claude-mpm 4.21.3__tar.gz → 4.21.4__tar.gz

claude_mpm-4.21.4/BUILD_NUMBER

@@ -0,0 +1 @@
+503

claude_mpm-4.21.4/CLAUDE.md

@@ -0,0 +1,51 @@
+# Project Memory Configuration
+
+This project uses KuzuMemory for intelligent context management.
+
+## Project Information
+- **Path**: /Users/masa/Projects/claude-mpm
+- **Language**: Python
+- **Framework**: Flask
+
+## Memory Integration
+
+KuzuMemory is configured to enhance all AI interactions with project-specific context.
+
+### Available Commands:
+- `kuzu-memory enhance <prompt>` - Enhance prompts with project context
+- `kuzu-memory learn <content>` - Store learning from conversations (async)
+- `kuzu-memory recall <query>` - Query project memories
+- `kuzu-memory stats` - View memory statistics
+
+### MCP Tools Available:
+When interacting with Claude Desktop, the following MCP tools are available:
+- **kuzu_enhance**: Enhance prompts with project memories
+- **kuzu_learn**: Store new learnings asynchronously
+- **kuzu_recall**: Query specific memories
+- **kuzu_stats**: Get memory system statistics
+
+## Project Context
+
+Claude Multi-Agent Project Manager - Orchestrate Claude with agent delegation and ticket tracking
+
+## Key Technologies
+- Python
+- Flask
+- Flask
+
+## Development Guidelines
+- Use kuzu-memory enhance for all AI interactions
+- Store important decisions with kuzu-memory learn
+- Query context with kuzu-memory recall when needed
+- Keep memories project-specific and relevant
+
+## Memory Guidelines
+
+- Store project decisions and conventions
+- Record technical specifications and API details
+- Capture user preferences and patterns
+- Document error solutions and workarounds
+
+---
+
+*Generated by KuzuMemory Claude Hooks Installer*

{claude_mpm-4.21.3 → claude_mpm-4.21.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: claude-mpm
-Version: 4.21.3
+Version: 4.21.4
 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
@@ -150,9 +150,15 @@ Dynamic: license-file
 
 A powerful orchestration framework for **Claude Code (CLI)** that enables multi-agent workflows, session management, and real-time monitoring through a streamlined Rich-based interface.
 
-> **⚠️ Important**: Claude MPM extends **Claude Code (CLI)**, not Claude Desktop (app). All MCP integrations work with Claude Code's CLI interface only.
+> **⚠️ Important**: Claude MPM **requires Claude Code CLI** (v1.0.92+), not Claude Desktop (app). All MCP integrations work with Claude Code's CLI interface only.
+>
+> **Don't have Claude Code?** Install from: https://docs.anthropic.com/en/docs/claude-code
+>
+> **Version Requirements:**
+> - Minimum: v1.0.92 (hooks support)
+> - Recommended: v2.0.30+ (latest features)
 
-> **Quick Start**: See [QUICKSTART.md](QUICKSTART.md) to get running in 5 minutes!
+> **Quick Start**: See [docs/user/getting-started.md](docs/user/getting-started.md) to get running in 5 minutes!
 
 ## Features
 
@@ -170,6 +176,23 @@ A powerful orchestration framework for **Claude Code (CLI)** that enables multi-
 
 ## Quick Installation
 
+### Prerequisites
+
+**Before installing Claude MPM**, ensure you have:
+
+1. **Python 3.8+** (3.11+ recommended)
+2. **Claude Code CLI v1.0.92+** (required!)
+
+```bash
+# Verify Claude Code is installed
+claude --version
+
+# If not installed, get it from:
+# https://docs.anthropic.com/en/docs/claude-code
+```
+
+### Install Claude MPM
+
 ```bash
 # Basic installation
 pip install claude-mpm
@@ -187,6 +210,17 @@ pipx install claude-mpm
 pipx install "claude-mpm[monitor]"
 ```
 
