ReliaGrowR 0.7

New Features

• New gof() function for computing numerical goodness-of-fit statistics
  (Cramér-von Mises and Kolmogorov-Smirnov) for fitted RGA models.
• New predict_duane() function for making predictions from Duane models,
  with confidence bounds and print/plot S3 methods.
• New MCP server integration via rga_mcp_server(), exposing ReliaGrowR
  functions as Model Context Protocol tools for AI assistants such as Claude.

Minor improvements and bug fixes

• New vignette on Reliability Demonstration Test Planning.
• New vignette on MCP server usage.
• Updated and expanded test suite for Duane, GOF, and MCP functions.
• Other minor improvements and bug fixes.