claude-mpm 4.18.0__py3-none-any.whl → 4.18.3__py3-none-any.whl

claude_mpm/VERSION

@@ -1 +1 @@
-4.18.0
+4.18.3

claude_mpm/agents/BASE_ENGINEER.md

@@ -262,6 +262,292 @@ Before writing ANY fix or optimization, you MUST:
 - **Test Coverage**: Minimum 80% for new code
 - **Documentation**: All public APIs must have docstrings
 
+## Engineering Quality Documentation Standards
+
+All engineers must provide comprehensive documentation for implementations. These standards ensure maintainability, knowledge transfer, and informed decision-making for future modifications.
+
+### Design Decision Documentation (MANDATORY)
+
+Every significant implementation must document:
+
+**Architectural Choices and Reasoning**
+- Explain WHY you chose this approach over alternatives
+- Document the problem context that influenced the decision
+- Link design to business requirements or technical constraints
+
+**Alternatives Considered**
+- List other approaches evaluated during design
+- Explain why each alternative was rejected
+- Note any assumptions that might invalidate the current choice
+
+**Trade-offs Analysis**
+- **Performance vs. Maintainability**: Document speed vs. readability choices
+- **Complexity vs. Flexibility**: Note when simplicity was chosen over extensibility
+- **Memory vs. Speed**: Explain resource allocation decisions
+- **Time vs. Quality**: Acknowledge technical debt taken for deadlines
+
+**Future Extensibility**
+- Identify extension points for anticipated changes
+- Document which parts are designed to be stable vs. flexible
+- Note refactoring opportunities for future consideration
+
+**Example**:
+```python
+class CacheManager:
+    """
+    Design Decision: In-memory LRU cache with TTL
+
+    Rationale: Selected in-memory caching for sub-millisecond access times
+    required by API SLA (<50ms p99 latency). Rejected Redis to avoid
+    network latency and operational complexity for this use case.
+
+    Trade-offs:
+    - Performance: O(1) access vs. Redis ~1-2ms network round-trip
+    - Scalability: Limited to single-node memory vs. distributed cache
+    - Persistence: Loses cache on restart vs. Redis durability
+
+    Alternatives Considered:
+    1. Redis: Rejected due to network latency and ops overhead
+    2. SQLite: Rejected due to disk I/O bottleneck on writes
+    3. No caching: Rejected due to database query load (2000+ QPS)
+
+    Extension Points: Cache backend interface allows future Redis migration
+    if horizontal scaling becomes necessary (>10K QPS threshold).
+    """
+```
+
+### Performance Analysis (RECOMMENDED)
+
+For algorithms and critical paths, provide:
+
+**Complexity Analysis**
+- **Time Complexity**: Big-O notation for all operations
+  - Best case, average case, worst case
+  - Explain what factors influence complexity
+- **Space Complexity**: Memory usage characteristics
+  - Auxiliary space requirements
+  - Scalability limits based on input size
+
+**Performance Metrics**
+- Expected performance for typical workloads
+- Benchmarks for critical operations
+- Comparison to previous implementation (if refactoring)
+
+**Bottleneck Identification**
+- Known performance limitations
+- Conditions that trigger worst-case behavior
+- Scalability ceilings and their causes
+
+**Example**:
+```python
+def binary_search(arr: list, target: int) -> int:
+    """
+    Find target in sorted array using binary search.
+
+    Performance:
+    - Time Complexity: O(log n) average/worst case, O(1) best case
+    - Space Complexity: O(1) iterative implementation
+
+    Expected Performance:
+    - 1M elements: ~20 comparisons maximum
+    - 1B elements: ~30 comparisons maximum
+
+    Bottleneck: Array must be pre-sorted. If frequent insertions/deletions,
+    consider balanced tree structure (O(log n) insert vs. O(n) array insert).
+    """
+```
+
+### Optimization Suggestions (RECOMMENDED)
+
+Document future improvement opportunities:
+
+**Potential Performance Improvements**
+- Specific optimizations not yet implemented
+- Conditions under which optimization becomes worthwhile
+- Estimated performance gains if implemented
+
+**Refactoring Opportunities**
+- Code structure improvements identified during implementation
+- Dependencies that could be reduced or eliminated
+- Patterns that could be extracted for reuse
+
+**Technical Debt Documentation**
+- Shortcuts taken with explanation and remediation plan
+- Areas needing cleanup or modernization
+- Test coverage gaps and plan to address
+
+**Scalability Considerations**
+- Current capacity limits and how to exceed them
+- Architectural changes needed for 10x/100x scale
+- Resource utilization projections
+
+**Example**:
+```python
+class ReportGenerator:
+    """
+    Current Implementation: Synchronous PDF generation
+
+    Optimization Opportunities:
+    1. Async Generation: Move to background queue for reports >100 pages
+       - Estimated speedup: 200ms -> 50ms API response time
+       - Requires: Celery/RQ task queue, S3 storage for results
+       - Threshold: Implement when report generation >500/day
+
+    2. Template Caching: Cache Jinja2 templates in memory
+       - Estimated speedup: 20% reduction in render time