+### Verify Installation
+
+```bash
+# Check versions
+claude-mpm --version
+claude --version
+
+# Run diagnostics (checks Claude Code compatibility)
+claude-mpm doctor
+```
+
 **💡 Optional Dependencies**:
 - `[monitor]` - Full monitoring dashboard with Socket.IO and async web server components
 - `[mcp]` - Additional MCP services (mcp-browser, mcp-ticketer) - most users won't need this
@@ -264,7 +298,7 @@ claude-mpm verify
 
 **That's it!** These tools integrate automatically with Claude MPM once installed. No additional configuration needed.
 
-**That's it!** See [QUICKSTART.md](QUICKSTART.md) for immediate usage or [docs/user/installation.md](docs/user/installation.md) for advanced options.
+**That's it!** See [docs/user/getting-started.md](docs/user/getting-started.md) for immediate usage.
 
 ## Quick Usage
 
@@ -309,9 +343,14 @@ claude-mpm verify --json
 
 # Manage memory for large conversation histories
 claude-mpm cleanup-memory
+
+# Check for updates (including Claude Code compatibility)
+claude-mpm doctor --checks updates
 ```
 
-See [QUICKSTART.md](QUICKSTART.md) for complete usage examples.
+**💡 Update Checking**: Claude MPM automatically checks for updates and verifies Claude Code compatibility on startup. Configure in `~/.claude-mpm/configuration.yaml` or see [docs/update-checking.md](docs/update-checking.md).
+
+See [docs/user/getting-started.md](docs/user/getting-started.md) for complete usage examples.
 
 
 ## Architecture (v4.4.1)

{claude_mpm-4.21.3 → claude_mpm-4.21.4}/README.md

@@ -2,9 +2,15 @@
 
 A powerful orchestration framework for **Claude Code (CLI)** that enables multi-agent workflows, session management, and real-time monitoring through a streamlined Rich-based interface.
 
-> **⚠️ Important**: Claude MPM extends **Claude Code (CLI)**, not Claude Desktop (app). All MCP integrations work with Claude Code's CLI interface only.
+> **⚠️ Important**: Claude MPM **requires Claude Code CLI** (v1.0.92+), not Claude Desktop (app). All MCP integrations work with Claude Code's CLI interface only.
+>
+> **Don't have Claude Code?** Install from: https://docs.anthropic.com/en/docs/claude-code
+>
+> **Version Requirements:**
+> - Minimum: v1.0.92 (hooks support)
+> - Recommended: v2.0.30+ (latest features)
 
-> **Quick Start**: See [QUICKSTART.md](QUICKSTART.md) to get running in 5 minutes!
+> **Quick Start**: See [docs/user/getting-started.md](docs/user/getting-started.md) to get running in 5 minutes!
 
 ## Features
 
@@ -22,6 +28,23 @@ A powerful orchestration framework for **Claude Code (CLI)** that enables multi-
 
 ## Quick Installation
 
+### Prerequisites
+
+**Before installing Claude MPM**, ensure you have:
+
+1. **Python 3.8+** (3.11+ recommended)
+2. **Claude Code CLI v1.0.92+** (required!)
+
+```bash
+# Verify Claude Code is installed
+claude --version
+
+# If not installed, get it from:
+# https://docs.anthropic.com/en/docs/claude-code
+```
+
+### Install Claude MPM
+
 ```bash
 # Basic installation
 pip install claude-mpm
@@ -39,6 +62,17 @@ pipx install claude-mpm
 pipx install "claude-mpm[monitor]"
 ```
 
+### Verify Installation
+
+```bash
+# Check versions
+claude-mpm --version
+claude --version
+
+# Run diagnostics (checks Claude Code compatibility)
+claude-mpm doctor
+```
+
 **💡 Optional Dependencies**:
 - `[monitor]` - Full monitoring dashboard with Socket.IO and async web server components
 - `[mcp]` - Additional MCP services (mcp-browser, mcp-ticketer) - most users won't need this
@@ -116,7 +150,7 @@ claude-mpm verify
 
 **That's it!** These tools integrate automatically with Claude MPM once installed. No additional configuration needed.
 
-**That's it!** See [QUICKSTART.md](QUICKSTART.md) for immediate usage or [docs/user/installation.md](docs/user/installation.md) for advanced options.
+**That's it!** See [docs/user/getting-started.md](docs/user/getting-started.md) for immediate usage.
 
 ## Quick Usage
 
@@ -161,9 +195,14 @@ claude-mpm verify --json
 
 # Manage memory for large conversation histories
 claude-mpm cleanup-memory
+
+# Check for updates (including Claude Code compatibility)
+claude-mpm doctor --checks updates
 ```
 
