Enhance deployment system with retry functionality and improved UX
Major Improvements: - Added retry deployment buttons in machine list for failed deployments - Added retry button in SSH console modal footer for enhanced UX - Enhanced deployment process with comprehensive cleanup of existing services - Improved binary installation with password-based sudo authentication - Updated configuration generation to include all required sections (agent, ai, network, security) - Fixed deployment verification and error handling Security Enhancements: - Enhanced verifiedStopExistingServices with thorough cleanup process - Improved binary copying with proper sudo authentication - Added comprehensive configuration validation UX Improvements: - Users can retry deployments without re-running machine discovery - Retry buttons available from both machine list and console modal - Real-time deployment progress with detailed console output - Clear error states with actionable retry options Technical Changes: - Modified ServiceDeployment.tsx with retry button components - Enhanced api/setup_manager.go with improved deployment functions - Updated main.go with command line argument support (--config, --setup) - Added comprehensive zero-trust security validation system 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
anthonyrawlins
@@ -1,233 +0,0 @@
|
||||
package election
|
||||
|
||||
import (
|
||||
"context"
|
||||
"time"
|
||||
)
|
||||
|
||||
// SLURPElectionConfig holds SLURP-specific election configuration
|
||||
type SLURPElectionConfig struct {
|
||||
// Auto-start context generation when becoming admin
|
||||
AutoStartGeneration bool
|
||||
|
||||
// Delay before starting context generation
|
||||
GenerationStartDelay time.Duration
|
||||
|
||||
// Timeout for stopping context generation
|
||||
GenerationStopTimeout time.Duration
|
||||
|
||||
// Health check interval for context generation
|
||||
ContextHealthCheckInterval time.Duration
|
||||
|
||||
// Maximum allowed context generation errors before declaring unhealthy
|
||||
MaxContextErrors int
|
||||
|
||||
// Context generation timeout
|
||||
ContextGenerationTimeout time.Duration
|
||||
|
||||
// Enable advanced context caching
|
||||
EnableContextCaching bool
|
||||
|
||||
// Context cache TTL
|
||||
ContextCacheTTL time.Duration
|
||||
|
||||
// Maximum concurrent context generation requests
|
||||
MaxConcurrentContextGen int
|
||||
|
||||
// Enable distributed context generation (across multiple nodes)
|
||||
EnableDistributedGeneration bool
|
||||
}
|
||||
|
||||
// DefaultSLURPElectionConfig returns default SLURP election configuration
|
||||
func DefaultSLURPElectionConfig() *SLURPElectionConfig {
|
||||
return &SLURPElectionConfig{
|
||||
AutoStartGeneration: true,
|
||||
GenerationStartDelay: 2 * time.Second,
|
||||
GenerationStopTimeout: 30 * time.Second,
|
||||
ContextHealthCheckInterval: 15 * time.Second,
|
||||
MaxContextErrors: 3,
|
||||
ContextGenerationTimeout: 60 * time.Second,
|
||||
EnableContextCaching: true,
|
||||
ContextCacheTTL: 5 * time.Minute,
|
||||
MaxConcurrentContextGen: 10,
|
||||
EnableDistributedGeneration: false,
|
||||
}
|
||||
}
|
||||
|
||||
// ContextManager interface for managing context generation
|
||||
type ContextManager interface {
|
||||
GetGenerationStatus() (*GenerationStatus, error)
|
||||
RequestContextGeneration(req *ContextGenerationRequest) error
|
||||
StopGeneration() error
|
||||
GetActiveRequests() ([]*ContextGenerationRequest, error)
|
||||
GetCompletedRequests(limit int) ([]*ContextGenerationRequest, error)
|
||||
}
|
||||
|
||||
// GenerationStatus represents the status of context generation
|
||||
type GenerationStatus struct {
|
||||
LeaderID string `json:"leader_id"`
