feat: implement XER MCP Server with 9 schedule query tools

Implement complete MCP server for parsing Primavera P6 XER files and
exposing schedule data through MCP tools. All 4 user stories complete.

Tools implemented:
- load_xer: Parse XER files into SQLite database
- list_activities: Query activities with pagination and filtering
- get_activity: Get activity details by ID
- list_relationships: Query activity dependencies
- get_predecessors/get_successors: Query activity relationships
- get_project_summary: Project overview with counts
- list_milestones: Query milestone activities
- get_critical_path: Query driving path activities

Features:
- Tab-delimited XER format parsing with pluggable table handlers
- In-memory SQLite database for fast queries
- Pagination with 100-item default limit
- Multi-project file support with project selection
- ISO8601 date formatting
- NO_FILE_LOADED error handling for all query tools

Test coverage: 81 tests (contract, integration, unit)

src/xer_mcp/parser/table_handlers/task.py

@@ -0,0 +1,43 @@
+"""TASK table handler."""
+
+from xer_mcp.parser.table_handlers.base import TableHandler
+from xer_mcp.parser.table_handlers.project import convert_date
+
+
+class TaskHandler(TableHandler):
+    """Handler for TASK table in XER files."""
+
+    @property
+    def table_name(self) -> str:
+        return "TASK"
+
+    def parse_row(self, fields: list[str], values: list[str]) -> dict | None:
+        """Parse a TASK row."""
+        if len(values) < len(fields):
+            values = values + [""] * (len(fields) - len(values))
+
+        data = dict(zip(fields, values, strict=False))
+
+        # Parse driving_path_flag (Y/N -> bool)
+        driving_flag = data.get("driving_path_flag", "N")
+        driving_path = driving_flag.upper() == "Y" if driving_flag else False
+
+        # Parse total_float_hr_cnt
+        float_str = data.get("total_float_hr_cnt", "")
+        total_float = float(float_str) if float_str else None
+
+        return {
+            "task_id": data.get("task_id", ""),
+            "proj_id": data.get("proj_id", ""),
+            "wbs_id": data.get("wbs_id") or None,
+            "task_code": data.get("task_code", ""),
+            "task_name": data.get("task_name", ""),
+            "task_type": data.get("task_type", ""),
+            "status_code": data.get("status_code") or None,
+            "target_start_date": convert_date(data.get("target_start_date")),
+            "target_end_date": convert_date(data.get("target_end_date")),
+            "act_start_date": convert_date(data.get("act_start_date")),
+            "act_end_date": convert_date(data.get("act_end_date")),
+            "total_float_hr_cnt": total_float,
+            "driving_path_flag": driving_path,
+        }