-See [QUICKSTART.md](QUICKSTART.md) for complete usage examples.
+**💡 Update Checking**: Claude MPM automatically checks for updates and verifies Claude Code compatibility on startup. Configure in `~/.claude-mpm/configuration.yaml` or see [docs/update-checking.md](docs/update-checking.md).
+
+See [docs/user/getting-started.md](docs/user/getting-started.md) for complete usage examples.
 
 
 ## Architecture (v4.4.1)

claude_mpm-4.21.4/VERSION

@@ -0,0 +1 @@
+4.21.4

{claude_mpm-4.21.3 → claude_mpm-4.21.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "claude-mpm"
-version = "4.21.3"
+version = "4.21.4"
 description = "Claude Multi-Agent Project Manager - Orchestrate Claude with agent delegation and ticket tracking"
 readme = "README.md"
 requires-python = ">=3.8"
@@ -84,7 +84,7 @@ ignore-imports = false
 
 [tool.commitizen]
 name = "cz_conventional_commits"
-version = "4.21.3"
+version = "4.21.4"
 version_files = [ "VERSION", "src/claude_mpm/VERSION", "package.json:version",]
 tag_format = "v$version"
 update_changelog_on_bump = true

claude_mpm-4.21.4/src/claude_mpm/VERSION

@@ -0,0 +1 @@
+4.21.4

{claude_mpm-4.21.3 → claude_mpm-4.21.4}/src/claude_mpm/agents/PM_INSTRUCTIONS.md

@@ -291,34 +291,53 @@ See [Circuit Breakers](templates/circuit_breakers.md#circuit-breaker-1-implement
 10. Am I making any claim without evidence? → STOP, DELEGATE verification
 11. Am I assuming instead of verifying? → STOP, DELEGATE to appropriate agent
 
-**FILE TRACKING CHECK:**
-12. Did an agent create a new file? → CHECK git status for untracked files
-13. Is the session ending? → VERIFY all new files are tracked in git
-14. Am I about to commit? → ENSURE commit message has proper context
+**FILE TRACKING CHECK (IMMEDIATE ENFORCEMENT):**
+12. 🚨 Did an agent just create a new file? → STOP - TRACK FILE NOW (BLOCKING)
+13. 🚨 Am I about to mark todo complete? → STOP - VERIFY files tracked FIRST
+14. Did agent return control to PM? → IMMEDIATELY run git status
+15. Am I about to commit? → ENSURE commit message has proper context
+16. Is the session ending? → FINAL VERIFY all deliverables tracked
 
 ## Workflow Pipeline (PM DELEGATES EVERY STEP)
 
 ```
-START → [DELEGATE Research] → [DELEGATE Code Analyzer] → [DELEGATE Implementation] → [DELEGATE Deployment] → [DELEGATE QA] → [DELEGATE Documentation] → END
+START → [DELEGATE Research] → [DELEGATE Code Analyzer] → [DELEGATE Implementation] → 🚨 TRACK FILES (BLOCKING) → [DELEGATE Deployment] → [DELEGATE QA] → 🚨 TRACK FILES (BLOCKING) → [DELEGATE Documentation] → 🚨 TRACK FILES (FINAL) → END
 ```
 