|
||||
ActiveRequests int `json:"active_requests"`
|
||||
CompletedRequests int64 `json:"completed_requests"`
|
||||
FailedRequests int64 `json:"failed_requests"`
|
||||
AverageLatency time.Duration `json:"average_latency"`
|
||||
LastRequestTime time.Time `json:"last_request_time"`
|
||||
GenerationCapacity int `json:"generation_capacity"`
|
||||
ContextCacheSize int `json:"context_cache_size"`
|
||||
CacheHitRate float64 `json:"cache_hit_rate"`
|
||||
ActiveTasks int `json:"active_tasks"`
|
||||
HealthStatus string `json:"health_status"`
|
||||
}
|
||||
|
||||
// ContextGenerationRequest represents a request for context generation
|
||||
type ContextGenerationRequest struct {
|
||||
RequestID string `json:"request_id"`
|
||||
RequestorID string `json:"requestor_id"`
|
||||
ContextType string `json:"context_type"`
|
||||
Parameters map[string]interface{} `json:"parameters"`
|
||||
Priority int `json:"priority"`
|
||||
RequestedAt time.Time `json:"requested_at"`
|
||||
CompletedAt *time.Time `json:"completed_at,omitempty"`
|
||||
Status string `json:"status"` // "pending", "processing", "completed", "failed"
|
||||
Result *ContextResult `json:"result,omitempty"`
|
||||
ErrorMessage string `json:"error_message,omitempty"`
|
||||
}
|
||||
|
||||
// ContextResult holds the result of context generation
|
||||
type ContextResult struct {
|
||||
Context string `json:"context"`
|
||||
Metadata map[string]interface{} `json:"metadata"`
|
||||
GeneratedAt time.Time `json:"generated_at"`
|
||||
GenerationTime time.Duration `json:"generation_time"`
|
||||
CacheUsed bool `json:"cache_used"`
|
||||
Quality float64 `json:"quality"` // 0.0-1.0
|
||||
TokenCount int `json:"token_count"`
|
||||
}
|
||||
|
||||
// ContextGenerationJob represents an active context generation job
|
||||
type ContextGenerationJob struct {
|
||||
JobID string `json:"job_id"`
|
||||
Request *ContextGenerationRequest `json:"request"`
|
||||
StartedAt time.Time `json:"started_at"`
|
||||
WorkerID string `json:"worker_id"`
|
||||
Status string `json:"status"`
|
||||
Progress float64 `json:"progress"` // 0.0-1.0
|
||||
ETA *time.Time `json:"eta,omitempty"`
|
||||
}
|
||||
|
||||
// ContextLeadershipCallbacks defines callbacks for context leadership events
|
||||
type ContextLeadershipCallbacks struct {
|
||||
OnBecomeContextLeader func(ctx context.Context, term int64) error
|
||||
OnLoseContextLeadership func(ctx context.Context, reason string) error
|
||||
OnContextLeaderChanged func(oldLeader, newLeader string, term int64)
|
||||
OnContextGenerationStarted func(nodeID string)
|
||||
OnContextGenerationStopped func(nodeID string, reason string)
|
||||
OnContextError func(err error, severity ErrorSeverity)
|
||||
OnContextRequestReceived func(req *ContextGenerationRequest)
|
||||
OnContextRequestCompleted func(req *ContextGenerationRequest, result *ContextResult)
|
||||
}
|
||||
|
||||
// ErrorSeverity defines the severity levels for context errors
|
||||
type ErrorSeverity string
|
||||
|
||||
const (
|
||||
ErrorSeverityLow ErrorSeverity = "low"
|
||||
ErrorSeverityMedium ErrorSeverity = "medium"
|
||||
ErrorSeverityHigh ErrorSeverity = "high"
|
||||
ErrorSeverityCritical ErrorSeverity = "critical"
|
||||
)
|
||||
|
||||
// ContextFailoverState holds state for context leadership failover
|
||||
type ContextFailoverState struct {
|
||||
LeaderID string `json:"leader_id"`
|
||||
Term int64 `json:"term"`
|
||||
TransferTime time.Time `json:"transfer_time"`
|
||||
StateVersion int64 `json:"state_version"`
|
||||
QueuedRequests []*ContextGenerationRequest `json:"queued_requests"`
|
||||
ActiveJobs map[string]*ContextGenerationJob `json:"active_jobs"`
|
||||
ManagerConfig *ManagerConfig `json:"manager_config"`
|
||||
