@stackmemoryai/stackmemory 0.5.51 → 0.5.53

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (33) hide show
  1. package/dist/cli/commands/handoff.js +215 -59
  2. package/dist/cli/commands/handoff.js.map +2 -2
  3. package/dist/cli/index.js +8 -2
  4. package/dist/cli/index.js.map +2 -2
  5. package/dist/integrations/claude-code/lifecycle-hooks.js +3 -3
  6. package/dist/integrations/claude-code/lifecycle-hooks.js.map +1 -1
  7. package/package.json +1 -1
  8. package/scripts/auto-handoff.sh +1 -1
  9. package/scripts/claude-sm-autostart.js +174 -132
  10. package/scripts/setup-claude-integration.js +14 -10
  11. package/scripts/stackmemory-auto-handoff.sh +3 -3
  12. package/scripts/test-session-handoff.sh +2 -2
  13. package/dist/core/context/compaction-handler.js +0 -330
  14. package/dist/core/context/compaction-handler.js.map +0 -7
  15. package/dist/core/context/context-bridge.js +0 -238
  16. package/dist/core/context/context-bridge.js.map +0 -7
  17. package/scripts/testing/scripts/testing/ab-test-runner.js +0 -363
  18. package/scripts/testing/scripts/testing/collect-metrics.js +0 -292
  19. package/scripts/testing/src/core/context/context-bridge.js +0 -253
  20. package/scripts/testing/src/core/context/frame-manager.js +0 -746
  21. package/scripts/testing/src/core/context/shared-context-layer.js +0 -437
  22. package/scripts/testing/src/core/database/database-adapter.js +0 -54
  23. package/scripts/testing/src/core/errors/index.js +0 -291
  24. package/scripts/testing/src/core/errors/recovery.js +0 -268
  25. package/scripts/testing/src/core/monitoring/logger.js +0 -145
  26. package/scripts/testing/src/core/retrieval/context-retriever.js +0 -516
  27. package/scripts/testing/src/core/session/index.js +0 -1
  28. package/scripts/testing/src/core/session/session-manager.js +0 -323
  29. package/scripts/testing/src/core/trace/cli-trace-wrapper.js +0 -140
  30. package/scripts/testing/src/core/trace/db-trace-wrapper.js +0 -251
  31. package/scripts/testing/src/core/trace/debug-trace.js +0 -398
  32. package/scripts/testing/src/core/trace/index.js +0 -120
  33. package/scripts/testing/src/core/trace/linear-api-wrapper.js +0 -204
@@ -1,7 +0,0 @@
1
- {
2
- "version": 3,
3
- "sources": ["../../../src/core/context/context-bridge.ts"],
4
- "sourcesContent": ["/**\n * Context Bridge - Automatic synchronization between sessions and shared context\n *\n * This bridge automatically:\n * - Syncs important frames to shared context\n * - Loads relevant context on session start\n * - Maintains consistency across sessions\n */\n\nimport { FrameManager, type Frame } from './index.js';\nimport { sharedContextLayer } from './shared-context-layer.js';\nimport { sessionManager } from '../session/session-manager.js';\nimport { logger } from '../monitoring/logger.js';\n\nexport interface BridgeOptions {\n autoSync: boolean;\n syncInterval: number;\n minFrameScore: number;\n importantTags: string[];\n}\n\nexport class ContextBridge {\n private static instance: ContextBridge;\n private frameManager: FrameManager | null = null;\n private syncTimer: NodeJS.Timeout | null = null;\n private lastSyncTime: number = 0;\n private options: BridgeOptions = {\n autoSync: true,\n syncInterval: 60000, // 1 minute\n minFrameScore: 0.5, // Include frames with score above 0.5\n importantTags: ['decision', 'error', 'milestone', 'learning'],\n };\n\n private constructor() {}\n\n static getInstance(): ContextBridge {\n if (!ContextBridge.instance) {\n ContextBridge.instance = new ContextBridge();\n }\n return ContextBridge.instance;\n }\n\n /**\n * Initialize the bridge with a frame manager\n */\n async initialize(\n frameManager: FrameManager,\n options?: Partial<BridgeOptions>\n ): Promise<void> {\n this.frameManager = frameManager;\n this.options = { ...this.options, ...options };\n\n // Load shared context on initialization\n await this.loadSharedContext();\n\n // Start auto-sync if enabled\n if (this.options.autoSync) {\n this.startAutoSync();\n }\n\n logger.info('Context bridge initialized', {\n autoSync: this.options.autoSync,\n syncInterval: this.options.syncInterval,\n });\n }\n\n /**\n * Load relevant shared context into current session\n */\n async loadSharedContext(): Promise<void> {\n try {\n const session = sessionManager.getCurrentSession();\n if (!session) return;\n\n // Get context discovery\n const discovery = await sharedContextLayer.autoDiscoverContext();\n\n if (!discovery.hasSharedContext) {\n logger.info('No shared context available to load');\n return;\n }\n\n // Load recent patterns as metadata\n if (discovery.recentPatterns.length > 0) {\n logger.info('Loaded recent patterns from shared context', {\n patternCount: discovery.recentPatterns.length,\n });\n }\n\n // Load last decisions for reference\n if (discovery.lastDecisions.length > 0) {\n logger.info('Loaded recent decisions from shared context', {\n decisionCount: discovery.lastDecisions.length,\n });\n }\n\n // Store suggested frames in metadata for quick reference\n if (discovery.suggestedFrames.length > 0) {\n const metadata = {\n suggestedFrames: discovery.suggestedFrames,\n loadedAt: Date.now(),\n };\n\n // Store in frame manager's context\n if (this.frameManager) {\n await this.frameManager.addContext(\n 'shared-context-suggestions',\n metadata\n );\n }\n\n logger.info('Loaded suggested frames from shared context', {\n frameCount: discovery.suggestedFrames.length,\n });\n }\n } catch (error: unknown) {\n logger.error('Failed to load shared context', error as Error);\n }\n }\n\n /**\n * Sync current session's important frames to shared context\n */\n async syncToSharedContext(): Promise<void> {\n try {\n if (!this.frameManager) return;\n\n const session = sessionManager.getCurrentSession();\n if (!session) return;\n\n // Get all active frames (filter out any nulls from missing frames)\n const activeFrames = this.frameManager\n .getActiveFramePath()\n .filter(Boolean);\n\n // Get recent closed frames (last 100)\n const recentFrames = await this.frameManager.getRecentFrames(100);\n\n // Combine and filter important frames\n const allFrames = [...activeFrames, ...recentFrames].filter(Boolean);\n const importantFrames = this.filterImportantFrames(allFrames);\n\n if (importantFrames.length === 0) {\n logger.debug('No important frames to sync');\n return;\n }\n\n // Add to shared context\n await sharedContextLayer.addToSharedContext(importantFrames, {\n minScore: this.options.minFrameScore,\n tags: this.options.importantTags,\n });\n\n this.lastSyncTime = Date.now();\n\n logger.info('Synced frames to shared context', {\n frameCount: importantFrames.length,\n sessionId: session.sessionId,\n });\n } catch (error: unknown) {\n logger.error('Failed to sync to shared context', error as Error);\n }\n }\n\n /**\n * Query shared context for relevant frames\n */\n async querySharedFrames(query: {\n tags?: string[];\n type?: string;\n limit?: number;\n }): Promise<any[]> {\n try {\n const results = await sharedContextLayer.querySharedContext({\n ...query,\n minScore: this.options.minFrameScore,\n });\n\n logger.info('Queried shared context', {\n query,\n resultCount: results.length,\n });\n\n