Docs: align feature pages with current behavior

docs/features/api-configuration-profiles.mdx

@@ -40,7 +40,7 @@ Having multiple configuration profiles lets you quickly switch between different
 Configuration profiles can have their own:
 - API providers (OpenAI, Anthropic, OpenRouter, Glama, etc.)
 - API keys and authentication details
-- Model selections (o3-mini-high, Claude 3.7 Sonnet, DeepSeek R1, etc.)
+- Model selections (for example: o3-mini-high, Claude 3.7 Sonnet, DeepSeek R1)
 - [Temperature settings](/features/model-temperature) for controlling response randomness
 - Thinking budgets
 - Provider-specific settings
@@ -73,9 +73,8 @@ Note that available settings vary by provider and model. Each provider offers di
 
       <img src="/img/api-configuration-profiles/api-configuration-profiles-8.png" alt="Model selection interface" width="550" />
    - Configure the **Rate Limit** for this profile:
-     - **Default is 0 (disabled), which is suitable for most users.** If needed, you can set a minimum time (in seconds) between API requests *for this profile* to help manage costs or avoid provider rate limits.
-     - A value of 0 disables rate limiting (default).
-     - Requests using other profiles follow their own rate limits.
+     - **Default is 0 (disabled), which is suitable for most users.** Set a minimum time (seconds) between requests *for this profile* to manage costs or reduce provider throttling.
+     - Other profiles use their own rate limit settings.
 
          <img src="/img/api-configuration-profiles/api-configuration-profiles-12.png" alt="Rate limit slider control within API profile settings" width="550" />
    - Adjust model parameters (like [temperature](/features/model-temperature))
@@ -95,8 +94,8 @@ The API configuration dropdown now supports pinning your favorite profiles for q
 
 1. Hover over any profile in the dropdown to reveal the pin icon
 2. Click the pin icon to add the profile to your pinned list
-3. Pinned profiles appear at the top of the dropdown, sorted alphabetically
-4. Unpinned profiles appear below a separator, also sorted alphabetically
+3. Pinned profiles appear at the top of the dropdown (with a separator)
+4. The list order follows your saved profile order (typically creation order)
 5. You can unpin a profile by clicking the same icon again
 
 <img src="/img/api-configuration-profiles/api-configuration-profiles-4.png" alt="Pinning API configuration profiles" width="550" />

docs/features/browser-use.mdx

@@ -82,12 +82,12 @@ Browse http://localhost:3000, scroll down to the bottom of the page and check if
 
 ## How Browser Actions Work
 
-The browser_action tool controls a browser instance that returns screenshots and console logs after each action, allowing you to see the results of interactions.
+Browser actions control a browser session and return screenshots (and logs) after each step, so you can verify results as you go.
 
 Key characteristics:
 - Each browser session must start with `launch` and end with `close`
 - Only one browser action can be used per message
-- While the browser is active, no other tools can be used
+- You can use other tools while the browser session is active
 - You must wait for the response (screenshot and logs) before performing the next action
 
 ### Available Browser Actions
@@ -103,10 +103,11 @@ Key characteristics:
 | `hover` | Moves cursor to coordinates | Triggering hover states |
 | `press` | Presses a key combination | Keyboard shortcuts, Enter, Esc |
 | `resize` | Resizes the viewport | Testing responsive designs |
+| `screenshot` | Saves a screenshot to a file path | Capturing page state for later review |
 
 ---
 
-## Browser Use Configuration/Settings
+## Settings
 
 :::info Default Browser Settings
 - **Enable browser tool**: Enabled

docs/features/codebase-indexing.mdx

@@ -166,7 +166,7 @@ This guide explains each setting available in the configuration popover.
 
 - **Embedder Provider**
   - **Purpose**: To select your source for generating AI embeddings.
-  - **Behavior**: This dropdown menu determines which configuration fields are shown. Your options are **OpenAI**, **Google Gemini**, **Ollama**, and **OpenAI Compatible**.
+  - **Behavior**: This dropdown menu determines which configuration fields are shown. Common options include **OpenAI**, **Google Gemini**, **Ollama**, and **OpenAI Compatible** (availability depends on your Roo Code version).
 
