query-orchestration/internal/backgroundtask/stats_test.go

package backgroundtask

import (
	"bytes"
	"context"
	"errors"
	"log/slog"
	"strings"
	"sync"
	"sync/atomic"
	"testing"
	"time"
)

// TestStats_WorkCycles verifies work cycle counting
func TestStats_WorkCycles(t *testing.T) {
	config := NewTestConfigMap()

	runner, err := Initialize(
		config,
		slog.Default(),
		FastWorkFunc,
		WithInterval(50*time.Millisecond),
	)
	if err != nil {
		t.Fatalf("Failed to initialize runner: %v", err)
	}

	// Check initial stats
	stats := runner.Stats()
	if stats.WorkCycles() != 0 {
		t.Errorf("Expected 0 initial work cycles, got %d", stats.WorkCycles())
	}

	if err := runner.Run(); err != nil {
		t.Fatalf("Failed to start runner: %v", err)
	}
	defer func() {
		ctx, cancel := context.WithTimeout(t.Context(), 2*time.Second)
		defer cancel()
		if err := runner.Shutdown(ctx); err != nil {
			t.Errorf("Shutdown error: %v", err)
		}
	}()

	// Wait for some work cycles from ticker
	if !WaitForWorkCycles(runner, 3, 300*time.Millisecond) {
		t.Fatal("Expected at least 3 work cycles from ticker")
	}

	tickerCycles := runner.Stats().WorkCycles()

	// Add some signaled work
	for i := 0; i < 5; i++ {
		if err := runner.Signal(); err != nil {
			t.Fatalf("Signal %d failed: %v", i, err)
		}
	}

	// Wait for signal work to complete
	time.Sleep(100 * time.Millisecond)

	finalStats := runner.Stats()
	finalCycles := finalStats.WorkCycles()

	// Should have more cycles after signals
	if finalCycles <= tickerCycles {
		t.Errorf("Expected work cycles to increase after signals: before=%d, after=%d",
			tickerCycles, finalCycles)
	}

	// Should have at least the ticker cycles
	if finalCycles < 3 {
		t.Errorf("Expected at least 3 work cycles, got %d", finalCycles)
	}
}

// TestStats_Timestamps verifies last start/finish timestamp tracking
func TestStats_Timestamps(t *testing.T) {
	config := NewTestConfigMap()
	testConfig, _ := GetTestConfig(config)
	testConfig.WorkDuration = 50 * time.Millisecond

	runner, err := Initialize(
		config,
		slog.Default(),
		TestWorkFunc,
		WithInterval(1*time.Hour), // Long interval
	)
	if err != nil {
		t.Fatalf("Failed to initialize runner: %v", err)
	}

	if err := runner.Run(); err != nil {
		t.Fatalf("Failed to start runner: %v", err)
	}
	defer func() {
		ctx, cancel := context.WithTimeout(t.Context(), 2*time.Second)
		defer cancel()
		if err := runner.Shutdown(ctx); err != nil {
			t.Errorf("Shutdown error: %v", err)
		}
	}()

	// Check initial timestamps (should be zero)
	stats := runner.Stats()
	if !stats.LastStart().IsZero() {
		t.Error("Expected zero LastStart initially")
	}
	if !stats.LastFinish().IsZero() {
		t.Error("Expected zero LastFinish initially")
	}

	beforeSignal := time.Now()

	// Signal work
	if err := runner.Signal(); err != nil {
		t.Fatalf("Signal failed: %v", err)
	}

	// Wait for work to complete
	if !WaitForWorkCycles(runner, 1, 200*time.Millisecond) {
		t.Fatal("Expected work to complete")
	}

	afterWork := time.Now()
	stats = runner.Stats()

	// Timestamps should be set and reasonable
	if stats.LastStart().IsZero() {
		t.Error("Expected LastStart to be set after work")
	}
	if stats.LastFinish().IsZero() {
		t.Error("Expected LastFinish to be set after work")
	}

