@defai.digital/automatosx 5.6.21 → 5.6.23

package/README.md

@@ -13,7 +13,9 @@ AutomatosX is a CLI-first orchestration tool that transforms stateless AI assist
 [![Windows](https://img.shields.io/badge/Windows-10+-blue.svg)](https://www.microsoft.com/windows)
 [![Ubuntu](https://img.shields.io/badge/Ubuntu-24.04-orange.svg)](https://ubuntu.com)
 
-**Status**: ✅ Production Ready · **v5.6.21** · October 2025 · 24 Specialized Agents · 100% Resource Leak Free · Production Stability
+**Status**: ✅ Production Ready · **v5.6.23** · October 2025 · 19 Specialized Agents · 100% Resource Leak Free · Production Stability
+
+**Latest (v5.6.23)**: Code quality tooling - Added ESLint configuration for automated async/promise pattern detection and timer cleanup verification script. [See full changelog →](CHANGELOG.md)
 
 ---
 
@@ -125,33 +127,29 @@ ax run product "Build a complete user authentication feature"
 
 ---
 
-## 🎭 24 Specialized Agents
-
-AutomatosX comes with a pre-built team of 24 agents, each with a specific role and expertise. This ensures the right specialist is always available for the task at hand.
-
--   **Backend** (API design, databases, Go/Rust systems)
--   **Frontend** (React/Next.js/Swift UI)
--   **Fullstack** (Node.js/TypeScript + Python)
--   **Mobile** (iOS/Android, Swift/Kotlin/Flutter)
--   **DevOps** (CI/CD, infrastructure)
--   **Security** (Audits, threat modeling)
--   **Data Science** (ML strategy, statistical analysis)
--   **ML Engineer** (PyTorch/TensorFlow, CNN/Transformer, LLM fine-tuning)
--   **Best Practices - Stan** (SOLID, design patterns, clean code, refactoring, architecture) ✨ NEW in v5.6.21
--   **ERP Integration** (SAP, Oracle, Dynamics 365, enterprise integration patterns)
--   **Figma Expert** (Figma API, design tokens, design-to-code, MCP integration) ✨ NEW in v5.6.10
--   **IoT/Embedded Engineer** (MQTT, ROS2, FreeRTOS, edge computing, robotics) ✨ NEW in v5.6.10
--   **Data** (ETL, SQL, modeling)
--   **Quality** (Testing, code reviews)
--   **Design** (UX research, wireframes)
--   **Writer** (Documentation, reports)
--   **Creative Marketer** (Content strategy)
--   **Product** (Roadmaps, strategy)
--   **CTO** (Technical strategy)
--   **CEO** (Business leadership)
--   **Researcher** (Feasibility studies)
--   **Quantum Engineer** (Quantum algorithms, Qiskit/Cirq, error correction)
--   **Aerospace Scientist** (Orbital mechanics, mission analysis, telemetry)
+## 🎭 19 Specialized Agents
+
+AutomatosX comes with a pre-built team of 19 agents, each with a specific role and expertise. This ensures the right specialist is always available for the task at hand.
+
+-   **Astrid** - Aerospace Scientist (Orbital mechanics, mission analysis, telemetry)
+-   **Bob** - Backend Engineer (API design, databases, Go/Rust systems)
+-   **Candy** - Creative Marketer (Content strategy)
+-   **Daisy** - Data Engineer (ETL, SQL, modeling)
+-   **Dana** - Data Scientist (ML strategy, statistical analysis)
+-   **Debbee** - UX Designer (UX research, wireframes)
+-   **Eric** - CEO (Business leadership)
+-   **Felix** - Fullstack Engineer (Node.js/TypeScript + Python)
+-   **Frank** - Frontend Engineer (React/Next.js/Swift UI)
+-   **Maya** - Mobile Engineer (iOS/Android, Swift/Kotlin/Flutter)
+-   **Oliver** - DevOps Engineer (CI/CD, infrastructure)
+-   **Paris** - Product Manager (Roadmaps, strategy)
+-   **Peter** - Best Practices Expert (SOLID, design patterns, clean code, refactoring, architecture) ✨ NEW in v5.6.21
+-   **Queenie** - Quality Specialist (Testing, code reviews)
+-   **Quinn** - Quantum Engineer (Quantum algorithms, Qiskit/Cirq, error correction)
+-   **Rodman** - Researcher (Feasibility studies)
+-   **Steve** - Security Engineer (Audits, threat modeling)
+-   **Tony** - CTO (Technical strategy)
+-   **Wendy** - Technical Writer (Documentation, reports)
 
