Merge pull request continuedev#4841 from continuedev/dallin/yaml-docs-priority

Edit mode and Settings Page docs updates

Author: RomneyDa

docs/docs/autocomplete/how-to-customize.md

@@ -5,6 +5,6 @@ keywords: [customize]
 sidebar_position: 5
 ---
 
-Continue offers a handful of settings to customize autocomplete behavior. For the most part, these options can be found in the [User Settings Page](../customize/deep-dives/settings.md).
+Continue offers a handful of settings to customize autocomplete behavior. Visit the [User Settings Page](../customize/deep-dives/settings.md) to manage these settings.
 
 For a comprehensive guide on all configuration options and their impacts, see the [Autocomplete deep dive](../customize/deep-dives/autocomplete.mdx).

docs/docs/customize/deep-dives/autocomplete.mdx

@@ -90,9 +90,9 @@ Explore autocomplete model configurations on [the hub](https://hub.continue.dev/
 
 ### Autocomplete User Settings
 
+{/* - `Use autocomplete cache`: If on, caches completions */}
 The following settings can be configured for autocompletion in the IDE extension [User Settings Page](./settings.md):
 
-- `Use autocomplete cache`: If on, caches completions
 - `Multiline Autocompletions`: Controls multiline completions for autocomplete. Can be set to `always`, `never`, or `auto`. Defaults to `auto`
 - `Disable autocomplete in files`: List of comma-separated glob pattern to disable autocomplete in matching files. E.g., "\_/.md, \*/.txt"
 

docs/docs/customize/deep-dives/docs.mdx

@@ -215,7 +215,10 @@ If your documentation is private, you can skip the default crawler and use a loc
   </TabItem>
 </Tabs>
 
-The default local crawler is a lightweight tool that cannot render sites that are dynamically generated using JavaScript. If your sites need to be rendered, you can enable the experimental `Use Chromium for Docs Crawling` feature from your [User Settings Page](./settings.md) This will download and install Chromium to `~/.continue/.utils`, and use it as the local crawler.
+:::info
+Chromium crawling has been deprecated
+{/* The default local crawler is a lightweight tool that cannot render sites that are dynamically generated using JavaScript. If your sites need to be rendered, you can enable the experimental `Use Chromium for Docs Crawling` feature from your [User Settings Page](../deep-dives/settings.md) This will download and install Chromium to `~/.continue/.utils`, and use it as the local crawler. */}
+:::
 
 Further notes:
 
@@ -401,4 +404,4 @@ The following configuration example includes:
   </TabItem>
 </Tabs>
 
-This could also involve enabling Chromium as a backup for local documentation the [User Settings Page](./settings.md).
+{/* This could also involve enabling Chromium as a backup for local documentation the [User Settings Page](../deep-dives/settings.md). */}

docs/docs/customize/deep-dives/settings.md

@@ -14,21 +14,21 @@ Which takes you to this page:
 
 ![User Settings Page](/img/settings-page.png)
 
-Click the `Open Assistant configuration` button to open your configuration file. See the [Configuration Reference](../../reference.md) for more information.
-
 Below that, the following settings which are not part of a configuration file are available:
 
