Harden CHORUS security and messaging stack
This commit is contained in:
@@ -2,9 +2,11 @@ package runtime
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"time"
|
||||
|
||||
"chorus/internal/logging"
|
||||
"chorus/pkg/dht"
|
||||
"chorus/pkg/health"
|
||||
"chorus/pkg/shutdown"
|
||||
"chorus/pubsub"
|
||||
@@ -43,37 +45,37 @@ func (r *SharedRuntime) StartAgentMode() error {
|
||||
|
||||
// === Comprehensive Health Monitoring & Graceful Shutdown ===
|
||||
shutdownManager := shutdown.NewManager(30*time.Second, &simpleLogger{logger: r.Logger})
|
||||
|
||||
|
||||
healthManager := health.NewManager(r.Node.ID().ShortString(), AppVersion, &simpleLogger{logger: r.Logger})
|
||||
healthManager.SetShutdownManager(shutdownManager)
|
||||
|
||||
|
||||
// Register health checks
|
||||
r.setupHealthChecks(healthManager)
|
||||
|
||||
|
||||
// Register components for graceful shutdown
|
||||
r.setupGracefulShutdown(shutdownManager, healthManager)
|
||||
|
||||
|
||||
// Start health monitoring
|
||||
if err := healthManager.Start(); err != nil {
|
||||
return err
|
||||
}
|
||||
r.HealthManager = healthManager
|
||||
r.Logger.Info("❤️ Health monitoring started")
|
||||
|
||||
|
||||
// Start health HTTP server
|
||||
if err := healthManager.StartHTTPServer(r.Config.Network.HealthPort); err != nil {
|
||||
r.Logger.Error("❌ Failed to start health HTTP server: %v", err)
|
||||
} else {
|
||||
r.Logger.Info("🏥 Health endpoints available at http://localhost:%d/health", r.Config.Network.HealthPort)
|
||||
}
|
||||
|
||||
|
||||
// Start shutdown manager
|
||||
shutdownManager.Start()
|
||||
r.ShutdownManager = shutdownManager
|
||||
r.Logger.Info("🛡️ Graceful shutdown manager started")
|
||||
|
||||
|
||||
r.Logger.Info("✅ CHORUS agent system fully operational with health monitoring")
|
||||
|
||||
|
||||
// Wait for graceful shutdown
|
||||
shutdownManager.Wait()
|
||||
r.Logger.Info("✅ CHORUS agent system shutdown completed")
|
||||
@@ -90,7 +92,7 @@ func (r *SharedRuntime) announceAvailability() {
|
||||
currentTasks := r.TaskTracker.GetActiveTasks()
|
||||
maxTasks := r.TaskTracker.GetMaxTasks()
|
||||
isAvailable := len(currentTasks) < maxTasks
|
||||
|
||||
|
||||
status := "ready"
|
||||
if len(currentTasks) >= maxTasks {
|
||||
status = "busy"
|
||||
@@ -99,13 +101,13 @@ func (r *SharedRuntime) announceAvailability() {
|
||||
}
|
||||
|
||||
availability := map[string]interface{}{
|
||||
"node_id": r.Node.ID().ShortString(),
|
||||
"node_id": r.Node.ID().ShortString(),
|
||||
"available_for_work": isAvailable,
|
||||
"current_tasks": len(currentTasks),
|
||||
"max_tasks": maxTasks,
|
||||
"last_activity": time.Now().Unix(),
|
||||
"status": status,
|
||||
"timestamp": time.Now().Unix(),
|
||||
"current_tasks": len(currentTasks),
|
||||
"max_tasks": maxTasks,
|
||||
"last_activity": time.Now().Unix(),
|
||||
"status": status,
|
||||
"timestamp": time.Now().Unix(),
|
||||
}
|
||||
if err := r.PubSub.PublishBzzzMessage(pubsub.AvailabilityBcast, availability); err != nil {
|
||||
r.Logger.Error("❌ Failed to announce availability: %v", err)
|
||||
@@ -126,16 +128,79 @@ func (r *SharedRuntime) statusReporter() {
|
||||
|
||||
// announceCapabilitiesOnChange announces capabilities when they change
|
||||
func (r *SharedRuntime) announceCapabilitiesOnChange() {
|
||||
// Implementation from CHORUS would go here
|
||||
// For now, just log that capabilities would be announced
|
||||
r.Logger.Info("📢 Agent capabilities announcement enabled")
|
||||
if r.PubSub == nil {
|
||||
