poimen-workflows/internal/tuning/analyzer.go

package tuning

import (
	"encoding/json"
	"fmt"
	"math"
	"os"
	"path/filepath"
	"sort"
	"sync"
	"time"
)

// ExecutionMetric represents a recorded activity execution
type ExecutionMetric struct {
	ActivityType string        `json:"activity_type"`
	Duration     time.Duration `json:"duration"`
	Success      bool          `json:"success"`
	Timestamp    time.Time     `json:"timestamp"`
	Error        string        `json:"error,omitempty"`
}

// TimeoutRecommendation represents a recommended timeout adjustment
type TimeoutRecommendation struct {
	ActivityType      string        `json:"activity_type"`
	CurrentTimeout    time.Duration `json:"current_timeout"`
	RecommendedTimeout time.Duration `json:"recommended_timeout"`
	P95Duration       time.Duration `json:"p95_duration"`
	P99Duration       time.Duration `json:"p99_duration"`
	MaxDuration       time.Duration `json:"max_duration"`
	FailureCount      int           `json:"failure_count"`
	SuccessCount      int           `json:"success_count"`
	Confidence        float64       `json:"confidence"` // 0.0-1.0
	Reason            string        `json:"reason"`
	Timestamp         time.Time     `json:"timestamp"`
}

// TimeoutAnalyzer analyzes activity execution metrics and recommends timeout adjustments
type TimeoutAnalyzer struct {
	mu            sync.RWMutex
	basePath      string
	metrics       []ExecutionMetric
	recommendations map[string]*TimeoutRecommendation
}

// NewTimeoutAnalyzer creates a new timeout analyzer
func NewTimeoutAnalyzer(basePath string) *TimeoutAnalyzer {
	return &TimeoutAnalyzer{
		basePath:        basePath,
		metrics:         make([]ExecutionMetric, 0),
		recommendations: make(map[string]*TimeoutRecommendation),
	}
}

// RecordExecution records an activity execution
func (ta *TimeoutAnalyzer) RecordExecution(activityType string, duration time.Duration, success bool, err error) {
	ta.mu.Lock()
	defer ta.mu.Unlock()

	errorMsg := ""
	if err != nil {
		errorMsg = err.Error()
	}

	metric := ExecutionMetric{
		ActivityType: activityType,
		Duration:     duration,
		Success:      success,
		Timestamp:    time.Now(),
		Error:        errorMsg,
	}

	ta.metrics = append(ta.metrics, metric)
}

// Analyze analyzes recorded metrics and generates recommendations
func (ta *TimeoutAnalyzer) Analyze(currentTimeouts map[string]time.Duration) ([]TimeoutRecommendation, error) {
	ta.mu.Lock()
	defer ta.mu.Unlock()

	// Group metrics by activity type
	metricsByActivity := ta.groupMetricsByActivity()

	recommendations := make([]TimeoutRecommendation, 0)

	for activityType, metrics := range metricsByActivity {
		if len(metrics) == 0 {
			continue
		}

		rec := ta.analyzeActivityMetrics(activityType, metrics, currentTimeouts)
		if rec != nil {
			recommendations = append(recommendations, *rec)
			ta.recommendations[activityType] = rec
		}
	}

	// Sort by confidence descending
	sort.Slice(recommendations, func(i, j int) bool {
		return recommendations[i].Confidence > recommendations[j].Confidence
	})

	return recommendations, nil
}

// groupMetricsByActivity groups metrics by activity type
func (ta *TimeoutAnalyzer) groupMetricsByActivity() map[string][]ExecutionMetric {
	groups := make(map[string][]ExecutionMetric)
	for _, m := range ta.metrics {
		groups[m.ActivityType] = append(groups[m.ActivityType], m)
	}
	return groups
}

// analyzeActivityMetrics analyzes metrics for a single activity type
func (ta *TimeoutAnalyzer) analyzeActivityMetrics(
	activityType string,
	metrics []ExecutionMetric,
	currentTimeouts map[string]time.Duration,
) *TimeoutRecommendation {
	if len(metrics) == 0 {
		return nil
	}

	// Calculate statistics
	durations := make([]time.Duration, 0)
	successCount := 0
	failureCount := 0

	for _, m := range metrics {
		if m.Success {
			successCount++
			durations = append(durations, m.Duration)
		} else {
			failureCount++
		}
	}

	if len(durations) == 0 {
		// All failed - need more lenient timeout
		return &TimeoutRecommendation{
			ActivityType:       activityType,
			CurrentTimeout:     currentTimeouts[activityType],
			RecommendedTimeout: currentTimeouts[activityType] * 2,
			FailureCount:       failureCount,
			SuccessCount:       successCount,
			Confidence:         0.3,
			Reason:             "All executions failed - timeout may be too aggressive",
			Timestamp:          time.Now(),
		}
	}

	// Sort durations for percentile calculation
	sort.Slice(durations, func(i, j int) bool {
		return durations[i] < durations[j]
	})

	p95 := calculatePercentile(durations, 0.95)
	p99 := calculatePercentile(durations, 0.99)
	maxDuration := durations[len(durations)-1]

	currentTimeout := currentTimeouts[activityType]

	// Determine if recommendation is needed
	rec := &TimeoutRecommendation{
		ActivityType:       activityType,
		CurrentTimeout:     currentTimeout,
		P95Duration:        p95,
		P99Duration:        p99,
		MaxDuration:        maxDuration,
		SuccessCount:       successCount,
		FailureCount:       failureCount,
		Timestamp:          time.Now(),
	}

	// Calculate recommended timeout (P99 + 20% buffer)
	buffer := time.Duration(float64(p99) * 0.2)
	recommendedTimeout := p99 + buffer