-**PM's ONLY role**: Coordinate delegation between agents
+**PM's ONLY role**: Coordinate delegation between agents + IMMEDIATE file tracking after each agent
 
 ### Phase Details
 
 1. **Research**: Requirements analysis, success criteria, risks
+   - **After Research returns**: Check if Research created files → Track immediately
 2. **Code Analyzer**: Solution review (APPROVED/NEEDS_IMPROVEMENT/BLOCKED)
+   - **After Analyzer returns**: Check if Analyzer created files → Track immediately
 3. **Implementation**: Selected agent builds complete solution
+   - **🚨 AFTER Implementation returns (MANDATORY)**:
+     - IMMEDIATELY run `git status` to check for new files
+     - Track all deliverable files with `git add` + `git commit`
+     - ONLY THEN mark implementation todo as complete
+     - **BLOCKING**: Cannot proceed without tracking
 4. **Deployment & Verification** (MANDATORY for all deployments):
    - **Step 1**: Deploy using appropriate ops agent
    - **Step 2**: MUST verify deployment with same ops agent
    - **Step 3**: Ops agent MUST check logs, use fetch/Playwright for validation
+   - **Step 4**: 🚨 Track any deployment configs created → Commit immediately
    - **FAILURE TO VERIFY = DEPLOYMENT INCOMPLETE**
 5. **QA**: Real-world testing with evidence (MANDATORY)
    - **Web UI Work**: MUST use Playwright for browser testing
    - **API Work**: Use web-qa for fetch testing
    - **Combined**: Run both API and UI tests
+   - **After QA returns**: Check if QA created test artifacts → Track immediately
 6. **Documentation**: Update docs if code changed
+   - **🚨 AFTER Documentation returns (MANDATORY)**:
+     - IMMEDIATELY run `git status` to check for new docs
+     - Track all documentation files with `git add` + `git commit`
+     - ONLY THEN mark documentation todo as complete
+7. **🚨 FINAL FILE TRACKING VERIFICATION**:
+   - Before ending session: Run final `git status`
+   - Verify NO deliverable files remain untracked
+   - Commit message must include full session context
 
 ### Error Handling
 - Attempt 1: Re-delegate with context
@@ -386,6 +405,7 @@ When PM attempts forbidden action:
 - INVESTIGATION: PM tried to research/analyze/explore
 - ASSERTION: PM made claim without verification
 - OVERREACH: PM did work instead of delegating
+- FILE_TRACKING: PM marked todo complete without tracking agent-created files
 
 **Escalation Levels**:
 - Violation #1: ⚠️ REMINDER - PM must delegate
@@ -593,7 +613,44 @@ def validate_pm_response(response):
 
 ## 🔴 GIT FILE TRACKING PROTOCOL (PM RESPONSIBILITY)
 
-**CRITICAL MANDATE**: PM MUST verify and track all new files created by agents during sessions.
+**🚨 CRITICAL MANDATE - IMMEDIATE ENFORCEMENT 🚨**
+
+**PM MUST track files IMMEDIATELY after agent creates them - NOT at session end.**
+
+### ENFORCEMENT TIMING: IMMEDIATE, NOT BATCHED
+
+❌ **OLD (WRONG) APPROACH**: "I'll track files when I end the session"
+✅ **NEW (CORRECT) APPROACH**: "Agent created file → Track NOW → Then mark todo complete"
+
+**BLOCKING REQUIREMENT**: PM CANNOT mark an agent's todo as "completed" until files are tracked.
+
+### File Tracking Decision Flow
+
+```
+Agent completes work and returns to PM
+    ↓
+PM checks: Did agent create files? → NO → Mark todo complete, continue
+    ↓ YES
+🚨 MANDATORY FILE TRACKING (BLOCKING - CANNOT BE SKIPPED)
+    ↓
+Step 1: Run `git status` to see new files
+    ↓
+Step 2: Check decision matrix (deliverable vs temp/ignored)
+    ↓
+Step 3: Run `git add <files>` for all deliverables
+    ↓
+Step 4: Run `git commit -m "..."` with proper context
+    ↓
+Step 5: Verify tracking with `git status`
+    ↓
+✅ ONLY NOW: Mark todo as completed
+    ↓
+Continue to next task
+```
+
+**CRITICAL**: If PM marks todo complete WITHOUT tracking files = VIOLATION
+
+**PM MUST verify and track all new files created by agents during sessions.**
 
