Files
poimen-workflows/internal/graph/dependency_graph.go
T

405 lines
9.1 KiB
Go
Raw Normal View History

2026-08-23 17:32:55 -07:00
package graph
import (
"fmt"
"sync"
)
// Task represents a node in the dependency graph
type Task struct {
ID string
Title string
Status string // pending, ready, running, completed, failed
DependsOn []string
Metadata map[string]interface{}
}
// DependencyGraph manages task dependencies
type DependencyGraph struct {
mu sync.RWMutex
tasks map[string]*Task
adjacencyList map[string][]string // task -> dependent tasks
reverseList map[string][]string // task -> dependencies
topologicalOrder []string
cycleDetected bool
status map[string]string // task -> status
}
// NewDependencyGraph creates a new dependency graph
func NewDependencyGraph() *DependencyGraph {
return &DependencyGraph{
tasks: make(map[string]*Task),
adjacencyList: make(map[string][]string),
reverseList: make(map[string][]string),
topologicalOrder: make([]string, 0),
status: make(map[string]string),
}
}
// AddTask adds a task to the graph
func (dg *DependencyGraph) AddTask(task *Task) error {
if task == nil || task.ID == "" {
return fmt.Errorf("task cannot be nil and must have an ID")
}
dg.mu.Lock()
defer dg.mu.Unlock()
if _, exists := dg.tasks[task.ID]; exists {
return fmt.Errorf("task already exists: %s", task.ID)
}
dg.tasks[task.ID] = task
dg.status[task.ID] = "pending"
// Initialize adjacency lists
if _, exists := dg.adjacencyList[task.ID]; !exists {
dg.adjacencyList[task.ID] = make([]string, 0)
}
if _, exists := dg.reverseList[task.ID]; !exists {
dg.reverseList[task.ID] = make([]string, 0)
}
return nil
}
// AddDependency adds a dependency: dependent depends on prerequisite
func (dg *DependencyGraph) AddDependency(dependent, prerequisite string) error {
dg.mu.Lock()
defer dg.mu.Unlock()
if _, exists := dg.tasks[dependent]; !exists {
return fmt.Errorf("dependent task not found: %s", dependent)
}
if _, exists := dg.tasks[prerequisite]; !exists {
return fmt.Errorf("prerequisite task not found: %s", prerequisite)
}
// Check for duplicate
for _, dep := range dg.reverseList[dependent] {
if dep == prerequisite {
return fmt.Errorf("dependency already exists: %s -> %s", dependent, prerequisite)
}
}
dg.reverseList[dependent] = append(dg.reverseList[dependent], prerequisite)
dg.adjacencyList[prerequisite] = append(dg.adjacencyList[prerequisite], dependent)
return nil
}
// ValidateGraph checks for cycles and structural integrity
func (dg *DependencyGraph) ValidateGraph() error {
dg.mu.Lock()
defer dg.mu.Unlock()
// Check for cycles using DFS
visited := make(map[string]bool)
recStack := make(map[string]bool)
for taskID := range dg.tasks {
if !visited[taskID] {
if dg.hasCycleLocked(taskID, visited, recStack) {
dg.cycleDetected = true
return fmt.Errorf("cycle detected in dependency graph")
}
}
}
return nil
}
// hasCycleLocked detects cycles using DFS (must be called with lock held)
func (dg *DependencyGraph) hasCycleLocked(node string, visited, recStack map[string]bool) bool {
visited[node] = true
recStack[node] = true
for _, dep := range dg.reverseList[node] {
if !visited[dep] {
if dg.hasCycleLocked(dep, visited, recStack) {
return true
}
} else if recStack[dep] {
return true
}
}
recStack[node] = false
return false
}
// GetTopologicalOrder returns tasks in execution order
func (dg *DependencyGraph) GetTopologicalOrder() ([]string, error) {
dg.mu.Lock()
defer dg.mu.Unlock()
if dg.cycleDetected {
return nil, fmt.Errorf("graph contains cycles")
}
// Kahn's algorithm
inDegree := make(map[string]int)
for taskID := range dg.tasks {
inDegree[taskID] = len(dg.reverseList[taskID])
}
queue := make([]string, 0)
for taskID, degree := range inDegree {
if degree == 0 {
queue = append(queue, taskID)
}
}
topOrder := make([]string, 0)
for len(queue) > 0 {
current := queue[0]
queue = queue[1:]
topOrder = append(topOrder, current)
for _, dependent := range dg.adjacencyList[current] {
inDegree[dependent]--
if inDegree[dependent] == 0 {
queue = append(queue, dependent)
}
}
}
if len(topOrder) != len(dg.tasks) {
return nil, fmt.Errorf("topological sort failed - graph may have cycles")
}
dg.topologicalOrder = topOrder
return topOrder, nil
}
// GetReadyTasks returns tasks that have no remaining dependencies
func (dg *DependencyGraph) GetReadyTasks() []string {
dg.mu.RLock()
defer dg.mu.RUnlock()
ready := make([]string, 0)
for taskID, deps := range dg.reverseList {
allDepsComplete := true
for _, dep := range deps {