+- `Show Session Tabs`: If on, displays tabs above the chat as an alternative way to organize and access your sessions. Off by default
 - `Wrap Codeblocks`: If on, enables text wrapping in code blocks. Off by default.
-- `Display Raw Markdown`: If on, shows raw markdown in responses. Off by default.
-- `Allow Anonymous Telemetry`: If on, allows Continue to send anonymous telemetry. **On** by default.
-- `Disable Indexing`: Prevents indexing of the codebase, useful primarily for debugging purposes. Off by default.
-- `Disable Session Titles`: Prevents generating summary titles for each chat session when turned on. Off by default
-- `Response Text to Speech`: If on, reads LLM responses aloud with TTS. Off by default.
 - `Show Chat Scrollbar`: If on, enables a scrollbar in the chat window. Off by default.
-- `Use autocomplete cache`: If on, caches completions.
-- `Use Chromium for Docs Crawling`: Use Chromium to crawl docs locally. Useful if the default Cheerio crawler fails on sites that require JavaScript rendering. Downloads and installs Chromium to ~/.continue/.utils. Off by default
-- `Codeblock Actions Position`: Sets the position for the actions that show when hovering over codeblocks. Defaults to `top`
-- `Multiline Autocompletions`: Controls multiline completions for autocomplete. Can be set to `always`, `never`, or `auto`. Defaults to `auto`
+- `Text-to-Speech Output`: If on, reads LLM responses aloud with TTS. Off by default.
+- `Enable Session Titles`: If on, generates summary titles for each chat session after the first message, using the current Chat model. On by default.
+- `Format Markdown`: If off, shows responses as raw text. On by default.
+- `Allow Anonymous Telemetry`: If on, allows Continue to send anonymous telemetry. **On** by default.
+- `Enable Indexing`: Enables indexing of the codebase for the @codebase and @code context providers. **On** by default.
 - `Font Size`: Specifies base font size for UI elements
-- `Workspace prompts path`: Where to find Prompt Files in a workspace - replaces the default .continue/prompts
+- `Multiline Autocompletions`: Controls multiline completions for autocomplete. Can be set to `always`, `never`, or `auto`. Defaults to `auto`
 - `Disable autocomplete in files`: List of comma-separated glob pattern to disable autocomplete in matching files. E.g., "\_/.md, \*/.txt"
+
+<!-- - `Use autocomplete cache`: If on, caches completions. -->
+<!-- - `Use Chromium for Docs Crawling`: Use Chromium to crawl docs locally. Useful if the default Cheerio crawler fails on sites that require JavaScript rendering. Downloads and installs Chromium to ~/.continue/.utils. Off by default -->
+<!-- - `Codeblock Actions Position`: Sets the position for the actions that show when hovering over codeblocks. Defaults to `top` -->
+<!-- - `Workspace prompts path`: Where to find Prompt Files in a workspace - replaces the default .continue/prompts -->

docs/docs/customize/model-roles/intro.mdx

@@ -22,10 +22,10 @@ These roles can be specified for a `config.yaml` model block using `roles`. See
 
 ## Selecting model roles
 
-You can control which of the models in your assistant for a given role will be currently used for that role. Visit the [Settings page](../deep-dives/settings.md) and go to the **Active Models** section.
+You can control which of the models in your assistant for a given role will be currently used for that role. Above the main input, click the 3 dots and then the cube icon to expand the `Models` section. Then you can use the dropdowns to select an active model for each role.
 
 ![Settings Active Models Section](/img/settings-model-roles.png)
 
 :::info
-Note that `roles` do not exist within `config.json` - they are infered by the top level keys like `embeddingsProvider`
+`roles` are not explicitly defined within `config.json` (deprecated) - they are infered by the top level keys like `embeddingsProvider`
 :::

docs/docs/edit/context-selection.md

@@ -9,10 +9,10 @@ keywords: [edit, cmd i, works]
 
 The input you provide is included in the prompt.
 
-## Highlighted code
+## Code to Edit
 
-The highlighted code you’ve selected is included in the prompt. This is the only section of code that the model will attempt to edit.
+The **entire contents** of each file (the current file for Jetbrains inline Edit, each `Code to Edit` item for VS Code Edit mode) are included in the prompt for context. The model will only attempt to edit the highlighted/specified ranges.
 
