CodeContinue v2.3.0
===================

🚀 FIRST THINGS FIRST: RUN THE SETUP WIZARD
--------------------------------------------
1. Press: Ctrl+Shift+P  (or Cmd+Shift+P on macOS)
2. Type:  CodeContinue: Configure
3. Press: Enter

The step-by-step setup wizard will configure everything in under 30 seconds:
  1. Completion Endpoint & Model (auto-detects models from server)
  2. Dual-Engine Chat Endpoint & Model (local runner or cloud like Claude/GPT)
  3. 1-Click Keybinding Setup (Recommended: Ctrl+Enter Suggest, Tab Accept, Esc Dismiss)


New Features:
• Custom system prompt: Tailor the AI's behaviour to your workflow. Set "system_prompt"
  in your user settings, or configure it interactively via the Configure Wizard
  (Package Settings → CodeContinue → Configure Wizard). Leave blank to keep the
  built-in default. Useful for guiding smaller models or suppressing docstrings/comments.

Bug Fixes:
• Remote server 403 errors: Added a User-Agent header to all API requests, preventing
  reverse proxies and hosted endpoints from rejecting the plugin with HTTP 403 Forbidden.

Debug Improvements:
• The raw HTTP response body is now logged (up to 2000 chars) before JSON parsing
  when debug: true is enabled. On parse failures, the raw body is also printed via
  the error logger so you can diagnose malformed or streaming responses without
  digging through network logs.

Installer:
• Both the CLI (install.py) and GUI (install_gui.py) installers now write user
  configuration to Packages/User/ (the standard Sublime Text override location)
  instead of overwriting the package defaults file. The defaults file now ships
  with the full built-in system prompt visible for reference.

Questions or issues?
https://github.com/kXborg/codeContinue/issues
