claude-mpm 0.3.0__tar.gz → 1.0.0__tar.gz

{claude_mpm-0.3.0 → claude_mpm-1.0.0}/CHANGELOG.md

@@ -5,6 +5,44 @@ All notable changes to claude-mpm will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.0.0] - 2025-07-26
+
+### BREAKING CHANGES
+- **Simplified architecture**: Replaced the entire orchestrator system with a simple runner
+  - Removed 16 orchestrator implementations and consolidated to `simple_runner.py`
+  - Deleted todo hijacking and subprocess runner features
+  - Removed agent modification tracker service
+  - Archived old orchestrators to `orchestration/archive/`
+
+### Added
+- **TodoWrite Agent Prefix Hook system**: Automatic delegation of todo items to specialized agents
+  - `todo_agent_prefix_hook.py` for automatic todo list delegation
+  - `tool_call_interceptor.py` for intercepting TodoWrite tool calls
+  - Comprehensive documentation and example implementations
+  - Test script for validating todo hook functionality
+- **Enhanced CLI with argument preprocessing**: Better command-line interaction
+  - Support for `@agent` syntax for direct agent specification
+  - Pass-through arguments to Claude with proper escaping
+  - Improved logging and error handling in CLI operations
+
+### Changed
+- **Updated agent instructions**: Clearer guidelines for agent development
+- **Simplified ticket manager**: Removed unnecessary complexity in ticket management
+- **Streamlined test suite**: Removed 15 obsolete test files related to old orchestration patterns
+- **Updated remaining tests**: Modified to work with simplified architecture
+- **Improved framework loader**: Better clarity and maintainability
+
+### Removed
+- Complex orchestrator system (moved to archive)
+- Todo hijacking features
+- Subprocess runner features
+- Agent modification tracker service
+- Obsolete tests for deprecated features
+
+### Fixed
+- Test suite compatibility with new architecture
+- Import paths and module references
+
 ## [0.5.0] - 2024-01-25
 
 ### Added
@@ -59,6 +97,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Framework loader
 - Basic CLI structure
 
+[1.0.0]: https://github.com/bobmatnyc/claude-mpm/compare/v0.5.0...v1.0.0
 [0.5.0]: https://github.com/bobmatnyc/claude-mpm/compare/v0.3.0...v0.5.0
 [0.3.0]: https://github.com/bobmatnyc/claude-mpm/compare/v0.2.0...v0.3.0
 [0.2.0]: https://github.com/bobmatnyc/claude-mpm/compare/v0.1.0...v0.2.0

{claude_mpm-0.3.0/src/claude_mpm.egg-info → claude_mpm-1.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: claude-mpm
-Version: 0.3.0
+Version: 1.0.0
 Summary: Claude Multi-agent Project Manager - Clean orchestration with ticket management
 Home-page: https://github.com/bobmatnyc/claude-mpm
 Author: Claude MPM Team

claude_mpm-1.0.0/VERSION

@@ -0,0 +1 @@
+1.0.1.dev0+g8dd1a55.d20250726

{claude_mpm-0.3.0 → claude_mpm-1.0.0}/examples/todo_prefix_hook_example.py

@@ -33,7 +33,7 @@ def demo_auto_prefix_enforcement():
                 {'content': 'implement user authentication', 'status': 'pending', 'priority': 'high', 'id': '1'},
                 {'content': 'write unit tests for auth module', 'status': 'pending', 'priority': 'medium', 'id': '2'},
                 {'content': 'research best practices for JWT', 'status': 'pending', 'priority': 'low', 'id': '3'},
-                {'content': 'Engineer: fix login bug', 'status': 'pending', 'priority': 'high', 'id': '4'},  # Already has prefix
+                {'content': '[Engineer] fix login bug', 'status': 'pending', 'priority': 'high', 'id': '4'},  # Already has prefix
             ]
         }
     ]
@@ -74,9 +74,9 @@ def demo_validation_only():
             'name': 'Valid todos with proper prefixes',
             'params': {
                 'todos': [
-                    {'content': 'Engineer: implement user authentication', 'status': 'pending', 'priority': 'high', 'id': '1'},
-                    {'content': 'QA: write unit tests for auth module', 'status': 'pending', 'priority': 'medium', 'id': '2'},
-                    {'content': 'Researcher: investigate OAuth2 best practices', 'status': 'pending', 'priority': 'low', 'id': '3'},
+                    {'content': '[Engineer] implement user authentication', 'status': 'pending', 'priority': 'high', 'id': '1'},
+                    {'content': '[QA] write unit tests for auth module', 'status': 'pending', 'priority': 'medium', 'id': '2'},
+                    {'content': '[Research] investigate OAuth2 best practices', 'status': 'pending', 'priority': 'low', 'id': '3'},
                 ]
             }
         },
@@ -93,9 +93,9 @@ def demo_validation_only():
             'name': 'Mixed valid and invalid',
             'params': {
                 'todos': [
-                    {'content': 'Security: audit authentication system', 'status': 'pending', 'priority': 'high', 'id': '1'},
+                    {'content': '[Security] audit authentication system', 'status': 'pending', 'priority': 'high', 'id': '1'},
                     {'content': 'update documentation', 'status': 'pending', 'priority': 'low', 'id': '2'},  # Missing prefix
-                    {'content': 'Ops: configure CI/CD pipeline', 'status': 'pending', 'priority': 'medium', 'id': '3'},
+                    {'content': '[Ops] configure CI/CD pipeline', 'status': 'pending', 'priority': 'medium', 'id': '3'},
                 ]
             }
         }

