iop/packages/go/agenttask/manager_integration_test.go

package agenttask

import (
	"context"
	"fmt"
	"strings"
	"testing"
	"time"
)

func TestManagerS03S16MultiProjectManualResumeAndParallelTrace(t *testing.T) {
	projectA := testSnapshot(
		"project-a", "shared-workspace",
		testUnit("a-disjoint", WriteSetDisjoint),
		testUnit("a-overlap", WriteSetOverlap),
	)
	projectB := testSnapshot(
		"project-b", "workspace-b",
		testUnit("b-unknown", WriteSetUnknown),
	)
	unselected := testSnapshot(
		"unselected", "workspace-unselected",
		testUnit("must-not-run", WriteSetUnknown),
	)
	harness := newHarness(
		t,
		map[ProjectID]ProjectWorkflowSnapshot{
			"project-a": projectA, "project-b": projectB, "unselected": unselected,
		},
		3,
	)
	for _, workID := range []WorkUnitID{"a-disjoint", "a-overlap", "b-unknown"} {
		harness.invoker.delays[workID] = 20 * time.Millisecond
	}
	harness.start("project-a", "shared-workspace", nil)
	harness.start("project-b", "workspace-b", nil)
	if err := harness.manager.Reconcile(context.Background()); err != nil {
		t.Fatalf("Reconcile: %v", err)
	}
	state := harness.store.snapshot()
	if state.Projects["project-a"].Status != ProjectStatusCompleted ||
		state.Projects["project-b"].Status != ProjectStatusCompleted {
		t.Fatalf(
			"manual projects = %s/%s",
			state.Projects["project-a"].Status, state.Projects["project-b"].Status,
		)
	}
	if state.Projects["unselected"].Status != ProjectStatusObserved {
		t.Fatalf("unselected project status = %s", state.Projects["unselected"].Status)
	}
	if harness.invoker.callCount() != 3 {
		t.Fatalf("invocations = %d, want selected work only", harness.invoker.callCount())
	}
	if harness.invoker.maxConcurrency() < 2 {
		t.Fatalf("max concurrency = %d, want isolated parallel dispatch", harness.invoker.maxConcurrency())
	}
	trace := make([]string, 0)
	for _, event := range harness.events.snapshot() {
		if event.Type != EventDispatchStarted && event.Type != EventIntegrationResult {
			continue
		}
		trace = append(trace, fmt.Sprintf(
			"%s:%s:%s:%d:%s:%s",
			event.Type, event.ProjectID, event.WorkUnitID, event.Ordinal,
			event.WriteSetKind, event.IsolationMode,
		))
		if event.WorkUnitID == "must-not-run" {
			t.Fatalf("unselected work appeared in execution trace: %v", trace)
		}
	}
	joined := strings.Join(trace, "\n")
	for _, expected := range []string{"a-disjoint", "a-overlap", "b-unknown"} {
		if !strings.Contains(joined, expected) {
			t.Fatalf("trace missing %s:\n%s", expected, joined)
		}
	}
	t.Logf(
		"S03 trace: unselected_invocations=0 manual_projects=2 terminal=2; "+
			"S16 trace: explicit_dependency_only=true isolated_parallel_max=%d integration_ordinals=%v\n%s",
		harness.invoker.maxConcurrency(), harness.integrator.ordinals(), joined,
	)
}

func TestManagerWorkflowEvidenceGateAndPiRepair(t *testing.T) {
	t.Run("complete evidence invokes review", func(t *testing.T) {
		harness := newHarness(t, map[ProjectID]ProjectWorkflowSnapshot{
			"project": testSnapshot("project", "workspace", testUnit("work", WriteSetUnknown)),
		}, 1)
		harness.start("project", "workspace", nil)
		if err := harness.manager.Reconcile(context.Background()); err != nil {
			t.Fatalf("Reconcile: %v", err)
		}
		if harness.reviewer.callCount() != 1 {
			t.Fatalf("review calls = %d, want 1", harness.reviewer.callCount())
		}
	})

	for _, test := range []struct {
		name       string
		configure  func(*managerHarness)
		wantCode   BlockerCode
		wantRepair int
	}{
		{
			name: "placeholder from another provider never repairs or reviews",
			configure: func(harness *managerHarness) {
				harness.evidence.observeFunc = func(request WorkflowEvidenceRequest, _ int) (ArtifactEvidence, error) {
					return ArtifactEvidence{
						Active: true, Identity: artifactIdentity(request.Project, request.Work, request.Submission),
						Completeness: ArtifactPlaceholder,
					}, nil
				}
			},
			wantCode: BlockerEvidenceRepairDenied,
		},
		{
			name: "wrong active artifact identity never invokes review",
			configure: func(harness *managerHarness) {
				harness.evidence.observeFunc = func(request WorkflowEvidenceRequest, _ int) (ArtifactEvidence, error) {
					identity := artifactIdentity(request.Project, request.Work, request.Submission)
					identity.AttemptID = "stale-attempt"
					return ArtifactEvidence{Active: true, Identity: identity, Completeness: ArtifactComplete}, nil
				}
			},
			wantCode: BlockerArtifactMismatch,
		},
		{
			name: "Pi repair rejects a stale native locator",
			configure: func(harness *managerHarness) {
				harness.manager.selector = fakeSelector{capacity: 1, providerID: "pi"}
				harness.invoker.locators["work"] = []LocatorRecord{{
					Kind: LocatorSession, Opaque: "native-session", Revision: "session-r1",
					ProjectID: "project", WorkspaceID: "workspace", WorkUnitID: "work", AttemptID: attemptID("work", 1),
				}}
				harness.evidence.observeFunc = func(request WorkflowEvidenceRequest, _ int) (ArtifactEvidence, error) {
					identity := artifactIdentity(request.Project, request.Work, request.Submission)
					return ArtifactEvidence{
						Active: true, Identity: identity, Completeness: ArtifactPlaceholder,
						RepairIntent: &EvidenceRepairIntent{
							Identity: identity, DispatchOrdinal: request.Work.DispatchOrdinal,
							NativeLocator: LocatorRecord{
								Kind: LocatorSession, Opaque: "stale-session", Revision: "session-r1",
								ProjectID: "project", WorkspaceID: "workspace", WorkUnitID: "work", AttemptID: attemptID("work", 1),
							},
						},
					}, nil
				}
			},
			wantCode: BlockerEvidenceRepairDenied,
		},
	} {
		t.Run(test.name, func(t *testing.T) {
			harness := newHarness(t, map[ProjectID]ProjectWorkflowSnapshot{
				"project": testSnapshot("project", "workspace", testUnit("work", WriteSetUnknown)),
			}, 1)
			test.configure(harness)
			harness.start("project", "workspace", nil)
			if err := harness.manager.Reconcile(context.Background()); err != nil {
				t.Fatalf("Reconcile: %v", err)
			}
			work := harness.store.snapshot().Projects["project"].Works["work"]
			if work.Blocker == nil || work.Blocker.Code != test.wantCode {
				t.Fatalf("work blocker = %#v, want %q", work.Blocker, test.wantCode)
			}
			if harness.reviewer.callCount() != 0 {
				t.Fatalf("review calls = %d, want 0", harness.reviewer.callCount())
			}
			_, repairs := harness.evidence.counts()
			if repairs != test.wantRepair {
				t.Fatalf("repair calls = %d, want %d", repairs, test.wantRepair)
			}
		})
	}

