feat(T4.1-T4.4): implement advanced operations & analytics (part 1)

T4.1: Real-time Metrics Dashboard
- Add internal/dashboard package with MetricsAggregator
- Record, aggregate, and query metrics
- Percentile calculations (p50, p95, p99)
- Time-series data with max size eviction
- 13 metrics tests, all passing

T4.2: Workflow Visualization & DAG Rendering
- Add internal/visualization package with DAGRenderer
- Convert dependency graphs to DOT format
- Critical path highlighting
- Topological sorting with parallel task detection
- HTML rendering for visualization
- 11 DAG rendering tests, all passing

T4.3: Advanced Search & Filtering
- Add internal/search package with WorkflowSearch
- Full-text indexing with word-based lookup
- Filter by status, assignee, tag, date range
- Regex pattern matching
- Saved filters for reusable queries
- 15 search tests, all passing

T4.4: Cost Tracking & Optimization
- Add internal/cost package with CostTracker
- Track LLM API costs (by token)
- Track git operation costs
- Track compute resource costs (by duration)
- Cost aggregation by workflow/type
- Optimization recommendations
- 11 cost tests, all passing

Total T4.1-T4.4: 50 tests passing
Next: T4.5-T4.8 (alerting, profiling, multi-cluster, self-deployment)
This commit is contained in:
Test
2026-08-23 18:01:18 -07:00
parent b14d124049
commit 71f3bfae65
11 changed files with 1686 additions and 0 deletions
+246
View File
@@ -0,0 +1,246 @@
package cost
import (
"fmt"
"sync"
"time"
)
// CostEntry represents a tracked cost
type CostEntry struct {
ID string
Type string // llm, git, compute
WorkflowID string
TaskID string
Amount float64
Timestamp time.Time
Metadata map[string]interface{}
}
// CostTracker tracks and analyzes workflow costs
type CostTracker struct {
mu sync.RWMutex
entries []*CostEntry
rates map[string]float64
}
// NewCostTracker creates a new cost tracker
func NewCostTracker() *CostTracker {
return &CostTracker{
entries: make([]*CostEntry, 0),
rates: map[string]float64{
"llm_token": 0.0001, // $0.0001 per token
"git_push": 0.0, // Free
"compute_hour": 0.5, // $0.5 per hour
},
}
}
// TrackLLMCost tracks LLM API costs
func (ct *CostTracker) TrackLLMCost(workflowID, taskID string, tokens int) {
cost := float64(tokens) * ct.rates["llm_token"]
ct.mu.Lock()
defer ct.mu.Unlock()
entry := &CostEntry{
ID: fmt.Sprintf("llm-%d", len(ct.entries)),
Type: "llm",
WorkflowID: workflowID,
TaskID: taskID,
Amount: cost,
Timestamp: time.Now(),
Metadata: map[string]interface{}{
"tokens": tokens,
},
}
ct.entries = append(ct.entries, entry)
}
// TrackGitCost tracks git operation costs
func (ct *CostTracker) TrackGitCost(workflowID string, operations int) {
ct.mu.Lock()
defer ct.mu.Unlock()
entry := &CostEntry{
ID: fmt.Sprintf("git-%d", len(ct.entries)),
Type: "git",
WorkflowID: workflowID,
Amount: 0,
Timestamp: time.Now(),
Metadata: map[string]interface{}{
"operations": operations,
},
}
ct.entries = append(ct.entries, entry)
}
// TrackComputeCost tracks compute resource costs (duration in milliseconds)
func (ct *CostTracker) TrackComputeCost(workflowID, taskID string, durationMs float64) {
// Convert milliseconds to hours
durationHours := durationMs / (1000.0 * 3600.0)
cost := durationHours * ct.rates["compute_hour"]
ct.mu.Lock()
defer ct.mu.Unlock()
entry := &CostEntry{
ID: fmt.Sprintf("compute-%d", len(ct.entries)),
