vxcontrol/pentagi · error

failed to get flow tasks: %w

Error message

failed to get flow tasks: %w

What it means

buildSummary fetches the flow's tasks via the database (GetFlowTasks) and wraps any failure with this message. This is a backend/data-access error — the tool arguments were fine, but the task list could not be loaded, so no status summary can be produced.

Source

Thrown at backend/pkg/tools/flow_manager.go:94

	case FlowStatusDetailSummary:
		return t.buildSummary(ctx, verbose)
	case FlowStatusDetailTasks:
		return t.buildTasksList(ctx, verbose)
	case FlowStatusDetailSubtasks:
		return t.buildSubtasksList(ctx, action.TaskID.PtrInt64(), verbose)
	case FlowStatusDetailRunning:
		return t.buildRunningInfo(ctx, verbose)
	case FlowStatusDetailPlanned:
		return t.buildPlannedList(ctx, action.TaskID.PtrInt64(), verbose)
	default:
		return "", fmt.Errorf("unknown detail level %q; use one of: summary, tasks, subtasks, running, planned", action.Detail)
	}
}

func (t *flowStatusTool) buildSummary(ctx context.Context, verbose bool) (string, error) {
	tasks, err := t.db.GetFlowTasks(ctx, t.flowID)
	if err != nil {
		return "", fmt.Errorf("failed to get flow tasks: %w", err)
	}

	subtasks, err := t.db.GetFlowSubtasks(ctx, t.flowID)
	if err != nil {
		return "", fmt.Errorf("failed to get flow subtasks: %w", err)
	}

	taskCounts := map[string]int{"created": 0, "running": 0, "waiting": 0, "finished": 0, "failed": 0}
	var activeTask *database.Task
	for i, task := range tasks {
		taskCounts[string(task.Status)]++
		if task.Status == database.TaskStatusRunning || task.Status == database.TaskStatusWaiting {
			activeTask = &tasks[i]
		}
	}

	stCounts := map[string]int{"created": 0, "running": 0, "waiting": 0, "finished": 0, "failed": 0}
	var activeST *database.Subtask

View on GitHub (pinned to ea665308ba)

Solutions

1. Check the wrapped cause in the error message and the backend logs for the underlying DB error.
2. Verify PostgreSQL is reachable and healthy (docker compose ps, connection env vars: DB host/port/user/password).
3. Confirm migrations ran (goose up) so the flow task tables exist.
4. Retry the tool call if the failure was transient (context timeout / connection reset).
5. Verify the flow ID still exists — the flow or its tasks may have been deleted.

Example fix

// .env before
DATABASE_HOST=localhost
DATABASE_PORT=5433

// .env after (match the running postgres service)
DATABASE_HOST=localhost
DATABASE_PORT=5432

func dbReachable(db *sql.DB) error {
	ctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
	defer cancel()
	return db.PingContext(ctx)
}

var out string
var lastErr error
for attempt := 0; attempt < 3; attempt++ {
	out, lastErr = tool.Handle(ctx, "get_flow_status", args)
	if lastErr == nil { return out, nil }
	if !strings.Contains(lastErr.Error(), "failed to get flow") { break }
	time.Sleep(time.Duration(1<<attempt) * 100 * time.Millisecond)
}
return lastErr

When it happens

Trigger: GetFlowTasks returns an error: database connection refused, context canceled (flow request timed out), the flows/tasks table missing or the flow row deleted mid-query, or a Postgres error (deadlock, OOM, disk full).

Common situations: PostgreSQL container down or restarting during local Docker Compose runs; wrong DB credentials in .env; migration not applied so tables are absent; context deadline exceeded on very large flows; transient network blip between backend and DB.

Understand the failure class

Background: Database query failed: Internal Server Error 500s wrapping SQL, Prisma, and connection failures — what to check first — this error's family across 16 libraries.

Related errors

• failed to create flow in DB: %w
• failed to set flow %d status: %w
• failed to delete assistant %d: %w
• failed to rename flow %d: %w
• failed to update flow provider in DB: %w

AI-assisted analysis of vxcontrol/pentagi@ea665308ba (2026-09-01). Data as JSON: /api/errors/df384c823ba88b49. Report an issue: GitHub.