claude-mpm 5.4.8__tar.gz → 5.4.50__tar.gz

{claude_mpm-5.4.8/src/claude_mpm.egg-info → claude_mpm-5.4.50}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: claude-mpm
-Version: 5.4.8
+Version: 5.4.50
 Summary: Claude Multi-Agent Project Manager - Orchestrate Claude with agent delegation and ticket tracking
 Author-email: Bob Matsuoka <bob@matsuoka.com>
 Maintainer: Claude MPM Team
@@ -49,7 +49,6 @@ Requires-Dist: rich>=13.0.0
 Requires-Dist: questionary>=2.0.0
 Requires-Dist: pyee>=13.0.0
 Requires-Dist: pathspec>=0.11.0
-Requires-Dist: kuzu-memory>=1.1.5
 Provides-Extra: mcp
 Requires-Dist: mcp>=0.1.0; extra == "mcp"
 Requires-Dist: mcp-vector-search>=0.1.0; extra == "mcp"
@@ -101,6 +100,8 @@ Requires-Dist: pymongo>=4.5.0; extra == "data-processing"
 Requires-Dist: redis>=5.0.0; extra == "data-processing"
 Requires-Dist: beautifulsoup4>=4.12.0; extra == "data-processing"
 Requires-Dist: jsonschema>=4.19.0; extra == "data-processing"
+Provides-Extra: memory
+Requires-Dist: kuzu-memory>=1.1.5; extra == "memory"
 Dynamic: license-file
 
 # Claude MPM - Multi-Agent Project Manager
@@ -246,17 +247,28 @@ claude --version
 # Basic installation
 pip install claude-mpm
 
+# Or with uv (faster)
+uv tool install claude-mpm
+
 # Install with monitoring dashboard (recommended)
 pip install "claude-mpm[monitor]"
+uv tool install "claude-mpm[monitor]"
 ```
 
-Or with pipx (recommended for isolated installation):
+Or with pipx/uvx (recommended for isolated installation):
 ```bash
 # Basic installation
 pipx install claude-mpm
 
+# Or with uv tool (permanent installation)
+uv tool install claude-mpm
+
+# Or with uvx (one-off execution)
+uvx claude-mpm
+
 # Install with monitoring dashboard (recommended)
 pipx install "claude-mpm[monitor]"
+uv tool install "claude-mpm[monitor]"
 ```
 
 ### Verify Installation
@@ -308,6 +320,8 @@ Claude MPM works excellently with these complementary MCP tools. While optional,
 **Installation:**
 ```bash
 pipx install kuzu-memory
+# Or with uv
+uv tool install kuzu-memory
 ```
 
 **Benefits with Claude MPM:**
@@ -330,6 +344,8 @@ pipx install kuzu-memory
 **Installation:**
 ```bash
 pipx install mcp-vector-search
+# Or with uv
+uv tool install mcp-vector-search
 ```
 
 **Benefits with Claude MPM:**
@@ -354,6 +370,10 @@ Install both recommended tools in one go:
 ```bash
 pipx install kuzu-memory
 pipx install mcp-vector-search
+
+# Or with uv
+uv tool install kuzu-memory
+uv tool install mcp-vector-search
 ```
 
 Then verify they're working:
@@ -368,12 +388,12 @@ claude-mpm verify
 
 ## Cache Management
 
-Claude MPM maintains a local cache of agent templates at `~/.claude-mpm/cache/remote-agents/`.
+Claude MPM maintains a local cache of agent templates at `~/.claude-mpm/cache/agents/`.
 
 ### Cache Structure
 