+       - Effort: 2-4 hours, low risk
+
+    Technical Debt:
+    - TODO: Add retry logic for external API calls (currently fails fast)
+    - TODO: Implement streaming for large datasets (current limit: 10K rows)
+
+    Scalability: Current design handles ~1000 reports/day. For >5000/day,
+    migrate to async architecture with dedicated worker pool.
+    """
+```
+
+### Error Case Documentation (MANDATORY)
+
+Every implementation must document failure modes:
+
+**All Error Conditions Handled**
+- List every exception caught and why
+- Document error recovery strategies
+- Explain error propagation decisions (catch vs. propagate)
+
+**Failure Modes and Degradation**
+- What happens when external dependencies fail
+- Graceful degradation paths (if applicable)
+- Data consistency guarantees during failures
+
+**Error Messages**
+- All error messages must be actionable
+- Include diagnostic information for debugging
+- Suggest remediation steps when possible
+
+**Recovery Strategies**
+- Automatic retry logic and backoff strategies
+- Manual intervention procedures
+- Data recovery or rollback mechanisms
+
+**Example**:
+```python
+def process_payment(payment_data: dict) -> PaymentResult:
+    """
+    Process payment through external gateway.
+
+    Error Handling:
+    1. NetworkError: Retry up to 3 times with exponential backoff (1s, 2s, 4s)
+       - After retries exhausted, queue for manual review
+       - User receives "processing delayed" message
+
+    2. ValidationError: Immediate failure, no retry
+       - Returns detailed field-level errors to user
+       - Logs validation failure for fraud detection
+
+    3. InsufficientFundsError: Immediate failure, no retry
+       - Clear user message: "Payment declined - insufficient funds"
+       - No sensitive details exposed in error response
+
+    4. GatewayTimeoutError: Single retry after 5s
+       - On failure, mark transaction as "pending review"
+       - Webhook reconciliation runs hourly to check status
+
+    Failure Mode: If payment gateway is completely down, transactions
+    are queued in database with "pending" status. Background worker
+    processes queue every 5 minutes. Users notified of delay via email.
+
+    Data Consistency: Transaction state transitions are atomic. No partial
+    payments possible. Database transaction wraps payment + order update.
+    """
+```
+
+### Usage Examples (RECOMMENDED)
+
+Provide practical code examples:
+
+**Common Use Cases**
+- Show typical usage patterns for APIs
+- Include complete, runnable examples
+- Demonstrate best practices
+
+**Edge Case Handling**
+- Show how to handle boundary conditions
+- Demonstrate error handling in practice
+- Illustrate performance considerations
+
+**Integration Examples**
+- How to use with other system components
+- Configuration examples
+- Dependency setup instructions
+
+**Test Case References**
+- Point to test files demonstrating usage
+- Explain what each test validates
+- Use tests as living documentation
+
+**Example**:
+```python
+class DataValidator:
+    """
+    Validate user input against schema definitions.
+
+    Common Usage:
+        >>> validator = DataValidator(schema=user_schema)
+        >>> result = validator.validate(user_data)
+        >>> if result.is_valid:
+        >>>     process_user(result.cleaned_data)
+        >>> else:
+        >>>     return {"errors": result.errors}
+
+    Edge Cases:
+        # Handle missing required fields
+        >>> result = validator.validate({})
+        >>> result.errors  # {"email": "required field missing"}
+
+        # Handle type coercion
+        >>> result = validator.validate({"age": "25"})
+        >>> result.cleaned_data["age"]  # 25 (int, not string)
+
+    Integration with Flask:
+        @app.route('/users', methods=['POST'])
+        def create_user():
+            validator = DataValidator(schema=user_schema)
+            result = validator.validate(request.json)
+            if not result.is_valid:
+                return jsonify({"errors": result.errors}), 400
+            # ... process valid data
+
+    Tests: See tests/test_validators.py for comprehensive examples
+    - test_required_fields: Required field validation
+    - test_type_coercion: Automatic type conversion
+    - test_custom_validators: Custom validation rules
+    """
+```
+
+## Documentation Enforcement
+
+**Mandatory Reviews**
+- Code reviews must verify documentation completeness
+- PRs without proper documentation must be rejected
+- Design decisions require explicit approval
+
+**Documentation Quality Checks**
+- MANDATORY sections must be present and complete
+- RECOMMENDED sections encouraged but not blocking
+- Examples must be runnable and tested
+- Error cases must cover all catch/except blocks
+
+**Success Criteria**
+- ✅ Design rationale clearly explained
+- ✅ Trade-offs explicitly documented
+- ✅ All error conditions documented
+- ✅ At least one usage example provided
+- ✅ Complexity analysis for non-trivial algorithms
+- ❌ "Self-documenting code" without explanation
+- ❌ Generic/copied docstring templates
+- ❌ Undocumented error handling
+
 ### Implementation Patterns
 
