Merge branch 'dev'

Author: robertpiosik

README.md

@@ -2,12 +2,14 @@
 
 <a href="https://marketplace.visualstudio.com/items?itemName=robertpiosik.gemini-coder" target="_blank"><img src="https://img.shields.io/badge/Install-VS_Code_Marketplace-blue" alt="Get from Visual Studio Code Marketplace" /></a> <a href="https://open-vsx.org/extension/robertpiosik/gemini-coder" target="_blank"><img src="https://img.shields.io/badge/Install-Open_VSX_Registry-a60ee5" alt="Get from Open VSX Registry" /></a> <a href="https://github.com/robertpiosik/CodeWebChat/blob/dev/LICENSE" target="_blank"><img src="https://img.shields.io/badge/License-GPL--3.0-green.svg" alt="GPL-3.0 license" /></a>
 
-Agent-free AI pair programming for VS Code, Cursor, and other forks. Master context to guide the model to the responses you expect—without tool calls.
+Agent-free AI pair programming for production-grade code. Steer the model with hand-picked context for fast and accurate edits with simple instructions.
+
+Works with VS Code, Cursor, Windsurf, and other forks.
 
 ❤️ **Free and open-source.** _Join our [discord server](https://discord.gg/KJySXsrSX5) and get involed!_
 
 ✅ **Initializes free chatbots**—ChatGPT, Claude, Gemini, AI Studio, Qwen, and 10+ more \
-✅ **Calls model providers**—bring your own key or use local model via Ollama \
+✅ **Calls model providers**—bring your own keys or use local models via Ollama \
 ✅ **Applies responses**—multi-file changes integration with easy rollback \
 ✅ **Batteries included**—code completions, commit messages, and more
 
@@ -24,7 +26,7 @@ Code Web Chat only starts new conversations. This idea is borrowed from [Firefox
 > [!NOTE]
 > The _Apply response_ button placed under responses is not a means of automatic output extraction, it's an alias for the original _copy to clipboard_ button.
 
-🧑‍💻 **Control the context, guide the model**
+🧑‍💻 **Guide the model with context**
 
 Large language models (LLMs) are trained on vast datasets targeting many use cases. For code generation, a model's training involves analyzing millions of simulated problem-solving flows, such as arriving at the accepted answer from a given StackOverflow question. For the purpose of agentic coding, models are trained on an additional layer of data that simulates gathering context and planning its next steps.
 

packages/shared/src/types/file-in-review.ts

@@ -1,5 +1,6 @@
 export type FileInReview = {
   file_path: string
+  is_checked: boolean
   workspace_name?: string
   is_new?: boolean
   is_deleted?: boolean

packages/ui/src/components/editor/panel/ResponseReview/ResponseReview.tsx

@@ -7,7 +7,7 @@ import { Checkbox } from '../../common/Checkbox'
 import { IconButton } from '../IconButton/IconButton'
 
 type Props = {
-  files: (FileInReview & { is_checked: boolean })[]
+  files: FileInReview[]
   has_multiple_workspaces: boolean
   on_discard: () => void
   on_approve: (files: FileInReview[]) => void
@@ -46,9 +46,7 @@ export const ResponseReview: FC<Props> = ({
   const fallback_count = files.filter((f) => f.is_fallback).length
 
   const sorted_files = useMemo(() => {
-    const get_sort_score = (
-      file: FileInReview & { is_checked: boolean }
-    ): number => {
+    const get_sort_score = (file: FileInReview): number => {
       if (file.diff_fallback_method == 'search_and_replace') {
         return 0
       }

packages/vscode/package.json

@@ -1,8 +1,8 @@
 {
   "name": "gemini-coder",
   "displayName": "Code Web Chat",
-  "description": "Initialize free chatbots, call model providers, apply responses, and more (CWC)",
-  "version": "1.490.0",
+  "description": "CWC: Initialize free chatbots, call model providers, apply responses, batteries included",
+  "version": "1.491.0",
   "scripts": {
     "build": "npx vsce package --no-dependencies",
     "vscode:prepublish": "rimraf out && npm run compile",