Add worker stats to the wizard, artifact pruning and offline-worker removal to the admin console

coordinator/internal/storage/postgres/job_repo.go

@@ -3,6 +3,7 @@ package postgres
 import (
 	"context"
 	"errors"
+	"fmt"
 	"time"
 
 	sq "github.com/Masterminds/squirrel"
@@ -153,3 +154,46 @@ func (r *JobRepo) UpdateStatus(ctx context.Context, id uuid.UUID,
 	}
 	return nil
 }
+
+// ListCompletedBefore returns jobs whose completion timestamp is older than
+// the cutoff (completed and failed both count as finished).
+func (r *JobRepo) ListCompletedBefore(ctx context.Context, cutoff time.Time) ([]domain.Job, error) {
+	sql, args, err := psql.Select(jobColumns...).From("jobs").
+		Where(sq.NotEq{"completed_at": nil}).
+		Where(sq.Lt{"completed_at": cutoff}).
+		OrderBy("completed_at ASC").
+		ToSql()
+	if err != nil {
+		return nil, err
+	}
+	rows, err := conn(ctx, r.pool).Query(ctx, sql, args...)
+	if err != nil {
+		return nil, fmt.Errorf("list completed jobs: %w", err)
+	}
+	defer rows.Close()
+	var jobs []domain.Job
+	for rows.Next() {
+		var j domain.Job
+		var status string
+		if err := rows.Scan(
+			&j.ID, &j.Workload, &j.InputURI, &j.Parameters, &status, &j.CreatedAt, &j.CompletedAt,
+			&j.InputArtifactID, &j.ResultArtifactID, &j.ErrorCode, &j.ErrorMessage, &j.ReducerStartedAt,
+			&j.OwnerID,
+		); err != nil {
+			return nil, err
+		}
+		j.Status = domain.JobStatus(status)
+		jobs = append(jobs, j)
+	}
+	return jobs, rows.Err()
+}
+
+// Delete removes the job row; tasks, artifacts and task_results cascade.
+func (r *JobRepo) Delete(ctx context.Context, id uuid.UUID) error {
+	sql, args, err := psql.Delete("jobs").Where(sq.Eq{"id": id}).ToSql()
+	if err != nil {
+		return err
+	}
+	_, err = conn(ctx, r.pool).Exec(ctx, sql, args...)
+	return err
+}

coordinator/internal/storage/postgres/worker_repo.go

@@ -123,3 +123,19 @@ func scanWorker(row pgx.Row) (*domain.Worker, error) {
 	w.TrustLevel = domain.WorkerTrust(trust)
 	return &w, nil
 }
+
+// Delete removes a worker from the registry.
+func (r *WorkerRepo) Delete(ctx context.Context, id uuid.UUID) error {
+	sql, args, err := psql.Delete("workers").Where(sq.Eq{"id": id}).ToSql()
+	if err != nil {
+		return err
+	}
+	tag, err := conn(ctx, r.pool).Exec(ctx, sql, args...)
+	if err != nil {
+		return fmt.Errorf("delete worker: %w", err)
+	}
+	if tag.RowsAffected() == 0 {
+		return domain.ErrWorkerNotFound
+	}
+	return nil
+}

coordinator/internal/storage/sqlite/admin_m2_test.go

@@ -88,3 +88,47 @@ func TestWorkerSetTrust(t *testing.T) {
 		t.Errorf("unknown worker trust err = %v, want ErrWorkerNotFound", err)
 	}
 }
+
+func TestJobRepoListCompletedBeforeAndDelete(t *testing.T) {
+	db := newTestDB(t)
+	ctx := context.Background()
+	repo := NewJobRepo(db)
+
+	old := seedJob(t, db, 2)
+	oldTime := fixedTime().Add(-40 * 24 * time.Hour)
+	if err := repo.UpdateStatus(ctx, old.ID, domain.JobCompleted, &oldTime); err != nil {
+		t.Fatal(err)
+	}
+	fresh := seedJob(t, db, 2)
+	freshTime := fixedTime().Add(-2 * time.Hour)
+	if err := repo.UpdateStatus(ctx, fresh.ID, domain.JobCompleted, &freshTime); err != nil {
+		t.Fatal(err)
+	}
+	// The failing check constraint needs no result artifact for completed; the
+	// UpdateStatus path is fine, but tasks stay pending — irrelevant here.
+
+	list, err := repo.ListCompletedBefore(ctx, fixedTime().Add(-7*24*time.Hour))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(list) != 1 || list[0].ID != old.ID {
+		t.Errorf("list = %d jobs, want only the old one", len(list))
+	}
+	if err := repo.Delete(ctx, old.ID); err != nil {
+		t.Fatal(err)
+	}
+	var n int
+	if err := db.QueryRowContext(ctx, "SELECT COUNT(*) FROM jobs WHERE id = ?", old.ID.String()).Scan(&n); err != nil {
+		t.Fatal(err)
+	}
+	if n != 0 {
+		t.Error("job row must be gone after Delete")
+	}
+	// Tasks cascaded away with the job.
+	if err := db.QueryRowContext(ctx, "SELECT COUNT(*) FROM tasks WHERE job_id = ?", old.ID.String()).Scan(&n); err != nil {
+		t.Fatal(err)
+	}
+	if n != 0 {
+		t.Error("tasks must cascade with the job")
+	}
+}

coordinator/internal/storage/sqlite/job_repo.go

@@ -3,6 +3,7 @@ package sqlite
 import (
 	"context"
 	"database/sql"
+	"fmt"
 	"time"
 
 	"github.com/google/uuid"
@@ -166,3 +167,30 @@ func nullableUUID(id *uuid.UUID) any {
 	}
 	return id.String()
 }
+
+// ListCompletedBefore returns jobs whose completion timestamp is older than
+// the cutoff (completed and failed both count as finished).
+func (r *JobRepo) ListCompletedBefore(ctx context.Context, cutoff time.Time) ([]domain.Job, error) {
+	rows, err := conn(ctx, r.db).QueryContext(ctx,
+		"SELECT "+jobColumns+" FROM jobs WHERE completed_at IS NOT NULL AND completed_at < ? ORDER BY completed_at ASC",
+		encodeTime(cutoff))
+	if err != nil {
+		return nil, fmt.Errorf("list completed jobs: %w", err)
+	}
+	defer func() { _ = rows.Close() }()
+	var jobs []domain.Job
+	for rows.Next() {
+		job, err := scanJob(rows)
+		if err != nil {
+			return nil, err
+		}
+		jobs = append(jobs, *job)
+	}
+	return jobs, rows.Err()
+}
+
+// Delete removes the job row; tasks, artifacts and task_results cascade.
+func (r *JobRepo) Delete(ctx context.Context, id uuid.UUID) error {
+	_, err := conn(ctx, r.db).ExecContext(ctx, "DELETE FROM jobs WHERE id = ?", id.String())
+	return err
+}

coordinator/internal/storage/sqlite/worker_repo.go

@@ -107,3 +107,19 @@ func (r *WorkerRepo) SetTrust(ctx context.Context, id uuid.UUID, trust domain.Wo
 	}
 	return nil
 }
+
+// Delete removes a worker from the registry.
+func (r *WorkerRepo) Delete(ctx context.Context, id uuid.UUID) error {
+	res, err := conn(ctx, r.db).ExecContext(ctx, "DELETE FROM workers WHERE id = ?", id.String())
+	if err != nil {
+		return err
+	}
+	affected, err := res.RowsAffected()
+	if err != nil {
+		return err
+	}
+	if affected == 0 {
+		return domain.ErrWorkerNotFound
+	}
+	return nil
+}