	// Timestamps should be in reasonable range
	if stats.LastStart().Before(beforeSignal) || stats.LastStart().After(afterWork) {
		t.Errorf("LastStart timestamp out of range: %v (should be between %v and %v)",
			stats.LastStart(), beforeSignal, afterWork)
	}

	if stats.LastFinish().Before(stats.LastStart()) {
		t.Error("LastFinish should be after LastStart")
	}

	if stats.LastFinish().After(afterWork) {
		t.Errorf("LastFinish timestamp after expected: %v > %v",
			stats.LastFinish(), afterWork)
	}

	// Duration should be reasonable
	duration := stats.LastFinish().Sub(stats.LastStart())
	if duration < testConfig.WorkDuration/2 || duration > testConfig.WorkDuration*3 {
		t.Errorf("Work duration seems wrong: %v (expected around %v)",
			duration, testConfig.WorkDuration)
	}
}

// TestStats_ErrorTracking verifies error tracking in stats
//
//nolint:cyclop // Test function with multiple subtests
func TestStats_ErrorTracking(t *testing.T) {
	t.Run("NoErrorInitially", func(t *testing.T) {
		config := NewTestConfigMap()

		runner, err := Initialize(
			config,
			slog.Default(),
			FastWorkFunc, // No error initially
			WithInterval(1*time.Hour),
		)
		if err != nil {
			t.Fatalf("Failed to initialize runner: %v", err)
		}

		if err := runner.Run(); err != nil {
			t.Fatalf("Failed to start runner: %v", err)
		}
		defer func() {
			ctx, cancel := context.WithTimeout(t.Context(), 2*time.Second)
			defer cancel()
			if err := runner.Shutdown(ctx); err != nil {
				t.Errorf("Shutdown error: %v", err)
			}
		}()

		// Signal successful work
		if err := runner.Signal(); err != nil {
			t.Fatalf("Signal failed: %v", err)
		}

		if !WaitForWorkCycles(runner, 1, 200*time.Millisecond) {
			t.Fatal("Expected work to complete")
		}

		// Should have no error
		stats := runner.Stats()
		if stats.LastErr() != nil {
			t.Errorf("Expected no error initially, got: %v", stats.LastErr())
		}
	})

	t.Run("ErrorRecording", func(t *testing.T) {
		config := NewTestConfigMap()
		errorWorkFunc := func(ctx context.Context, logger *slog.Logger, config map[string]any) error {
			return errors.New("test error message")
		}

		errorRunner, err := Initialize(
			config,
			slog.Default(),
			errorWorkFunc,
			WithInterval(1*time.Hour),
		)
		if err != nil {
			t.Fatalf("Failed to initialize error runner: %v", err)
		}

		if err := errorRunner.Run(); err != nil {
			t.Fatalf("Failed to start error runner: %v", err)
		}
		defer func() {
			ctx, cancel := context.WithTimeout(t.Context(), 2*time.Second)
			defer cancel()
			if err := errorRunner.Shutdown(ctx); err != nil {
				t.Errorf("Error runner shutdown error: %v", err)
			}
		}()

		// Signal error work
		if err := errorRunner.Signal(); err != nil {
			t.Fatalf("Error runner signal failed: %v", err)
		}

		if !WaitForWorkCycles(errorRunner, 1, 200*time.Millisecond) {
			t.Fatal("Expected error work to complete")
		}

		// Should have error recorded
		errorStats := errorRunner.Stats()
		if errorStats.LastErr() == nil {
			t.Error("Expected error to be recorded")
		} else if errorStats.LastErr().Error() != "test error message" {
			t.Errorf("Expected 'test error message', got: %v", errorStats.LastErr())
		}
	})

	t.Run("ErrorClearing", func(t *testing.T) {
		config := NewTestConfigMap()
		successWorkFunc := func(ctx context.Context, logger *slog.Logger, config map[string]any) error {
			return nil
		}

		successRunner, err := Initialize(
			config,
			slog.Default(),
			successWorkFunc,
			WithInterval(1*time.Hour),
		)
		if err != nil {
			t.Fatalf("Failed to initialize success runner: %v", err)
		}