r.Logger.Warn("⚠️ Capability broadcast skipped: PubSub not initialized")
|
||||
return
|
||||
}
|
||||
|
||||
r.Logger.Info("📢 Broadcasting agent capabilities to network")
|
||||
|
||||
activeTaskCount := 0
|
||||
if r.TaskTracker != nil {
|
||||
activeTaskCount = len(r.TaskTracker.GetActiveTasks())
|
||||
}
|
||||
|
||||
announcement := map[string]interface{}{
|
||||
"agent_id": r.Config.Agent.ID,
|
||||
"node_id": r.Node.ID().ShortString(),
|
||||
"version": AppVersion,
|
||||
"capabilities": r.Config.Agent.Capabilities,
|
||||
"expertise": r.Config.Agent.Expertise,
|
||||
"models": r.Config.Agent.Models,
|
||||
"specialization": r.Config.Agent.Specialization,
|
||||
"max_tasks": r.Config.Agent.MaxTasks,
|
||||
"current_tasks": activeTaskCount,
|
||||
"timestamp": time.Now().Unix(),
|
||||
"availability": "ready",
|
||||
}
|
||||
|
||||
if err := r.PubSub.PublishBzzzMessage(pubsub.CapabilityBcast, announcement); err != nil {
|
||||
r.Logger.Error("❌ Failed to broadcast capabilities: %v", err)
|
||||
return
|
||||
}
|
||||
|
||||
r.Logger.Info("✅ Capabilities broadcast published")
|
||||
|
||||
// TODO: Watch for live capability changes (role updates, model changes) and re-broadcast
|
||||
}
|
||||
|
||||
// announceRoleOnStartup announces role when the agent starts
|
||||
func (r *SharedRuntime) announceRoleOnStartup() {
|
||||
// Implementation from CHORUS would go here
|
||||
// For now, just log that role would be announced
|
||||
r.Logger.Info("🎭 Agent role announcement enabled")
|
||||
role := r.Config.Agent.Role
|
||||
if role == "" {
|
||||
r.Logger.Info("🎭 No agent role configured; skipping role announcement")
|
||||
return
|
||||
}
|
||||
if r.PubSub == nil {
|
||||
r.Logger.Warn("⚠️ Role announcement skipped: PubSub not initialized")
|
||||
return
|
||||
}
|
||||
|
||||
r.Logger.Info("🎭 Announcing agent role to collaboration mesh")
|
||||
|
||||
announcement := map[string]interface{}{
|
||||
"agent_id": r.Config.Agent.ID,
|
||||
"node_id": r.Node.ID().ShortString(),
|
||||
"role": role,
|
||||
"expertise": r.Config.Agent.Expertise,
|
||||
"capabilities": r.Config.Agent.Capabilities,
|
||||
"reports_to": r.Config.Agent.ReportsTo,
|
||||
"specialization": r.Config.Agent.Specialization,
|
||||
"timestamp": time.Now().Unix(),
|
||||
}
|
||||
|
||||
opts := pubsub.MessageOptions{
|
||||
FromRole: role,
|
||||
Priority: "medium",
|
||||
ThreadID: fmt.Sprintf("role:%s", role),
|
||||
}
|
||||
|
||||
if err := r.PubSub.PublishRoleBasedMessage(pubsub.RoleAnnouncement, announcement, opts); err != nil {
|
||||
r.Logger.Error("❌ Failed to announce role: %v", err)
|
||||
return
|
||||
}
|
||||
|
||||
r.Logger.Info("✅ Role announcement published")
|
||||
}
|
||||
|
||||
func (r *SharedRuntime) setupHealthChecks(healthManager *health.Manager) {
|
||||
@@ -151,31 +216,108 @@ func (r *SharedRuntime) setupHealthChecks(healthManager *health.Manager) {
|
||||
Checker: func(ctx context.Context) health.CheckResult {
|
||||
healthInfo := r.BackbeatIntegration.GetHealth()
|
||||
connected, _ := healthInfo["connected"].(bool)
|
||||
|
||||
|
||||
result := health.CheckResult{
|
||||
Healthy: connected,
|
||||
Details: healthInfo,
|
||||
Timestamp: time.Now(),
|
||||
}
|
||||
|
||||
|
||||
if connected {
|
||||
result.Message = "BACKBEAT integration healthy and connected"
|
||||
} else {
|
||||
result.Message = "BACKBEAT integration not connected"
|
||||
}
|
||||
|
||||
|
||||
return result
|
||||
},
|
||||
}
|
||||
healthManager.RegisterCheck(backbeatCheck)
|
||||
}
|
||||
|
||||
// Add other health checks (P2P, DHT, etc.)