{claude_mpm-0.3.0 → claude_mpm-1.0.0}/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bobmatnyc/claude-mpm",
-  "version": "0.3.1",
+  "version": "1.0.0",
   "description": "Claude Multi-Agent Project Manager - Orchestrate Claude with agent delegation and ticket tracking",
   "keywords": [
     "claude",

claude_mpm-1.0.0/scripts/debug_hook_behavior.py

@@ -0,0 +1,62 @@
+#!/usr/bin/env python3
+"""Debug script to understand hook behavior."""
+
+import sys
+import os
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+from datetime import datetime
+from claude_mpm.hooks.builtin.todo_agent_prefix_hook import TodoAgentPrefixHook
+from claude_mpm.hooks.base_hook import HookContext, HookType
+
+# Create hook instance
+hook = TodoAgentPrefixHook()
+
+# Test case
+test_todo = "Research best practices for testing"
+context = HookContext(
+    hook_type=HookType.CUSTOM,
+    data={
+        'tool_name': 'TodoWrite',
+        'parameters': {
+            'todos': [{'content': test_todo}]
+        }
+    },
+    metadata={},
+    timestamp=datetime.now()
+)
+
+print(f"Testing todo: '{test_todo}'")
+print(f"Hook validation: {hook.validate(context)}")
+
+# Execute hook
+result = hook.execute(context)
+
+print(f"\nResult:")
+print(f"  Success: {result.success}")
+print(f"  Modified: {result.modified}")
+print(f"  Error: {result.error}")
+
+if result.success and result.modified:
+    updated_todos = result.data['parameters']['todos']
+    print(f"  Updated content: '{updated_todos[0]['content']}'")
+
+# Test with a todo that already has a prefix
+prefixed_todo = "[Research] Analyze patterns"
+context2 = HookContext(
+    hook_type=HookType.CUSTOM,
+    data={
+        'tool_name': 'TodoWrite',
+        'parameters': {
+            'todos': [{'content': prefixed_todo}]
+        }
+    },
+    metadata={},
+    timestamp=datetime.now()
+)
+
+print(f"\n\nTesting prefixed todo: '{prefixed_todo}'")
+result2 = hook.execute(context2)
+print(f"Result:")
+print(f"  Success: {result2.success}")
+print(f"  Modified: {result2.modified}")

claude_mpm-1.0.0/scripts/debug_hook_behavior2.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+"""Debug script to understand hook behavior in detail."""
+
+import sys
+import os
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+from datetime import datetime
+from claude_mpm.hooks.builtin.todo_agent_prefix_hook import TodoAgentPrefixHook
+from claude_mpm.hooks.base_hook import HookContext, HookType
+from claude_mpm.core.agent_name_normalizer import agent_name_normalizer
+
+# Create hook instance
+hook = TodoAgentPrefixHook()
+
+# Test cases from the failing test
+test_cases = [
+    ("Research best practices for testing", "[Research]"),
+    ("Implement new feature", "[Engineer]"),
+    ("Test the implementation", "[QA]"),
+    ("Document the API", "[Documentation]"),
+    ("Check security vulnerabilities", "[Security]"),
+    ("Deploy to production", "[Ops]"),
+    ("Create data pipeline", "[Data Engineer]"),
+    ("Create new git branch", "[Version Control]"),
+]
+
+for content, expected_prefix in test_cases:
+    print(f"\nTesting: '{content}'")
+    print(f"Expected prefix: {expected_prefix}")
+    
+    # Check if it already has a prefix
+    has_prefix = hook._has_agent_prefix(content)
+    print(f"Has prefix: {has_prefix}")
+    
+    # Check what agent it suggests
+    suggested = hook._suggest_agent(content)
+    print(f"Suggested agent: {suggested}")
+    
+    if suggested:
+        prefix = agent_name_normalizer.to_todo_prefix(suggested)
+        print(f"Generated prefix: {prefix}")
+    
+    # Create context and execute
+    context = HookContext(
+        hook_type=HookType.CUSTOM,
+        data={
+            'tool_name': 'TodoWrite',
+            'parameters': {
+                'todos': [{'content': content}]
+            }
+        },
+        metadata={},
+        timestamp=datetime.now()
+    )
+    
+    result = hook.execute(context)
+    print(f"Result - Success: {result.success}, Modified: {result.modified}")
+    
+    if result.modified and result.data:
+        updated_content = result.data['parameters']['todos'][0]['content']
+        print(f"Updated content: '{updated_content}'")
+    elif result.error:
+        print(f"Error: {result.error}")
+    
+    print("-" * 50)