	// Safety checks
	if recommendedTimeout < currentTimeout {
		// Current timeout is more than enough
		if currentTimeout > recommendedTimeout*2 {
			// Can be reduced
			rec.RecommendedTimeout = recommendedTimeout
			rec.Confidence = calculateConfidence(successCount, failureCount)
			rec.Reason = fmt.Sprintf("Current timeout (%v) is %.1fx P99 (%v) - can be reduced", 
				currentTimeout, float64(currentTimeout)/float64(p99), p99)
		} else {
			return nil // No change needed
		}
	} else if recommendedTimeout > currentTimeout {
		// Need to increase timeout
		timeoutRatio := float64(recommendedTimeout) / float64(currentTimeout)
		if timeoutRatio > 1.1 {
			// More than 10% difference
			rec.RecommendedTimeout = recommendedTimeout
			rec.Confidence = calculateConfidence(successCount, failureCount)
			rec.Reason = fmt.Sprintf("Timeout increases needed - P99: %v, current: %v, %d failures", 
				p99, currentTimeout, failureCount)
		} else {
			return nil // Minor difference, not worth changing
		}
	}

	if rec.RecommendedTimeout == 0 {
		return nil // No recommendation
	}

	return rec
}

// calculatePercentile calculates a percentile from sorted durations
func calculatePercentile(durations []time.Duration, percentile float64) time.Duration {
	if len(durations) == 0 {
		return 0
	}

	index := int(math.Ceil(float64(len(durations))*percentile)) - 1
	if index < 0 {
		index = 0
	}
	if index >= len(durations) {
		index = len(durations) - 1
	}

	return durations[index]
}

// calculateAverage calculates the average duration
func calculateAverage(durations []time.Duration) time.Duration {
	if len(durations) == 0 {
		return 0
	}

	var sum time.Duration
	for _, d := range durations {
		sum += d
	}

	return sum / time.Duration(len(durations))
}

// calculateConfidence calculates confidence in the recommendation (0-1)
func calculateConfidence(successCount, failureCount int) float64 {
	total := successCount + failureCount
	if total == 0 {
		return 0.0
	}

	// More samples = higher confidence
	sampleConfidence := math.Min(float64(total)/100.0, 1.0)

	// Lower failure rate = higher confidence
	failureRate := float64(failureCount) / float64(total)
	reliabilityConfidence := 1.0 - failureRate

	// Weighted average
	return sampleConfidence*0.4 + reliabilityConfidence*0.6
}

// SaveMetrics saves metrics to disk
func (ta *TimeoutAnalyzer) SaveMetrics() error {
	ta.mu.RLock()
	defer ta.mu.RUnlock()

	metricsPath := filepath.Join(ta.basePath, "metrics", "execution_metrics.jsonl")

	// Create directory if it doesn't exist
	if err := os.MkdirAll(filepath.Dir(metricsPath), 0755); err != nil {
		return err
	}

	f, err := os.Create(metricsPath)
	if err != nil {
		return err
	}
	defer f.Close()

	for _, m := range ta.metrics {
		data, err := json.Marshal(m)
		if err != nil {
			return err
		}
		_, err = f.Write(append(data, '\n'))
		if err != nil {
			return err
		}
	}

	return nil
}

// LoadMetrics loads metrics from disk
func (ta *TimeoutAnalyzer) LoadMetrics() error {
	ta.mu.Lock()
	defer ta.mu.Unlock()

	metricsPath := filepath.Join(ta.basePath, "metrics", "execution_metrics.jsonl")

	data, err := os.ReadFile(metricsPath)
	if err != nil {
		if os.IsNotExist(err) {
			return nil // File doesn't exist yet
		}
		return err
	}

	ta.metrics = make([]ExecutionMetric, 0)

	// Parse JSONL line by line
	content := string(data)
	var inLine []byte
	for _, ch := range []byte(content) {
		if ch == '\n' {
			if len(inLine) > 0 {
				var m ExecutionMetric
				if err := json.Unmarshal(inLine, &m); err == nil {
					ta.metrics = append(ta.metrics, m)
				}
			}
			inLine = nil
		} else {
			inLine = append(inLine, ch)
		}
	}

	return nil
}

// SaveRecommendations saves recommendations to disk
func (ta *TimeoutAnalyzer) SaveRecommendations(recommendations []TimeoutRecommendation) error {
	ta.mu.Lock()
	defer ta.mu.Unlock()

	recPath := filepath.Join(ta.basePath, "tuning", "timeout_recommendations.json")

	// Create directory if it doesn't exist
	if err := os.MkdirAll(filepath.Dir(recPath), 0755); err != nil {
		return err
	}

	data, err := json.MarshalIndent(recommendations, "", "  ")
	if err != nil {
		return err
	}

	return os.WriteFile(recPath, data, 0644)
}

// GetRecommendations returns stored recommendations
func (ta *TimeoutAnalyzer) GetRecommendations() map[string]*TimeoutRecommendation {
	ta.mu.RLock()
	defer ta.mu.RUnlock()

	// Return a copy
	recCopy := make(map[string]*TimeoutRecommendation)
	for k, v := range ta.recommendations {
		recCopy[k] = v
	}
	return recCopy
}

// ClearMetrics clears all recorded metrics
func (ta *TimeoutAnalyzer) ClearMetrics() {
	ta.mu.Lock()
	defer ta.mu.Unlock()

	ta.metrics = make([]ExecutionMetric, 0)
}

// GetMetricsCount returns the number of recorded metrics
func (ta *TimeoutAnalyzer) GetMetricsCount() int {
	ta.mu.RLock()
	defer ta.mu.RUnlock()

	return len(ta.metrics)
}