Security & Query Safety

• Ensured only single statements are passed to EXPLAIN (#224), with improved parsing to block multiple commands.
• Renamed explainQuery to unsafeExplainQuery to highlight potential risks where edge cases might escape safety checks.
• Introduced safeExplainQuery, which fetches SQL directly from pg_stat_statements by queryId.
• Switched unsafe explain to use generic_plan for consistency and safety (#229).

AI Model Updates

• Migrated OpenAI integration to GPT-5 only (#211):

  • GPT-5 is now the default (chat + scheduling).
  • Removed support for GPT-4 and other deprecated OpenAI models.
  • Migration ensures schedules using GPT-4 are upgraded to GPT-5.
  • Pending LiteLLM and judge/eval testing.

Dev Experience & Tooling

• Removed unused sample MCP server (#218).
• Updated docker-compose behavior:
  • Containers now use unless-stopped restart policy for more predictable restarts across host reboots (#195).
  • Updated release references in docker-compose files.