From 95ec893139bc54ec5d87f4066f95b790ce5ecb29 Mon Sep 17 00:00:00 2001 From: Mark IJbema Date: Thu, 2 Apr 2026 13:56:08 +0200 Subject: [PATCH] docs: update FAQ items to match new extension terminology and features --- .../code-with-ai/platforms/vscode/whats-new.md | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/packages/kilo-docs/pages/code-with-ai/platforms/vscode/whats-new.md b/packages/kilo-docs/pages/code-with-ai/platforms/vscode/whats-new.md index 7e79c0b2cdf..f8ea0523bac 100644 --- a/packages/kilo-docs/pages/code-with-ai/platforms/vscode/whats-new.md +++ b/packages/kilo-docs/pages/code-with-ai/platforms/vscode/whats-new.md @@ -21,19 +21,19 @@ Code indexing is temporarily unavailable in the new extension. It is actively be ### How do checkpoints work in the new extension? -Checkpoints are available in the new extension. You can use them to save and restore your workspace state during a task. See the [Checkpoints documentation](/docs/code-with-ai/features/checkpoints) for details on how to use them. +Checkpoints are now called **snapshots** in the new extension. They use git-based snapshots of your working directory, taken before and after agent edits. You can revert any message's changes directly from the chat, and a revert banner appears when you're viewing an earlier state. See the [Checkpoints documentation](/docs/code-with-ai/features/checkpoints) for details. -### Where is the auto-confirm commands settings UI? +### Where is the auto-approve settings UI? -The auto-confirm commands settings have moved to the new settings panel. The UI has changed, but the functionality is the same. Open the settings panel to configure which commands are auto-approved. See [Auto-Approving Actions](/docs/getting-started/settings/auto-approving-actions) for more information. +The old auto-confirm commands UI has been replaced by a granular per-tool permission system. Open **Settings → Auto Approve** to configure each tool (bash, read, edit, glob, grep, etc.) with **Allow**, **Ask**, or **Deny**. There is no longer a separate command allowlist — shell execution is controlled by the `bash` tool permission. See [Auto-Approving Actions](/docs/getting-started/settings/auto-approving-actions) for more information. ### Where did the file reading settings go? -File reading settings are available in the new settings panel. Open settings to configure file reading behavior. +File reading is now controlled by the `read` tool permission in **Settings → Auto Approve**. By default, file reading is allowed, but `.env` files will prompt for approval. You can adjust this behavior per tool in the Auto Approve tab. ### Where is the UI for configuring local LLM providers? -Local LLM providers can be configured through the new settings panel. See the [Local Models](/docs/automate/extending/local-models) documentation for setup instructions. +Local LLM providers like Ollama and LM Studio can be configured through **Settings → Providers**. The extension and CLI share the same config, so changes in either place are reflected in both. See the [Local Models](/docs/automate/extending/local-models) documentation for setup instructions. ### The model selection feels bloated. Can I simplify it? @@ -53,12 +53,12 @@ MCP configuration has been migrated to the new settings panel. If you had MCPs c ### Where is the diff view for file changes? -The diff view is still available when reviewing file changes. When the agent proposes changes to a file, you can review the diff before approving. +Each message that caused file changes shows a **diff badge** in the chat — click it to open the Diff Viewer and review what changed. The Agent Manager also includes a built-in diff reviewer that shows every change file by file, in unified or split view. ### How do I do code reviews in the new extension? -Code reviews follow the CLI workflow in the new extension. See the [CLI documentation](/docs/code-with-ai/platforms/cli) for current instructions. Documentation specific to code reviews in the VS Code extension is being updated. +The Agent Manager includes inline code review — you can leave **line-level review comments directly on the diff**, the same way you would on a pull request. Click a line, type your feedback, and hit "Send all to chat" to send every comment with its file path and line number as structured context to the agent. See the [Agent Manager](/docs/automate/agent-manager) documentation for details. -### Settings include Linux commands that don't exist on Windows +### I had custom command allowlists — where did they go? -This is a known issue. The default command allowlist currently shows bash/Linux commands regardless of your platform. A fix is being worked on to make the default commands platform-dependent. In the meantime, you can manually edit the command allowlist in your settings to match your operating system. +The new extension no longer uses a command allowlist. Instead, shell execution is controlled by the `bash` tool permission in **Settings → Auto Approve**. You can set it to Allow, Ask, or Deny. When set to Ask, you approve or deny each individual command invocation at runtime.