.Background()) // finalizeArbitration runs

	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 != "NEEDS_FIX" {
		t.Errorf("story status: want NEEDS_FIX, got %q", got.Status)
	}
}

// TestStoryOrchestrator_ArbitrationApproves_SetsReviewReady proves the
// mirror case: an explicit approved=true verdict still routes to
// REVIEW_READY, same as today's unconditional behavior -- this isn't just
// "absence of a verdict defaults to proceed", a real approval also proceeds.
func TestStoryOrchestrator_ArbitrationApproves_SetsReviewReady(t *testing.T) {
	store, st, evaluators := seedStoryWithEvaluators(t, task.StateCompleted)

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

	arbitrations := store.dependentsWithRole(evaluators[0].ID, "planner")
	arb := arbitrations[0]

	payload, _ := json.Marshal(struct {
		Approved  bool   `json:"approved"`
		Reasoning string `json:"reasoning"`
	}{Approved: true, Reasoning: "meets all acceptance criteria"})
	if err := store.CreateEvent(&event.Event{
		TaskID:  arb.ID,
		Kind:    event.KindVerdictReported,
		Actor:   event.ActorAgent,
		Payload: payload,
	}); err != nil {
		t.Fatalf("seed verdict event: %v", err)
	}

	store.setTaskState(arb.ID, task.StateCompleted)
	store.setTaskSummary(arb.ID, "ship it")

	orch.Tick(context.Background())

	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)
	}
}

// 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))
	}
}

// seedDoneStory wires up a story whose entire Builder->Evaluators->
// Arbitration pipeline has already completed (mirroring what would actually
// be true of any real story by the time it reaches DONE) and whose status
// is DONE, returning the fakeStoryStore, story, root, evaluators, and
// arbitration task. Used by the Phase 8 retro-stage tests below.
func seedDoneStory(t *testing.T) (*fakeStoryStore, *story.Story, *task.Task, []*task.Task, *task.Task) {
	t.Helper()
	store, st, evaluators := seedStoryWithEvaluators(t, task.StateCompleted)
	st.Status = "DONE"

	ids := make([]string, len(evaluators))
	for i, ev := range evaluators {
		ids[i] = ev.ID
	}
	arb := &task.Task{
		ID:        "arbitration-1",
		Name:      "Arbitration",
		Agent:     task.AgentConfig{Role: arbitrationRole},
		DependsOn: ids,
		State:     task.StateCompleted,
		Summary:   "ship it",
	}
	store.tasks[arb.ID] = arb

	root, err := store.GetTask(st.RootTaskID)
	if err != nil {
		t.Fatal(err)
	}
	return store, st, root, evaluators, arb
}

// TestStoryOrchestrator_Retro_SpawnsRetroTask_WhenStoryDone is verification
// item (a): a story reaching DONE spawns exactly one retro-role task
// depending on the arbitration task, whose instructions contain the story's
// context (name and ID, at minimum).
func TestStoryOrchestrator_Retro_SpawnsRetroTask_WhenStoryDone(t *testing.T) {
	store, st, _, _, arb := seedDoneStory(t)

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

	retros := store.dependentsWithRole(arb.ID, retroRole)
	if len(retros) != 1 {
		t.Fatalf("expected exactly 1 retro task depending on the arbitration task, got %d", len(retros))
	}
	retro := retros[0]
	if retro.ParentTaskID != "" {
		t.Errorf("retro task should be a DAG sibling (no ParentTaskID), got %q", retro.ParentTaskID)
	}
	if retro.State != task.StateQueued {
		t.Errorf("retro task state: want QUEUED, got %v", retro.State)
	}
	if !strings.Contains(retro.Agent.Instructions, st.Name) || !strings.Contains(retro.Agent.Instructions, st.ID) {
		t.Errorf("retro instructions should contain the story's name/ID, got: %s", retro.Agent.Instructions)
	}
}

// TestStoryOrchestrator_Retro_DoesNotDuplicate is verification item (b):
// checking the same DONE story again does not spawn a second retro task.
func TestStoryOrchestrator_Retro_DoesNotDuplicate(t *testing.T) {
	store, _, _, _, arb := seedDoneStory(t)

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

	retros := store.dependentsWithRole(arb.ID, retroRole)
	if len(retros) != 1 {
		t.Fatalf("expected still exactly 1 retro task after repeated ticks, got %d", len(retros))
	}
}

