chore: release 4.2.0 with superagent mcp

Author: hyunjae

.gitignore

@@ -108,7 +108,7 @@ GEMINI.md
 *.backup
 *.bak
 SuperGemini/Agents/
-AGENTS.md
+AGENTS.md
 
 # Project specific
 Tests/

CHANGELOG.md

@@ -7,13 +7,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
-## [4.0.10] - 2025-09-26
+## [4.2.0] - 2025-09-26
 
 ### Fixed
 - Enhanced MCP prerequisite detection to reliably locate `node`, `npm`, and `uv` across common version managers and PATH fallbacks, preventing false "not found" errors during installation (`setup/components/mcp.py`).
 
 ### Changed
-- Synchronized all published artifacts (PyPI + npm) and documentation with version `4.0.10`, ensuring installers and badges reference the corrected release.
+- Synchronized all published artifacts (PyPI + npm) and documentation with version `4.2.0`, ensuring installers and badges reference the corrected release.
 
 ## [4.0.9] - 2025-08-24
 

Docs/Reference/README.md

@@ -99,8 +99,8 @@ Advanced Analysis: diagnostic-reference.md
 |----------------|---------|---------|
 | `/sg:load` | Restore session context | `/sg:load project_name` |
 | `/sg:save` | Preserve session state | `/sg:save "milestone checkpoint"` |
-| `--think` | Enable structured analysis | `--think analyze performance bottlenecks` |
-| `` | Collaborative requirement discovery | ` new authentication system` |
+| `--introspect` | Expose structured reasoning | `--introspect analyze performance bottlenecks` |
+| `/sg:brainstorm` | Collaborative requirement discovery | `/sg:brainstorm "new authentication system"` |
 | `--task-manage` | Multi-step operation orchestration | `--task-manage refactor user module` |
 
 ### Performance & Efficiency Flags
@@ -133,7 +133,7 @@ Advanced Analysis: diagnostic-reference.md
 --c7 --magic "implement Next.js authentication with TypeScript"
 
 # Component development workflow  
---magic --think "create responsive dashboard component"
+--magic --introspect "create responsive dashboard component"
 ```
 
 ### Node.js/Express Backend
@@ -142,7 +142,7 @@ Advanced Analysis: diagnostic-reference.md
 --c7 --seq "design RESTful API with Express and MongoDB"
 
 # Performance optimization
---think --orchestrate "optimize database queries and caching"
+--introspect --orchestrate "optimize database queries and caching"
 ```
 
 ### Full-Stack Development
@@ -203,7 +203,7 @@ Found outdated information or broken examples?
 
 ### Daily Workflow Optimization
 1. **Session Management**: Always start with `/sg:load`, end with `/sg:save`
-2. **Flag Combinations**: Combine complementary flags: `--think --c7` for documented analysis
+2. **Flag Combinations**: Combine complementary flags: `--introspect --c7` for documented analysis
 3. **Progressive Complexity**: Start simple, add sophistication incrementally
 4. **Tool Specialization**: Match tools to tasks: Magic for UI, Sequential for analysis
 
@@ -215,7 +215,7 @@ Found outdated information or broken examples?
 
 ### Troubleshooting Mastery
 1. **Systematic Approach**: Always start with [common-issues.md](common-issues.md)
-2. **Evidence Gathering**: Use `--think` for complex problem analysis
+2. **Evidence Gathering**: Use `--introspect` for complex problem analysis
 3. **Root Cause Focus**: Address underlying issues, not just symptoms
 4. **Documentation First**: Check official docs before experimental solutions
 
@@ -247,4 +247,4 @@ Found outdated information or broken examples?
 
 **Need Answers Now**: Jump to [basic-examples.md](basic-examples.md) for copy-paste solutions.
 
-**Ready for Advanced**: Explore [advanced-patterns.md](advanced-patterns.md) for expert-level orchestration.
+**Ready for Advanced**: Explore [advanced-patterns.md](advanced-patterns.md) for expert-level orchestration.