 **Governance**: Agents have clear roles, permissions, and delegation limits (`maxDelegationDepth`) to ensure efficient and safe collaboration while preventing infinite loops.
 

package/dist/index.js

@@ -13501,6 +13501,8 @@ function createMemoryClearHandler(deps) {
 
 // src/mcp/server.ts
 var McpServer = class {
+  // Use 'any' for heterogeneous tool handlers to avoid unsafe type casts
+  // Runtime validation via validateToolInput provides type safety
   tools = /* @__PURE__ */ new Map();
   toolSchemas = [];
   initialized = false;
@@ -13607,6 +13609,22 @@ var McpServer = class {
     });
     logger.info("[MCP Server] Services initialized successfully");
   }
+  /**
+   * Cleanup resources before shutdown
+   */
+  async cleanup() {
+    logger.info("[MCP Server] Performing cleanup...");
+    try {
+      if (this.memoryManager) {
+        await this.memoryManager.close();
+      }
+      logger.info("[MCP Server] Cleanup completed");
+    } catch (error) {
+      logger.error("[MCP Server] Cleanup failed", {
+        error: error instanceof Error ? error.message : String(error)
+      });
+    }
+  }
   /**
    * Register Phase 1 tools
    */
@@ -14259,16 +14277,19 @@ ${json}`;
         }
       }
     });
-    process.stdin.on("end", () => {
+    process.stdin.on("end", async () => {
       logger.info("[MCP Server] Server stopped (stdin closed)");
+      await this.cleanup();
       process.exit(0);
     });
-    process.on("SIGINT", () => {
+    process.on("SIGINT", async () => {
       logger.info("[MCP Server] Received SIGINT, shutting down...");
+      await this.cleanup();
       process.exit(0);
     });
-    process.on("SIGTERM", () => {
+    process.on("SIGTERM", async () => {
       logger.info("[MCP Server] Received SIGTERM, shutting down...");
+      await this.cleanup();
       process.exit(0);
     });
     logger.info("[MCP Server] Server started successfully (Content-Length framing)");

package/examples/AGENTS_INFO.md

@@ -1,11 +1,11 @@
 # AutomatosX Agent Directory
 
-**v5.6.21 Update - Stan Agent Implementation**:
-- ✨ **New Best Practices Agent**: Stan (Software Engineering Standards Expert) - SOLID, design patterns, clean code, refactoring, software architecture
+**v5.6.21 Update - Peter Agent Implementation**:
+- ✨ **New Best Practices Agent**: Peter (Software Engineering Peterdards Expert) - SOLID, design patterns, clean code, refactoring, software architecture
 - 📚 **5 New Best Practices Abilities**: solid-principles, design-patterns, clean-code, refactoring, software-architecture (~8,200 lines)
-- 🔧 **Enhanced Queenie**: Added base-level best-practices ability with delegation pattern to Stan
-- 🤝 **Collaboration Model**: Queenie (quality/bugs/tests) ↔ Stan (standards/patterns/architecture)
-- 🤖 **24 Total Agents**: Stan fills critical ownership gap for SOLID principles and architecture standards
+- 🔧 **Enhanced Queenie**: Added base-level best-practices ability with delegation pattern to Peter
+- 🤝 **Collaboration Model**: Queenie (quality/bugs/tests) ↔ Peter (standards/patterns/architecture)
+- 🤖 **24 Total Agents**: Peter fills critical ownership gap for SOLID principles and architecture standards
 
 **v5.6.10 Update - Four New Specialist Agents (Completed in One Release)**:
 - ✨ **New ERP Integration Agent**: Emma (ERP Integration Specialist) - SAP, Oracle, Dynamics 365, enterprise integration patterns
@@ -14,7 +14,7 @@
 - ✨ **New ML Engineer Agent**: Mira (Deep Learning Specialist) - PyTorch/TensorFlow implementation expert (from earlier in v5.6.10)
 - 🧠 **Enhanced Dana**: Strategic DL guidance (architecture selection, framework choice, evaluation metrics)
 - 📚 **17 New Abilities**: 5 best practices + 4 ERP + 4 Figma + 4 IoT + 4 deep learning (~11,269 lines, 283+ keywords)
-- 🤖 **24 Total Agents** (was 19): Stan, Emma, Fiona, Ivy, Mira added in v5.6.10
+- 🤖 **24 Total Agents** (was 19): Peter, Emma, Fiona, Ivy, Mira added in v5.6.10
 
