agentic-sdlc 1.6.0 → 1.8.1

package/CHANGELOG.md

@@ -4,6 +4,77 @@ All notable changes to this project will be documented in this file.
 
 ## [Unreleased]
 
+---
+
+## [1.8.1] - 2026-01-10 (Sprint 6)
+
+### Documentation
+- [Workflows] add npm publish step to release workflow
+
+### Maintenance
+- [Tools] fix import paths and update package.json for new structure
+
+
+---
+
+## [1.8.0] - 2026-01-10 (Sprint 6)
+
+### Added
+- [Telegram] implement custom login, file previews, and os polyfill fixes
+- [Telegram] implement user-based MTProto authentication with GramJS, dual login UI, and demo file previews
+- [Workflows] add missing intelligence workflows (observe, ab, score, monitor, planning)
+- [Workflows] reach 100 health score
+- [Workflows] restore metrics dashboard functionality and reach 100 health score
+- [Core] complete project restructure, fix import errors and update documentation
+- Initialize the FFmpeg editor project with Tauri, React, and core UI components.
+- [Autogen] integrate Microsoft AutoGen for multi-agent task execution
+- [Landing Page] add /worktree workflow to landing page
+- [Worktree] add Worktrunk CLI integration for parallel AI agent workflows
+- Replace `kb` scripts with new `brain` and Neo4j-related commands.
+- introduce Layer 2 Intelligence with core agentic capabilities and initial Multi-Agent Control Plane.
+
+### Fixed
+- [Workflows] resolve sys.path and import errors in all workflow scripts
+- [Workflows] repair housekeeping workflow and crash issues - fix: update housekeeping.py to use knowledge_graph instead of legacy modules - fix: patch brain_parallel.py with explicit utf-8 encoding for windows compatibility - fix: add missing --kb-path argument to sync_skills_to_neo4j.py - feat: enhance housekeeping cleanup to remove *_output.txt and debug_*.txt - fix: prevent self_improver from flagging __pycache__ as errors
+
+### Documentation
+- update workflow count to 23 and add /planning to workflow list
+- [Report] update validation report timestamp and health score confirmation
+- update workflow count to 18 and add AutoGen feature
+- add release walkthrough
+
+### Maintenance
+- [Workflows] enforce specification workflow in rules and docs
+- finalize project restructure and reach 100 health score
+- [Workflows] fix broken tool paths after restructure
+- [Scripts] add landing-page project scripts to root package.json
+- [Landing-Page] update obsolete KB references to neo4j brain
+- [Arch] remediate architecture audit findings
+- [Knowledge Base] remove file-based knowledge base and associated tools
+
+
+---
+
+## [1.7.0] - 2026-01-05
+
+### Added
+- add push capability to /commit workflow
+- implement /commit workflow and helper tool
+- remove interactive prompts and add non-interactive modes for automation
+- Implement agent brain protocol and enforcement gates with a new judge tool.
+- introduce agentic SDLC CLI, implement various agent workflows, and establish a comprehensive documentation structure.
+- introduce agentic SDLC workflow definitions for various operational tasks.
+
+### Fixed
+- mermaid syntax error in system-flow diagram
+
+### Documentation
+- update documentation and landing page with /commit workflow and agent autonomy features
+- update knowledge base index
+- add audit walkthrough and validation reports
+- add Next Steps section to all workflows and skills
+
+
 ---
 
 ## [1.6.0] - 2026-01-04 (Sprint 6)

package/README.md

@@ -7,8 +7,9 @@
 **Agentic SDLC** is an AI-powered development framework that simulates a complete software development team within your IDE. It provides:
 
 - **14 Specialized AI Roles** - PM, BA, SA, UI/UX, QA, Security, Dev, DevOps, Tester, Reporter, and more
-- **12 Automated Workflows** - From planning to deployment with `/slash` commands
+- **18 Automated Workflows** - From planning to deployment with `/slash` commands
 - **Intelligent Brain System** - 3-Layer architecture with state management and self-learning
+- **Multi-Agent Teams** - AutoGen-powered autonomous agent collaboration
 - **Cross-IDE Compatibility** - Works with Cursor, Windsurf, Cline, Aider, Gemini, and any AI-powered IDE
 - **Monorepo Architecture** - Shared brain system across multiple projects
 