|
||||
// Implementation from CHORUS would go here
|
||||
|
||||
// Register enhanced health instrumentation when core subsystems are available
|
||||
if r.PubSub == nil {
|
||||
r.Logger.Warn("⚠️ Skipping enhanced health checks: PubSub not initialized")
|
||||
return
|
||||
}
|
||||
if r.ElectionManager == nil {
|
||||
r.Logger.Warn("⚠️ Skipping enhanced health checks: election manager not ready")
|
||||
return
|
||||
}
|
||||
|
||||
var replication *dht.ReplicationManager
|
||||
if r.DHTNode != nil {
|
||||
replication = r.DHTNode.ReplicationManager()
|
||||
}
|
||||
|
||||
enhanced := health.NewEnhancedHealthChecks(
|
||||
healthManager,
|
||||
r.ElectionManager,
|
||||
r.DHTNode,
|
||||
r.PubSub,
|
||||
replication,
|
||||
&simpleLogger{logger: r.Logger},
|
||||
)
|
||||
|
||||
r.EnhancedHealth = enhanced
|
||||
r.Logger.Info("🩺 Enhanced health checks registered")
|
||||
}
|
||||
|
||||
func (r *SharedRuntime) setupGracefulShutdown(shutdownManager *shutdown.Manager, healthManager *health.Manager) {
|
||||
// Register components for graceful shutdown
|
||||
// Implementation would register all components that need graceful shutdown
|
||||
if shutdownManager == nil {
|
||||
r.Logger.Warn("⚠️ Shutdown manager not initialized; graceful teardown skipped")
|
||||
return
|
||||
}
|
||||
|
||||
if r.HTTPServer != nil {
|
||||
httpComponent := shutdown.NewGenericComponent("http-api-server", 10, true).
|
||||
SetShutdownFunc(func(ctx context.Context) error {
|
||||
return r.HTTPServer.Stop()
|
||||
})
|
||||
shutdownManager.Register(httpComponent)
|
||||
}
|
||||
|
||||
if healthManager != nil {
|
||||
healthComponent := shutdown.NewGenericComponent("health-manager", 15, true).
|
||||
SetShutdownFunc(func(ctx context.Context) error {
|
||||
return healthManager.Stop()
|
||||
})
|
||||
shutdownManager.Register(healthComponent)
|
||||
}
|
||||
|
||||
if r.UCXIServer != nil {
|
||||
ucxiComponent := shutdown.NewGenericComponent("ucxi-server", 20, true).
|
||||
SetShutdownFunc(func(ctx context.Context) error {
|
||||
return r.UCXIServer.Stop()
|
||||
})
|
||||
shutdownManager.Register(ucxiComponent)
|
||||
}
|
||||
|
||||
if r.PubSub != nil {
|
||||
shutdownManager.Register(shutdown.NewPubSubComponent("pubsub", r.PubSub.Close, 30))
|
||||
}
|
||||
|
||||
if r.DHTNode != nil {
|
||||
dhtComponent := shutdown.NewGenericComponent("dht-node", 35, true).
|
||||
SetCloser(r.DHTNode.Close)
|
||||
shutdownManager.Register(dhtComponent)
|
||||
}
|
||||
|
||||
if r.Node != nil {
|
||||
shutdownManager.Register(shutdown.NewP2PNodeComponent("p2p-node", r.Node.Close, 40))
|
||||
}
|
||||
|
||||
if r.ElectionManager != nil {
|
||||
shutdownManager.Register(shutdown.NewElectionManagerComponent("election-manager", r.ElectionManager.Stop, 45))
|
||||
}
|
||||
|
||||
if r.BackbeatIntegration != nil {
|
||||
backbeatComponent := shutdown.NewGenericComponent("backbeat-integration", 50, true).