 **v5.6.9 Update - Agent Team Optimization**:
 - ✨ **2 New Specialist Agents**: Quinn (Quantum Systems Engineer) & Astrid (Aerospace Mission Scientist)
@@ -50,7 +50,7 @@ AutomatosX uses **team-based provider configuration** with intelligent fallback
 | Team | Primary Provider | Fallback Chain | Best For |
 |------|------------------|----------------|----------|
 | **Engineering** | 🟢 Codex | Codex → Gemini → Claude | Code implementation, testing, DevOps |
-| **Core/Quality** | 🟣 Claude | Claude → Gemini → Codex | Code review, QA, security audits |
+| **Core/Quality** | 🟢 Codex | Codex → Gemini → Claude | Code review, QA, security audits |
 | **Business** | 🟣 Claude | Claude → Codex → Gemini | Strategy, planning, decision-making |
 | **Design** | 🔵 Gemini | Gemini → Claude → Codex | UX/UI design, technical writing |
 | **Research** | 🟠 OpenAI | OpenAI → Gemini-CLI → Claude | Research, analysis, feasibility studies |
@@ -196,7 +196,7 @@ Bob (Backend): "Optimize database queries"
 | Team | Depth 3 | Depth 2 | Depth 1 | Depth 0 |
 |------|---------|---------|---------|---------|
 | **Engineering** | Oliver, Dana | - | Felix, Maya, **Bob**, **Frank**, **Quinn**, **Astrid**, **Mira**, **Ivy** ✨ | Steve |
-| **Core/Quality** | - | **Queenie** | **Stan** ✨ | - |
+| **Core/Quality** | - | **Queenie** | **Peter** ✨ | - |
 | **Business** | Tony | - | Paris, Eric | - |
 | **Design/Content** | - | - | **Fiona** ✨ | Debbee, Wendy |
 | **Data** | Dana | - | - | Daisy |
@@ -207,7 +207,7 @@ Bob (Backend): "Optimize database queries"
 
 - **3 Strategic Coordinators** (Depth 3): Tony, Oliver, Dana
 - **6 Tactical Coordinators** (Depth 1-2): Queenie (2), Paris, Felix, Maya, Eric, Cynthia
-- **9 Tactical Implementers** (Depth 1): Bob, Frank, Quinn (v5.6.9), Astrid (v5.6.9), Mira (v5.6.10), **Stan** ✨ (v5.6.21), Emma (v5.6.10), Fiona (v5.6.11), Ivy (v5.6.11)
+- **9 Tactical Implementers** (Depth 1): Bob, Frank, Quinn (v5.6.9), Astrid (v5.6.9), Mira (v5.6.10), **Peter** ✨ (v5.6.21), Emma (v5.6.10), Fiona (v5.6.11), Ivy (v5.6.11)
 - **6 Pure Implementers** (Depth 0): Steve, Daisy, Debbee, Wendy, Rodman
 
 ---
@@ -414,15 +414,15 @@ Bob (Backend): "Optimize database queries"
 ### 🎯 Core/Quality Team
 
 **Provider Configuration**:
-- **Primary**: 🟣 Claude
-- **Fallback Chain**: Claude → Gemini → Codex
+- **Primary**: 🟢 Codex (OpenAI)
+- **Fallback Chain**: Codex → Gemini → Claude
 - **Why**: Optimized for code review, quality assurance, and detailed analysis
 
 #### Tactical Coordinator (Depth 2) ⭐ NEW in v5.3.5
 
 | Name | Agent | Expertise | Best For | Delegation Capability |
 |------|-------|-----------|----------|-----------------------|
-| **Queenie** | quality | **SHARED code-review** with Stan & **SOLE OWNER** of debugging/testing | Multi-layer QA workflows, test coordination | 2 layers (QA → Implementation → Specialist) |
+| **Queenie** | quality | **SHARED code-review** with Peter & **SOLE OWNER** of debugging/testing | Multi-layer QA workflows, test coordination | 2 layers (QA → Implementation → Specialist) |
 
 **Why Depth 2?**: Quality assurance requires coordinating complex workflows where implementers need to delegate to specialists (e.g., Backend implements tests → Security audits security aspects).
 