return results;\n } catch (error: unknown) {\n logger.error('Failed to query shared context', error as Error);\n return [];\n }\n }\n\n /**\n * Add a decision to shared context\n */\n async addDecision(decision: string, reasoning: string): Promise<void> {\n try {\n await sharedContextLayer.addDecision({\n decision,\n reasoning,\n outcome: 'pending',\n });\n\n logger.info('Added decision to shared context', { decision });\n } catch (error: unknown) {\n logger.error('Failed to add decision', error as Error);\n }\n }\n\n /**\n * Start automatic synchronization\n */\n private startAutoSync(): void {\n if (this.syncTimer) {\n clearInterval(this.syncTimer);\n }\n\n this.syncTimer = setInterval(() => {\n this.syncToSharedContext().catch((error) => {\n logger.error('Auto-sync failed', error as Error);\n });\n }, this.options.syncInterval);\n\n // Also sync on important events\n this.setupEventListeners();\n }\n\n /**\n * Stop automatic synchronization\n */\n stopAutoSync(): void {\n if (this.syncTimer) {\n clearInterval(this.syncTimer);\n this.syncTimer = null;\n }\n }\n\n /**\n * Filter frames that are important enough to share\n */\n private filterImportantFrames(frames: Frame[]): Frame[] {\n return frames.filter((frame) => {\n // Check if frame has important tags\n const hasImportantTag = this.options.importantTags.some((tag) =>\n frame.metadata?.tags?.includes(tag)\n );\n\n // Check frame type importance\n const isImportantType = [\n 'task',\n 'milestone',\n 'error',\n 'resolution',\n 'decision',\n ].includes(frame.type);\n\n // Check metadata importance flag\n const markedImportant = frame.metadata?.importance === 'high';\n\n return hasImportantTag || isImportantType || markedImportant;\n });\n }\n\n /**\n * Setup event listeners for automatic syncing\n */\n private setupEventListeners(): void {\n if (!this.frameManager) return;\n\n // Sync when a frame is closed\n const originalClose = this.frameManager.closeFrame.bind(this.frameManager);\n this.frameManager.closeFrame = async (frameId: string, metadata?: any) => {\n const result = await originalClose(frameId, metadata);\n\n // Sync if it was an important frame\n const frame = await this.frameManager!.getFrame(frameId);\n if (frame && this.filterImportantFrames([frame]).length > 0) {\n await this.syncToSharedContext();\n }\n\n return result;\n };\n\n // Sync when a milestone is reached\n const originalMilestone = this.frameManager.createFrame.bind(\n this.frameManager\n );\n this.frameManager.createFrame = async (params: any) => {\n const result = await originalMilestone(params);\n\n if (params.type === 'milestone') {\n await this.syncToSharedContext();\n }\n\n return result;\n };\n }\n\n /**\n * Get sync statistics\n */\n getSyncStats(): {\n lastSyncTime: number;\n autoSyncEnabled: boolean;\n syncInterval: number;\n } {\n return {\n lastSyncTime: this.lastSyncTime,\n autoSyncEnabled: this.options.autoSync,\n syncInterval: this.options.syncInterval,\n };\n }\n\n /**\n * Manual trigger for immediate sync\n */\n async forceSyncNow(): Promise<void> {\n logger.info('Force sync triggered');\n await this.syncToSharedContext();\n }\n}\n\nexport const contextBridge = ContextBridge.getInstance();\n\n// Export for testing\nexport { BridgeOptions };\n"],
5