		// Set an initial error
		successRunner.stats.setLastErr(errors.New("initial error"))

		if err := successRunner.Run(); err != nil {
			t.Fatalf("Failed to start success runner: %v", err)
		}
		defer func() {
			ctx, cancel := context.WithTimeout(t.Context(), 2*time.Second)
			defer cancel()
			if err := successRunner.Shutdown(ctx); err != nil {
				t.Errorf("Success runner shutdown error: %v", err)
			}
		}()

		if err := successRunner.Signal(); err != nil {
			t.Fatalf("Success runner signal failed: %v", err)
		}

		if !WaitForWorkCycles(successRunner, 1, 200*time.Millisecond) {
			t.Fatal("Expected success work to complete")
		}

		// Error should be cleared
		finalStats := successRunner.Stats()
		if finalStats.LastErr() != nil {
			t.Errorf("Expected error to be cleared after successful work, got: %v", finalStats.LastErr())
		}
	})
}

// TestStats_ThreadSafety verifies thread-safe access to stats
func TestStats_ThreadSafety(t *testing.T) {
	config := NewTestConfigMap()

	runner, err := Initialize(
		config,
		slog.Default(),
		FastWorkFunc,
		WithInterval(10*time.Millisecond), // Fast interval
	)
	if err != nil {
		t.Fatalf("Failed to initialize runner: %v", err)
	}

	if err := runner.Run(); err != nil {
		t.Fatalf("Failed to start runner: %v", err)
	}

	var wg sync.WaitGroup
	const numReaders = 10
	const numWrites = 100
	var errors int64

	// Start multiple readers
	for i := 0; i < numReaders; i++ {
		wg.Add(1)
		go func() {
			defer wg.Done()
			for j := 0; j < numWrites; j++ {
				stats := runner.Stats()
				// Access all stats methods concurrently
				_ = stats.WorkCycles()
				_ = stats.LastStart()
				_ = stats.LastFinish()
				_ = stats.LastErr()
				_ = stats.MaxConcurrent()
				_ = stats.CurrentConcurrent()
				time.Sleep(1 * time.Millisecond)
			}
		}()
	}

	// Also send signals to trigger work and stats updates
	wg.Add(1)
	go func() {
		defer wg.Done()
		for i := 0; i < 50; i++ {
			if err := runner.Signal(); err != nil && err != ErrStopped {
				atomic.AddInt64(&errors, 1)
			}
			time.Sleep(5 * time.Millisecond)
		}
	}()

	wg.Wait()

	ctx, cancel := context.WithTimeout(t.Context(), 2*time.Second)
	defer cancel()
	if err := runner.Shutdown(ctx); err != nil {
		t.Errorf("Shutdown error: %v", err)
	}

	// Check that we didn't get any signal errors (except possibly ErrStopped at the end)
	if errors > 5 { // Allow a few ErrStopped at shutdown
		t.Errorf("Too many signal errors during concurrent access: %d", errors)
	}

	// Final stats should be consistent
	finalStats := runner.Stats()
	if finalStats.WorkCycles() == 0 {
		t.Error("Expected some work cycles")
	}

	if finalStats.CurrentConcurrent() != 0 {
		t.Errorf("Expected current concurrent to be 0 after shutdown, got %d",
			finalStats.CurrentConcurrent())
	}
}

// TestStats_MaxConcurrent verifies max concurrent tracking
func TestStats_MaxConcurrent(t *testing.T) {
	config := map[string]any{"test": true}
	var currentConcurrent int64
	var maxObserved int64

	// Work function that simulates overlapping work attempts
	workFunc := func(ctx context.Context, logger *slog.Logger, cfg map[string]any) error {
		current := atomic.AddInt64(&currentConcurrent, 1)
		defer atomic.AddInt64(&currentConcurrent, -1)

		// Track max we observe
		for {
			max := atomic.LoadInt64(&maxObserved)
			if current <= max || atomic.CompareAndSwapInt64(&maxObserved, max, current) {
				break
			}
		}

		time.Sleep(50 * time.Millisecond)
		return nil
	}

	runner, err := Initialize(
		config,
		slog.Default(),
		workFunc,
		WithInterval(25*time.Millisecond), // Faster than work duration
	)
	if err != nil {
		t.Fatalf("Failed to initialize runner: %v", err)
	}