-## Current file
+## Context Providers
 
-The entire contents of the file containing your highlighted code selection are included as additional context. This gives the model a broader understanding of the code's environment. If the file is too large to fit within the context window, we will trim the file's contents to fit.
+In VS Code Edit mode, you can use `@` to add context using [Context Providers](../customize/context-providers.mdx), similar to [Chat](../chat/context-selection.md). Some context providers may be disabled in Edit mode.

docs/docs/edit/how-it-works.md

@@ -1,14 +1,14 @@
 ---
 title: How Edit works
 sidebar_position: 4
-description: How Edit works
+description: How it works
 keywords: [edit, cmd l, works]
 ---
 
-Using the highlighted code, the contents of the file containing your highlight, and your input instructions, we prompt the model to edit the code according to your instructions. No other additional context is provided to the model.
+Using the highlighted code, the contents of the current file containing your highlight, and your input instructions, we prompt the model to edit the code according to your instructions. No other additional context is provided to the model.
 
 The model response is then streamed directly back to the highlighted range in your code, where we apply a diff formatting to show the proposed changes.
 
 If you accept the diff, we remove the previously highlighted lines, and if you reject the diff, we remove the proposed changes.
 
-If you would like to view the exact prompt that is sent to the model during an edit, you can [view this in the prompt logs](../troubleshooting.mdx#check-the-logs).
+If you would like to view the exact prompt that is sent to the model during an edit, you can [find it in the prompt logs](../troubleshooting.mdx#check-the-logs).

docs/docs/edit/how-to-customize.mdx

@@ -5,7 +5,10 @@ description: How to customize Edit
 keywords: [edit, cmd i, works]
 ---
 
-import TabItem from "@theme/TabItem";
-import Tabs from "@theme/Tabs";
+## Setting active Edit/Apply model
 
-You can configure a particular model to be used for Edit by setting/overriding `roles` in the model's YAML config. See [Edit role](../customize/model-roles/edit.mdx) for more details.
+You can configure particular models from your Assistant to be used for Edit and Apply requests (see [How it Works](./how-it-works.md)). Above the main input, click the 3 dots and then the cube icon to expand the `Models` section. Then, you can use the dropdowns to select models to use for Edit and Apply.
+
+![Settings Active Models Section](/img/model-roles-edit.png)
+
+See [Edit role](../customize/model-roles/edit.mdx) and [Apply role](../customize/model-roles/apply.mdx) for more details.

docs/docs/edit/how-to-use-it.md

@@ -10,17 +10,17 @@ keywords: [edit, cmd l, use]
 
 ## How to use it
 
-Edit is a convenient way to modify code without leaving your current file. Highlight a block of code, describe your code changes, and a diff will be streamed inline to your file which you can accept or reject.
+Edit is a convenient way to make quick changes to specific code and files. Select code, describe your code changes, and a diff will be streamed inline to your file which you can accept or reject.
 
-Edit is best used for small, quick changes such as:
+Edit is recommended for small, targeted changes, such as
 
 - Writing comments
 - Generating unit tests
 - Refactoring functions or methods
 
 ## Highlight code and activate
 
-Highlight the block of code you would like to modify, and press <kbd>cmd/ctrl</kbd> + <kbd>i</kbd> to activate the edit input.
+Highlight the block of code you would like to modify and press <kbd>cmd/ctrl</kbd> + <kbd>i</kbd> to active Edit mode. You can also enter Edit mode by pressing <kbd>cmd/ctrl</kbd> + <kbd>i</kbd> with no code highlighted.
 
 ## Describe code changes
 
@@ -35,3 +35,45 @@ You can navigate through each proposed change, accepting or rejecting them using
 You can also accept or reject all changes at once using <kbd>cmd/ctrl</kbd> + <kbd>shift</kbd> + <kbd>enter</kbd> (to accept) or <kbd>cmd/ctrl</kbd> + <kbd>shift</kbd> + <kbd>delete/backspace</kbd> (to reject).
 