- "mappings": ";;;;AAUA,SAAS,0BAA0B;AACnC,SAAS,sBAAsB;AAC/B,SAAS,cAAc;AAShB,MAAM,cAAc;AAAA,EACzB,OAAe;AAAA,EACP,eAAoC;AAAA,EACpC,YAAmC;AAAA,EACnC,eAAuB;AAAA,EACvB,UAAyB;AAAA,IAC/B,UAAU;AAAA,IACV,cAAc;AAAA;AAAA,IACd,eAAe;AAAA;AAAA,IACf,eAAe,CAAC,YAAY,SAAS,aAAa,UAAU;AAAA,EAC9D;AAAA,EAEQ,cAAc;AAAA,EAAC;AAAA,EAEvB,OAAO,cAA6B;AAClC,QAAI,CAAC,cAAc,UAAU;AAC3B,oBAAc,WAAW,IAAI,cAAc;AAAA,IAC7C;AACA,WAAO,cAAc;AAAA,EACvB;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,WACJ,cACA,SACe;AACf,SAAK,eAAe;AACpB,SAAK,UAAU,EAAE,GAAG,KAAK,SAAS,GAAG,QAAQ;AAG7C,UAAM,KAAK,kBAAkB;AAG7B,QAAI,KAAK,QAAQ,UAAU;AACzB,WAAK,cAAc;AAAA,IACrB;AAEA,WAAO,KAAK,8BAA8B;AAAA,MACxC,UAAU,KAAK,QAAQ;AAAA,MACvB,cAAc,KAAK,QAAQ;AAAA,IAC7B,CAAC;AAAA,EACH;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,oBAAmC;AACvC,QAAI;AACF,YAAM,UAAU,eAAe,kBAAkB;AACjD,UAAI,CAAC,QAAS;AAGd,YAAM,YAAY,MAAM,mBAAmB,oBAAoB;AAE/D,UAAI,CAAC,UAAU,kBAAkB;AAC/B,eAAO,KAAK,qCAAqC;AACjD;AAAA,MACF;AAGA,UAAI,UAAU,eAAe,SAAS,GAAG;AACvC,eAAO,KAAK,8CAA8C;AAAA,UACxD,cAAc,UAAU,eAAe;AAAA,QACzC,CAAC;AAAA,MACH;AAGA,UAAI,UAAU,cAAc,SAAS,GAAG;AACtC,eAAO,KAAK,+CAA+C;AAAA,UACzD,eAAe,UAAU,cAAc;AAAA,QACzC,CAAC;AAAA,MACH;AAGA,UAAI,UAAU,gBAAgB,SAAS,GAAG;AACxC,cAAM,WAAW;AAAA,UACf,iBAAiB,UAAU;AAAA,UAC3B,UAAU,KAAK,IAAI;AAAA,QACrB;AAGA,YAAI,KAAK,cAAc;AACrB,gBAAM,KAAK,aAAa;AAAA,YACtB;AAAA,YACA;AAAA,UACF;AAAA,QACF;AAEA,eAAO,KAAK,+CAA+C;AAAA,UACzD,YAAY,UAAU,gBAAgB;AAAA,QACxC,CAAC;AAAA,MACH;AAAA,IACF,SAAS,OAAgB;AACvB,aAAO,MAAM,iCAAiC,KAAc;AAAA,IAC9D;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,sBAAqC;AACzC,QAAI;AACF,UAAI,CAAC,KAAK,aAAc;AAExB,YAAM,UAAU,eAAe,kBAAkB;AACjD,UAAI,CAAC,QAAS;AAGd,YAAM,eAAe,KAAK,aACvB,mBAAmB,EACnB,OAAO,OAAO;AAGjB,YAAM,eAAe,MAAM,KAAK,aAAa,gBAAgB,GAAG;AAGhE,YAAM,YAAY,CAAC,GAAG,cAAc,GAAG,YAAY,EAAE,OAAO,OAAO;AACnE,YAAM,kBAAkB,KAAK,sBAAsB,SAAS;AAE5D,UAAI,gBAAgB,WAAW,GAAG;AAChC,eAAO,MAAM,6BAA6B;AAC1C;AAAA,MACF;AAGA,YAAM,mBAAmB,mBAAmB,iBAAiB;AAAA,QAC3D,UAAU,KAAK,QAAQ;AAAA,QACvB,MAAM,KAAK,QAAQ;AAAA,MACrB,CAAC;AAED,WAAK,eAAe,KAAK,IAAI;AAE7B,aAAO,KAAK,mCAAmC;AAAA,QAC7C,YAAY,gBAAgB;AAAA,QAC5B,WAAW,QAAQ;AAAA,MACrB,CAAC;AAAA,IACH,SAAS,OAAgB;AACvB,aAAO,MAAM,oCAAoC,KAAc;AAAA,IACjE;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,kBAAkB,OAIL;AACjB,QAAI;AACF,YAAM,UAAU,MAAM,mBAAmB,mBAAmB;AAAA,QAC1D,GAAG;AAAA,QACH,UAAU,KAAK,QAAQ;AAAA,MACzB,CAAC;AAED,aAAO,KAAK,0BAA0B;AAAA,QACpC;AAAA,QACA,aAAa,QAAQ;AAAA,MACvB,CAAC;AAED,aAAO;AAAA,IACT,SAAS,OAAgB;AACvB,aAAO,MAAM,kCAAkC,KAAc;AAC7D,aAAO,CAAC;AAAA,IACV;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,YAAY,UAAkB,WAAkC;AACpE,QAAI;AACF,YAAM,mBAAmB,YAAY;AAAA,QACnC;AAAA,QACA;AAAA,QACA,SAAS;AAAA,MACX,CAAC;AAED,aAAO,KAAK,oCAAoC,EAAE,SAAS,CAAC;AAAA,IAC9D,SAAS,OAAgB;AACvB,aAAO,MAAM,0BAA0B,KAAc;AAAA,IACvD;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKQ,gBAAsB;AAC5B,QAAI,KAAK,WAAW;AAClB,oBAAc,KAAK,SAAS;AAAA,IAC9B;AAEA,SAAK,YAAY,YAAY,MAAM;AACjC,WAAK,oBAAoB,EAAE,MAAM,CAAC,UAAU;AAC1C,eAAO,MAAM,oBAAoB,KAAc;AAAA,MACjD,CAAC;AAAA,IACH,GAAG,KAAK,QAAQ,YAAY;AAG5B,SAAK,oBAAoB;AAAA,EAC3B;AAAA;AAAA;AAAA;AAAA,EAKA,eAAqB;AACnB,QAAI,KAAK,WAAW;AAClB,oBAAc,KAAK,SAAS;AAC5B,WAAK,YAAY;AAAA,IACnB;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKQ,sBAAsB,QAA0B;AACtD,WAAO,OAAO,OAAO,CAAC,UAAU;AAE9B,YAAM,kBAAkB,KAAK,QAAQ,cAAc;AAAA,QAAK,CAAC,QACvD,MAAM,UAAU,MAAM,SAAS,GAAG;AAAA,MACpC;AAGA,YAAM,kBAAkB;AAAA,QACtB;AAAA,QACA;AAAA,QACA;AAAA,QACA;AAAA,QACA;AAAA,MACF,EAAE,SAAS,MAAM,IAAI;AAGrB,YAAM,kBAAkB,MAAM,UAAU,eAAe;AAEvD,aAAO,mBAAmB,mBAAmB;AAAA,IAC/C,CAAC;AAAA,EACH;AAAA;AAAA;AAAA;AAAA,EAKQ,sBAA4B;AAClC,QAAI,CAAC,KAAK,aAAc;AAGxB,UAAM,gBAAgB,KAAK,aAAa,WAAW,KAAK,KAAK,YAAY;AACzE,SAAK,aAAa,aAAa,OAAO,SAAiB,aAAmB;AACxE,YAAM,SAAS,MAAM,cAAc,SAAS,QAAQ;AAGpD,YAAM,QAAQ,MAAM,KAAK,aAAc,SAAS,OAAO;AACvD,UAAI,SAAS,KAAK,sBAAsB,CAAC,KAAK,CAAC,EAAE,SAAS,GAAG;AAC3D,cAAM,KAAK,oBAAoB;AAAA,MACjC;AAEA,aAAO;AAAA,IACT;AAGA,UAAM,oBAAoB,KAAK,aAAa,YAAY;AAAA,MACtD,KAAK;AAAA,IACP;AACA,SAAK,aAAa,cAAc,OAAO,WAAgB;AACrD,YAAM,SAAS,MAAM,kBAAkB,MAAM;AAE7C,UAAI,OAAO,SAAS,aAAa;AAC/B,cAAM,KAAK,oBAAoB;AAAA,MACjC;AAEA,aAAO;AAAA,IACT;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,eAIE;AACA,WAAO;AAAA,MACL,cAAc,KAAK;AAAA,MACnB,iBAAiB,KAAK,QAAQ;AAAA,MAC9B,cAAc,KAAK,QAAQ;AAAA,IAC7B;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,eAA8B;AAClC,WAAO,KAAK,sBAAsB;AAClC,UAAM,KAAK,oBAAoB;AAAA,EACjC;AACF;AAEO,MAAM,gBAAgB,cAAc,YAAY;",