|
||||
SetShutdownFunc(func(ctx context.Context) error {
|
||||
return r.BackbeatIntegration.Stop()
|
||||
})
|
||||
shutdownManager.Register(backbeatComponent)
|
||||
}
|
||||
|
||||
r.Logger.Info("🛡️ Graceful shutdown components registered")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -21,8 +21,10 @@ import (
|
||||
"chorus/pkg/dht"
|
||||
"chorus/pkg/election"
|
||||
"chorus/pkg/health"
|
||||
"chorus/pkg/shutdown"
|
||||
"chorus/pkg/metrics"
|
||||
"chorus/pkg/prompt"
|
||||
"chorus/pkg/shhh"
|
||||
"chorus/pkg/shutdown"
|
||||
"chorus/pkg/ucxi"
|
||||
"chorus/pkg/ucxl"
|
||||
"chorus/pubsub"
|
||||
@@ -53,8 +55,8 @@ func (l *SimpleLogger) Error(msg string, args ...interface{}) {
|
||||
|
||||
// SimpleTaskTracker tracks active tasks for availability reporting
|
||||
type SimpleTaskTracker struct {
|
||||
maxTasks int
|
||||
activeTasks map[string]bool
|
||||
maxTasks int
|
||||
activeTasks map[string]bool
|
||||
decisionPublisher *ucxl.DecisionPublisher
|
||||
}
|
||||
|
||||
@@ -80,7 +82,7 @@ func (t *SimpleTaskTracker) AddTask(taskID string) {
|
||||
// RemoveTask marks a task as completed and publishes decision if publisher available
|
||||
func (t *SimpleTaskTracker) RemoveTask(taskID string) {
|
||||
delete(t.activeTasks, taskID)
|
||||
|
||||
|
||||
// Publish task completion decision if publisher is available
|
||||
if t.decisionPublisher != nil {
|
||||
t.publishTaskCompletion(taskID, true, "Task completed successfully", nil)
|
||||
@@ -92,7 +94,7 @@ func (t *SimpleTaskTracker) publishTaskCompletion(taskID string, success bool, s
|
||||
if t.decisionPublisher == nil {
|
||||
return
|
||||
}
|
||||
|
||||
|
||||
if err := t.decisionPublisher.PublishTaskCompletion(taskID, success, summary, filesModified); err != nil {
|
||||
fmt.Printf("⚠️ Failed to publish task completion for %s: %v\n", taskID, err)
|
||||
} else {
|
||||
@@ -102,32 +104,35 @@ func (t *SimpleTaskTracker) publishTaskCompletion(taskID string, success bool, s
|
||||
|
||||
// SharedRuntime contains all the shared P2P infrastructure components
|
||||
type SharedRuntime struct {
|
||||
Config *config.Config
|
||||
Logger *SimpleLogger
|
||||
Context context.Context
|
||||
Cancel context.CancelFunc
|
||||
Node *p2p.Node
|
||||
PubSub *pubsub.PubSub
|
||||
HypercoreLog *logging.HypercoreLog
|
||||
MDNSDiscovery *discovery.MDNSDiscovery
|
||||
BackbeatIntegration *backbeat.Integration
|
||||
DHTNode *dht.LibP2PDHT
|
||||
EncryptedStorage *dht.EncryptedDHTStorage
|
||||
DecisionPublisher *ucxl.DecisionPublisher
|
||||
ElectionManager *election.ElectionManager
|
||||
TaskCoordinator *coordinator.TaskCoordinator
|
||||
HTTPServer *api.HTTPServer
|
||||
UCXIServer *ucxi.Server
|
||||
HealthManager *health.Manager
|
||||
ShutdownManager *shutdown.Manager
|
||||
TaskTracker *SimpleTaskTracker
|
||||
Config *config.Config
|
||||
Logger *SimpleLogger
|
||||
Context context.Context
|
||||
Cancel context.CancelFunc
|
||||
Node *p2p.Node
|
||||
PubSub *pubsub.PubSub
|
||||
HypercoreLog *logging.HypercoreLog
|
||||
MDNSDiscovery *discovery.MDNSDiscovery
|
||||
BackbeatIntegration *backbeat.Integration
|
||||
DHTNode *dht.LibP2PDHT
|
||||
EncryptedStorage *dht.EncryptedDHTStorage
|
||||
DecisionPublisher *ucxl.DecisionPublisher
|
||||
ElectionManager *election.ElectionManager
|
||||
TaskCoordinator *coordinator.TaskCoordinator
|
||||
HTTPServer *api.HTTPServer
|
||||
UCXIServer *ucxi.Server
|
||||
HealthManager *health.Manager
|
||||