Docs/Reference/advanced-workflows.md

@@ -89,7 +89,7 @@
 
 /sg:save "ecommerce-requirements-complete"
 
-/sg:analyze "microservices architecture for e-commerce" --focus architecture --think-hard
+/sg:analyze "microservices architecture for e-commerce" --focus architecture --introspect
 # Expected: Service boundaries, data flow diagrams, technology recommendations
 # ✅ Verified: SuperGemini v4.0
 
@@ -123,7 +123,7 @@
 # Expected: Full test suite with E2E, integration, and unit coverage
 # ✅ Verified: SuperGemini v4.0
 
-/sg:analyze . --focus performance --think-hard && /sg:implement "performance optimizations" --focus performance --orchestrate
+/sg:analyze . --focus performance --introspect && /sg:implement "performance optimizations" --focus performance --orchestrate
 # Expected: Performance bottleneck identification and optimization
 # ✅ Verified: SuperGemini v4.0
 ```
@@ -144,7 +144,7 @@
 # Phase 2: Modernization Strategy
 /sg:load "legacy-analysis-complete"
 
-/sg:analyze "microservices migration strategy" --focus architecture --think-hard --c7
+/sg:analyze "microservices migration strategy" --focus architecture --introspect --c7
 # Activates: system-architect + enterprise patterns + migration strategies
 # Expected: Service decomposition plan, migration roadmap, risk assessment
 # ✅ Verified: SuperGemini v4.0
@@ -184,7 +184,7 @@
 ### Open Source Project Development
 ```bash
 # Understanding and Contributing to Large Projects
-/sg:load open-source-project/ && /sg:analyze . --focus architecture --think-hard --serena
+/sg:load open-source-project/ && /sg:analyze . --focus architecture --introspect --serena
 # Expected: Architecture understanding, contribution patterns, codebase navigation
 # ✅ Verified: SuperGemini v4.0
 
@@ -201,7 +201,7 @@
 # ✅ Verified: SuperGemini v4.0
 
 # Community Integration and Documentation
-/sg:analyze . --focus architecture --think-hard --c7 --serena
+/sg:analyze . --focus architecture --introspect --c7 --serena
 # Expected: Compatibility analysis, community impact assessment
 # ✅ Verified: SuperGemini v4.0
 
@@ -397,7 +397,7 @@
 ### Safety and Validation for Production
 ```bash
 # Production-ready development with comprehensive validation
-/sg:implement "payment processing system" --focus security --think-hard --c7 --serena
+/sg:implement "payment processing system" --focus security --introspect --c7 --serena
 # Activates: Security-focused implementation with official patterns and context
 # Expected: Production-ready implementation with security best practices
 # ✅ Verified: SuperGemini v4.0
@@ -420,7 +420,7 @@
 # Expected: MVP implementation with enterprise-scale architecture planning
 
 # Month 2-3: Scale Preparation
-/sg:load "mvp-requirements" && /sg:analyze . --focus architecture --think-hard
+/sg:load "mvp-requirements" && /sg:analyze . --focus architecture --introspect
 # Expected: Scalability assessment and optimization recommendations
 
 /sg:implement "microservices migration and containerization" --orchestrate
@@ -437,7 +437,7 @@
 ### Multi-Platform Application Development
 ```bash
 # Phase 1: Architecture Planning
-/sg:analyze "cross-platform architecture strategies" --focus architecture --think-hard --c7
+/sg:analyze "cross-platform architecture strategies" --focus architecture --introspect --c7
 # Expected: Multi-platform architecture with shared business logic
 # ✅ Verified: SuperGemini v4.0
 

Docs/Reference/basic-examples.md

@@ -85,10 +85,10 @@
 
 #### Command: /sg:analyze (Security Focus)
 **Purpose**: Security-focused code review
-**Syntax**: `/sg:analyze [target] --focus security [--think]`
+**Syntax**: `/sg:analyze [target] --focus security [--introspect]`
 **Example**:
 ```bash
-/sg:analyze src/ --focus security --think
+/sg:analyze src/ --focus security --introspect
 ```
 **Verification**: ✅ Verified SuperGemini v4.0
 
@@ -377,18 +377,18 @@
 
 ## Basic Flag Examples
 
-### Analysis Depth Control
+### Insight Modes
 ```bash
 # Quick analysis
 /sg:analyze src/ --scope file
 # ✅ Verified: SuperGemini v4.0
 
-# Standard analysis
-/sg:analyze . --think
+# Reflective analysis
+/sg:analyze . --introspect
 # ✅ Verified: SuperGemini v4.0
 
-# Deep analysis
-/sg:analyze . --think-hard --focus architecture
+# Architecture-focused insight
+/sg:analyze . --introspect --focus architecture
 # ✅ Verified: SuperGemini v4.0
 ```
 
@@ -484,4 +484,4 @@
 
 ---
 
-**Remember**: Start simple, practice frequently, and gradually increase complexity. These basic examples form the foundation for all advanced SuperGemini usage.
+**Remember**: Start simple, practice frequently, and gradually increase complexity. These basic examples form the foundation for all advanced SuperGemini usage.