claude_mpm-1.0.0/scripts/test_agent_name_consistency.py

@@ -0,0 +1,282 @@
+#!/usr/bin/env python3
+"""
+Demonstration script showing agent name consistency between TodoWrite and Task tools.
+
+This script demonstrates:
+1. TodoWrite accepting bracketed agent names like [Research], [Version Control]
+2. Task tool accepting both capitalized and lowercase formats
+3. Proper conversion between formats
+4. Error handling for invalid agent names
+"""
+
+import sys
+import os
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+from datetime import datetime
+from claude_mpm.core.agent_name_normalizer import AgentNameNormalizer, agent_name_normalizer
+from claude_mpm.hooks.builtin.todo_agent_prefix_hook import (
+    TodoAgentPrefixHook,
+    TodoAgentPrefixValidatorHook
+)
+from claude_mpm.hooks.base_hook import HookContext, HookType
+
+
+def print_section(title):
+    """Print a formatted section header."""
+    print(f"\n{'='*60}")
+    print(f" {title}")
+    print('='*60)
+
+
+def demonstrate_agent_normalization():
+    """Demonstrate the agent name normalization functionality."""
+    print_section("Agent Name Normalization")
+    
+    # Show all supported agents
+    print("\nSupported agent types:")
+    for key, canonical in AgentNameNormalizer.CANONICAL_NAMES.items():
+        print(f"  {key:20} -> {canonical}")
+    
+    # Demonstrate normalization
+    print("\nNormalization examples:")
+    test_inputs = [
+        "research", "Research", "RESEARCH", "researcher",
+        "version_control", "version-control", "Version Control", "git",
+        "data_engineer", "data-engineer", "Data Engineer", "data",
+        "qa", "QA", "testing", "test",
+    ]
+    
+    for input_name in test_inputs:
+        normalized = AgentNameNormalizer.normalize(input_name)
+        print(f"  '{input_name:20}' -> '{normalized}'")
+
+
+def demonstrate_todo_format():
+    """Demonstrate TodoWrite format handling."""
+    print_section("TodoWrite Format")
+    
+    # Show TODO prefix generation
+    print("\nTODO prefix generation:")
+    agents = ["Research", "Engineer", "Version Control", "Data Engineer", "QA"]
+    for agent in agents:
+        prefix = AgentNameNormalizer.to_todo_prefix(agent)
+        print(f"  {agent:20} -> {prefix}")
+    
+    # Show extraction from TODOs
+    print("\nExtracting agents from TODO text:")
+    todos = [
+        "[Research] Analyze user behavior patterns",
+        "[Version Control] Create release branch v2.0",
+        "[Data Engineer] Build data pipeline for analytics",
+        "[QA] Run integration test suite",
+        "[Security] Perform security audit",
+    ]
+    
+    for todo in todos:
+        agent = AgentNameNormalizer.extract_from_todo(todo)
+        print(f"  '{todo[:50]}...' -> Agent: {agent}")
+    
+    # Show validation
+    print("\nTODO format validation:")
+    test_todos = [
+        "[Research] Valid todo",
+        "[Invalid Agent] This won't work",
+        "Missing prefix todo",
+        "[Version Control] Another valid todo",
+    ]
+    
+    for todo in test_todos:
+        is_valid, error = AgentNameNormalizer.validate_todo_format(todo)
+        status = "✓ Valid" if is_valid else f"✗ Invalid: {error[:50]}..."
+        print(f"  '{todo[:30]:30}' -> {status}")
+
+
+def demonstrate_task_format_conversion():
+    """Demonstrate conversion between TodoWrite and Task formats."""
+    print_section("TodoWrite <-> Task Format Conversion")
+    
+    # TodoWrite to Task format
+    print("\nTodoWrite format -> Task format:")
+    todo_formats = [
+        "Research", "Engineer", "QA", "Security",
+        "Documentation", "Ops", "Version Control",
+        "Data Engineer", "Architect", "PM"
+    ]
+    
+    for todo_format in todo_formats:
+        task_format = AgentNameNormalizer.to_task_format(todo_format)
+        print(f"  {todo_format:20} -> {task_format}")
+    
+    # Task to TodoWrite format
+    print("\nTask format -> TodoWrite format:")
+    task_formats = [
+        "research", "engineer", "qa", "security",
+        "documentation", "ops", "version-control",
+        "data-engineer", "architect", "pm"
+    ]
+    
+    for task_format in task_formats:
+        todo_format = AgentNameNormalizer.from_task_format(task_format)
+        print(f"  {task_format:20} -> {todo_format}")
+
+
+def demonstrate_hook_behavior():
+    """Demonstrate the TodoAgentPrefixHook behavior."""
+    print_section("TodoAgentPrefixHook Behavior")
+    
+    hook = TodoAgentPrefixHook()
+    
+    # Test auto-prefix addition
+    print("\nAuto-prefix addition:")
+    test_todos = [
+        "Research best practices for microservices",
+        "Implement user authentication feature",
+        "Test the new API endpoints",
+        "Document the deployment process",