 ```
-~/.claude-mpm/cache/remote-agents/
+~/.claude-mpm/cache/agents/
 └── bobmatnyc/
     └── claude-mpm-agents/
         ├── .git/              # Git repository
@@ -381,6 +401,8 @@ Claude MPM maintains a local cache of agent templates at `~/.claude-mpm/cache/re
         └── docs/
 ```
 
+> **Note**: Prior to v5.4.23, agents were cached to `~/.claude-mpm/cache/remote-agents/`. This has been standardized to `~/.claude-mpm/cache/agents/`. Existing caches are automatically migrated.
+
 ### Git Workflow (Optional)
 
 If your cache is a git repository, you can manage agents with git operations:
@@ -716,7 +738,19 @@ Claude MPM includes 15 specialized agents:
 - **Code Analyzer** - Static code analysis with AST and tree-sitter
 
 ### Agent Memory System
-Agents learn project-specific patterns using a simple list format and can update memories via JSON response fields (`remember` for incremental updates, `MEMORIES` for complete replacement). Initialize with `claude-mpm memory init`.
+
+**NEW in v5.4.13**: Runtime memory loading for instant updates and better efficiency.
+
+**How It Works:**
+- **Memory Files**: Store agent memories in `.claude-mpm/memories/{agent_id}.md` (e.g., `engineer.md`, `qa.md`)
+- **Runtime Loading**: Memories loaded dynamically when agents are delegated to (no restart required)
+- **Instant Updates**: Memory changes take effect immediately
+- **Event Observability**: Memory loading tracked via EventBus (`agent.memory.loaded` events)
+
+**Memory Format:**
+Agents learn project-specific patterns using a simple markdown list format and can update memories via JSON response fields (`remember` for incremental updates, `MEMORIES` for complete replacement).
+
+**See:** [Memory Flow Architecture](docs/architecture/memory-flow.md) for complete technical details.
 
 ### Skills System
 

{claude_mpm-5.4.8 → claude_mpm-5.4.50}/README.md

@@ -141,17 +141,28 @@ claude --version
 # Basic installation
 pip install claude-mpm
 
+# Or with uv (faster)
+uv tool install claude-mpm
+
 # Install with monitoring dashboard (recommended)
 pip install "claude-mpm[monitor]"
+uv tool install "claude-mpm[monitor]"
 ```
 
-Or with pipx (recommended for isolated installation):
+Or with pipx/uvx (recommended for isolated installation):
 ```bash
 # Basic installation
 pipx install claude-mpm
 
+# Or with uv tool (permanent installation)
+uv tool install claude-mpm
+
+# Or with uvx (one-off execution)
+uvx claude-mpm
+
 # Install with monitoring dashboard (recommended)
 pipx install "claude-mpm[monitor]"
+uv tool install "claude-mpm[monitor]"
 ```
 
 ### Verify Installation
@@ -203,6 +214,8 @@ Claude MPM works excellently with these complementary MCP tools. While optional,
 **Installation:**
 ```bash
 pipx install kuzu-memory
+# Or with uv
+uv tool install kuzu-memory
 ```
 
 **Benefits with Claude MPM:**
@@ -225,6 +238,8 @@ pipx install kuzu-memory
 **Installation:**
 ```bash
 pipx install mcp-vector-search
+# Or with uv
+uv tool install mcp-vector-search
 ```
 
 **Benefits with Claude MPM:**
@@ -249,6 +264,10 @@ Install both recommended tools in one go:
 ```bash
 pipx install kuzu-memory
 pipx install mcp-vector-search
+
+# Or with uv
+uv tool install kuzu-memory
+uv tool install mcp-vector-search
 ```
 
 Then verify they're working:
@@ -263,12 +282,12 @@ claude-mpm verify
 
 ## Cache Management
 
-Claude MPM maintains a local cache of agent templates at `~/.claude-mpm/cache/remote-agents/`.
+Claude MPM maintains a local cache of agent templates at `~/.claude-mpm/cache/agents/`.
 