EnhancedHealth *health.EnhancedHealthChecks
|
||||
ShutdownManager *shutdown.Manager
|
||||
TaskTracker *SimpleTaskTracker
|
||||
Metrics *metrics.CHORUSMetrics
|
||||
Shhh *shhh.Sentinel
|
||||
}
|
||||
|
||||
// Initialize sets up all shared P2P infrastructure components
|
||||
func Initialize(appMode string) (*SharedRuntime, error) {
|
||||
runtime := &SharedRuntime{}
|
||||
runtime.Logger = &SimpleLogger{}
|
||||
|
||||
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
runtime.Context = ctx
|
||||
runtime.Cancel = cancel
|
||||
@@ -142,7 +147,7 @@ func Initialize(appMode string) (*SharedRuntime, error) {
|
||||
return nil, fmt.Errorf("configuration error: %v", err)
|
||||
}
|
||||
runtime.Config = cfg
|
||||
|
||||
|
||||
runtime.Logger.Info("✅ Configuration loaded successfully")
|
||||
runtime.Logger.Info("🤖 Agent ID: %s", cfg.Agent.ID)
|
||||
runtime.Logger.Info("🎯 Specialization: %s", cfg.Agent.Specialization)
|
||||
@@ -166,6 +171,21 @@ func Initialize(appMode string) (*SharedRuntime, error) {
|
||||
}
|
||||
runtime.Logger.Info("✅ AI provider configured successfully")
|
||||
|
||||
// Initialize metrics collector
|
||||
runtime.Metrics = metrics.NewCHORUSMetrics(nil)
|
||||
|
||||
// Initialize SHHH sentinel
|
||||
sentinel, err := shhh.NewSentinel(
|
||||
shhh.Config{},
|
||||
shhh.WithFindingObserver(runtime.handleShhhFindings),
|
||||
)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to initialize SHHH sentinel: %v", err)
|
||||
}
|
||||
sentinel.SetAuditSink(&shhhAuditSink{logger: runtime.Logger})
|
||||
runtime.Shhh = sentinel
|
||||
runtime.Logger.Info("🛡️ SHHH sentinel initialized")
|
||||
|
||||
// Initialize BACKBEAT integration
|
||||
var backbeatIntegration *backbeat.Integration
|
||||
backbeatIntegration, err = backbeat.NewIntegration(cfg, cfg.Agent.ID, runtime.Logger)
|
||||
@@ -198,6 +218,9 @@ func Initialize(appMode string) (*SharedRuntime, error) {
|
||||
|
||||
// Initialize Hypercore-style logger for P2P coordination
|
||||
hlog := logging.NewHypercoreLog(node.ID())
|
||||
if runtime.Shhh != nil {
|
||||
hlog.SetRedactor(runtime.Shhh)
|
||||
}
|
||||
hlog.Append(logging.PeerJoined, map[string]interface{}{"status": "started"})
|
||||
runtime.HypercoreLog = hlog
|
||||
runtime.Logger.Info("📝 Hypercore logger initialized")
|
||||
@@ -214,8 +237,11 @@ func Initialize(appMode string) (*SharedRuntime, error) {
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to create PubSub: %v", err)
|
||||
}
|
||||
if runtime.Shhh != nil {
|
||||
ps.SetRedactor(runtime.Shhh)
|
||||
}
|
||||
runtime.PubSub = ps
|
||||
|
||||
|
||||
runtime.Logger.Info("📡 PubSub system initialized")
|
||||
|
||||
// Join role-based topics if role is configured
|
||||
@@ -294,12 +320,12 @@ func (r *SharedRuntime) Cleanup() {
|
||||
func (r *SharedRuntime) initializeElectionSystem() error {
|
||||
// === Admin Election System ===
|
||||
electionManager := election.NewElectionManager(r.Context, r.Config, r.Node.Host(), r.PubSub, r.Node.ID().ShortString())
|
||||
|
||||
|
||||
// Set election callbacks with BACKBEAT integration
|
||||
electionManager.SetCallbacks(
|
||||
func(oldAdmin, newAdmin string) {
|
||||
r.Logger.Info("👑 Admin changed: %s -> %s", oldAdmin, newAdmin)
|
||||
|
||||
|
||||
// Track admin change with BACKBEAT if available
|
||||
if r.BackbeatIntegration != nil {
|
||||
operationID := fmt.Sprintf("admin-change-%d", time.Now().Unix())
|
||||
@@ -311,7 +337,7 @@ func (r *SharedRuntime) initializeElectionSystem() error {