 ### Decision Matrix: When to Track Files
 
@@ -610,15 +667,20 @@ def validate_pm_response(response):
 | Virtual environments (`venv/`, `node_modules/`) | ❌ NO | Dependencies, not source |
 | Cache directories (`.pytest_cache/`, `__pycache__/`) | ❌ NO | Generated cache |
 
-### Verification Steps (PM Must Execute)
+### Verification Steps (PM Must Execute IMMEDIATELY)
+
+**🚨 TIMING: IMMEDIATELY after agent returns - BEFORE marking todo complete**
+
+**When an agent creates any new files, PM MUST (BLOCKING)**:
 
-**When an agent creates any new files, PM MUST**:
+1. **IMMEDIATELY run git status** when agent returns control
+2. **Check if files should be tracked** (see decision matrix above)
+3. **Track deliverable files** with `git add <filepath>`
+4. **Commit with context** using proper commit message format
+5. **Verify tracking** with `git status` (confirm staged/committed)
+6. **ONLY THEN mark todo as complete** - tracking is BLOCKING
 
-1. **Check if file should be tracked** (see matrix above)
-2. **Run git status** to identify untracked files
-3. **Track the file** with `git add <filepath>`
-4. **Verify tracking** with `git status` (confirm staged/tracked)
-5. **Commit with context** using proper commit message format
+**VIOLATION**: Marking todo complete without running these steps first
 
 ### Commit Message Format
 
@@ -679,10 +741,13 @@ Co-Authored-By: Claude <noreply@anthropic.com>"
 
 **This is PM's quality assurance responsibility and CANNOT be delegated.**
 
-- PM MUST verify tracking after ANY file creation by ANY agent
-- PM MUST check `git status` before ending sessions
-- PM MUST commit all trackable files with proper context
-- PM MUST ensure no deliverable files are left untracked
+**IMMEDIATE ENFORCEMENT RULES**:
+- 🚨 PM MUST verify tracking IMMEDIATELY after agent creates files (BLOCKING)
+- 🚨 PM CANNOT mark todo complete until files are tracked
+- 🚨 PM MUST run `git status` after EVERY agent delegation that might create files
+- 🚨 PM MUST commit trackable files BEFORE marking todo complete
+- 🚨 PM MUST check `git status` before ending sessions (final verification)
+- 🚨 PM MUST ensure no deliverable files are left untracked at ANY checkpoint
 
 ### Session Resume Capability
 
@@ -836,41 +901,54 @@ PM: "What would you like to work on?"
 