 ### Cache Structure
 
 ```
-~/.claude-mpm/cache/remote-agents/
+~/.claude-mpm/cache/agents/
 └── bobmatnyc/
     └── claude-mpm-agents/
         ├── .git/              # Git repository
@@ -276,6 +295,8 @@ Claude MPM maintains a local cache of agent templates at `~/.claude-mpm/cache/re
         └── docs/
 ```
 
+> **Note**: Prior to v5.4.23, agents were cached to `~/.claude-mpm/cache/remote-agents/`. This has been standardized to `~/.claude-mpm/cache/agents/`. Existing caches are automatically migrated.
+
 ### Git Workflow (Optional)
 
 If your cache is a git repository, you can manage agents with git operations:
@@ -611,7 +632,19 @@ Claude MPM includes 15 specialized agents:
 - **Code Analyzer** - Static code analysis with AST and tree-sitter
 
 ### Agent Memory System
-Agents learn project-specific patterns using a simple list format and can update memories via JSON response fields (`remember` for incremental updates, `MEMORIES` for complete replacement). Initialize with `claude-mpm memory init`.
+
+**NEW in v5.4.13**: Runtime memory loading for instant updates and better efficiency.
+
+**How It Works:**
+- **Memory Files**: Store agent memories in `.claude-mpm/memories/{agent_id}.md` (e.g., `engineer.md`, `qa.md`)
+- **Runtime Loading**: Memories loaded dynamically when agents are delegated to (no restart required)
+- **Instant Updates**: Memory changes take effect immediately
+- **Event Observability**: Memory loading tracked via EventBus (`agent.memory.loaded` events)
+
+**Memory Format:**
+Agents learn project-specific patterns using a simple markdown list format and can update memories via JSON response fields (`remember` for incremental updates, `MEMORIES` for complete replacement).
+
+**See:** [Memory Flow Architecture](docs/architecture/memory-flow.md) for complete technical details.
 
 ### Skills System
 

{claude_mpm-5.4.8 → claude_mpm-5.4.50}/pyproject.toml

@@ -4,13 +4,13 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "claude-mpm"
-version = "5.4.8"
+version = "5.4.50"
 description = "Claude Multi-Agent Project Manager - Orchestrate Claude with agent delegation and ticket tracking"
 readme = "README.md"
 requires-python = ">=3.11"
 keywords = [ "claude", "orchestration", "multi-agent", "ticket-management",]
 classifiers = [ "Development Status :: 3 - Alpha", "Intended Audience :: Developers", "License :: Other/Proprietary License", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.11", "Programming Language :: Python :: 3.12", "Programming Language :: Python :: 3.13",]
-dependencies = [ "ai-trackdown-pytools>=1.4.0", "pyyaml>=6.0", "python-dotenv>=0.19.0", "click>=8.0.0", "pexpect>=4.8.0", "psutil>=5.9.0", "requests>=2.25.0", "flask>=3.0.0", "flask-cors>=4.0.0", "watchdog>=3.0.0", "python-socketio>=5.14.0", "aiohttp>=3.9.0", "aiohttp-cors>=0.7.0,<0.8.0", "python-engineio>=4.8.0", "aiofiles>=23.0.0", "websockets>=12.0", "python-frontmatter>=1.0.0", "mistune>=3.0.0", "tree-sitter>=0.21.0", "ijson>=3.2.0", "toml>=0.10.2", "packaging>=21.0", "pydantic>=2.0.0", "pydantic-settings>=2.0.0", "rich>=13.0.0", "questionary>=2.0.0", "pyee>=13.0.0", "pathspec>=0.11.0", "kuzu-memory>=1.1.5",]
+dependencies = [ "ai-trackdown-pytools>=1.4.0", "pyyaml>=6.0", "python-dotenv>=0.19.0", "click>=8.0.0", "pexpect>=4.8.0", "psutil>=5.9.0", "requests>=2.25.0", "flask>=3.0.0", "flask-cors>=4.0.0", "watchdog>=3.0.0", "python-socketio>=5.14.0", "aiohttp>=3.9.0", "aiohttp-cors>=0.7.0,<0.8.0", "python-engineio>=4.8.0", "aiofiles>=23.0.0", "websockets>=12.0", "python-frontmatter>=1.0.0", "mistune>=3.0.0", "tree-sitter>=0.21.0", "ijson>=3.2.0", "toml>=0.10.2", "packaging>=21.0", "pydantic>=2.0.0", "pydantic-settings>=2.0.0", "rich>=13.0.0", "questionary>=2.0.0", "pyee>=13.0.0", "pathspec>=0.11.0",]
 [[project.authors]]
 name = "Bob Matsuoka"
 email = "bob@matsuoka.com"
@@ -36,21 +36,20 @@ eval = [ "deepeval>=1.0.0", "pytest>=7.4.0", "pytest-asyncio>=0.21.0", "pytest-t
 docs = [ "sphinx>=7.2.0", "sphinx-rtd-theme>=1.3.0", "sphinx-autobuild>=2021.3.14",]
 monitor = [ "python-socketio>=5.14.0", "aiohttp>=3.9.0", "aiohttp-cors>=0.7.0,<0.8.0", "python-engineio>=4.8.0", "aiofiles>=23.0.0", "websockets>=12.0",]
 data-processing = [ "pandas>=2.1.0", "openpyxl>=3.1.0", "xlsxwriter>=3.1.0", "numpy>=1.24.0", "pyarrow>=14.0.0", "dask>=2023.12.0", "polars>=0.19.0", "xlrd>=2.0.0", "xlwt>=1.3.0", "csvkit>=1.3.0", "tabulate>=0.9.0", "python-dateutil>=2.8.0", "lxml>=4.9.0", "sqlalchemy>=2.0.0", "psycopg2-binary>=2.9.0", "pymongo>=4.5.0", "redis>=5.0.0", "beautifulsoup4>=4.12.0", "jsonschema>=4.19.0",]
+# KuzuMemory requires cmake to build - optional for users who want graph-based memory
+memory = [ "kuzu-memory>=1.1.5",]
 