@@ -78,7 +79,7 @@ Delivery    → @REPORTER, @STAKEHOLDER
 Meta        → @BRAIN, @ORCHESTRATOR
 ```
 
-### 2. Slash Commands (12 Workflows)
+### 2. Slash Commands (18 Workflows)
 
 Execute complete workflows with simple commands:
 
@@ -92,9 +93,15 @@ Execute complete workflows with simple commands:
 /metrics         # View metrics dashboard
 /release         # Release management
 /emergency       # Critical incident response
-/route           # Intelligent workflow routing
-/compound        # Knowledge capture
 /housekeeping    # Cleanup & maintenance
+/review          # Code review workflow (NEW)
+/debug           # Systematic debugging (NEW)
+/refactor        # Safe refactoring (NEW)
+/onboarding      # Agent ramp-up (NEW)
+/docs            # Documentation creation (NEW)
+/commit          # Smart git commit (NEW)
+/worktree        # Parallel AI agent workflows (NEW)
+/autogen         # Multi-agent task execution (NEW)
 ```
 
 ### 3. Monorepo Architecture
@@ -203,6 +210,7 @@ python tools/neo4j/brain_parallel.py --sync      # Sync brain
 | Inconsistent code quality | Enforced by @QA, @SECA |
 | Lost knowledge | Compound learning brain |
 | Repetitive tasks | Automated with @AUTO |
+| Single-agent limits | Multi-agent teams with AutoGen |
 | Solo problem-solving | 13+ AI experts available |
 
 ## 🔗 Links

package/bin/cli.js

@@ -7,32 +7,121 @@ import fs from 'fs';
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const rootDir = resolve(__dirname, '..');
 
+// Command mappings: command -> python script path
 const commands = {
+    // Brain & Core
+    'brain': 'tools/brain/brain_cli.py',
+    'learn': 'tools/neo4j/learning_engine.py',
+    'research': 'tools/research/research_agent.py',
+
+    // Layer 2: Intelligence
+    'score': 'tools/layer2/scorer/input_scorer.py',
+    'score-input': 'tools/layer2/scorer/input_scorer.py',
+    'score-output': 'tools/layer2/scorer/output_scorer.py',
+    'route': 'tools/layer2/router/workflow_router.py',
+    'route-workflow': 'tools/layer2/router/workflow_router.py',
+    'route-agent': 'tools/layer2/router/agent_router.py',
+    'rules': 'tools/layer2/router/rules_engine.py',
+    'monitor': 'tools/layer2/monitor/observer.py',
+    'observe': 'tools/layer2/monitor/observer.py',
+    'check-rules': 'tools/layer2/monitor/rule_checker.py',
+    'audit': 'tools/layer2/monitor/audit_logger.py',
+
+    // Layer 3: Infrastructure
     'release': 'tools/release/release.py',
-    'kb': 'bin/kb_cli.py',
+
     'agent': 'tools/run.py',
     'validate': 'tools/validation/validate.py',
     'health': 'tools/validation/health-check.py',
     'setup': 'tools/setup/init.py',
-    'brain': 'tools/brain/brain_cli.py',
-    'research': 'tools/research/research_agent.py'
+
+
+    // MCP
+    'mcp': 'mcp/protocol.py',
+
+    // AutoGen Multi-Agent
+    'autogen': 'tools/autogen/runner.py',
+
+    // Run arbitrary scripts
+    'run': null // Special: run <path>
+};
+
+// Command aliases
+const aliases = {
+    'l2': 'layer2',
+    'wf': 'workflow',
+    's': 'score',
+    'r': 'route',
+    'm': 'monitor',
+    'b': 'brain'
 };
 
 const args = process.argv.slice(2);
-const command = args[0];
+let command = args[0];
+
+// Resolve alias
+if (aliases[command]) {
+    command = aliases[command];
+}
 