Docs/Reference/examples-cookbook.md

@@ -85,7 +85,7 @@
 - `/sg:reflect` - Context analysis and optimization
 
 **Verified Flags**:
-- `--think`, `--think-hard`, `--ultrathink` - Analysis depth control
+- `--introspect`, `--task-manage`, `--orchestrate` - Analysis and coordination control
 - `--uc` - Ultra-compressed token-efficient mode
 - `--orchestrate` - Intelligent coordination mode
 - `--c7`, `--serena`, `--all-mcp` - MCP server integration
@@ -169,4 +169,4 @@
 
 **Your Journey**: Start with [Basic Examples](basic-examples.md), progress through [Advanced Workflows](advanced-workflows.md), and master [Integration Patterns](integration-patterns.md). SuperGemini grows with you from simple commands to sophisticated development orchestration.
 
-**Remember**: Every expert was once a beginner. Focus on practical application, experiment with different approaches, and leverage the community for support and learning.
+**Remember**: Every expert was once a beginner. Focus on practical application, experiment with different approaches, and leverage the community for support and learning.

Docs/Reference/integration-patterns.md

@@ -221,7 +221,7 @@
 ### Backend Performance Optimization
 ```bash
 # Database and API performance optimization
-/sg:analyze backend/ --focus performance --think-hard --serena
+/sg:analyze backend/ --focus performance --introspect --serena
 
 # Backend performance areas:
 # - Database query optimization and indexing
@@ -273,7 +273,7 @@
 ### Distributed System Debugging
 ```bash
 # Complex distributed system troubleshooting
-/sg:troubleshoot "intermittent service failures in microservices architecture" --think-hard --all-mcp
+/sg:troubleshoot "intermittent service failures in microservices architecture" --introspect --all-mcp
 
 # Systematic debugging approach:
 # 1. Service dependency mapping and health analysis

Docs/Reference/optimization-guide.md

@@ -313,7 +313,7 @@ Layer 5: /sg:test . --security --vulnerability    # Security validation
 
 # Refactor Phase: Code improvement
 /sg:improve . --focus quality --safe-mode
-/sg:analyze . --focus quality --think
+/sg:analyze . --focus quality --introspect
 /sg:test . --coverage --validate
 
 # Cycle benefits: Higher code quality, better test coverage, reduced bugs
@@ -345,7 +345,7 @@ Layer 5: /sg:test . --security --vulnerability    # Security validation
 **Quality Prediction and Prevention:**
 ```bash
 # Advanced quality management with comprehensive analysis
-/sg:analyze . --focus quality --think-hard --validate
+/sg:analyze . --focus quality --introspect --validate
 
 # Predictive analysis capabilities:
 # - Quality degradation prediction based on code change patterns
@@ -356,7 +356,7 @@ Layer 5: /sg:test . --security --vulnerability    # Security validation
 
 # Proactive optimization workflow:
 /sg:implement "new feature" --validate --safe-mode
-/sg:analyze . --focus quality --think  
+/sg:analyze . --focus quality --introspect  
 /sg:improve . --focus quality --validate
 
 # Outcomes: Significant reduction in production issues and lower maintenance costs
@@ -757,4 +757,4 @@ Optimization is an ongoing process. Start with immediate performance gains, esta
 - **Performance**: 30-70% improvement in execution time and resource efficiency
 - **Quality**: Measurable reduction in issues and improvement in code quality metrics
 - **Productivity**: Faster development cycles with maintained or improved quality
-- **Sustainability**: Consistent optimization practices integrated into daily workflows
+- **Sustainability**: Consistent optimization practices integrated into daily workflows

Docs/Reference/quick-start-practices.md

@@ -152,7 +152,7 @@ Day 7: /sg:workflow "week 2 learning plan"
 ```bash
 # Use when: Code review, refactoring, optimization, testing
 /sg:test --coverage --validate
-/sg:analyze . --focus security --think-hard
+/sg:analyze . --focus security --introspect
 /sg:cleanup . --safe-mode
 /sg:document . --scope project
 
@@ -242,8 +242,8 @@ Day 7: /sg:workflow "week 2 learning plan"
 # --safe-mode: Maximum safety checks and rollback capability
 