6
- "names": []
7
- }
@@ -1,363 +0,0 @@
1
- #!/usr/bin/env node
2
- import { MetricsCollector } from './collect-metrics.js';
3
- import { spawn } from 'child_process';
4
- import * as fs from 'fs/promises';
5
- import * as path from 'path';
6
- export class ABTestRunner {
7
- constructor() {
8
- this.scenarios = new Map();
9
- this.runs = [];
10
- this.stackMemoryEnabled = false;
11
- this.collector = new MetricsCollector();
12
- this.loadScenarios();
13
- }
14
- loadScenarios() {
15
- // Define test scenarios
16
- const scenarios = [
17
- {
18
- id: 'multi_session_feature',
19
- name: 'E-commerce checkout flow',
20
- type: 'feature_dev',
21
- description: 'Implement a complete checkout flow with payment integration',
22
- complexity: 'high',
23
- expectedDuration: 180,
24
- steps: [
25
- { action: 'Design checkout flow architecture', requiresContext: false },
26
- { action: 'Implement cart validation', requiresContext: true },
27
- { action: 'Add payment gateway integration', requiresContext: true },
28
- { action: 'Create checkout UI components', requiresContext: true },
29
- { action: 'Add order confirmation', requiresContext: true },
30
- { action: 'Write integration tests', requiresContext: true }
31
- ],
32
- contextBreaks: [
33
- { afterStep: 2, duration: 480, type: 'session_end' }, // Overnight
34
- { afterStep: 4, duration: 60, type: 'interruption' } // Lunch break
35
- ]
36
- },
37
- {
38
- id: 'complex_debugging',
39
- name: 'Performance issue in production',
40
- type: 'complex_debug',
41
- description: 'Debug and fix a memory leak causing performance degradation',
42
- complexity: 'high',
43
- expectedDuration: 120,
44
- steps: [
45
- { action: 'Analyze performance metrics', requiresContext: false },
46
- { action: 'Profile memory usage', requiresContext: true },
47
- { action: 'Identify memory leak source', requiresContext: true },
48
- { action: 'Implement fix', requiresContext: true },
49
- { action: 'Verify fix with tests', requiresContext: true }
50
- ],
51
- contextBreaks: [
52
- { afterStep: 3, duration: 30, type: 'team_handoff' }
53
- ]
54
- },
55
- {
56
- id: 'large_refactoring',
57
- name: 'Migrate authentication system',
58
- type: 'refactor',
59
- description: 'Refactor from session-based to JWT authentication',
60
- complexity: 'very_high',
61
- expectedDuration: 360,
62
- steps: [
63
- { action: 'Analyze current auth implementation', requiresContext: false },
64
- { action: 'Design JWT architecture', requiresContext: true },
65
- { action: 'Implement JWT service', requiresContext: true },
66
- { action: 'Migrate user sessions', requiresContext: true },
67
- { action: 'Update API endpoints', requiresContext: true },
68
- { action: 'Migrate frontend auth', requiresContext: true },
69
- { action: 'Add refresh token logic', requiresContext: true },
70
- { action: 'Update tests', requiresContext: true },
71
- { action: 'Performance testing', requiresContext: true }
72
- ],
73
- contextBreaks: [
74
- { afterStep: 2, duration: 480, type: 'session_end' },
75
- { afterStep: 4, duration: 480, type: 'session_end' },
76
- { afterStep: 6, duration: 60, type: 'interruption' },
77
- { afterStep: 7, duration: 480, type: 'session_end' }