	// Initial max concurrent should be 0
	stats := runner.Stats()
	if stats.MaxConcurrent() != 0 {
		t.Errorf("Expected initial max concurrent to be 0, got %d", stats.MaxConcurrent())
	}

	if err := runner.Run(); err != nil {
		t.Fatalf("Failed to start runner: %v", err)
	}

	// Let it run with fast ticking and send some signals
	time.Sleep(100 * time.Millisecond)

	for i := 0; i < 10; i++ {
		if err := runner.Signal(); err != nil {
			t.Fatalf("Signal failed: %v", err)
		}
	}

	time.Sleep(200 * time.Millisecond)

	ctx, cancel := context.WithTimeout(t.Context(), 2*time.Second)
	defer cancel()
	if err := runner.Shutdown(ctx); err != nil {
		t.Fatalf("Shutdown failed: %v", err)
	}

	// Max concurrent should be 1 (no actual concurrency in background task)
	finalStats := runner.Stats()
	if finalStats.MaxConcurrent() != 1 {
		t.Errorf("Expected max concurrent to be 1, got %d", finalStats.MaxConcurrent())
	}

	// Our test tracking should also show max of 1
	if maxObserved != 1 {
		t.Errorf("Expected observed max concurrent to be 1, got %d", maxObserved)
	}

	// Current should be 0 after shutdown
	if finalStats.CurrentConcurrent() != 0 {
		t.Errorf("Expected current concurrent to be 0 after shutdown, got %d",
			finalStats.CurrentConcurrent())
	}
}

// TestStats_Reset verifies stats reset functionality
func TestStats_Reset(t *testing.T) {
	config := NewTestConfigMap()

	runner, err := Initialize(
		config,
		slog.Default(),
		ErrorWorkFunc, // Will set error
		WithInterval(1*time.Hour),
	)
	if err != nil {
		t.Fatalf("Failed to initialize runner: %v", err)
	}

	if err := runner.Run(); err != nil {
		t.Fatalf("Failed to start runner: %v", err)
	}
	defer func() {
		ctx, cancel := context.WithTimeout(t.Context(), 2*time.Second)
		defer cancel()
		if err := runner.Shutdown(ctx); err != nil {
			t.Errorf("Shutdown error: %v", err)
		}
	}()

	// Do some work to populate stats
	if err := runner.Signal(); err != nil {
		t.Fatalf("Signal failed: %v", err)
	}

	if !WaitForWorkCycles(runner, 1, 200*time.Millisecond) {
		t.Fatal("Expected work to complete")
	}

	// Verify stats are populated
	stats := runner.Stats()
	if stats.WorkCycles() == 0 {
		t.Fatal("Expected work cycles to be > 0")
	}
	if stats.LastErr() == nil {
		t.Fatal("Expected error to be set")
	}
	if stats.LastStart().IsZero() {
		t.Fatal("Expected LastStart to be set")
	}
	if stats.MaxConcurrent() == 0 {
		t.Fatal("Expected MaxConcurrent to be > 0")
	}

	// Reset stats
	runner.stats.Reset()

	// Verify stats are cleared
	resetStats := runner.Stats()
	if resetStats.WorkCycles() != 0 {
		t.Errorf("Expected work cycles to be 0 after reset, got %d", resetStats.WorkCycles())
	}
	if resetStats.LastErr() != nil {
		t.Errorf("Expected error to be nil after reset, got %v", resetStats.LastErr())
	}
	if !resetStats.LastStart().IsZero() {
		t.Error("Expected LastStart to be zero after reset")
	}
	if !resetStats.LastFinish().IsZero() {
		t.Error("Expected LastFinish to be zero after reset")
	}
	if resetStats.MaxConcurrent() != 0 {
		t.Errorf("Expected MaxConcurrent to be 0 after reset, got %d", resetStats.MaxConcurrent())
	}
	if resetStats.CurrentConcurrent() != 0 {
		t.Errorf("Expected CurrentConcurrent to be 0 after reset, got %d", resetStats.CurrentConcurrent())
	}
}