 function printUsage() {
-    console.log("Usage: agentic-sdlc <command> [args]");
-    console.log("Commands:");
-    console.log("  release   Manage releases (args: release, preview, changelog, version)");
-    console.log("  workflow  Run workflows (args: cycle, housekeeping, etc.)");
-    console.log("  kb        Knowledge Base tools");
-    console.log("  agent     Run default agent");
-    console.log("  validate  Validate system");
-    console.log("  health    Check health");
-    console.log("  setup     Initialize project");
-    console.log("  brain     Brain system management");
-    console.log("  research  Research agent");
+    console.log(`
+╔═══════════════════════════════════════════════════════════════╗
+║                    AGENTIC SDLC CLI                           ║
+║            3-Layer Brain Architecture Control                 ║
+╚═══════════════════════════════════════════════════════════════╝
+
+Usage: agentic-sdlc <command> [args]
+
+╭─────────────────────────────────────────────────────────────────╮
+│ LAYER 1: CORE                                                   │
+├─────────────────────────────────────────────────────────────────┤
+│  brain       Brain system management & state control            │
+│  learn       Self-learning engine (Neo4j integration)           │
+│  research    Research agent for deep investigation              │
+╰─────────────────────────────────────────────────────────────────╯
+
+╭─────────────────────────────────────────────────────────────────╮
+│ LAYER 2: INTELLIGENCE                                           │
+├─────────────────────────────────────────────────────────────────┤
+│  score         Score input/output quality                       │
+│  score-input   Score input request quality                      │
+│  score-output  Score output/response quality                    │
+│  route         Route to appropriate workflow                    │
+│  route-agent   Route to appropriate AI agent/role               │
+│  rules         Evaluate routing rules                           │
+│  monitor       Monitor system & detect violations               │
+│  observe       Alias for monitor                                │
+│  check-rules   Validate rule compliance                         │
+│  audit         View audit logs                                  │
+╰─────────────────────────────────────────────────────────────────╯
+
+╭─────────────────────────────────────────────────────────────────╮
+│ LAYER 3: INFRASTRUCTURE                                         │
+├─────────────────────────────────────────────────────────────────┤
+│  release     Manage releases & version bumping                  │
+│  workflow    Run workflows (cycle, orchestrator, debug, etc.)   │
+
+│  validate    Validate system configuration                      │
+│  health      Check system health                                │
+│  setup       Initialize project                                 │
+
+│  mcp         MCP (Model Context Protocol) management            │
+│  autogen     Multi-agent task execution (AutoGen)               │
+│  run         Run arbitrary Python script                        │
+╰─────────────────────────────────────────────────────────────────╯
+
+Examples:
+  agentic-sdlc brain status              # Check brain status
+  agentic-sdlc score --score "Add login" # Score input quality
+  agentic-sdlc route --route "fix bug"   # Get workflow recommendation
+  agentic-sdlc monitor --status          # Check monitor status
+  agentic-sdlc release --preview         # Preview release changes
+  agentic-sdlc workflow cycle            # Run cycle workflow
+  agentic-sdlc run tools/brain/judge.py  # Run any Python script
+
+Aliases: l2=layer2, wf=workflow, s=score, r=route, m=monitor, b=brain
+`);
 }
 
 if (!command || command === '--help' || command === '-h') {
@@ -43,6 +132,31 @@ if (!command || command === '--help' || command === '-h') {
 let scriptPath = commands[command];
 let scriptArgs = args.slice(1);
 
+// Special handling for layer2 namespace
+if (command === 'layer2') {
+    const sub = args[1];
+    if (!sub) {
+        console.log(`
+Layer 2 (Intelligence) Commands:
+  scorer         Input/output quality scoring
+  ab_test        A/B testing engine
+  self_learning  Pattern recognition & improvement
+  artifact_gen   Artifact generation
+  router         Workflow & agent routing
+  proxy          Model cost optimization
+  task_manager   Kanban-style task management
+  monitor        Compliance monitoring
+  performance    Flow optimization
+
+Usage: agentic-sdlc layer2 <component> [args]
+Example: agentic-sdlc layer2 scorer --score "your text"
+`);
+        process.exit(0);
+    }
+    scriptPath = `tools/layer2/${sub}/__init__.py`;
+    scriptArgs = args.slice(2);
+}
+
 // Special handling for workflows
 if (command === 'workflow') {
     const sub = args[1];
@@ -51,13 +165,24 @@ if (command === 'workflow') {
         scriptArgs = args.slice(2);
     } else {
         console.error("Please specify a workflow (e.g., cycle, housekeeping)");
+        console.log("Available: cycle, orchestrator, debug, refactor, review, release, emergency, housekeeping");
         process.exit(1);
     }
 }
 
