Changes in version 0.1.0 (2026-05-28)                  

CRAN release

  - First CRAN release of llmshieldr.
  - Added model-agnostic scanners for prompts, model outputs,
    conversations, retrieved context, tool calls, tool outputs, and
    streaming chunks.
  - Added built-in policies mapped to the OWASP LLM Top 10 for Large
    Language Model Applications 2025.
  - Added deterministic rule checks, optional NLP intent checks,
    optional semantic reviewer checks, configurable redaction
    strategies, audit logs, rate guards, and Ollama helpers.
  - Added vignettes for getting started, policy design, custom rules,
    RAG pipelines, OWASP coverage, evaluation, operations, threat
    modeling, architecture, ecosystem context, and Ollama usage.