// TestStats_ConsistentStateAfterWork verifies stats are consistent after work execution
func TestStats_ConsistentStateAfterWork(t *testing.T) {
	config := NewTestConfigMap()
	testConfig, _ := GetTestConfig(config)

	runner, err := Initialize(
		config,
		slog.Default(),
		TestWorkFunc,
		WithInterval(1*time.Hour),
	)
	if err != nil {
		t.Fatalf("Failed to initialize runner: %v", err)
	}

	if err := runner.Run(); err != nil {
		t.Fatalf("Failed to start runner: %v", err)
	}
	defer func() {
		ctx, cancel := context.WithTimeout(t.Context(), 2*time.Second)
		defer cancel()
		if err := runner.Shutdown(ctx); err != nil {
			t.Errorf("Shutdown error: %v", err)
		}
	}()

	const numCycles = 5
	for i := 0; i < numCycles; i++ {
		if err := runner.Signal(); err != nil {
			t.Fatalf("Signal %d failed: %v", i, err)
		}
		// Small delay between signals to ensure they're processed
		time.Sleep(10 * time.Millisecond)
	}

	// Wait for all work to complete
	if !WaitForWorkCycles(runner, int64(numCycles), 2*time.Second) {
		t.Fatalf("Expected all work cycles to complete, got %d", runner.Stats().WorkCycles())
	}

	// Verify consistency
	stats := runner.Stats()

	// Work cycles should match what we triggered
	if stats.WorkCycles() != int64(numCycles) {
		t.Errorf("Expected %d work cycles, got %d", numCycles, stats.WorkCycles())
	}

	// Counter should also match
	if testConfig.Counter.Load() != int64(numCycles) {
		t.Errorf("Expected counter to be %d, got %d", numCycles, testConfig.Counter.Load())
	}

	// Should have no current concurrent work
	if stats.CurrentConcurrent() != 0 {
		t.Errorf("Expected current concurrent to be 0, got %d", stats.CurrentConcurrent())
	}

	// Max concurrent should be 1
	if stats.MaxConcurrent() != 1 {
		t.Errorf("Expected max concurrent to be 1, got %d", stats.MaxConcurrent())
	}

	// Should have valid timestamps
	if stats.LastStart().IsZero() || stats.LastFinish().IsZero() {
		t.Error("Expected valid last start/finish timestamps")
	}

	if stats.LastFinish().Before(stats.LastStart()) {
		t.Error("LastFinish should not be before LastStart")
	}
}

// TestStats_Print verifies the Print function output
//
//nolint:cyclop // Multiple subtests with setup/teardown logic
func TestStats_Print(t *testing.T) {
	t.Run("EmptyStats", func(t *testing.T) {
		config := NewTestConfigMap()
		runner, err := Initialize(
			config,
			slog.Default(),
			TestWorkFunc,
			WithInterval(1*time.Hour),
		)
		if err != nil {
			t.Fatalf("Failed to initialize runner: %v", err)
		}

		// Print stats before any work
		var buf bytes.Buffer
		runner.Stats().Print(&buf)
		output := buf.String()

		// Verify key elements are present
		if !strings.Contains(output, "Background Task Runner Stats") {
			t.Error("Expected title in output")
		}
		if !strings.Contains(output, "Work Cycles:        0") {
			t.Error("Expected 0 work cycles")
		}
		if !strings.Contains(output, "Last Start:  Never") {
			t.Error("Expected 'Never' for last start")
		}
		if !strings.Contains(output, "Last Error:  None") {
			t.Error("Expected 'None' for last error")
		}

		t.Logf("Empty stats output:\n%s", output)
	})

	t.Run("StatsAfterWork", func(t *testing.T) {
		config := NewTestConfigMap()
		runner, err := Initialize(
			config,
			slog.Default(),
			TestWorkFunc,
			WithInterval(1*time.Hour),
		)
		if err != nil {
			t.Fatalf("Failed to initialize runner: %v", err)
		}

		if err := runner.Run(); err != nil {
			t.Fatalf("Failed to start runner: %v", err)
		}
		defer func() {
			ctx, cancel := context.WithTimeout(t.Context(), 2*time.Second)
			defer cancel()
			if err := runner.Shutdown(ctx); err != nil {
				t.Errorf("Shutdown error: %v", err)
			}
		}()