 # For comprehensive analysis
-/sg:analyze . --think --focus security
-# --think: Standard structured analysis (~4K tokens)
+/sg:analyze . --focus security --introspect
+# --introspect: Deep reasoning with transparent analysis markers
 # --focus security: Domain-specific expertise
 
 # Quality improvements: Better validation through systematic checks
@@ -650,4 +650,4 @@ Focus on building solid foundations before advancing to complex features. These
 - **Week 3**: Confident session management and context preservation
 - **Week 4**: Ready for advanced coordination and optimization techniques
 
-Remember: Start simple, practice consistently, and gradually increase complexity as your confidence grows.
+Remember: Start simple, practice consistently, and gradually increase complexity as your confidence grows.

Docs/Reference/validate_commands.py

@@ -77,7 +77,7 @@ def __init__(self, verbose: bool = False, quick_mode: bool = False):
         )
 
         # Documented flags from flags.md
-        self.analysis_flags = ["--think", "--think-hard", "--ultrathink"]
+        self.analysis_flags = ["--introspect"]
         self.mode_flags = ["--introspect", "--task-manage"]
         self.efficiency_flags = ["--uc", "--token-efficient", "--orchestrate"]
         self.mcp_flags = [
@@ -158,7 +158,7 @@ def _is_valid_flag_syntax(self, flag: str) -> bool:
 
         valid_flag_patterns = [
             # Analysis flags
-            "--think", "--think-hard", "--ultrathink",
+            "--introspect",
             # Mode flags  
             "--introspect", "--task-manage", "--delegate",
             # Efficiency flags
@@ -200,9 +200,7 @@ def _check_flag_conflicts(self, flags: List[str]) -> Optional[str]:
             ("--all-mcp", "--no-mcp", "Cannot use all MCP servers and no MCP servers simultaneously"),
             ("--parallel", "--sequential", "Cannot use parallel and sequential execution simultaneously"),
             ("--verbose", "--quiet", "Cannot use verbose and quiet modes simultaneously"),
-            ("--think", "--no-mcp", "Deep thinking modes require MCP servers (--think conflicts with --no-mcp)"),
-            ("--think-hard", "--no-mcp", "Deep thinking modes require MCP servers (--think-hard conflicts with --no-mcp)"),
-            ("--ultrathink", "--no-mcp", "Deep thinking modes require MCP servers (--ultrathink conflicts with --no-mcp)"),
+            ("--introspect", "--no-mcp", "Introspect mode requires MCP servers (--introspect conflicts with --no-mcp)"),
         ]
 
         for flag1, flag2, message in conflicts:
@@ -246,17 +244,17 @@ def validate_flag_combinations(self) -> None:
         # Test common flag combinations from documentation
         test_combinations = [
             # Analysis combinations
-            ("/sg:analyze src/ --think", "Standard analysis with structured thinking"),
-            ("/sg:analyze --focus security --think-hard", "Deep security analysis"),
-            ("/sg:troubleshoot 'issue' --ultrathink --seq", "Maximum troubleshooting"),
+            ("/sg:analyze src/ --introspect", "Standard analysis with structured reasoning"),
+            ("/sg:analyze --focus security --introspect", "Deep security analysis"),
+            ("/sg:troubleshoot 'issue' --introspect --seq", "Structured troubleshooting"),
 
             # Development combinations
             ("/sg:implement 'feature' --magic --c7", "UI feature with patterns"),
             ("/sg:improve code/ --morph --serena", "Code improvement with context"),
             ("/sg:build --optimize --validate", "Safe production build"),
 
             # Workflow combinations
-            ("/sg:brainstorm 'idea' --think --c7", "Structured brainstorming"),
+            ("/sg:brainstorm 'idea' --introspect --c7", "Structured brainstorming"),
             ("/sg:task 'complex' --task-manage --delegate", "Complex task coordination"),
             ("/sg:test --coverage --play", "Comprehensive testing"),
 
@@ -476,7 +474,7 @@ def run_integration_tests(self) -> None:
         # Test session lifecycle
         session_commands = [
             "/sg:load test-project/",
-            "/sg:analyze src/ --think",
+            "/sg:analyze src/ --introspect",
             "/sg:implement 'test feature' --magic",
             "/sg:save 'test-session'"
         ]
@@ -706,4 +704,4 @@ def main():
         sys.exit(1)
 
 if __name__ == "__main__":
-    main()
+    main()