+// Special handling for 'run' command
+if (command === 'run') {
+    if (args.length < 2) {
+        console.error("Usage: agentic-sdlc run <script_path> [args]");
+        process.exit(1);
+    }
+    scriptPath = args[1];
+    scriptArgs = args.slice(2);
+}
+
 if (!scriptPath) {
     console.error(`Unknown command: ${command}`);
-    printUsage();
+    console.log("Run 'agentic-sdlc --help' for usage information.");
     process.exit(1);
 }
 
@@ -65,6 +190,7 @@ const fullPath = join(rootDir, scriptPath);
 
 if (!fs.existsSync(fullPath)) {
     console.error(`Script not found: ${scriptPath}`);
+    console.log(`Full path: ${fullPath}`);
     process.exit(1);
 }
 

package/docs/.brain-health-history.json

@@ -0,0 +1,42 @@
+[
+  {
+    "status": "healthy",
+    "score": 100.0,
+    "issues": [],
+    "metrics": {
+      "walkthrough_count": 10,
+      "plan_count": 7
+    },
+    "timestamp": "2026-01-08T06:55:27.350396"
+  },
+  {
+    "status": "healthy",
+    "score": 100.0,
+    "issues": [],
+    "metrics": {
+      "walkthrough_count": 10,
+      "plan_count": 7
+    },
+    "timestamp": "2026-01-08T07:15:47.509650"
+  },
+  {
+    "status": "healthy",
+    "score": 100.0,
+    "issues": [],
+    "metrics": {
+      "walkthrough_count": 10,
+      "plan_count": 7
+    },
+    "timestamp": "2026-01-08T20:35:08.123731"
+  },
+  {
+    "status": "healthy",
+    "score": 100.0,
+    "issues": [],
+    "metrics": {
+      "walkthrough_count": 10,
+      "plan_count": 7
+    },
+    "timestamp": "2026-01-08T20:58:54.707900"
+  }
+]

package/docs/.brain-improvements.json

@@ -0,0 +1,53 @@
+{
+  "plans": [
+    {
+      "id": "PLAN-20260105-0931",
+      "createdAt": "2026-01-05T09:31:37.457263",
+      "status": "CREATED",
+      "insights": [
+        {
+          "source": "Judge",
+          "finding": "Average score is low (3.4/10)",
+          "suggestion": "Improve report quality - add more detail, follow templates"
+        },
+        {
+          "source": "Judge",
+          "finding": "Reports consistently fail in 'completeness'",
+          "suggestion": "Focus on improving completeness in reports"
+        }
+      ],
+      "actions": [
+        {
+          "id": "ACTION-1",
+          "source": "Judge",
+          "action": "Improve report quality - add more detail, follow templates",
+          "priority": "medium",
+          "status": "PENDING"
+        },
+        {
+          "id": "ACTION-2",
+          "source": "Judge",
+          "action": "Focus on improving completeness in reports",
+          "priority": "high",
+          "status": "PENDING"
+        }
+      ],
+      "summary": "2 improvement actions identified"
+    }
+  ],
+  "insights": [
+    {
+      "source": "Judge",
+      "finding": "Average score is low (3.4/10)",
+      "suggestion": "Improve report quality - add more detail, follow templates"
+    },
+    {
+      "source": "Judge",
+      "finding": "Reports consistently fail in 'completeness'",
+      "suggestion": "Focus on improving completeness in reports"
+    }
+  ],
+  "appliedImprovements": 0,
+  "createdAt": "2026-01-05T09:31:37.457374",
+  "lastUpdated": "2026-01-05T09:31:37.457582"
+}

package/docs/.brain-learner-log.json

@@ -0,0 +1,27 @@
+{
+  "learnings": [
+    {
+      "description": "Updated landing page with 15 workflows, brain protocol, solutions feature",
+      "timestamp": "2026-01-05T09:01:02.577360",
+      "success": true,
+      "steps": [
+        {
+          "step": "KB Index Update",
+          "status": "success"
+        },
+        {
+          "step": "Neo4j Sync",
+          "status": "success"
+        },
+        {
+          "step": "Learning Engine",
+          "status": "success"
+        }
+      ]
+    }
+  ],
+  "totalLearnings": 1,
+  "autoLearnEnabled": true,
+  "createdAt": "2026-01-05T09:00:11.930196",
+  "lastUpdated": "2026-01-05T09:01:02.581164"
+}