		// Trigger work
		if err := runner.Signal(); err != nil {
			t.Fatalf("Signal failed: %v", err)
		}

		if !WaitForWorkCycles(runner, 1, 500*time.Millisecond) {
			t.Fatal("Expected work to complete")
		}

		// Print stats after work
		var buf bytes.Buffer
		runner.Stats().Print(&buf)
		output := buf.String()

		// Verify stats reflect work
		if !strings.Contains(output, "Work Cycles:        1") {
			t.Error("Expected 1 work cycle")
		}
		if strings.Contains(output, "Last Start:  Never") {
			t.Error("Expected valid last start time")
		}
		if strings.Contains(output, "Last Finish: Never") {
			t.Error("Expected valid last finish time")
		}
		if !strings.Contains(output, "Duration:") {
			t.Error("Expected duration to be shown")
		}

		t.Logf("Stats after work output:\n%s", output)
	})

	t.Run("StatsWithError", func(t *testing.T) {
		config := NewTestConfigMap()
		runner, err := Initialize(
			config,
			slog.Default(),
			ErrorWorkFunc,
			WithInterval(1*time.Hour),
		)
		if err != nil {
			t.Fatalf("Failed to initialize runner: %v", err)
		}

		if err := runner.Run(); err != nil {
			t.Fatalf("Failed to start runner: %v", err)
		}
		defer func() {
			ctx, cancel := context.WithTimeout(t.Context(), 2*time.Second)
			defer cancel()
			if err := runner.Shutdown(ctx); err != nil {
				t.Errorf("Shutdown error: %v", err)
			}
		}()

		// Trigger work that will error
		if err := runner.Signal(); err != nil {
			t.Fatalf("Signal failed: %v", err)
		}

		if !WaitForWorkCycles(runner, 1, 500*time.Millisecond) {
			t.Fatal("Expected work to complete")
		}

		// Print stats with error
		var buf bytes.Buffer
		runner.Stats().Print(&buf)
		output := buf.String()

		// Verify error is shown
		if !strings.Contains(output, "Last Error:  test error") {
			t.Error("Expected error to be shown in output")
		}

		t.Logf("Stats with error output:\n%s", output)
	})

	t.Run("LongErrorTruncation", func(t *testing.T) {
		config := NewTestConfigMap()

		// Create work function with long error message
		longErrorFunc := func(ctx context.Context, logger *slog.Logger, cfg map[string]any) error {
			return errors.New("this is a very long error message that should be truncated in the pretty print output")
		}

		runner, err := Initialize(
			config,
			slog.Default(),
			longErrorFunc,
			WithInterval(1*time.Hour),
		)
		if err != nil {
			t.Fatalf("Failed to initialize runner: %v", err)
		}

		if err := runner.Run(); err != nil {
			t.Fatalf("Failed to start runner: %v", err)
		}
		defer func() {
			ctx, cancel := context.WithTimeout(t.Context(), 2*time.Second)
			defer cancel()
			if err := runner.Shutdown(ctx); err != nil {
				t.Errorf("Shutdown error: %v", err)
			}
		}()

		// Trigger work that will error
		if err := runner.Signal(); err != nil {
			t.Fatalf("Signal failed: %v", err)
		}

		if !WaitForWorkCycles(runner, 1, 500*time.Millisecond) {
			t.Fatal("Expected work to complete")
		}

		// Print stats with long error
		var buf bytes.Buffer
		runner.Stats().Print(&buf)
		output := buf.String()

		// Verify error is truncated with ellipsis
		if !strings.Contains(output, "...") {
			t.Error("Expected long error to be truncated with ellipsis")
		}

		t.Logf("Stats with truncated error output:\n%s", output)
	})
}