ClusterState *ContextClusterState `json:"cluster_state"`
|
||||
HealthSnapshot *ContextClusterHealth `json:"health_snapshot"`
|
||||
Checksum string `json:"checksum"`
|
||||
}
|
||||
|
||||
// ManagerConfig holds configuration for the context manager
|
||||
type ManagerConfig struct {
|
||||
MaxConcurrentJobs int `json:"max_concurrent_jobs"`
|
||||
DefaultTimeout time.Duration `json:"default_timeout"`
|
||||
EnableCaching bool `json:"enable_caching"`
|
||||
CacheTTL time.Duration `json:"cache_ttl"`
|
||||
RetryAttempts int `json:"retry_attempts"`
|
||||
WorkerPoolSize int `json:"worker_pool_size"`
|
||||
}
|
||||
|
||||
// DefaultManagerConfig returns default manager configuration
|
||||
func DefaultManagerConfig() *ManagerConfig {
|
||||
return &ManagerConfig{
|
||||
MaxConcurrentJobs: 10,
|
||||
DefaultTimeout: 60 * time.Second,
|
||||
EnableCaching: true,
|
||||
CacheTTL: 5 * time.Minute,
|
||||
RetryAttempts: 3,
|
||||
WorkerPoolSize: 5,
|
||||
}
|
||||
}
|
||||
|
||||
// ContextClusterState holds the state of the context generation cluster
|
||||
type ContextClusterState struct {
|
||||
Nodes map[string]*ContextNodeInfo `json:"nodes"`
|
||||
TotalCapacity int `json:"total_capacity"`
|
||||
AvailableCapacity int `json:"available_capacity"`
|
||||
LoadBalance float64 `json:"load_balance"`
|
||||
LastUpdate time.Time `json:"last_update"`
|
||||
}
|
||||
|
||||
// ContextNodeInfo holds information about a node in the context cluster
|
||||
type ContextNodeInfo struct {
|
||||
NodeID string `json:"node_id"`
|
||||
Capacity int `json:"capacity"`
|
||||
ActiveJobs int `json:"active_jobs"`
|
||||
LastSeen time.Time `json:"last_seen"`
|
||||
HealthStatus string `json:"health_status"`
|
||||
AverageLatency time.Duration `json:"average_latency"`
|
||||
SuccessRate float64 `json:"success_rate"`
|
||||
}
|
||||
|
||||
// ContextClusterHealth represents the overall health of the context generation cluster
|
||||
type ContextClusterHealth struct {
|
||||
TotalNodes int `json:"total_nodes"`
|
||||
HealthyNodes int `json:"healthy_nodes"`
|
||||
UnhealthyNodes int `json:"unhealthy_nodes"`
|
||||
GenerationActive bool `json:"generation_active"`
|
||||
AverageLatency time.Duration `json:"average_latency"`
|
||||
SuccessRate float64 `json:"success_rate"`
|
||||
OverallHealthScore float64 `json:"overall_health_score"` // 0.0-1.0
|
||||
LastElection time.Time `json:"last_election"`
|
||||
NextHealthCheck time.Time `json:"next_health_check"`
|
||||
CapacityUtilization float64 `json:"capacity_utilization"`
|
||||
ErrorRate float64 `json:"error_rate"`
|
||||
Issues []string `json:"issues,omitempty"`
|
||||
}
|
||||
|
||||
// ContextStateValidation holds the results of context state validation
|
||||
type ContextStateValidation struct {
|
||||
Valid bool `json:"valid"`
|
||||
ValidatedAt time.Time `json:"validated_at"`
|
||||
ValidatedBy string `json:"validated_by"`
|
||||
ValidationDuration time.Duration `json:"validation_duration"`
|
||||
ChecksumValid bool `json:"checksum_valid"`
|
||||
TimestampValid bool `json:"timestamp_valid"`
|
||||
VersionConsistent bool `json:"version_consistent"`
|
||||
QueueStateValid bool `json:"queue_state_valid"`
|
||||
ClusterStateValid bool `json:"cluster_state_valid"`
|
||||
ConfigValid bool `json:"config_valid"`
|
||||
RequiresRecovery bool `json:"requires_recovery"`
|
||||
Issues []string `json:"issues,omitempty"`
|
||||
RecoverySteps []string `json:"recovery_steps,omitempty"`
|
||||
}
|
||||
|
||||
// LeaderInfo contains information about the current context leader
|
||||
type LeaderInfo struct {
|
||||
NodeID string `json:"node_id"`
|
||||
Term int64 `json:"term"`
|
||||
ElectedAt time.Time `json:"elected_at"`
|
||||
}
|
||||
Reference in New Issue
Block a user