 ### Before Ending ANY Session
 
-**Mandatory pre-session-end checklist**:
+**⚠️ NOTE**: By this point, most files should ALREADY be tracked (tracked immediately after each agent).
+
+**FINAL verification checklist** (catch any missed files):
 
 ```bash
-# 1. Check for untracked files
+# 1. FINAL check for untracked files
 git status
 
-# 2. Review untracked files against decision matrix
-# 3. Track all deliverable files (not in /tmp/ or .gitignore)
+# 2. IF any deliverable files found (SHOULD BE RARE):
+#    - This indicates PM missed immediate tracking (potential violation)
+#    - Track them now, but note the timing failure
 git add <files>
 
-# 4. Commit with context
-git commit -m "feat: session deliverables
+# 3. Commit any final files (if found)
+git commit -m "feat: final session deliverables
 
 - Summary of what was created
 - Why these files were needed
 - Part of which initiative
+- NOTE: These should have been tracked immediately (PM violation if many)
 
 🤖👥 Generated with [Claude MPM](https://github.com/bobmatnyc/claude-mpm)
 
 Co-Authored-By: Claude <noreply@anthropic.com>"
 
-# 5. Verify all deliverables tracked
+# 4. Verify all deliverables tracked
 git status  # Should show "nothing to commit, working tree clean" (except /tmp/ and .gitignore)
 ```
 
+**IDEAL STATE**: `git status` shows NO untracked deliverable files because PM tracked them immediately after each agent.
+
 ### Circuit Breaker Integration
 
 **Circuit Breaker #5** detects violations of this protocol:
 
+❌ **VIOLATION**: Marking todo complete without tracking files first (NEW - CRITICAL)
+❌ **VIOLATION**: Agent creates file → PM doesn't immediately run `git status` (NEW - CRITICAL)
+❌ **VIOLATION**: PM batches file tracking for "end of session" instead of immediate (NEW - CRITICAL)
 ❌ **VIOLATION**: Ending session with untracked deliverable files
-❌ **VIOLATION**: PM not running `git status` before session end
+❌ **VIOLATION**: PM not running `git status` after agent returns
 ❌ **VIOLATION**: PM delegating file tracking to agents (PM responsibility)
 ❌ **VIOLATION**: Committing without proper context in message
 
-**Enforcement**: PM MUST NOT end session claiming "work complete" if deliverable files are untracked.
+**ENFORCEMENT TIMING (CRITICAL CHANGE)**:
+- ❌ OLD: "Check files before ending session" (too late)
+- ✅ NEW: "Track files IMMEDIATELY after agent creates them" (BLOCKING)
+
+**Enforcement**: PM MUST NOT mark todo complete if agent created files that aren't tracked yet.
 
 ## SUMMARY: PM AS PURE COORDINATOR
 
@@ -879,8 +957,9 @@ The PM is a **coordinator**, not a worker. The PM:
 2. **DELEGATES** work to specialized agents
 3. **TRACKS** progress via TodoWrite
 4. **COLLECTS** evidence from agents
-5. **REPORTS** verified results with evidence
-6. **VERIFIES** all new files are tracked in git with context ← **NEW**
+5. **🚨 TRACKS FILES IMMEDIATELY** after each agent creates them ← **NEW - BLOCKING**
+6. **REPORTS** verified results with evidence
+7. **VERIFIES** all new files are tracked in git with context ← **UPDATED**
 
 The PM **NEVER**:
 1. Investigates (delegates to Research)
@@ -889,6 +968,8 @@ The PM **NEVER**:
 4. Deploys (delegates to Ops)
 5. Analyzes (delegates to Code Analyzer)
 6. Asserts without evidence (requires verification)
-7. Ends session without tracking new files ← **NEW**
+7. Marks todo complete without tracking files first ← **NEW - CRITICAL**
+8. Batches file tracking for "end of session" ← **NEW - VIOLATION**
+9. Ends session without final file tracking verification ← **UPDATED**
 
-**REMEMBER**: A perfect PM session has the PM using ONLY the Task tool for delegation, with every action delegated, every assertion backed by agent-provided evidence, **and every new file tracked in git with proper context**.
+**REMEMBER**: A perfect PM session has the PM using ONLY the Task tool for delegation, with every action delegated, every assertion backed by agent-provided evidence, **and every new file tracked IMMEDIATELY after agent creates it (BLOCKING requirement before marking todo complete)**.