 #### Technical Patterns

claude_mpm/agents/templates/engineer.json

@@ -112,7 +112,11 @@
       "Plan modularization at 600 lines",
       "Review file commit history before modifications: git log --oneline -5 <file_path>",
       "Write succinct commit messages explaining WHAT changed and WHY",
-      "Follow conventional commits format: feat/fix/docs/refactor/perf/test/chore"
+      "Follow conventional commits format: feat/fix/docs/refactor/perf/test/chore",
+      "Document design decisions and architectural trade-offs",
+      "Provide complexity analysis (time/space) for algorithms",
+      "Include practical usage examples in documentation",
+      "Document all error cases and failure modes"
     ],
     "constraints": [],
     "examples": []

claude_mpm/core/config.py

@@ -578,6 +578,11 @@ class Config:
                     "[PM-REMINDER] Your role is coordination and management",
                 ],
             },
+            # Session management configuration
+            "session": {
+                "auto_save": True,  # Enable automatic session saving
+                "save_interval": 300,  # Auto-save interval in seconds (5 minutes)
+            },
         }
 
         # Apply defaults for missing keys
@@ -588,6 +593,9 @@ class Config:
         # Validate health and recovery configuration
         self._validate_health_recovery_config()
 
+        # Validate session configuration
+        self._validate_session_config()
+
     def get(self, key: str, default: Any = None) -> Any:
         """Get configuration value."""
         # Support nested keys with dot notation
@@ -764,6 +772,40 @@ class Config:
         except Exception as e:
             logger.error(f"Error validating health/recovery configuration: {e}")
 
+    def _validate_session_config(self) -> None:
+        """Validate session management configuration."""
+        try:
+            session_config = self.get("session", {})
+
+            # Validate save_interval range (60-1800 seconds)
+            save_interval = session_config.get("save_interval", 300)
+            if not isinstance(save_interval, int):
+                logger.warning(
+                    f"Session save_interval must be integer, got {type(save_interval).__name__}, using default 300"
+                )
+                self.set("session.save_interval", 300)
+            elif save_interval < 60:
+                logger.warning(
+                    f"Session save_interval must be at least 60 seconds, got {save_interval}, using 60"
+                )
+                self.set("session.save_interval", 60)
+            elif save_interval > 1800:
+                logger.warning(
+                    f"Session save_interval must be at most 1800 seconds (30 min), got {save_interval}, using 1800"
+                )
+                self.set("session.save_interval", 1800)
+
+            # Validate auto_save is boolean
+            auto_save = session_config.get("auto_save", True)
+            if not isinstance(auto_save, bool):
+                logger.warning(
+                    f"Session auto_save must be boolean, got {type(auto_save).__name__}, using True"
+                )
+                self.set("session.auto_save", True)
+
+        except Exception as e:
+            logger.error(f"Error validating session configuration: {e}")
+
     def get_health_monitoring_config(self) -> Dict[str, Any]:
         """Get health monitoring configuration with defaults."""
         base_config = {

claude_mpm/services/agents/deployment/agent_validator.py

@@ -329,10 +329,26 @@ class AgentValidator:
             "type": "agent",  # Default type
         }
 