78
- ]
79
- },
80
- {
81
- id: 'rapid_bug_fixes',
82
- name: 'Fix 5 related bugs',
83
- type: 'bug_fix',
84
- description: 'Fix multiple related bugs in the user registration flow',
85
- complexity: 'medium',
86
- expectedDuration: 90,
87
- steps: [
88
- { action: 'Fix email validation bug', requiresContext: false },
89
- { action: 'Fix password strength checker', requiresContext: true },
90
- { action: 'Fix duplicate user check', requiresContext: true },
91
- { action: 'Fix confirmation email sending', requiresContext: true },
92
- { action: 'Fix redirect after registration', requiresContext: true }
93
- ],
94
- contextBreaks: [
95
- { afterStep: 1, duration: 15, type: 'interruption' },
96
- { afterStep: 2, duration: 15, type: 'interruption' },
97
- { afterStep: 3, duration: 15, type: 'interruption' },
98
- { afterStep: 4, duration: 15, type: 'interruption' }
99
- ]
100
- }
101
- ];
102
- scenarios.forEach(scenario => {
103
- this.scenarios.set(scenario.id, scenario);
104
- });
105
- }
106
- async initialize() {
107
- await this.collector.initialize();
108
- }
109
- async enableStackMemory() {
110
- console.log('Enabling StackMemory...');
111
- this.stackMemoryEnabled = true;
112
- // Start StackMemory daemon if not running
113
- try {
114
- await this.executeCommand('stackmemory-daemon status');
115
- }
116
- catch {
117
- await this.executeCommand('stackmemory-daemon start');
118
- }
119
- }
120
- async disableStackMemory() {
121
- console.log('Disabling StackMemory...');
122
- this.stackMemoryEnabled = false;
123
- // Stop StackMemory daemon
124
- try {
125
- await this.executeCommand('stackmemory-daemon stop');
126
- }
127
- catch {
128
- // Ignore if already stopped
129
- }
130
- }
131
- executeCommand(command) {
132
- return new Promise((resolve, reject) => {
133
- const child = spawn(command, { shell: true });
134
- let output = '';
135
- let error = '';
136
- child.stdout.on('data', (data) => {
137
- output += data.toString();
138
- });
139
- child.stderr.on('data', (data) => {
140
- error += data.toString();
141
- });
142
- child.on('close', (code) => {
143
- if (code === 0) {
144
- resolve(output);
145
- }
146
- else {
147
- reject(new Error(error || `Command failed with code ${code}`));
148
- }
149
- });
150
- });
151
- }
152
- async runScenario(scenarioId, variant) {
153
- const scenario = this.scenarios.get(scenarioId);
154
- if (!scenario) {
155
- throw new Error(`Scenario ${scenarioId} not found`);
156
- }
157
- console.log(`\nRunning scenario: ${scenario.name} (${variant})`);
158
- console.log(`Expected duration: ${scenario.expectedDuration} minutes`);
159
- console.log(`Complexity: ${scenario.complexity}`);
160
- console.log(`Context breaks: ${scenario.contextBreaks.length}`);
161
- // Enable/disable StackMemory based on variant
162
- if (variant === 'with_stackmemory') {
163
- await this.enableStackMemory();
164
- }
165
- else {
166
- await this.disableStackMemory();
167
- }
168
- const runId = `${scenarioId}-${variant}-${Date.now()}`;
169
- const sessionId = await this.collector.startSession(variant);
170
- const run = {
171
- id: runId,
172
- scenario,
173
- variant,
174
- startTime: new Date(),
175
- metrics: {},
176
- recordings: [],
177
- success: false,
178
- errors: []
179
- };
180
- try {
181
- // Execute scenario steps
182
- for (let i = 0; i < scenario.steps.length; i++) {
183
- const step = scenario.steps[i];
184
- console.log(`\nStep ${i + 1}/${scenario.steps.length}: ${step.action}`);
185
- // Simulate step execution
186
- await this.executeStep(step, sessionId, run);