	t.Run("Pi repair rematches before review", func(t *testing.T) {
		harness := newHarness(t, map[ProjectID]ProjectWorkflowSnapshot{
			"project": testSnapshot("project", "workspace", testUnit("work", WriteSetUnknown)),
		}, 1)
		harness.manager.selector = fakeSelector{capacity: 1, providerID: "pi"}
		harness.invoker.locators["work"] = []LocatorRecord{{
			Kind: LocatorSession, Opaque: "native-session", Revision: "session-r1",
			ProjectID: "project", WorkspaceID: "workspace", WorkUnitID: "work", AttemptID: attemptID("work", 1),
		}}
		harness.evidence.observeFunc = func(request WorkflowEvidenceRequest, call int) (ArtifactEvidence, error) {
			identity := artifactIdentity(request.Project, request.Work, request.Submission)
			if call == 0 {
				return ArtifactEvidence{
					Active: true, Identity: identity, Completeness: ArtifactPlaceholder,
					RepairIntent: &EvidenceRepairIntent{
						Identity: identity, DispatchOrdinal: request.Work.DispatchOrdinal,
						NativeLocator: request.Work.Locators[LocatorSession],
					},
				}, nil
			}
			return ArtifactEvidence{Active: true, Identity: identity, Completeness: ArtifactComplete}, nil
		}
		harness.start("project", "workspace", nil)
		if err := harness.manager.Reconcile(context.Background()); err != nil {
			t.Fatalf("Reconcile: %v", err)
		}
		observations, repairs := harness.evidence.counts()
		if observations != 2 || repairs != 1 {
			t.Fatalf("observe/repair calls = %d/%d, want 2/1", observations, repairs)
		}
		if harness.reviewer.callCount() != 1 {
			t.Fatalf("review calls = %d, want 1 after fresh rematch", harness.reviewer.callCount())
		}
	})

	t.Run("Pi repair without a fresh completed match never invokes review", func(t *testing.T) {
		harness := newHarness(t, map[ProjectID]ProjectWorkflowSnapshot{
			"project": testSnapshot("project", "workspace", testUnit("work", WriteSetUnknown)),
		}, 1)
		harness.manager.selector = fakeSelector{capacity: 1, providerID: "pi"}
		harness.invoker.locators["work"] = []LocatorRecord{{
			Kind: LocatorSession, Opaque: "native-session", Revision: "session-r1",
			ProjectID: "project", WorkspaceID: "workspace", WorkUnitID: "work", AttemptID: attemptID("work", 1),
		}}
		harness.evidence.observeFunc = func(request WorkflowEvidenceRequest, call int) (ArtifactEvidence, error) {
			identity := artifactIdentity(request.Project, request.Work, request.Submission)
			if call == 0 {
				return ArtifactEvidence{
					Active: true, Identity: identity, Completeness: ArtifactPlaceholder,
					RepairIntent: &EvidenceRepairIntent{
						Identity: identity, DispatchOrdinal: request.Work.DispatchOrdinal,
						NativeLocator: request.Work.Locators[LocatorSession],
					},
				}, nil
			}
			return ArtifactEvidence{Active: true, Identity: identity, Completeness: ArtifactPlaceholder}, nil
		}
		harness.start("project", "workspace", nil)
		if err := harness.manager.Reconcile(context.Background()); err != nil {
			t.Fatalf("Reconcile: %v", err)
		}
		work := harness.store.snapshot().Projects["project"].Works["work"]
		if work.Blocker == nil || work.Blocker.Code != BlockerSubmissionIncomplete {
			t.Fatalf("work blocker = %#v, want %q", work.Blocker, BlockerSubmissionIncomplete)
		}
		observations, repairs := harness.evidence.counts()
		if observations != 2 || repairs != 1 {
			t.Fatalf("observe/repair calls = %d/%d, want 2/1", observations, repairs)
		}
		if harness.reviewer.callCount() != 0 {
			t.Fatalf("review calls = %d, want 0 without a fresh completed match", harness.reviewer.callCount())
		}
	})
}