-        # Extract from YAML frontmatter
+        # Extract ONLY from YAML frontmatter (between --- markers)
         lines = content.split("\n")
+        in_frontmatter = False
+        frontmatter_ended = False
+
         for line in lines:
             stripped_line = line.strip()
+
+            # Track frontmatter boundaries
+            if stripped_line == "---":
+                if not in_frontmatter:
+                    in_frontmatter = True
+                    continue
+                frontmatter_ended = True
+                break  # Stop parsing after frontmatter ends
+
+            # Only parse within frontmatter
+            if not in_frontmatter or frontmatter_ended:
+                continue
+
             if stripped_line.startswith("name:"):
                 agent_info["name"] = stripped_line.split(":", 1)[1].strip().strip("\"'")
             elif stripped_line.startswith("description:"):

claude_mpm/services/cli/session_manager.py

@@ -11,8 +11,10 @@ DESIGN DECISIONS:
 - Automatic session cleanup and archiving
 - Thread-safe session operations
 - Non-blocking validation with structured warnings
+- Async-first design with periodic auto-save task
 """
 
+import asyncio
 import gzip
 import json
 import uuid
@@ -217,8 +219,39 @@ class SessionManager(ISessionManager):
         self.config_service = config_service
         self.logger = get_logger("SessionManager")
         self._sessions_cache: Dict[str, SessionInfo] = {}
+        self._auto_save_task: Optional[asyncio.Task] = None
+        self._running = False
         self._load_sessions()
 
+        # Start auto-save task if enabled and event loop is running
+        if config_service:
+            auto_save_enabled = config_service.get("session.auto_save", True)
+            if auto_save_enabled:
+                self._start_auto_save()
+            else:
+                self.logger.info("Auto-save disabled by configuration")
+        else:
+            self.logger.debug("No config service provided, auto-save not started")
+
+    def _start_auto_save(self) -> None:
+        """Start the auto-save background task.
+
+        WHY: Separated from __init__ to allow safe initialization without event loop.
+        Can be called when event loop is available.
+        """
+        try:
+            loop = asyncio.get_running_loop()
+            self._running = True
+            self._auto_save_task = loop.create_task(self._periodic_session_save())
+            self.logger.info("Auto-save task started")
+        except RuntimeError:
+            # No event loop running, schedule for later
+            self.logger.debug(
+                "No event loop running, auto-save will start when loop is available"
+            )
+            # Set flag so we know to start it later
+            self._running = True
+
     def create_session(
         self, context: str = "default", options: Optional[Dict[str, Any]] = None
     ) -> SessionInfo:
@@ -477,6 +510,60 @@ class SessionManager(ISessionManager):
             self.logger.error(f"Failed to load sessions: {e}")
             self._sessions_cache = {}
 
+    async def _periodic_session_save(self) -> None:
+        """Periodically save sessions to disk.
+
+        WHY: Ensures sessions are persisted regularly to prevent data loss.
+        Follows the async pattern from EventAggregator._periodic_cleanup().
+        """
+        if not self.config_service:
+            self.logger.warning("No config service, cannot determine save interval")
+            return
+
+        save_interval = self.config_service.get("session.save_interval", 300)
+        self.logger.info(f"Starting periodic session save (interval: {save_interval}s)")
+
+        while self._running:
+            try:
+                await asyncio.sleep(save_interval)
+
+                if self._sessions_cache:
+                    self._save_sessions()
+                    self.logger.debug(
+                        f"Auto-saved {len(self._sessions_cache)} session(s)"
+                    )
+                else:
+                    self.logger.debug("No sessions to save")
+
+            except asyncio.CancelledError:
+                self.logger.info("Auto-save task cancelled")
+                break
+            except Exception as e:
+                self.logger.error(f"Error in auto-save task: {e}")
+
+    async def cleanup(self) -> None:
+        """Clean up resources and stop background tasks.
+
+        WHY: Ensures graceful shutdown of the SessionManager and all background tasks.
+        """
+        self.logger.info("Shutting down SessionManager...")
+        self._running = False
+
+        # Cancel auto-save task
+        if self._auto_save_task and not self._auto_save_task.done():
+            self._auto_save_task.cancel()
+            try:
+                await self._auto_save_task
+            except asyncio.CancelledError:
+                pass
+
+        # Final save before shutdown
+        if self._sessions_cache:
+            self._save_sessions()
+            self.logger.info(f"Final save: {len(self._sessions_cache)} session(s)")
+
+        self.logger.info("SessionManager shutdown complete")
+
 
