CodeContinue v2.4.0
===================

🚀 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:
• Dynamic Endpoint Normalization: Base URLs like http://localhost:1234 or
  https://api.openai.com are automatically completed with the correct API path
  (/v1/chat/completions or /v1/messages).
• Automatic Model Discovery: Setup wizards now query /v1/models (or /api/tags)
  and present a quick-pick list of available models automatically.
• Endpoint Pre-flight Check: Instant connection verification during configuration
  with clear diagnostic messages if your local server is offline.
• Inline Edit & Refactor: Rewrite code in-place with instructions via right-click
  >> "CodeContinue: Edit Selection" (or Ctrl+Shift+P).
• Native Anthropic Support: Full compatibility with Anthropic /v1/messages endpoints.

Chat Improvements:
• Instant curated greeting on chat open without unsolicited analysis dumps.
• Clear guidance on using "CodeContinue: Edit Selection" for in-place modifications.
• Polished chat UI with distinct user/assistant headings and blockquote cues.

Installers:
• Both CLI (install.py) and GUI (install_gui.py) installers now feature automatic
  endpoint normalization, connection tests, and interactive model pickers.

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