+        "Deploy to production environment",
+        "Create data pipeline for analytics",
+        "Create git branch for hotfix",
+    ]
+    
+    for todo_content in test_todos:
+        context = HookContext(
+            hook_type=HookType.CUSTOM,
+            data={
+                'tool_name': 'TodoWrite',
+                'parameters': {
+                    'todos': [{'content': todo_content}]
+                }
+            },
+            metadata={},
+            timestamp=datetime.now()
+        )
+        
+        result = hook.execute(context)
+        
+        if result.success and result.modified:
+            new_content = result.data['parameters']['todos'][0]['content']
+            print(f"  '{todo_content[:40]:40}' -> '{new_content}'")
+        else:
+            print(f"  '{todo_content[:40]:40}' -> Error: {result.error[:30]}...")
+    
+    # Test preservation of existing prefixes
+    print("\nPreservation of existing prefixes:")
+    prefixed_todos = [
+        "[Research] Analyze patterns",
+        "[Version Control] Create release",
+        "[Data Engineer] Build pipeline",
+    ]
+    
+    for todo_content in prefixed_todos:
+        context = HookContext(
+            hook_type=HookType.CUSTOM,
+            data={
+                'tool_name': 'TodoWrite',
+                'parameters': {
+                    'todos': [{'content': todo_content}]
+                }
+            },
+            metadata={},
+            timestamp=datetime.now()
+        )
+        
+        result = hook.execute(context)
+        
+        status = "Not modified" if not result.modified else "Modified"
+        print(f"  '{todo_content}' -> {status}")
+
+
+def demonstrate_color_coding():
+    """Demonstrate agent color coding."""
+    print_section("Agent Color Coding")
+    
+    print("\nColorized agent names:")
+    agents = ["Research", "Engineer", "QA", "Security", "Documentation", 
+              "Ops", "Version Control", "Data Engineer", "Architect", "PM"]
+    
+    for agent in agents:
+        colorized = AgentNameNormalizer.colorize(agent)
+        print(f"  {colorized}")
+    
+    print("\nColorized with custom text:")
+    colorized = AgentNameNormalizer.colorize("research", "[Research] Analyze patterns")
+    print(f"  {colorized}")
+
+
+def demonstrate_error_cases():
+    """Demonstrate error handling."""
+    print_section("Error Handling")
+    
+    # Unknown agents
+    print("\nHandling unknown agents:")
+    unknown = ["unknown_agent", "random", "xyz", ""]
+    for agent in unknown:
+        normalized = AgentNameNormalizer.normalize(agent)
+        print(f"  '{agent:20}' -> '{normalized}' (fallback)")
+    
+    # Invalid TODO formats
+    validator = TodoAgentPrefixValidatorHook()
+    
+    print("\nValidating invalid TODO formats:")
+    invalid_todos = [
+        "No prefix here",
+        "[Unknown] Invalid agent",
+        "[] Empty brackets",
+        "[Research] [Engineer] Multiple prefixes?",
+    ]
+    
+    for todo_content in invalid_todos:
+        context = HookContext(
+            hook_type=HookType.CUSTOM,
+            data={
+                'tool_name': 'TodoWrite',
+                'parameters': {
+                    'todos': [{'content': todo_content}]
+                }
+            },
+            metadata={},
+            timestamp=datetime.now()
+        )
+        
+        result = validator.execute(context)
+        
+        if not result.success:
+            print(f"  '{todo_content[:30]:30}' -> Error detected")
+
+
+def main():
+    """Run all demonstrations."""
+    print("\n" + "="*60)
+    print(" Agent Name Consistency Demonstration")
+    print(" TodoWrite and Task Tool Integration")
+    print("="*60)
+    
+    demonstrate_agent_normalization()
+    demonstrate_todo_format()
+    demonstrate_task_format_conversion()
+    demonstrate_hook_behavior()
+    demonstrate_color_coding()
+    demonstrate_error_cases()
+    
+    print_section("Summary")
+    print("""
+This demonstration shows that:
+
+1. ✓ TodoWrite accepts bracketed agent names like [Research], [Version Control]
+2. ✓ Task tool can accept both formats:
+   - Capitalized: "Research", "Version Control"
+   - Lowercase with hyphens: "research", "version-control"
+3. ✓ Proper conversion between formats is supported
+4. ✓ Invalid agent names are handled with appropriate errors
+5. ✓ All agent types have consistent naming across the system
+
+The agent name normalization ensures consistency between:
+- TodoWrite prefixes: [Research], [Version Control], [Data Engineer]
+- Task tool formats: research, version-control, data-engineer
+- Display names: Research, Version Control, Data Engineer
+""")
+
+
+if __name__ == "__main__":
+    main()