 # Context manager for session management
 class ManagedSession:

{claude_mpm-4.18.0.dist-info → claude_mpm-4.18.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: claude-mpm
-Version: 4.18.0
+Version: 4.18.3
 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

{claude_mpm-4.18.0.dist-info → claude_mpm-4.18.3.dist-info}/RECORD

@@ -1,5 +1,5 @@
 claude_mpm/BUILD_NUMBER,sha256=9JfxhnDtr-8l3kCP2U5TVXSErptHoga8m7XA8zqgGOc,4
-claude_mpm/VERSION,sha256=5mYNrbR8YeYxplD-PUtT0GgvvhJGMI06lnDR4IEMHyw,7
+claude_mpm/VERSION,sha256=Q5Zpc7PYaq2Bzb0frfdpC9P0XLSuxcM8tmuczgbBofk,7
 claude_mpm/__init__.py,sha256=UCw6j9e_tZQ3kJtTqmdfNv7MHyw9nD1jkj80WurwM2g,2064
 claude_mpm/__main__.py,sha256=Ro5UBWBoQaSAIoSqWAr7zkbLyvi4sSy28WShqAhKJG0,723
 claude_mpm/constants.py,sha256=sLjJF6Kw7H4V9WWeaEYltM-77TgXqzEMX5vx4ukM5-0,5977
@@ -7,7 +7,7 @@ claude_mpm/init.py,sha256=HFJR_JmTHa53FAhbGusm3P1iXT6VR6V7S-YJz4pOZ1Q,15967
 claude_mpm/ticket_wrapper.py,sha256=qe5xY579t7_7fK5nyeAfHN_fr7CXdeOD3jfXEc8-7yo,828
 claude_mpm/agents/BASE_AGENT_TEMPLATE.md,sha256=wFqZssWaeCGaW04yy7eScYOlqJmsu1VhsA83s2X_yMU,9138
 claude_mpm/agents/BASE_DOCUMENTATION.md,sha256=iGub94w3IRURz2PwT0YrfNegMlEzgZ9mzeWa_WBk1rA,1504
-claude_mpm/agents/BASE_ENGINEER.md,sha256=V637uK7cZazlc3aagAhY4G0WCuGtruLKbhuAbKvteRc,14695
+claude_mpm/agents/BASE_ENGINEER.md,sha256=I7BusSGQfuV0uSkRBro51qzCzagUEPrXnndIElypPJk,24434
 claude_mpm/agents/BASE_OPS.md,sha256=azAjZTrj77IZIBgZxX2hcjPOQMznV0v6B4ZWNUhAT9g,7636
 claude_mpm/agents/BASE_PM.md,sha256=4asvm0xIxstAJFqZxC-eJKGSTGmgmzRQGWcoyzCfyQY,7292
 claude_mpm/agents/BASE_PROMPT_ENGINEER.md,sha256=DHw7KXA6Nw7RfTyQiY06B_hH6ng2meimhgUKpQp08MM,21736
@@ -40,7 +40,7 @@ claude_mpm/agents/templates/content-agent.json,sha256=KfE8ozTsLmQiJgKnX-6yH1bOhd
 claude_mpm/agents/templates/dart_engineer.json,sha256=2XsrLpeL9-f94S7mq7e8Rela-W-dl2tGwksOY8S4nEo,22685
 claude_mpm/agents/templates/data_engineer.json,sha256=BPGgVsQPdg5YHRxlSGSIfA3xBihIXGYcrWbtaeYGd6g,20028
 claude_mpm/agents/templates/documentation.json,sha256=jdDZdz8eCW6jF-jow5l1Z6SFBHyd6t-34hNAb0bbfe4,10355
-claude_mpm/agents/templates/engineer.json,sha256=ChVSh78Y6K8JNVCGGZzL0GY19sUDMP-7e0WVL3chVRw,5807
+claude_mpm/agents/templates/engineer.json,sha256=1z2tXmuGfdk8_T43A__piMSHv-RK7BxwoyOMRPt8Qz8,6047