187
- // Check for context break
188
- const contextBreak = scenario.contextBreaks.find(cb => cb.afterStep === i + 1);
189
- if (contextBreak) {
190
- console.log(`\nContext break: ${contextBreak.type} for ${contextBreak.duration} minutes`);
191
- await this.simulateContextBreak(contextBreak, sessionId);
192
- }
193
- }
194
- run.success = true;
195
- }
196
- catch (error) {
197
- console.error(`Scenario failed: ${error.message}`);
198
- run.errors.push(error.message);
199
- this.collector.trackError(sessionId, error);
200
- }
201
- // Collect final metrics
202
- run.endTime = new Date();
203
- run.metrics = await this.collector.endSession(sessionId);
204
- // Save run results
205
- this.runs.push(run);
206
- await this.saveRun(run);
207
- return run;
208
- }
209
- async executeStep(step, sessionId, run) {
210
- const startTime = Date.now();
211
- // Track tool call
212
- this.collector.trackToolCall(sessionId, 'execute_step');
213
- // If step requires context and we're testing with StackMemory
214
- if (step.requiresContext && this.stackMemoryEnabled) {
215
- const contextTime = await this.collector.measureContextReestablishment(sessionId);
216
- console.log(` Context retrieved in ${(contextTime / 1000).toFixed(2)}s`);
217
- }
218
- // Simulate step execution with command if provided
219
- if (step.command) {
220
- try {
221
- const output = await this.executeCommand(step.command);
222
- // Record tool call
223
- run.recordings.push({
224
- timestamp: new Date(),
225
- tool: 'command',
226
- parameters: { command: step.command },
227
- result: output,
228
- duration: Date.now() - startTime
229
- });
230
- }
231
- catch (error) {
232
- this.collector.trackError(sessionId, error);
233
- throw error;
234
- }
235
- }
236
- else {
237
- // Simulate work being done
238
- await this.simulateWork(2000 + Math.random() * 3000);
239
- }
240
- // Randomly simulate decisions and frame creation
241
- if (Math.random() > 0.5) {
242
- this.collector.trackFrameCreation(sessionId, `frame-${Date.now()}`);
243
- }
244
- if (Math.random() > 0.7) {
245
- this.collector.trackDecision(sessionId, `Decision for ${step.action}`);
246
- }
247
- console.log(` Step completed in ${((Date.now() - startTime) / 1000).toFixed(2)}s`);
248
- }
249
- async simulateContextBreak(contextBreak, sessionId) {
250
- // Simulate time passing
251
- console.log(` Simulating ${contextBreak.duration} minute break...`);
252
- if (contextBreak.type === 'session_end' && this.stackMemoryEnabled) {
253
- // Simulate session end with StackMemory
254
- this.collector.trackFrameClosure(sessionId, 'session-frame', true);
255
- }
256
- // In real testing, we would actually wait or simulate the time passing
257
- await this.simulateWork(1000);
258
- // After break, measure context reestablishment
259
- if (this.stackMemoryEnabled) {
260
- const reestablishTime = await this.collector.measureContextReestablishment(sessionId);
261
- console.log(` Context reestablished in ${(reestablishTime / 1000).toFixed(2)}s`);
262
- }
263
- else {
264
- // Without StackMemory, simulate manual context reestablishment
265
- console.log(` Manual context reestablishment required (est. 5 minutes)`);
266
- this.collector.trackRework(sessionId);
267
- }
268
- }
269
- simulateWork(ms) {
270
- return new Promise(resolve => setTimeout(resolve, ms));
271
- }
272
- async runAllScenarios() {
273
- console.log('='.repeat(60));
274
- console.log('Starting A/B Test Suite');
275
- console.log('='.repeat(60));
276
- for (const scenario of this.scenarios.values()) {
277
- // Run without StackMemory
278