claude_mpm-1.0.0/scripts/test_agent_name_formats.py

@@ -0,0 +1,82 @@
+#!/usr/bin/env python3
+"""Test script to verify agent name normalization functionality."""
+
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'src'))
+
+from claude_mpm.core.agent_name_normalizer import AgentNameNormalizer
+
+def test_agent_name_formats():
+    """Test various agent name format conversions."""
+    normalizer = AgentNameNormalizer()
+    
+    print("Testing Agent Name Format Conversions")
+    print("=" * 50)
+    
+    # Test cases mapping TodoWrite format to Task format
+    test_cases = [
+        ("Research", "research"),
+        ("Engineer", "engineer"),
+        ("QA", "qa"),
+        ("Documentation", "documentation"),
+        ("Security", "security"),
+        ("Ops", "ops"),
+        ("Version Control", "version-control"),
+        ("Data Engineer", "data-engineer"),
+        # Also test lowercase inputs
+        ("research", "research"),
+        ("version-control", "version-control"),
+        ("data-engineer", "data-engineer"),
+    ]
+    
+    print("\nTodoWrite Format → Task Format:")
+    print("-" * 50)
+    
+    all_passed = True
+    for todo_format, expected_task_format in test_cases:
+        actual = normalizer.to_task_format(todo_format)
+        status = "✓" if actual == expected_task_format else "✗"
+        
+        if actual != expected_task_format:
+            all_passed = False
+            
+        print(f"{status} '{todo_format}' → '{actual}' (expected: '{expected_task_format}')")
+    
+    print("\n" + "-" * 50)
+    
+    # Test reverse conversion
+    print("\nTask Format → TodoWrite Format:")
+    print("-" * 50)
+    
+    reverse_test_cases = [
+        ("research", "Research"),
+        ("engineer", "Engineer"),
+        ("qa", "QA"),
+        ("documentation", "Documentation"),
+        ("security", "Security"),
+        ("ops", "Ops"),
+        ("version-control", "Version Control"),
+        ("data-engineer", "Data Engineer"),
+    ]
+    
+    for task_format, expected_todo_format in reverse_test_cases:
+        actual = normalizer.from_task_format(task_format)
+        status = "✓" if actual == expected_todo_format else "✗"
+        
+        if actual != expected_todo_format:
+            all_passed = False
+            
+        print(f"{status} '{task_format}' → '{actual}' (expected: '{expected_todo_format}')")
+    
+    print("\n" + "=" * 50)
+    
+    if all_passed:
+        print("✅ All tests passed!")
+        return 0
+    else:
+        print("❌ Some tests failed!")
+        return 1
+
+if __name__ == "__main__":
+    sys.exit(test_agent_name_formats())