orchestra/internal/store/debt_projection_test.go

package store

import (
	"encoding/json"
	"testing"
	"time"

	"orchestra/internal/domain"
)

func debtEvent(id, typ, task string, payload map[string]any) domain.Event {
	b, _ := json.Marshal(payload)
	return domain.Event{ID: id, Type: typ, TaskID: task, Payload: b, At: time.Now().UTC()}
}

// The opencode shape from run 14: one harness failing the same way across
// several tasks. That is the recurrence the ledger exists to notice.
func TestProjectDebtGroupsOneFailureShapeAcrossTasks(t *testing.T) {
	events := []domain.Event{
		debtEvent("e1", "TaskFailed", "t1", map[string]any{"failure_class": "retry_limit", "harness_id": "workpc-opencode"}),
		debtEvent("e2", "TaskFailed", "t2", map[string]any{"failure_class": "retry_limit", "harness_id": "workpc-opencode"}),
		debtEvent("e3", "TaskFailed", "t3", map[string]any{"failure_class": "retry_limit", "harness_id": "workpc-opencode"}),
		debtEvent("e4", "TaskFailed", "t4", map[string]any{"failure_class": "retry_limit", "harness_id": "workpc-claude"}),
		// A handoff release is ordinary progress and must not become debt.
		debtEvent("e5", "TaskReleased", "t5", map[string]any{"handoff_ref": "sha256:abc", "harness_id": "workpc-claude"}),
	}
	ledger := ProjectDebt(events)
	if len(ledger.Items) != 2 {
		t.Fatalf("want one item per harness, got %d: %+v", len(ledger.Items), ledger.Items)
	}
	top := ledger.Items[0]
	if top.Recurrence() != 3 || top.AffectedTasks() != 3 {
		t.Fatalf("recurrence %d across %d tasks, want 3 and 3", top.Recurrence(), top.AffectedTasks())
	}
	if top.Class != domain.DebtOperational {
		t.Fatalf("class %q, want operational", top.Class)
	}
	if got := top.ID; got != "v1:operational:retry_limit:workpc-opencode:lease" {
		t.Fatalf("signature %q", got)
	}
	for _, o := range top.Observations {
		if o.EventID == "" || o.LegacyRef != "" {
			t.Fatalf("observation lost its event provenance: %+v", o)
		}
	}
}

// A lifecycle stop is the system working. Waiting for a human is not debt, and
// counting it would drown the real signal.
func TestProjectDebtIgnoresOrdinaryLifecycleStops(t *testing.T) {
	events := []domain.Event{
		debtEvent("e1", "TaskBlocked", "t1", map[string]any{"block_reason": "human_decision", "blocker": "which route"}),
		debtEvent("e2", "TaskBlocked", "t2", map[string]any{"block_reason": "trajectory_gate", "blocker": "confirm plan"}),
		debtEvent("e3", "TaskBlocked", "t3", map[string]any{"block_reason": "lease_expired", "blocker": "lease expired"}),
	}
	ledger := ProjectDebt(events)
	if len(ledger.Items) != 1 || ledger.Items[0].Class != domain.DebtOperational {
		t.Fatalf("want only the lease_expired item, got %+v", ledger.Items)
	}
}

// Incompleteness is part of the result. A ledger that stays silent about what
// it cannot record reads as "no operator cost" when it means "operator cost is
// not recorded anywhere".
func TestProjectDebtReportsWhatItCannotSee(t *testing.T) {
	ledger := ProjectDebt(nil)
	for _, g := range ledger.Gaps {
		if g.Reason == "" {
			t.Fatalf("gap %q has no reason", g.Kind)
		}
		// Slice B closed the two holes this ledger used to report about
		// itself. Every silence is now a fact about one history, never a kind
		// of evidence the system cannot record at all.
		if !g.Durable {
			t.Fatalf("gap %q is reported as unrecordable: %+v", g.Kind, g)
		}
	}
	var worker, manual bool
	for _, g := range ledger.Gaps {
		switch g.Kind {
		case domain.ObservationWorkerFailure:
			worker = true
		case domain.ObservationManualIntervention:
			manual = true
		}
	}
	if !worker || !manual {
		t.Fatalf("an empty history should still name both kinds as absent: %+v", ledger.Gaps)
	}
}

// The whole point of incidents. One worker stuck in a retry loop must not
// manufacture recurrence, while its intensity is still on the record.
func TestRecurrenceCountsIncidentsAndKeepsIntensitySeparate(t *testing.T) {
	closed := func(id, worker, task, epoch string, repeats int) domain.Event {
		b, _ := json.Marshal(domain.ObservationIncident{
			ID: id, WorkerID: worker, TaskID: task, LeaseEpoch: epoch,
			Signature:   "lease <id> not renewed: agent status idle and pane unchanged",
			Detail:      "lease " + task + " not renewed: agent status idle and pane unchanged",
			RepeatCount: repeats, CloseReason: domain.ObservationCloseEpochChange,
		})
		return domain.Event{ID: id, Type: domain.EventObservationIncidentClosed, TaskID: "system", Payload: b}
	}
	ledger := ProjectDebt([]domain.Event{
		closed("i1", "workpc-claude", "task-a", "e1", 301),
		closed("i2", "workpc-claude", "task-b", "e2", 2),
	})
	if len(ledger.Items) != 1 {
		t.Fatalf("one kind of failure produced %d items", len(ledger.Items))
	}
	item := ledger.Items[0]
	if len(item.Observations) != 2 {
		t.Fatalf("recurrence = %d, want one per incident", len(item.Observations))
	}
	intensity := 0
	for _, o := range item.Observations {
		if o.Kind != domain.ObservationWorkerFailure {
			t.Fatalf("observation kind = %q", o.Kind)
		}
		intensity += o.Repeats
	}
	if intensity != 303 {
		t.Fatalf("intensity = %d, want 303 carried alongside a recurrence of 2", intensity)
	}
	tasks := map[string]bool{}
	for _, o := range item.Observations {
		tasks[o.TaskID] = true
	}
	if len(tasks) != 2 {
		t.Fatalf("the two incidents are not attributed to their tasks: %+v", item.Observations)
	}
}

// A repair the operator made by hand is evidence like any other, once they say
// it happened.
func TestAnOperatorRepairBecomesDebtEvidence(t *testing.T) {
	b, _ := json.Marshal(domain.OperatorIntervention{
		WorkerID: "workpc-opencode", Kind: domain.InterventionTransactionClean,
		Reason: "deleted a release transaction stuck at prepared so the pane could be reused",
	})
	ledger := ProjectDebt([]domain.Event{{
		ID: "i1", Type: domain.EventOperatorInterventionRecorded, TaskID: "system", Payload: b,
	}})
	if len(ledger.Items) != 1 || len(ledger.Items[0].Observations) != 1 {
		t.Fatalf("the repair produced no debt evidence: %+v", ledger.Items)
	}
	if got := ledger.Items[0].Observations[0].Kind; got != domain.ObservationManualIntervention {
		t.Fatalf("kind = %q", got)
	}
	for _, g := range ledger.Gaps {
		if g.Kind == domain.ObservationManualIntervention {
			t.Fatal("manual intervention is still reported as missing from a history that contains one")
		}
	}
}