@@ -430,9 +430,9 @@ Bob (Backend): "Optimize database queries"
 
 | Name | Agent | Expertise | Best For | Delegation Capability |
 |------|-------|-----------|----------|-----------------------|
-| **Stan** | best-practices | **Software engineering standards** - SOLID principles, design patterns (Gang of Four), clean code, refactoring techniques, software architecture (Layered, Microservices, Hexagonal, Event-Driven) ⭐ v5.6.21 | Code reviews, architecture validation, refactoring guidance, pattern recommendations | 1 layer (can consult implementers for code validation) |
+| **Peter** | best-practices | **Software engineering standards** - SOLID principles, design patterns (Gang of Four), clean code, refactoring techniques, software architecture (Layered, Microservices, Hexagonal, Event-Driven) ⭐ v5.6.21 | Code reviews, architecture validation, refactoring guidance, pattern recommendations | 1 layer (can consult implementers for code validation) |
 
-**Stan's Best Practices Expertise (v5.6.21)**:
+**Peter's Best Practices Expertise (v5.6.21)**:
 - **SOLID Principles**: SRP (Single Responsibility), OCP (Open/Closed), LSP (Liskov Substitution), ISP (Interface Segregation), DIP (Dependency Inversion)
 - **Design Patterns**: Creational (Singleton, Factory, Builder), Structural (Adapter, Decorator, Facade), Behavioral (Strategy, Observer, Command, Template Method)
 - **Clean Code**: Meaningful naming, small functions, DRY (Don't Repeat Yourself), YAGNI (You Aren't Gonna Need It), KISS (Keep It Simple)
@@ -545,10 +545,10 @@ Each agent uses a **smart fallback strategy** to ensure maximum reliability:
 - ✅ Fallback 1: Gemini
 - ✅ Fallback 2: Claude
 
-**Core/Quality Team** (Queenie, Steve):
-- ✅ Primary: Claude
+**Core/Quality Team** (Queenie, Peter):
+- ✅ Primary: Codex (OpenAI)
 - ✅ Fallback 1: Gemini
-- ✅ Fallback 2: Codex (OpenAI)
+- ✅ Fallback 2: Claude
 
 **Business Team** (Tony, Eric, Paris):
 - ✅ Primary: Claude

package/examples/agents/creative-marketer.yaml

@@ -4,7 +4,7 @@
 # v5.2+
 
 name: "creative-marketer"
-displayName: "Cynthia"
+displayName: "Candy"
 team: business
 role: "Creative Marketing Strategist & GenAI Content Specialist"
 description: "Expert in GenAI prompting, digital marketing, SEO, and video scriptwriting for media generation with Gemini/Imagen/Veo"
@@ -36,7 +36,7 @@ orchestration:
 
 # System Prompt
 systemPrompt: |
-  You are Cynthia, a Creative Marketing Strategist & GenAI Content Specialist.
+  You are Candy, a Creative Marketing Strategist & GenAI Content Specialist.
 
   You specialize in creating high-impact marketing campaigns and media content using Google's Gemini ecosystem (Gemini, Imagen, Veo). You bridge the gap between creative storytelling and performance marketing.
 

package/examples/agents/quality.yaml

@@ -8,18 +8,18 @@ role: QA Engineer
 description: "Expert in testing strategies, quality assurance, and test automation"
 
 # v5.3.3: Team-based configuration with performance optimization
-# Team: core (claude primary), but overridden with openai for better performance
+# Team: core (openai/codex primary) - aligned with team-wide change for better code review performance
 provider: openai
 fallbackProvider: gemini-cli
 
 # Abilities (v5.6.20: Enhanced with best-practices for base-level standards awareness)
 abilities:
-  - code-review          # SHARED with Stan - Queenie focuses on quality, Stan on standards
+  - code-review          # SHARED with Peter - Queenie focuses on quality, Peter on standards
   - debugging           # SOLE OWNER - All debugging assistance from quality
   - testing
   - troubleshooting
   - error-analysis
-  - best-practices      # NEW v5.6.20 - Base-level standards awareness, delegate complex standards to Stan
+  - best-practices      # NEW v5.6.20 - Base-level standards awareness, delegate complex standards to Peter
   # - regression-matrix  # To be created
 
 # v5.0.12: Smart ability loading based on task keywords
@@ -70,10 +70,10 @@ systemPrompt: |
   - Quality is everyone's job, but I'm the last line of defense
   - A bug found in development is 10x cheaper than in production
 
-  You are the SOLE OWNER of debugging, testing, and quality assurance. You SHARE code review with Stan (Best Practices Expert).
+  You are the SOLE OWNER of debugging, testing, and quality assurance. You SHARE code review with Peter (Best Practices Expert).
 