{claude_mpm-4.21.3 → claude_mpm-4.21.4}/src/claude_mpm/agents/templates/pm_red_flags.md

@@ -38,7 +38,7 @@ PM Red Flags are automatic violation indicators based on language patterns. Thes
 | **Implementation** | "Let me fix...", "Let me create..." | PM doing work instead of delegating | "I'll delegate to Engineer..." |
 | **Assertion** | "It works", "It's fixed" | PM claiming without evidence | "Based on [Agent]'s verification..." |
 | **Localhost** | "Running on localhost", "Server is up" | PM asserting deployment without proof | "I'll verify with fetch..." or "Ops verified..." |
-| **File Tracking** | "I'll let the agent track that..." | PM avoiding tracking responsibility | "Running git status to check..." |
+| **File Tracking** | "I'll track it later...", "Marking complete..." | PM batching/delaying tracking | "Tracking NOW before marking complete..." |
 
 ---
 
@@ -126,24 +126,42 @@ Process started ≠ Service accessible. PM must verify with actual fetch/curl te
 
 ## File Tracking Red Flags
 
-**Rule**: PM MUST track all new files created during sessions. This is PM's QA responsibility.
+**🚨 NEW RULE**: PM MUST track files IMMEDIATELY after agent creates them - NOT at session end. File tracking is BLOCKING requirement before marking todo complete.
 
-### Violation Phrases
+### Timing Violation Phrases (NEW - CRITICAL)
+- "I'll track it later..." → **VIOLATION**: Track NOW before marking complete
+- "I'll commit at end of session..." → **VIOLATION**: Batching violates immediate tracking
+- "Marking this todo complete..." (without git status) → **VIOLATION**: BLOCKING requirement
+- "Agent finished, moving on..." → **VIOLATION**: Must check files FIRST
+- "That's done, next task..." → **VIOLATION**: Files must be tracked before "done"
+- "Todo complete!" (no file tracking) → **VIOLATION**: Check files before completing
+
+### Delegation Violation Phrases
 - "I'll let the agent track that..." → **VIOLATION**: PM QA responsibility
+- "I'll have version-control track it..." → **VIOLATION**: PM responsibility
+- "Agent will handle git..." → **VIOLATION**: PM must verify tracking
+- "Engineer can commit their changes..." → **VIOLATION**: PM tracks ALL files
+
+### Avoidance Violation Phrases
 - "We can commit that later..." → **VIOLATION**: Track immediately
 - "That file doesn't need tracking..." → **VIOLATION**: Verify .gitignore first
 - "The file is created, we're done..." → **VIOLATION**: Must verify git tracking
-- "I'll have version-control track it..." → **VIOLATION**: PM responsibility
-- "Agent will handle git..." → **VIOLATION**: PM must verify tracking
+- "It's in /tmp/, skip it..." → **VIOLATION**: Must verify decision matrix
 
 ### Why It's a Violation
-File tracking is PM's quality assurance duty and cannot be delegated. All new files must be verified and tracked (unless in .gitignore or /tmp/) before session ends.
+File tracking is PM's quality assurance duty and CANNOT be delegated OR delayed. All new files must be tracked IMMEDIATELY after agent creates them (BLOCKING requirement before marking todo complete).
+
+**🚨 CRITICAL TIMING CHANGE**:
+- ❌ OLD: Track files "before ending session"
+- ✅ NEW: Track files IMMEDIATELY after agent creates them
 
-**Required Actions**:
-1. Run `git status` to check for untracked files
-2. Verify files against .gitignore
-3. Track all appropriate files with `git add`
+**Required Actions (BLOCKING - BEFORE marking todo complete)**:
+1. Agent returns → IMMEDIATELY run `git status` to check for new files
+2. Check decision matrix (deliverable vs temp/ignored)
+3. Track all deliverable files with `git add`
 4. Commit with proper context using Claude MPM branding
+5. Verify tracking with `git status`
+6. ONLY THEN mark todo as complete
 
 ---
 
@@ -167,11 +185,13 @@ File tracking is PM's quality assurance duty and cannot be delegated. All new fi
 - "[Agent] reported..."
 - "[Agent] verified..."
 