|
||||
r.BackbeatIntegration.CompleteP2POperation(operationID, 1)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
// If this node becomes admin, enable SLURP functionality
|
||||
if newAdmin == r.Node.ID().ShortString() {
|
||||
r.Logger.Info("🎯 This node is now admin - enabling SLURP functionality")
|
||||
@@ -324,12 +350,12 @@ func (r *SharedRuntime) initializeElectionSystem() error {
|
||||
},
|
||||
func(winner string) {
|
||||
r.Logger.Info("🏆 Election completed, winner: %s", winner)
|
||||
|
||||
|
||||
// Track election completion with BACKBEAT if available
|
||||
if r.BackbeatIntegration != nil {
|
||||
operationID := fmt.Sprintf("election-completed-%d", time.Now().Unix())
|
||||
if err := r.BackbeatIntegration.StartP2POperation(operationID, "election", 1, map[string]interface{}{
|
||||
"winner": winner,
|
||||
"winner": winner,
|
||||
"node_id": r.Node.ID().ShortString(),
|
||||
}); err == nil {
|
||||
r.BackbeatIntegration.CompleteP2POperation(operationID, 1)
|
||||
@@ -337,22 +363,22 @@ func (r *SharedRuntime) initializeElectionSystem() error {
|
||||
}
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
if err := electionManager.Start(); err != nil {
|
||||
return fmt.Errorf("failed to start election manager: %v", err)
|
||||
}
|
||||
r.ElectionManager = electionManager
|
||||
r.Logger.Info("✅ Election manager started with automated heartbeat management")
|
||||
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func (r *SharedRuntime) initializeDHTStorage() error {
|
||||
// === DHT Storage and Decision Publishing ===
|
||||
var dhtNode *dht.LibP2PDHT
|
||||
var encryptedStorage *dht.EncryptedDHTStorage
|
||||
var encryptedStorage *dht.EncryptedDHTStorage
|
||||
var decisionPublisher *ucxl.DecisionPublisher
|
||||
|
||||
|
||||
if r.Config.V2.DHT.Enabled {
|
||||
// Create DHT
|
||||
var err error
|
||||
@@ -361,14 +387,14 @@ func (r *SharedRuntime) initializeDHTStorage() error {
|
||||
r.Logger.Warn("⚠️ Failed to create DHT: %v", err)
|
||||
} else {
|
||||
r.Logger.Info("🕸️ DHT initialized")
|
||||
|
||||
|
||||
// Bootstrap DHT with BACKBEAT tracking
|
||||
if r.BackbeatIntegration != nil {
|
||||
operationID := fmt.Sprintf("dht-bootstrap-%d", time.Now().Unix())
|
||||
if err := r.BackbeatIntegration.StartP2POperation(operationID, "dht_bootstrap", 4, nil); err == nil {
|
||||
r.BackbeatIntegration.UpdateP2POperationPhase(operationID, backbeat.PhaseConnecting, 0)
|
||||
}
|
||||
|
||||
|
||||
if err := dhtNode.Bootstrap(); err != nil {
|
||||
r.Logger.Warn("⚠️ DHT bootstrap failed: %v", err)
|
||||
r.BackbeatIntegration.FailP2POperation(operationID, err.Error())
|
||||
@@ -380,22 +406,22 @@ func (r *SharedRuntime) initializeDHTStorage() error {
|
||||
r.Logger.Warn("⚠️ DHT bootstrap failed: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// Connect to bootstrap peers if configured
|
||||
|
||||
// Connect to bootstrap peers if configured
|
||||
for _, addrStr := range r.Config.V2.DHT.BootstrapPeers {
|
||||
addr, err := multiaddr.NewMultiaddr(addrStr)
|
||||
if err != nil {
|
||||
r.Logger.Warn("⚠️ Invalid bootstrap address %s: %v", addrStr, err)
|
||||
continue
|
||||
}
|
||||
|
||||
|
||||
// Extract peer info from multiaddr
|
||||
info, err := peer.AddrInfoFromP2pAddr(addr)
|
||||
if err != nil {
|
||||
r.Logger.Warn("⚠️ Failed to parse peer info from %s: %v", addrStr, err)
|
||||
continue
|
||||
}
|
||||
|
||||
|
||||
// Track peer discovery with BACKBEAT if available
|
||||