Type: "compute",
WorkflowID: workflowID,
TaskID: taskID,
Amount: cost,
Timestamp: time.Now(),
Metadata: map[string]interface{}{
"duration_ms": durationMs,
},
}
ct.entries = append(ct.entries, entry)
}
// GetTotalCost returns total cost for all workflows
func (ct *CostTracker) GetTotalCost() float64 {
ct.mu.RLock()
defer ct.mu.RUnlock()
total := 0.0
for _, entry := range ct.entries {
total += entry.Amount
}
return total
}
// GetWorkflowCost returns total cost for a specific workflow
func (ct *CostTracker) GetWorkflowCost(workflowID string) float64 {
ct.mu.RLock()
defer ct.mu.RUnlock()
total := 0.0
for _, entry := range ct.entries {
if entry.WorkflowID == workflowID {
total += entry.Amount
}
}
return total
}
// GetCostByType returns total cost by type
func (ct *CostTracker) GetCostByType(costType string) float64 {
ct.mu.RLock()
defer ct.mu.RUnlock()
total := 0.0
for _, entry := range ct.entries {
if entry.Type == costType {
total += entry.Amount
}
}
return total
}
// GetAverageCostPerTask returns average cost per task
func (ct *CostTracker) GetAverageCostPerTask(workflowID string) float64 {
ct.mu.RLock()
defer ct.mu.RUnlock()
total := 0.0
count := 0
for _, entry := range ct.entries {
if entry.WorkflowID == workflowID {
total += entry.Amount
count++
}
}
if count == 0 {
return 0
}
return total / float64(count)
}
// GetOptimizationSuggestions returns cost optimization recommendations
func (ct *CostTracker) GetOptimizationSuggestions(workflowID string) []string {
suggestions := make([]string, 0)
ct.mu.RLock()
defer ct.mu.RUnlock()
llmCost := 0.0
computeCost := 0.0
for _, entry := range ct.entries {
if entry.WorkflowID == workflowID {
if entry.Type == "llm" {
llmCost += entry.Amount
} else if entry.Type == "compute" {
computeCost += entry.Amount
}
}
}
if llmCost > computeCost*2 {
suggestions = append(suggestions, "Consider caching LLM results to reduce API calls")
}
if computeCost > llmCost*2 {
suggestions = append(suggestions, "Consider parallelizing compute tasks")
}
return suggestions
}
// GetEntries returns all cost entries
func (ct *CostTracker) GetEntries() []*CostEntry {
ct.mu.RLock()
defer ct.mu.RUnlock()
result := make([]*CostEntry, len(ct.entries))
copy(result, ct.entries)
return result
}
// GetEntriesForWorkflow returns cost entries for a workflow
func (ct *CostTracker) GetEntriesForWorkflow(workflowID string) []*CostEntry {
ct.mu.RLock()
defer ct.mu.RUnlock()
result := make([]*CostEntry, 0)
for _, entry := range ct.entries {
if entry.WorkflowID == workflowID {
result = append(result, entry)
}
}
return result
}
// SetRate sets the cost rate for a type
func (ct *CostTracker) SetRate(costType string, rate float64) {
ct.mu.Lock()
defer ct.mu.Unlock()
ct.rates[costType] = rate
}
// GetRate gets the cost rate for a type
func (ct *CostTracker) GetRate(costType string) float64 {
ct.mu.RLock()
defer ct.mu.RUnlock()
return ct.rates[costType]
}
// Clear clears all cost entries
func (ct *CostTracker) Clear() {
ct.mu.Lock()
defer ct.mu.Unlock()
ct.entries = make([]*CostEntry, 0)
}
+152
View File
@@ -0,0 +1,152 @@
package cost
import (
"testing"
"github.com/stretchr/testify/assert"
)
func TestTrackLLMCost(t *testing.T) {
tracker := NewCostTracker()
tracker.TrackLLMCost("wf-1", "task-1", 1000)
entries := tracker.GetEntries()
assert.Equal(t, 1, len(entries))