 If you want to request a new suggestion for the same highlighted code section, you can use <kbd>cmd/ctrl</kbd> + <kbd>i</kbd> to re-prompt the model.
+
+## VS Code
+
+In VS Code, Edit is implemented in the extension sidebar with a similar interface to [Chat](../chat/how-it-works.md), and you can also enter Edit mode by using the Mode Selector below the main Chat input to select `Edit`.
+
+![edit mode selected](/img/select-edit-mode.png)
+
+You can also reject and accept diffs using the `Reject All` and `Accept All` buttons that show up in the Chat when diffs are present (see examples below).
+
+### Adding Code to Edit
+
+Along with adding highlighted code, you can also manually add files to edit using the `Add file` combobox or by clicking the dropdown and selecting `Add all open files` to add all files that are currently open in the editor.
+
+**_Add file combobox_**
+
+![edit mode add file combobox](/img/edit-mode-add-files.png)
+
+**_Add all open files dropdown_**
+
+![edit mode add file combobox](/img/edit-mode-add-all-open-files.png)
+
+### Single File Edit
+
+If one file/range is present in `Code to Edit` on submission, Continue will prompt the Edit model and then automatically stream the diff into the editor.
+
+![Edit mode single file diffs](/img/edit-mode-single-file-diff.png)
+
+### Multi-File Edit
+
+If multiple files/ranges are present in `Code to Edit` on submission, Continue will prompt the Edit model to output codeblocks per-file, which the user can then choose to apply and accept/reject independently.
+
+**_Generated Content_**
+
+![Edit mode multi file generated content](/img/edit-mode-multi-file-generation.png)
+
+**_Diffs_**
+
+![Edit mode multi file diffs](/img/edit-mode-multi-file-diffs.png)
+
+## Jetbrains
+
+In Jetbrains, Edit is implemented as an inline popup (see the header GIF example) for single-file edit. Multi-file edit mode is not currently implemented.

docs/docs/edit/model-setup.md

@@ -5,8 +5,6 @@ description: How to set up an Edit model
 keywords: [edit, cmd l, model]
 ---
 
-By default, Edit uses the [same model as Chat](../chat/model-setup.mdx) since we recommend a similar, 400B+ parameter model or one of the frontier model for code edits.
+By default, Edit uses the [same model as Chat](../chat/model-setup.mdx), and we recommend [Claude 3.7 Sonnet](https://hub.continue.dev/anthropic/claude-3-7-sonnet) from Anthropic. Visit [the Hub](https://hub.continue.dev/explore/models?roles=edit) to explore other Edit models.
 
-Visit [the hub](https://hub.continue.dev/explore/models?roles=edit) to explore Edit models.
-
-You can configure a different model to be used for edits by updating your [configuration](../customize/model-roles/edit.mdx).
+For the best Edit experience, we also recommend setting up an Apply model, specially trained to apply diffs to files. We recommend [Morph v0 Fast Apply](https://hub.continue.dev/morphllm/morph-v0) or [Relace Instant Apply](https://hub.continue.dev/relace/instant-apply). Explore other apply models on the [the Hub](https://hub.continue.dev/explore/models?roles=apply).

docs/docs/json-reference.md

@@ -405,7 +405,7 @@ Example
 
 ### Fully deprecated settings
 
-Some deprecated `config.json` settings are no longer stored in config and have been moved to be editable through the [User Settings Page](./customize/deep-dives/settings.md). If found in `config.json`, they will be migrated to the [User Settings Page](./customize/deep-dives/settings.md) and removed from `config.json`.
+Some deprecated `config.json` settings are no longer stored in config and have been moved to be editable through the [User Settings Page](./customize/deep-dives/settings.md). If found in `config.json`, they will be auto-migrated to User Settings and removed from `config.json`.
 