 claude_mpm/agents/templates/gcp_ops_agent.json,sha256=HtW3m9S6FLxxoa3ATzOWB2YLuCsRdNnQ4pztuyei6Q0,11208
 claude_mpm/agents/templates/git_file_tracking.md,sha256=r8qckL8pS2nIvZAImFgbjAzpaEhzV44B1lzz6V8Jg8M,18842
 claude_mpm/agents/templates/golang_engineer.json,sha256=_I5G6fmQb1Qf5uIM4Q46HCujndU2Lq96V0CoH6qi3D4,12905
@@ -195,7 +195,7 @@ claude_mpm/core/api_validator.py,sha256=U2PfksS1gEwMCkBMUjsUmFVPg2coZ6mwugBE_5kw
 claude_mpm/core/base_service.py,sha256=4Zrt-vQ6g_KVk4hEfvd4QccuItYoOf7wUHCimIW6zJQ,29953
 claude_mpm/core/cache.py,sha256=orh8B40oYnRRGmXdANR4P4f-KVMIHV0vg7vrsemk0no,17232
 claude_mpm/core/claude_runner.py,sha256=h64Nbo0eh7pfTk_QMO3tb3rQZEEULRvSfLN8vgpZXdQ,34686
-claude_mpm/core/config.py,sha256=ruUxfmGaGtqK1o7DYet8olw6ewLKjeL-q0YMHVeVHgg,39434
+claude_mpm/core/config.py,sha256=qBus1zl0l56XntWaElWWyiqQ4mhDDPG7o1ELUOXiK2k,41300
 claude_mpm/core/config_aliases.py,sha256=QpNNECkTY4TYYAhVlFZvB-msPnZrui90g19u0-v0HDE,9703
 claude_mpm/core/config_constants.py,sha256=MEF35Y2Lj5FMzRdhgSgZrZeTzHfCzistPGZVY8INta4,10073
 claude_mpm/core/constants.py,sha256=uBCd4kUbwSFKW79pH7_yUzRpMoNY2AcAflENTkIZIaU,11558
@@ -496,7 +496,7 @@ claude_mpm/services/agents/deployment/agent_record_service.py,sha256=dNkygfKDn4V
 claude_mpm/services/agents/deployment/agent_restore_handler.py,sha256=YDPVY4m_4l5wSFq9fxsTqm0ixX8AeTyzERh-PtabuUY,3101
 claude_mpm/services/agents/deployment/agent_state_service.py,sha256=cFBv8GEdW8gmch5OlpI6zCQdv3ANEqYV1YL0VIBRp0U,11799
 claude_mpm/services/agents/deployment/agent_template_builder.py,sha256=0apuovTjKbIPLKdo0xHXd1-ABZH5_twnErl4ooZHmFU,46004
-claude_mpm/services/agents/deployment/agent_validator.py,sha256=CwK_uREKix78_2sV5vxGuXUMz-I7f3dJc1xnWvHGFlo,12923
+claude_mpm/services/agents/deployment/agent_validator.py,sha256=4kUKHotEq_3HSNMbgSDdbtxUOVuFxtbFch87qF54c7Y,13438
 claude_mpm/services/agents/deployment/agent_version_manager.py,sha256=Q2COYmnWDvDxsBh_ikN9Govk3o8Dy1T0X-rioMpUsis,11189
 claude_mpm/services/agents/deployment/agent_versioning.py,sha256=PrOrauoe0rUftZvNSf0Uhch9DkqY4rtDrJf2uUXX9oE,999
 claude_mpm/services/agents/deployment/agents_directory_resolver.py,sha256=4ylwNMs9i8eGa1jSBkU0wW1O0Jvr4GNrrWX81F0wQWU,2175
@@ -577,7 +577,7 @@ claude_mpm/services/cli/agent_output_formatter.py,sha256=FcJ18m3CyeFr_wotJfEmIUR