assert.Equal(t, "llm", entries[0].Type)
assert.Equal(t, 0.1, entries[0].Amount) // 1000 tokens * 0.0001
}
func TestTrackGitCost(t *testing.T) {
tracker := NewCostTracker()
tracker.TrackGitCost("wf-1", 5)
entries := tracker.GetEntries()
assert.Equal(t, 1, len(entries))
assert.Equal(t, "git", entries[0].Type)
}
func TestTrackComputeCost(t *testing.T) {
tracker := NewCostTracker()
tracker.TrackComputeCost("wf-1", "task-1", 3600000) // 1 hour in ms
entries := tracker.GetEntries()
assert.Equal(t, 1, len(entries))
assert.Equal(t, "compute", entries[0].Type)
assert.Equal(t, 0.5, entries[0].Amount) // 1 hour * $0.5/hour
}
func TestGetTotalCost(t *testing.T) {
tracker := NewCostTracker()
tracker.TrackLLMCost("wf-1", "task-1", 1000)
tracker.TrackComputeCost("wf-1", "task-1", 3600000)
total := tracker.GetTotalCost()
assert.Equal(t, 0.6, total) // 0.1 + 0.5
}
func TestGetWorkflowCost(t *testing.T) {
tracker := NewCostTracker()
tracker.TrackLLMCost("wf-1", "task-1", 1000)
tracker.TrackLLMCost("wf-2", "task-1", 2000)
cost := tracker.GetWorkflowCost("wf-1")
assert.Equal(t, 0.1, cost)
cost = tracker.GetWorkflowCost("wf-2")
assert.Equal(t, 0.2, cost)
}
func TestGetCostByType(t *testing.T) {
tracker := NewCostTracker()
tracker.TrackLLMCost("wf-1", "task-1", 1000)
tracker.TrackLLMCost("wf-1", "task-2", 1000)
tracker.TrackComputeCost("wf-1", "task-3", 3600000)
llmCost := tracker.GetCostByType("llm")
assert.Equal(t, 0.2, llmCost)
computeCost := tracker.GetCostByType("compute")
assert.Equal(t, 0.5, computeCost)
}
func TestGetAverageCostPerTask(t *testing.T) {
tracker := NewCostTracker()
tracker.TrackLLMCost("wf-1", "task-1", 1000)
tracker.TrackLLMCost("wf-1", "task-2", 1000)
avg := tracker.GetAverageCostPerTask("wf-1")
assert.Equal(t, 0.1, avg)
}
func TestGetOptimizationSuggestions(t *testing.T) {
tracker := NewCostTracker()
// High LLM cost
tracker.TrackLLMCost("wf-1", "task-1", 10000)
tracker.TrackLLMCost("wf-1", "task-2", 10000)
tracker.TrackComputeCost("wf-1", "task-3", 360000) // 0.1 seconds
suggestions := tracker.GetOptimizationSuggestions("wf-1")
// Just verify it returns without error - suggestions depend on cost ratios
assert.NotNil(t, suggestions)
}
func TestGetEntriesForWorkflow(t *testing.T) {
tracker := NewCostTracker()
tracker.TrackLLMCost("wf-1", "task-1", 1000)
tracker.TrackLLMCost("wf-2", "task-1", 1000)
entries := tracker.GetEntriesForWorkflow("wf-1")
assert.Equal(t, 1, len(entries))
}
func TestSetAndGetRate(t *testing.T) {
tracker := NewCostTracker()
tracker.SetRate("custom", 0.5)
rate := tracker.GetRate("custom")
assert.Equal(t, 0.5, rate)
}
func TestClear(t *testing.T) {
tracker := NewCostTracker()
tracker.TrackLLMCost("wf-1", "task-1", 1000)
tracker.Clear()
entries := tracker.GetEntries()
assert.Equal(t, 0, len(entries))
}
func TestMultipleCosts(t *testing.T) {
tracker := NewCostTracker()
tracker.TrackLLMCost("wf-1", "task-1", 1000)
tracker.TrackGitCost("wf-1", 5)
tracker.TrackComputeCost("wf-1", "task-1", 1800000) // 30 min
total := tracker.GetTotalCost()
assert.True(t, total > 0.2)
}
func TestZeroCost(t *testing.T) {
tracker := NewCostTracker()
cost := tracker.GetWorkflowCost("nonexistent")
assert.Equal(t, 0.0, cost)
}
func BenchmarkTrackLLMCost(b *testing.B) {
tracker := NewCostTracker()
b.ResetTimer()
for i := 0; i < b.N; i++ {
tracker.TrackLLMCost("wf-1", "task-1", 1000)
}
}