 - `allowAnonymousTelemetry`: This value will be migrated to the safest merged value (`false` if either are `false`).
 - `promptPath`: This value will override during migration.

docs/docs/reference.md

@@ -8,10 +8,15 @@ keywords: [config, yaml, configuration, customize, customization]
 
 ## Introduction
 
-Continue hub assistants are defined using the `config.yaml` specification. Local assistants can also be configured using a YAML file `config.yaml` placed in your global `.continue` folder (`~/.continue` on Mac, `%USERPROFILE%\.continue`)
+Continue hub assistants are defined using the `config.yaml` specification. Assistants can be loaded from [the Hub](https://hub.continue.dev/explore/assistants) or locally
+
+- [Continue Hub](https://hub.continue.dev/explore/assistants) - YAML is stored on the hub and automatically synced to the extension
+- Locally
+  - in your global `.continue` folder (`~/.continue` on Mac, `%USERPROFILE%\.continue`) within `.continue/assistants`. The name of the file will be used as the display name of the assistant, e.g. `My Assistant.yaml`
+  - in your workspace in a `/.continue/assistants` folder, with the same naming convention
 
 :::info
-Config YAML replaces `config.json`. View the **[Migration Guide](/yaml-migration)**.
+Config YAML replaces `config.json`, which is deprecated. View the **[Migration Guide](/yaml-migration)**.
 :::
 
 An assistant is made up of:
@@ -32,7 +37,7 @@ Hub blocks and assistants are identified with a slug in the format `owner-slug/b
 Blocks can be imported into an assistant by adding a `uses` clause under the block type. This can be alongside other `uses` clauses or explicit blocks of that type.
 
 :::info
-Note that `uses` blocks cannot be used with a local `config.yaml`
+Note that local assistants cannot use blocks that require organization-level secrets.
 :::
 
 For example, the following assistant imports an Anthropic model and defines an Ollama DeepSeek one.
@@ -473,28 +478,3 @@ models:
     roles:
       - autocomplete
 ```
-
-### Fully deprecated settings
-
-Some deprecated `config.json` settings are no longer stored in config and have been moved to be editable through the [User Settings Page](./customize/deep-dives/settings.md). If found in `config.json`, they will be migrated to the [User Settings Page](./customize/deep-dives/settings.md) and removed from `config.json`.
-
-- `allowAnonymousTelemetry`: This value will be migrated to the safest merged value (`false` if either are `false`).
-- `promptPath`: This value will override during migration.
-- `disableIndexing`: This value will be migrated to the safest merged value (`true` if either are `true`).
-- `disableSessionTitles`/`ui.getChatTitles`: This value will be migrated to the safest merged value (`true` if either are `true`). `getChatTitles` takes precedence if set to false
-- `tabAutocompleteOptions`
-  - `useCache`: This value will override during migration.
-  - `disableInFiles`: This value will be migrated to the safest merged value (arrays of file matches merged/deduplicated)
-  - `multilineCompletions`: This value will override during migration.
-- `experimental`
-  - `useChromiumForDocsCrawling`: This value will override during migration.
-  - `readResponseTTS`: This value will override during migration.
-- `ui` - all will override during migration
-
-  - `codeBlockToolbarPosition`
-  - `fontSize`
-  - `codeWrap`
-  - `displayRawMarkdown`
-  - `showChatScrollbar`
-
-  See [User Settings Page](./customize/deep-dives/settings.md) for more information about each option.

docs/docs/yaml-migration.md

@@ -327,7 +327,7 @@ mcpServers:
 
 ## Deprecated configuration options
 
-Some deprecated `config.json` settings are no longer stored in config and have been moved to be editable through the [User Settings Page](./customize/deep-dives/settings.md) (Gear Icon). If found in `config.json`, they will be migrated to the [User Settings Page](./customize/deep-dives/settings.md) and removed from `config.json`.
+Some deprecated `config.json` settings are no longer stored in config and have been moved to be editable through the [User Settings Page](./customize/deep-dives/settings.md) (Gear Icon). If found in `config.json`, they will be auto-migrated to User Settings and removed from `config.json`.
 
 See the [JSON Config Reference](./json-reference#fully-deprecated-settings) for more information on fully deprecated options.
 

docs/sidebars.js

@@ -171,7 +171,7 @@ const sidebars = {
       type: "link",
       label: "Customize",
       href: "/customize/overview",
-    }
+    },
   ],
 };