if r.BackbeatIntegration != nil {
|
||||
operationID := fmt.Sprintf("peer-discovery-%d", time.Now().Unix())
|
||||
@@ -403,7 +429,7 @@ func (r *SharedRuntime) initializeDHTStorage() error {
|
||||
"peer_addr": addrStr,
|
||||
}); err == nil {
|
||||
r.BackbeatIntegration.UpdateP2POperationPhase(operationID, backbeat.PhaseConnecting, 0)
|
||||
|
||||
|
||||
if err := r.Node.Host().Connect(r.Context, *info); err != nil {
|
||||
r.Logger.Warn("⚠️ Failed to connect to bootstrap peer %s: %v", addrStr, err)
|
||||
r.BackbeatIntegration.FailP2POperation(operationID, err.Error())
|
||||
@@ -420,20 +446,20 @@ func (r *SharedRuntime) initializeDHTStorage() error {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
// Initialize encrypted storage
|
||||
encryptedStorage = dht.NewEncryptedDHTStorage(
|
||||
r.Context,
|
||||
r.Node.Host(),
|
||||
r.Node.Host(),
|
||||
dhtNode,
|
||||
r.Config,
|
||||
r.Node.ID().ShortString(),
|
||||
)
|
||||
|
||||
|
||||
// Start cache cleanup
|
||||
encryptedStorage.StartCacheCleanup(5 * time.Minute)
|
||||
r.Logger.Info("🔐 Encrypted DHT storage initialized")
|
||||
|
||||
|
||||
// Initialize decision publisher
|
||||
decisionPublisher = ucxl.NewDecisionPublisher(
|
||||
r.Context,
|
||||
@@ -451,11 +477,24 @@ func (r *SharedRuntime) initializeDHTStorage() error {
|
||||
r.DHTNode = dhtNode
|
||||
r.EncryptedStorage = encryptedStorage
|
||||
r.DecisionPublisher = decisionPublisher
|
||||
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func (r *SharedRuntime) initializeServices() error {
|
||||
// Create simple task tracker ahead of coordinator so broadcasts stay accurate
|
||||
taskTracker := &SimpleTaskTracker{
|
||||
maxTasks: r.Config.Agent.MaxTasks,
|
||||
activeTasks: make(map[string]bool),
|
||||
}
|
||||
|
||||
// Connect decision publisher to task tracker if available
|
||||
if r.DecisionPublisher != nil {
|
||||
taskTracker.decisionPublisher = r.DecisionPublisher
|
||||
r.Logger.Info("📤 Task completion decisions will be published to DHT")
|
||||
}
|
||||
r.TaskTracker = taskTracker
|
||||
|
||||
// === Task Coordination Integration ===
|
||||
taskCoordinator := coordinator.NewTaskCoordinator(
|
||||
r.Context,
|
||||
@@ -464,8 +503,9 @@ func (r *SharedRuntime) initializeServices() error {
|
||||
r.Config,
|
||||
r.Node.ID().ShortString(),
|
||||
nil, // HMMM router placeholder
|
||||
taskTracker,
|
||||
)
|
||||
|
||||
|
||||
taskCoordinator.Start()
|
||||
r.TaskCoordinator = taskCoordinator
|
||||
r.Logger.Info("✅ Task coordination system active")
|
||||
@@ -487,14 +527,14 @@ func (r *SharedRuntime) initializeServices() error {
|
||||
if storageDir == "" {
|
||||
storageDir = filepath.Join(os.TempDir(), "chorus-ucxi-storage")
|
||||
}
|
||||
|
||||
|
||||
storage, err := ucxi.NewBasicContentStorage(storageDir)
|
||||
if err != nil {
|
||||
r.Logger.Warn("⚠️ Failed to create UCXI storage: %v", err)
|
||||
} else {
|
||||
resolver := ucxi.NewBasicAddressResolver(r.Node.ID().ShortString())
|
||||
resolver.SetDefaultTTL(r.Config.UCXL.Resolution.CacheTTL)
|
||||
|
||||
|
||||
ucxiConfig := ucxi.ServerConfig{
|
||||
Port: r.Config.UCXL.Server.Port,
|
||||
BasePath: r.Config.UCXL.Server.BasePath,
|
||||
@@ -502,7 +542,7 @@ func (r *SharedRuntime) initializeServices() error {
|
||||
Storage: storage,
|
||||
Logger: ucxi.SimpleLogger{},
|
||||
}
|
||||
|
||||
|
||||
ucxiServer = ucxi.NewServer(ucxiConfig)
|
||||
go func() {
|
||||
r.Logger.Info("🔗 UCXI server starting on :%d", r.Config.UCXL.Server.Port)