 [project.scripts]
 claude-mpm = "claude_mpm.cli:main"
-claude-mpm-ticket = "claude_mpm.cli.ticket_cli:main"
-ticket = "claude_mpm.cli.ticket_cli:main"
-claude-mpm-version = "claude_mpm.scripts.manage_version:main"
+claude-mpm-doctor = "claude_mpm.scripts.mpm_doctor:main"
 claude-mpm-monitor = "claude_mpm.scripts.launch_monitor:main"
 claude-mpm-socketio = "claude_mpm.scripts.socketio_daemon:main"
 # DEPRECATED: MCP gateway archived 2025-12-11
 # claude-mpm-mcp = "claude_mpm.services.mcp_gateway.server.stdio_server:main_sync"
 # claude-mpm-mcp-wrapper = "claude_mpm.scripts.mcp_wrapper:entry_point"
-claude-mpm-doctor = "claude_mpm.scripts.mpm_doctor:main"
 
-[tool.uv]
-dev-dependencies = [ "pytest>=7.0", "pytest-asyncio", "pytest-cov", "ruff>=0.8.0", "mypy>=1.0.0", "types-PyYAML>=6.0.0", "types-requests>=2.25.0",]
+[dependency-groups]
+dev = [ "pytest>=7.0", "pytest-asyncio", "pytest-cov", "ruff>=0.8.0", "mypy>=1.0.0", "types-PyYAML>=6.0.0", "types-requests>=2.25.0",]
 
 [tool.mypy]
 python_version = "3.11"
@@ -190,14 +189,14 @@ ignore-imports = false
 
 [tool.commitizen]
 name = "cz_conventional_commits"
-version = "5.4.8"
+version = "5.4.49"
 version_files = [ "VERSION", "src/claude_mpm/VERSION", "package.json:version",]
 tag_format = "v$version"
 update_changelog_on_bump = true
 changelog_incremental = true
 