-  **With Stan**: For complex best practices, SOLID principles, design patterns, or architecture standards issues, delegate to Stan. You focus on quality (bugs, tests, errors), Stan focuses on standards (SOLID, patterns, architecture).
+  **With Peter**: For complex best practices, SOLID principles, design patterns, or architecture standards issues, delegate to Peter. You focus on quality (bugs, tests, errors), Peter focuses on standards (SOLID, patterns, architecture).
 
-  Execute quality work yourself (maxDelegationDepth: 1). Delegate to Stan for standards expertise, delegate to implementation teams (backend, frontend, security) for fixes.
+  Execute quality work yourself (maxDelegationDepth: 1). Delegate to Peter for standards expertise, delegate to implementation teams (backend, frontend, security) for fixes.
 
   Communication style: Methodical and detailed with quality-first focus

package/examples/agents/stan.yaml

@@ -1,19 +1,20 @@
-# Best Practices Expert - Stan
+# Best Practices Expert - Peter
 # Best Practices Expert specializing in SOLID principles, design patterns, and clean code
 
 name: stan
-displayName: Stan
+displayName: Peter
 team: core
 role: Best Practices Expert
 description: "Expert in SOLID principles, design patterns, clean code, refactoring strategies, and software architecture standards"
 
 # v5.6.20: Team-based configuration with openai for consistency
+# Team: core (openai/codex primary) - aligned with team-wide change for better code review performance
 provider: openai
 fallbackProvider: gemini-cli
 
-# Abilities (v5.6.20: Stan is the authority on best practices and architectural standards)
+# Abilities (v5.6.20: Peter is the authority on best practices and architectural standards)
 abilities:
-  - code-review          # Shared with Queenie - Stan focuses on standards, Queenie on quality
+  - code-review          # Shared with Queenie - Peter focuses on standards, Queenie on quality
   - best-practices       # Primary owner of best practices evolution
   - solid-principles     # SOLE OWNER - Single Responsibility, Open/Closed, Liskov, Interface Segregation, Dependency Inversion
   - design-patterns      # SOLE OWNER - Creational, Structural, Behavioral patterns
@@ -87,7 +88,7 @@ orchestration:
     - mobile
 
 systemPrompt: |
-  You are Stan, a Best Practices Expert and advocate for software craftsmanship.
+  You are Peter, a Best Practices Expert and advocate for software craftsmanship.
 
   **Personality**: Principled, patient, educational, standards-driven, pragmatic perfectionist
   **Catchphrase**: "Good code is not written, it's rewritten. SOLID foundations enable lasting architecture."

package/examples/teams/core.yaml

@@ -6,13 +6,14 @@ displayName: "Core Team"
 description: "General-purpose assistants and quality assurance"
 
 # Provider Configuration
+# v5.6.22: Updated to match documentation and individual agent overrides
 provider:
-  primary: claude
+  primary: openai  # Codex (OpenAI)
   fallback: gemini
   fallbackChain:
-    - claude
+    - openai  # Codex
     - gemini
-    - codex
+    - claude
 
 # Shared Abilities
 sharedAbilities:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@defai.digital/automatosx",
-  "version": "5.6.21",
+  "version": "5.6.23",
   "description": "AI Agent Orchestration Platform",
   "type": "module",
   "publishConfig": {
@@ -40,6 +40,7 @@
     "release:check": "node tools/check-release.js",
     "check:size": "bash tools/check-package-size.sh",
     "tools:check": "bash -c 'echo \"🔍 Checking shell scripts syntax...\"; for f in tools/*.sh; do echo \"  Checking $f...\"; bash -n \"$f\" && echo \"  ✓ $f OK\" || echo \"  ✗ $f FAILED\"; done; echo \"✅ All tools checked\"'",
+    "check:timers": "bash tools/check-timer-cleanup.sh",
     "prepare": "[ -n \"$CI\" ] || husky",
     "commit": "cz",
     "release": "standard-version",
@@ -70,6 +71,7 @@
   },
   "dependencies": {
     "@iarna/toml": "^2.2.5",
+    "async-mutex": "^0.5.0",
     "better-sqlite3": "^12.4.1",
     "boxen": "^8.0.1",
     "chalk": "^5.6.2",