- await this.runScenario(scenario.id, 'without_stackmemory');
279
- // Run with StackMemory
280
- await this.runScenario(scenario.id, 'with_stackmemory');
281
- }
282
- await this.generateComparison();
283
- }
284
- async generateComparison() {
285
- const withStackMemory = this.runs.filter(r => r.variant === 'with_stackmemory');
286
- const withoutStackMemory = this.runs.filter(r => r.variant === 'without_stackmemory');
287
- console.log('\n' + '='.repeat(60));
288
- console.log('A/B Test Results Summary');
289
- console.log('='.repeat(60));
290
- for (const scenario of this.scenarios.values()) {
291
- const withRun = withStackMemory.find(r => r.scenario.id === scenario.id);
292
- const withoutRun = withoutStackMemory.find(r => r.scenario.id === scenario.id);
293
- if (withRun && withoutRun) {
294
- console.log(`\n${scenario.name}:`);
295
- console.log(` Without StackMemory: ${((withoutRun.metrics.completionTime || 0) / 1000 / 60).toFixed(2)} min`);
296
- console.log(` With StackMemory: ${((withRun.metrics.completionTime || 0) / 1000 / 60).toFixed(2)} min`);
297
- const improvement = ((withoutRun.metrics.completionTime - withRun.metrics.completionTime) /
298
- withoutRun.metrics.completionTime) * 100;
299
- console.log(` Improvement: ${improvement.toFixed(1)}%`);
300
- }
301
- }
302
- // Generate detailed report
303
- await this.collector.generateReport('./test-results/ab-test-report.md');
304
- }
305
- async saveRun(run) {
306
- const outputDir = './test-results/runs';
307
- await fs.mkdir(outputDir, { recursive: true });
308
- const filename = path.join(outputDir, `${run.id}.json`);
309
- await fs.writeFile(filename, JSON.stringify(run, null, 2));
310
- console.log(`Run saved to: ${filename}`);
311
- }
312
- async runSpecificScenario(scenarioId) {
313
- if (!this.scenarios.has(scenarioId)) {
314
- console.error(`Scenario '${scenarioId}' not found`);
315
- console.log('Available scenarios:');
316
- for (const [id, scenario] of this.scenarios) {
317
- console.log(` - ${id}: ${scenario.name}`);
318
- }
319
- return;
320
- }
321
- // Run both variants
322
- await this.runScenario(scenarioId, 'without_stackmemory');
323
- await this.runScenario(scenarioId, 'with_stackmemory');
324
- await this.generateComparison();
325
- }
326
- }
327
- // CLI interface
328
- if (import.meta.url === `file://${process.argv[1]}`) {
329
- const runner = new ABTestRunner();
330
- async function main() {
331
- await runner.initialize();
332
- const command = process.argv[2];
333
- const scenarioId = process.argv[3];
334
- switch (command) {
335
- case 'all':
336
- await runner.runAllScenarios();
337
- break;
338
- case 'scenario':
339
- if (!scenarioId) {
340
- console.error('Please specify a scenario ID');
341
- process.exit(1);
342
- }
343
- await runner.runSpecificScenario(scenarioId);
344
- break;
345
- case 'list':
346
- console.log('Available scenarios:');
347
- console.log(' - multi_session_feature: E-commerce checkout flow');
348
- console.log(' - complex_debugging: Performance issue in production');
349
- console.log(' - large_refactoring: Migrate authentication system');
350
- console.log(' - rapid_bug_fixes: Fix 5 related bugs');
351
- break;
352
- default:
353
- console.log('Usage: ab-test-runner.ts [all|scenario|list] [scenario-id]');
354
- console.log('');
355
- console.log('Commands:');
356
- console.log(' all - Run all test scenarios');
357
- console.log(' scenario - Run a specific scenario');
358
- console.log(' list - List available scenarios');
359
- }
360
- process.exit(0);
361
- }
362
- main().catch(console.error);
363
- }