// TestStoryOrchestrator_Retro_DoesNothing_UntilPipelineSettled proves
// processRetro never backfills a Builder/Evaluator/Arbitration task itself:
// a story marked DONE whose evaluators/arbitration don't actually exist yet
// (a hypothetical/malformed case — a real story never reaches DONE any
// other way) leaves the task tree untouched, exactly like
// TestStoryOrchestrator_SkipsTerminalStories already proves for the
// evaluator-spawning side of this.
func TestStoryOrchestrator_Retro_DoesNothing_UntilPipelineSettled(t *testing.T) {
	store := newFakeStoryStore()
	root := builderTask("builder-1", task.StateCompleted)
	store.tasks[root.ID] = root
	st := newStoryWithRoot("story-1", root.ID, "DONE")
	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 tasks spawned when the pipeline never actually ran, got %d", len(deps))
	}
}

// TestStoryOrchestrator_Retro_EmitsRetroCaptured_WhenRetroTaskCompletes is
// verification item (d): once the retro task reaches COMPLETED (via
// auto-accept from READY, exactly like every other task in this pipeline),
// KindRetroCaptured is emitted attached to the story's ID, aggregating every
// role_config_proposed event the retro task itself recorded plus its
// reported summary.
func TestStoryOrchestrator_Retro_EmitsRetroCaptured_WhenRetroTaskCompletes(t *testing.T) {
	store, st, _, _, arb := seedDoneStory(t)

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

	retros := store.dependentsWithRole(arb.ID, retroRole)
	if len(retros) != 1 {
		t.Fatalf("expected 1 retro task, got %d", len(retros))
	}
	retro := retros[0]

	// Simulate the retro agent having called propose_role_config twice
	// (recording KindRoleConfigProposed events attached to its own task ID,
	// exactly as storeChannel.ProposeRoleConfig does — see
	// internal/executor/channel.go) before finishing with a summary.
	mustMarshal := func(v any) json.RawMessage {
		b, err := json.Marshal(v)
		if err != nil {
			t.Fatal(err)
		}
		return b
	}
	store.CreateEvent(&event.Event{
		TaskID: retro.ID,
		Kind:   event.KindRoleConfigProposed,
		Actor:  event.ActorAgent,
		Payload: mustMarshal(struct {
			Role    string `json:"role"`
			Version int    `json:"version"`
		}{Role: "builder", Version: 2}),
	})
	store.CreateEvent(&event.Event{
		TaskID: retro.ID,
		Kind:   event.KindRoleConfigProposed,
		Actor:  event.ActorAgent,
		Payload: mustMarshal(struct {
			Role    string `json:"role"`
			Version int    `json:"version"`
		}{Role: "evaluator_quality", Version: 1}),
	})
	store.setTaskState(retro.ID, task.StateReady)
	store.setTaskSummary(retro.ID, "The builder over-escalated twice; tightening its system prompt should help.")

	// Tick 2: retro task auto-accepted to COMPLETED, retro_captured emitted.
	orch.Tick(context.Background())

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

	captured := store.eventsOfKind(event.KindRetroCaptured)
	if len(captured) != 1 {
		t.Fatalf("expected exactly 1 retro_captured event, got %d", len(captured))
	}
	if captured[0].TaskID != st.ID {
		t.Errorf("retro_captured should be attached to the story ID %q, got %q", st.ID, captured[0].TaskID)
	}
	var payload struct {
		TaskID    string `json:"task_id"`
		Proposals []struct {
			Role    string `json:"role"`
			Version int    `json:"version"`
		} `json:"proposals"`
		Summary string `json:"summary"`
	}
	if err := json.Unmarshal(captured[0].Payload, &payload); err != nil {
		t.Fatalf("unmarshal payload: %v", err)
	}
	if payload.TaskID != retro.ID {
		t.Errorf("payload.task_id: want %q, got %q", retro.ID, payload.TaskID)
	}
	if len(payload.Proposals) != 2 {
		t.Fatalf("expected 2 proposals in payload, got %d: %+v", len(payload.Proposals), payload.Proposals)
	}
	if payload.Proposals[0].Role != "builder" || payload.Proposals[0].Version != 2 {
		t.Errorf("proposal[0] mismatch: %+v", payload.Proposals[0])
	}
	if payload.Proposals[1].Role != "evaluator_quality" || payload.Proposals[1].Version != 1 {
		t.Errorf("proposal[1] mismatch: %+v", payload.Proposals[1])
	}
	if !strings.Contains(payload.Summary, "over-escalated") {
		t.Errorf("expected the retro's summary in the payload, got %q", payload.Summary)
	}

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