|
||||
@@ -515,35 +555,41 @@ func (r *SharedRuntime) initializeServices() error {
|
||||
r.Logger.Info("⚪ UCXI server disabled")
|
||||
}
|
||||
r.UCXIServer = ucxiServer
|
||||
|
||||
// Create simple task tracker
|
||||
taskTracker := &SimpleTaskTracker{
|
||||
maxTasks: r.Config.Agent.MaxTasks,
|
||||
activeTasks: make(map[string]bool),
|
||||
}
|
||||
|
||||
// Connect decision publisher to task tracker if available
|
||||
if r.DecisionPublisher != nil {
|
||||
taskTracker.decisionPublisher = r.DecisionPublisher
|
||||
r.Logger.Info("📤 Task completion decisions will be published to DHT")
|
||||
}
|
||||
r.TaskTracker = taskTracker
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func (r *SharedRuntime) handleShhhFindings(ctx context.Context, findings []shhh.Finding) {
|
||||
if r == nil || r.Metrics == nil {
|
||||
return
|
||||
}
|
||||
for _, finding := range findings {
|
||||
r.Metrics.IncrementSHHHFindings(finding.Rule, string(finding.Severity), finding.Count)
|
||||
}
|
||||
}
|
||||
|
||||
type shhhAuditSink struct {
|
||||
logger *SimpleLogger
|
||||
}
|
||||
|
||||
func (s *shhhAuditSink) RecordRedaction(_ context.Context, event shhh.AuditEvent) {
|
||||
if s == nil || s.logger == nil {
|
||||
return
|
||||
}
|
||||
s.logger.Warn("🔒 SHHH redaction applied (rule=%s severity=%s path=%s)", event.Rule, event.Severity, event.Path)
|
||||
}
|
||||
|
||||
// initializeAIProvider configures the reasoning engine with the appropriate AI provider
|
||||
func initializeAIProvider(cfg *config.Config, logger *SimpleLogger) error {
|
||||
// Set the AI provider
|
||||
reasoning.SetAIProvider(cfg.AI.Provider)
|
||||
|
||||
|
||||
// Configure the selected provider
|
||||
switch cfg.AI.Provider {
|
||||
case "resetdata":
|
||||
if cfg.AI.ResetData.APIKey == "" {
|
||||
return fmt.Errorf("RESETDATA_API_KEY environment variable is required for resetdata provider")
|
||||
}
|
||||
|
||||
|
||||
resetdataConfig := reasoning.ResetDataConfig{
|
||||
BaseURL: cfg.AI.ResetData.BaseURL,
|
||||
APIKey: cfg.AI.ResetData.APIKey,
|
||||
@@ -551,19 +597,19 @@ func initializeAIProvider(cfg *config.Config, logger *SimpleLogger) error {
|
||||
Timeout: cfg.AI.ResetData.Timeout,
|
||||
}
|
||||
reasoning.SetResetDataConfig(resetdataConfig)
|
||||
logger.Info("🌐 ResetData AI provider configured - Endpoint: %s, Model: %s",
|
||||
logger.Info("🌐 ResetData AI provider configured - Endpoint: %s, Model: %s",
|
||||
cfg.AI.ResetData.BaseURL, cfg.AI.ResetData.Model)
|
||||
|
||||
|
||||
case "ollama":
|
||||
reasoning.SetOllamaEndpoint(cfg.AI.Ollama.Endpoint)
|
||||
logger.Info("🦙 Ollama AI provider configured - Endpoint: %s", cfg.AI.Ollama.Endpoint)
|
||||
|
||||
|
||||
default:
|
||||
logger.Warn("⚠️ Unknown AI provider '%s', defaulting to resetdata", cfg.AI.Provider)
|
||||
if cfg.AI.ResetData.APIKey == "" {
|
||||
return fmt.Errorf("RESETDATA_API_KEY environment variable is required for default resetdata provider")
|
||||
}
|
||||
|
||||
|
||||
resetdataConfig := reasoning.ResetDataConfig{
|
||||
BaseURL: cfg.AI.ResetData.BaseURL,
|
||||
APIKey: cfg.AI.ResetData.APIKey,
|
||||
@@ -573,7 +619,7 @@ func initializeAIProvider(cfg *config.Config, logger *SimpleLogger) error {
|
||||
reasoning.SetResetDataConfig(resetdataConfig)
|
||||
reasoning.SetAIProvider("resetdata")
|
||||
}
|
||||
|
||||
|
||||
// Configure model selection
|
||||
reasoning.SetModelConfig(
|
||||
cfg.Agent.Models,
|
||||
|
||||
Reference in New Issue
Block a user