 [tool.setuptools.package-data]
-claude_mpm = [ "VERSION", "BUILD_NUMBER", "scripts/*", "scripts/*.sh", "commands/*.md", "skills/bundled/*.md", "dashboard/*.html", "dashboard/templates/*.html", "dashboard/static/*.css", "dashboard/static/*.js", "dashboard/static/css/*.css", "dashboard/static/js/*.js", "dashboard/static/js/components/*.js", "agents/*.md", "agents/*.json", "agents/*.yaml", "agents/templates/*.json", "agents/templates/*.md", "agents/schema/*.json", "hooks/**/*.py", "hooks/**/*.sh", "hooks/claude_hooks/*", "hooks/claude_hooks/**/*",]
+claude_mpm = [ "VERSION", "BUILD_NUMBER", "scripts/*", "scripts/*.sh", "commands/*.md", "skills/bundled/*.md", "dashboard/*.html", "dashboard/templates/*.html", "dashboard/static/*.css", "dashboard/static/*.js", "dashboard/static/css/*.css", "dashboard/static/js/*.js", "dashboard/static/js/components/*.js", "dashboard/static/svelte-build/**/*", "agents/*.md", "agents/*.json", "agents/*.yaml", "agents/templates/*.json", "agents/templates/*.md", "agents/schema/*.json", "hooks/**/*.py", "hooks/**/*.sh", "hooks/claude_hooks/*", "hooks/claude_hooks/**/*",]
 
 [tool.pytest.ini_options]
 testpaths = [ "tests",]

claude_mpm-5.4.50/src/claude_mpm/VERSION

@@ -0,0 +1 @@
+5.4.49

claude_mpm-5.4.50/src/claude_mpm/agents/BASE_AGENT.md

@@ -0,0 +1,164 @@
+# Base Agent Instructions (Root Level)
+
+> This file is automatically appended to ALL agent definitions in the repository.
+> It contains universal instructions that apply to every agent regardless of type.
+
+## Git Workflow Standards
+
+All agents should follow these git protocols:
+
+### Before Modifications
+- Review file commit history: `git log --oneline -5 <file_path>`
+- Understand previous changes and context
+- Check for related commits or patterns
+
+### Commit Messages
+- Write succinct commit messages explaining WHAT changed and WHY
+- Follow conventional commits format: `feat/fix/docs/refactor/perf/test/chore`
+- Examples:
+  - `feat: add user authentication service`
+  - `fix: resolve race condition in async handler`
+  - `refactor: extract validation logic to separate module`
+  - `perf: optimize database query with indexing`
+  - `test: add integration tests for payment flow`
+
+### Commit Best Practices
+- Keep commits atomic (one logical change per commit)
+- Reference issue numbers when applicable: `feat: add OAuth support (#123)`
+- Explain WHY, not just WHAT (the diff shows what)
+
+## Memory Routing
+
+All agents participate in the memory system:
+
+### Memory Categories
+- Domain-specific knowledge and patterns
+- Anti-patterns and common mistakes
+- Best practices and conventions
+- Project-specific constraints
+
+### Memory Keywords
+Each agent defines keywords that trigger memory storage for relevant information.
+
+## Output Format Standards
+
+### Structure
+- Use markdown formatting for all responses
+- Include clear section headers
+- Provide code examples where applicable
+- Add comments explaining complex logic
+
+### Analysis Sections
+When providing analysis, include:
+- **Objective**: What needs to be accomplished
+- **Approach**: How it will be done
+- **Trade-offs**: Pros and cons of chosen approach
+- **Risks**: Potential issues and mitigation strategies
+
+### Code Sections
+When providing code:
+- Include file path as header: `## path/to/file.py`
+- Add inline comments for non-obvious logic
+- Show usage examples for new APIs
+- Document error handling approaches
+
+## Handoff Protocol
+
+When completing work that requires another agent:
+
+### Handoff Information
+- Clearly state which agent should continue
+- Summarize what was accomplished
+- List remaining tasks for next agent
+- Include relevant context and constraints
+
+### Common Handoff Flows
+- Engineer → QA: After implementation, for testing
+- Engineer → Security: After auth/crypto changes
+- Engineer → Documentation: After API changes
+- QA → Engineer: After finding bugs
+- Any → Research: When investigation needed
+
+## Proactive Code Quality Improvements
+
+### Search Before Implementing
+Before creating new code, ALWAYS search the codebase for existing implementations:
+- Use grep/glob to find similar functionality: `grep -r "relevant_pattern" src/`
+- Check for existing utilities, helpers, and shared components
+- Look in standard library and framework features first
+- **Report findings**: "✅ Found existing [component] at [path]. Reusing instead of duplicating."
+- **If nothing found**: "✅ Verified no existing implementation. Creating new [component]."
+
+### Mimic Local Patterns and Naming Conventions
+Follow established project patterns unless they represent demonstrably harmful practices:
+- **Detect patterns**: naming conventions, file structure, error handling, testing approaches
+- **Match existing style**: If project uses `camelCase`, use `camelCase`. If `snake_case`, use `snake_case`.
+- **Respect project structure**: Place files where similar files exist
+- **When patterns are harmful**: Flag with "⚠️ Pattern Concern: [issue]. Suggest: [improvement]. Implement current pattern or improved version?"
+
+### Suggest Improvements When Issues Are Seen
+Proactively identify and suggest improvements discovered during work:
+- **Format**:
+  ```
+  💡 Improvement Suggestion
+  Found: [specific issue with file:line]
+  Impact: [security/performance/maintainability/etc.]
+  Suggestion: [concrete fix]
+  Effort: [Small/Medium/Large]
+  ```
+- **Ask before implementing**: "Want me to fix this while I'm here?"
+- **Limit scope creep**: Maximum 1-2 suggestions per task unless critical (security/data loss)
+- **Critical issues**: Security vulnerabilities and data loss risks should be flagged immediately regardless of limit
+
+## Agent Responsibilities
+
+### What Agents DO
+- Execute tasks within their domain expertise
+- Follow best practices and patterns
+- Provide clear, actionable outputs
+- Report blockers and uncertainties
+- Validate assumptions before proceeding
+- Document decisions and trade-offs
+
+### What Agents DO NOT
+- Work outside their defined domain
+- Make assumptions without validation
+- Skip error handling or edge cases
+- Ignore established patterns
+- Proceed when blocked or uncertain
+
+## Quality Standards
+
+### All Work Must Include
+- Clear documentation of approach
+- Consideration of edge cases
+- Error handling strategy
+- Testing approach (for code changes)
+- Performance implications (if applicable)
+
+### Before Declaring Complete
+- All requirements addressed
+- No obvious errors or gaps
+- Appropriate tests identified
+- Documentation provided
+- Handoff information clear
+
+## Communication Standards
+
+### Clarity
+- Use precise technical language
+- Define domain-specific terms
+- Provide examples for complex concepts
+- Ask clarifying questions when uncertain
+
+### Brevity
+- Be concise but complete
+- Avoid unnecessary repetition
+- Focus on actionable information
+- Omit obvious explanations
+
+### Transparency
+- Acknowledge limitations
+- Report uncertainties clearly
+- Explain trade-off decisions
+- Surface potential issues early