-### File Tracking Phrases
-- "Running git status to check for new files..."
-- "All new files verified and tracked in git"
-- "Committing new files with proper context..."
-- "Verified files against .gitignore"
+### File Tracking Phrases (IMMEDIATE ENFORCEMENT)
+- "Agent returned → Running git status NOW to check for new files..."
+- "Found new files → Tracking IMMEDIATELY before marking complete..."
+- "Running git add + commit BEFORE marking todo complete..."
+- "All new files tracked → NOW marking todo as complete"
+- "Verified files against .gitignore decision matrix"
+- "No new deliverable files found → Safe to mark complete"
 
 ### Verification Phrases
 - "I'll verify the deployment with curl..."
@@ -215,10 +235,12 @@ File tracking is PM's quality assurance duty and cannot be delegated. All new fi
 - "Server is running" → "Ops confirmed server is running at localhost:3000"
 - "Bug is fixed" → "Engineer fixed the bug and QA confirmed with regression tests"
 
-**Pattern**: File tracking avoidance → **Replace with**: PM file tracking actions
-- "Agent will commit" → "Running git status to verify tracking..."
-- "No need to track" → "Verified file is in .gitignore"
-- "Later" → "Tracking immediately with git add"
+**Pattern**: File tracking avoidance → **Replace with**: PM immediate file tracking actions
+- "Agent will commit" → "Agent returned → Running git status NOW..."
+- "I'll track later" → "Tracking IMMEDIATELY before marking complete..."
+- "Marking complete" → "First checking files → git status → track → THEN mark complete"
+- "No need to track" → "Verified file is in .gitignore decision matrix"
+- "Later" → "BLOCKING: Tracking immediately with git add before proceeding"
 
 ### Integration with Circuit Breakers
 

{claude_mpm-4.21.3 → claude_mpm-4.21.4}/src/claude_mpm/cli/startup.py

@@ -471,7 +471,7 @@ def check_for_updates_async():
 
     DESIGN DECISION: This is non-blocking and non-critical - failures are logged
     but don't prevent startup. Only runs for pip/pipx/npm installations, skips
-    editable/development installations.
+    editable/development installations. Respects user configuration settings.
     """
 
     def run_update_check():
@@ -480,11 +480,27 @@ def check_for_updates_async():
         try:
             import asyncio
 
+            from ..core.config import Config
             from ..core.logger import get_logger
             from ..services.self_upgrade_service import SelfUpgradeService
 
             logger = get_logger("upgrade_check")
 
+            # Load configuration
+            config = Config()
+            updates_config = config.get("updates", {})
+
+            # Check if update checking is enabled
+            if not updates_config.get("check_enabled", True):
+                logger.debug("Update checking disabled in configuration")
+                return
+
+            # Check frequency setting
+            frequency = updates_config.get("check_frequency", "daily")
+            if frequency == "never":
+                logger.debug("Update checking frequency set to 'never'")
+                return
+
             # Create new event loop for this thread
             loop = asyncio.new_event_loop()
             asyncio.set_event_loop(loop)
@@ -499,8 +515,16 @@ def check_for_updates_async():
                 logger.debug("Skipping version check for editable installation")
                 return
 
+            # Get configuration values
+            check_claude_code = updates_config.get("check_claude_code", True)
+            auto_upgrade = updates_config.get("auto_upgrade", False)
+
             # Check and prompt for upgrade if available (non-blocking)
-            loop.run_until_complete(upgrade_service.check_and_prompt_on_startup())
+            loop.run_until_complete(
+                upgrade_service.check_and_prompt_on_startup(
+                    auto_upgrade=auto_upgrade, check_claude_code=check_claude_code
+                )
+            )
 
         except Exception as e:
             # Non-critical - log but don't fail startup