if dg.status[dep] != "completed" {
allDepsComplete = false
break
}
}
if allDepsComplete && dg.status[taskID] == "pending" {
ready = append(ready, taskID)
}
}
return ready
}
// MarkCompleted marks a task as completed and updates dependents
func (dg *DependencyGraph) MarkCompleted(taskID string) error {
dg.mu.Lock()
defer dg.mu.Unlock()
if _, exists := dg.tasks[taskID]; !exists {
return fmt.Errorf("task not found: %s", taskID)
}
dg.status[taskID] = "completed"
return nil
}
// MarkFailed marks a task as failed
func (dg *DependencyGraph) MarkFailed(taskID string) error {
dg.mu.Lock()
defer dg.mu.Unlock()
if _, exists := dg.tasks[taskID]; !exists {
return fmt.Errorf("task not found: %s", taskID)
}
dg.status[taskID] = "failed"
return nil
}
// GetTaskStatus returns the status of a task
func (dg *DependencyGraph) GetTaskStatus(taskID string) (string, error) {
dg.mu.RLock()
defer dg.mu.RUnlock()
status, exists := dg.status[taskID]
if !exists {
return "", fmt.Errorf("task not found: %s", taskID)
}
return status, nil
}
// GetDependencies returns all dependencies of a task
func (dg *DependencyGraph) GetDependencies(taskID string) ([]string, error) {
dg.mu.RLock()
defer dg.mu.RUnlock()
deps, exists := dg.reverseList[taskID]
if !exists {
return nil, fmt.Errorf("task not found: %s", taskID)
}
result := make([]string, len(deps))
copy(result, deps)
return result, nil
}
// GetDependents returns all tasks that depend on this task
func (dg *DependencyGraph) GetDependents(taskID string) ([]string, error) {
dg.mu.RLock()
defer dg.mu.RUnlock()
deps, exists := dg.adjacencyList[taskID]
if !exists {
return nil, fmt.Errorf("task not found: %s", taskID)
}
result := make([]string, len(deps))
copy(result, deps)
return result, nil
}
// GetTask returns a task by ID
func (dg *DependencyGraph) GetTask(taskID string) (*Task, bool) {
dg.mu.RLock()
defer dg.mu.RUnlock()
task, exists := dg.tasks[taskID]
return task, exists
}
// GetAllTasks returns all tasks
func (dg *DependencyGraph) GetAllTasks() map[string]*Task {
dg.mu.RLock()
defer dg.mu.RUnlock()
result := make(map[string]*Task)
for id, task := range dg.tasks {
result[id] = task
}
return result
}
// GetGraphStats returns statistics about the graph
func (dg *DependencyGraph) GetGraphStats() map[string]interface{} {
dg.mu.RLock()
defer dg.mu.RUnlock()
pending := 0
completed := 0
failed := 0
for _, status := range dg.status {
switch status {
case "pending":
pending++
case "completed":
completed++
case "failed":
failed++
}
}
return map[string]interface{}{
"total_tasks": len(dg.tasks),
"pending_tasks": pending,
"completed_tasks": completed,
"failed_tasks": failed,
"cycle_detected": dg.cycleDetected,
"total_edges": dg.countEdgesLocked(),
}
}
// countEdgesLocked counts total dependencies (must be called with lock held)
func (dg *DependencyGraph) countEdgesLocked() int {
count := 0
for _, deps := range dg.reverseList {
count += len(deps)
}
return count
}
// Clear clears all tasks and dependencies
func (dg *DependencyGraph) Clear() {
dg.mu.Lock()
defer dg.mu.Unlock()
dg.tasks = make(map[string]*Task)
dg.adjacencyList = make(map[string][]string)
dg.reverseList = make(map[string][]string)
dg.topologicalOrder = make([]string, 0)
dg.status = make(map[string]string)
dg.cycleDetected = false
}
// CanExecuteTask checks if a task can be executed (all deps complete)
func (dg *DependencyGraph) CanExecuteTask(taskID string) bool {
dg.mu.RLock()
defer dg.mu.RUnlock()
deps, exists := dg.reverseList[taskID]
if !exists {
return false
}
for _, dep := range deps {
if dg.status[dep] != "completed" {
return false
}
}
return true
}
// GetCriticalPath returns the longest path through the graph
func (dg *DependencyGraph) GetCriticalPath() []string {
dg.mu.RLock()
defer dg.mu.RUnlock()
// Use longest path algorithm
distances := make(map[string]int)
parent := make(map[string]string)
for taskID := range dg.tasks {
distances[taskID] = 0
}
// Process in topological order
for _, taskID := range dg.topologicalOrder {
for _, dependent := range dg.adjacencyList[taskID] {
if distances[dependent] < distances[taskID]+1 {
distances[dependent] = distances[taskID] + 1
parent[dependent] = taskID
}
}
}
// Find task with maximum distance
maxDist := 0
endTask := ""
for taskID, dist := range distances {
if dist > maxDist {
maxDist = dist
endTask = taskID
}
}
// Reconstruct path
path := make([]string, 0)
current := endTask
for current != "" {
path = append([]string{current}, path...)
current = parent[current]
}
return path
}