{claude_mpm-5.4.8 → claude_mpm-5.4.50}/src/claude_mpm/agents/CLAUDE_MPM_TEACHER_OUTPUT_STYLE.md

@@ -1495,7 +1495,7 @@ MPM couldn't find an agent named "custom-agent". This usually means:
 **Let's Debug Together**:
 1. Does `.claude/agents/custom-agent.md` exist?
 2. Check the frontmatter - is `name: custom-agent` correct?
-3. Run: `mpm-agents-list` - does custom-agent appear?
+3. Run: `/mpm-configure` and check available agents - does custom-agent appear?
 
 Based on your answers, I'll help you fix it!
 

{claude_mpm-5.4.8 → claude_mpm-5.4.50}/src/claude_mpm/agents/MEMORY.md

@@ -30,7 +30,7 @@ This system provides **Static Memory** support where you (PM) directly manage me
 
 **When memory indicators detected**:
 1. **Identify** which agent should store this knowledge
-2. **Read** current memory file: `.claude-mpm/memories/{agent_id}_agent.md`
+2. **Read** current memory file: `.claude-mpm/memories/{agent_name}.md`
 3. **Consolidate** new information with existing content
 4. **Write** updated memory file maintaining structure and limits
 5. **Confirm** to user: "Updated {agent} memory with: [brief summary]"