 claude_mpm/services/cli/agent_validation_service.py,sha256=QtpP9GOwCD2wW40winh5NDrYXXLiFd_CXFUBWeYiMCk,21746
 claude_mpm/services/cli/memory_crud_service.py,sha256=tU0zegxba5lhpOCGqLijN2NfEMLwnEoYyjaF5cZ1A90,22863
 claude_mpm/services/cli/memory_output_formatter.py,sha256=iNXMSu-K24rkgVhJURS-B6GqUBxR1XEZg8ZewOll0SU,24796
-claude_mpm/services/cli/session_manager.py,sha256=SmZHNDdSj9GYIVSGeAmlkTqcSDc2wKNMq4GOLikYp7c,16757
+claude_mpm/services/cli/session_manager.py,sha256=-zG0osFnDYyta9iPCwmL5Dxu6Z-4_LHylFfqQAnIEvY,20126
 claude_mpm/services/cli/startup_checker.py,sha256=MmztJ7yAnk5O5shArGDzRzwBDmx1WikhtE5s9P4IU9M,12251
 claude_mpm/services/cli/unified_dashboard_manager.py,sha256=LH45wbiKn5GqEZWPH-18TQnsisR3vQchvSnxa-_CDZI,15607
 claude_mpm/services/communication/__init__.py,sha256=b4qc7_Rqy4DE9q7BAUlfUZjoYG4uimAyUnE0irPcXyU,560
@@ -886,9 +886,9 @@ claude_mpm/utils/subprocess_utils.py,sha256=D0izRT8anjiUb_JG72zlJR_JAw1cDkb7kalN
 claude_mpm/validation/__init__.py,sha256=YZhwE3mhit-lslvRLuwfX82xJ_k4haZeKmh4IWaVwtk,156
 claude_mpm/validation/agent_validator.py,sha256=GprtAvu80VyMXcKGsK_VhYiXWA6BjKHv7O6HKx0AB9w,20917
 claude_mpm/validation/frontmatter_validator.py,sha256=YpJlYNNYcV8u6hIOi3_jaRsDnzhbcQpjCBE6eyBKaFY,7076
-claude_mpm-4.18.0.dist-info/licenses/LICENSE,sha256=lpaivOlPuBZW1ds05uQLJJswy8Rp_HMNieJEbFlqvLk,1072
-claude_mpm-4.18.0.dist-info/METADATA,sha256=bdliQNOG4BU37WplLd-b5L3HGb8RcTvNJ4WMrg66dKQ,22476
-claude_mpm-4.18.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-claude_mpm-4.18.0.dist-info/entry_points.txt,sha256=Vlw3GNi-OtTpKSrez04iNrPmxNxYDpIWxmJCxiZ5Tx8,526
-claude_mpm-4.18.0.dist-info/top_level.txt,sha256=1nUg3FEaBySgm8t-s54jK5zoPnu3_eY6EP6IOlekyHA,11
-claude_mpm-4.18.0.dist-info/RECORD,,
+claude_mpm-4.18.3.dist-info/licenses/LICENSE,sha256=lpaivOlPuBZW1ds05uQLJJswy8Rp_HMNieJEbFlqvLk,1072
+claude_mpm-4.18.3.dist-info/METADATA,sha256=Y03L0BmDQCSMbwp5WhxA8b1ZR-OjCMivxy2roQkXPPc,22476
+claude_mpm-4.18.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+claude_mpm-4.18.3.dist-info/entry_points.txt,sha256=Vlw3GNi-OtTpKSrez04iNrPmxNxYDpIWxmJCxiZ5Tx8,526
+claude_mpm-4.18.3.dist-info/top_level.txt,sha256=1nUg3FEaBySgm8t-s54jK5zoPnu3_eY6EP6IOlekyHA,11
+claude_mpm-4.18.3.dist-info/RECORD,,