 - **API Key** (for OpenAI, Gemini, OpenAI Compatible)
   - **Purpose**: The secret key to authenticate with your chosen provider.
@@ -221,10 +221,10 @@ The system uses a sophisticated parsing strategy:
 
 1. **Tree-sitter First**: For supported languages, it uses AST parsing to identify semantic code blocks (functions, classes, methods)
 2. **Markdown Support**: Indexes Markdown files by treating headers as semantic entry points
-3. **Intelligent Fallback**: For unsupported file types, it falls back to line-based chunking
+3. **Intelligent Fallback**: For supported file types where Tree-sitter parsing isn’t used (or yields no semantic captures), it falls back to line-based chunking
 
 **Block Sizing**:
-- Minimum: 100 characters
+- Minimum: 50 characters
 - Maximum: 1,000 characters
 - Large functions are split intelligently at logical boundaries
 

docs/features/concurrent-file-reads.md

@@ -10,7 +10,7 @@ keywords:
 sidebar_label: 'Multi-File Reads'
 ---
 
-# Concurrent File Reads (AKA Multi-File Reads)
+# Multi-File Reads (Concurrent File Reads)
 
 The Concurrent File Reads feature allows Roo to read multiple files from your workspace in a single step. This significantly improves efficiency when working on tasks that require context from several files, as Roo can gather all the necessary information at once instead of reading files one by one.
 
@@ -64,7 +64,7 @@ When Roo requests to read multiple files, you'll see a batch approval interface
 
 ## Configuration
 
-You can configure the Multi-File Read feature by clicking the <Codicon name="gear" /> icon and navigating to the "Context" section of the settings.
+You can configure Multi-File Reads by clicking the gear icon in Roo Code settings, then opening the **Context** section.
 
 <img src="/img/concurrent-file-reads/concurrent-file-reads-1.png" alt="Concurrent file reads settings showing limit slider" width="600" />
 
@@ -73,5 +73,5 @@ You can configure the Multi-File Read feature by clicking the <Codicon name="gea
     *   **Description**: This setting determines the maximum number of files that Roo can read in a single request. The default is 5, with a range of 1-100 files. Higher values can speed up tasks involving many small files but may use more memory. Setting the value to 1 effectively disables concurrent reads, reverting to single-file reads.
 
 :::note
-The per‑request file limit is configured in the UI (default 5, up to 100). The backend [`read_file`](/advanced-usage/available-tools/read-file) tool doesn’t hard‑enforce a cap; actual behavior may also depend on the selected model/tool.
+The per‑request file limit is configured in the UI (default 5, up to 100). The [`read_file`](/advanced-usage/available-tools/read-file) tool enforces this cap; if you request more files than allowed, Roo will ask you to split reads into smaller batches.
 :::

docs/features/custom-instructions.md

@@ -73,7 +73,7 @@ These instructions apply across all workspaces and maintain your preferences reg
 **How to set them:**
 
 <img src="/img/custom-instructions/custom-instructions.png" alt="Roo Code Prompts tab showing global custom instructions interface" width="600" />
-1.  **Open Prompts Tab:** Click the <Codicon name="notebook" /> icon in the Roo Code top menu bar
+1.  **Open Prompts Tab:** Click the notebook icon in the Roo Code top menu bar
 2.  **Find Section:** Find the "Custom Instructions for All Modes" section
 3.  **Enter Instructions:** Enter your instructions in the text area
 4.  **Save Changes:** Click "Done" to save your changes
@@ -204,7 +204,7 @@ Mode-specific instructions can be set in two independent ways that can be used s
 1.  **Using the Prompts Tab:**
 
     <img src="/img/custom-instructions/custom-instructions-2.png" alt="Roo Code Prompts tab showing mode-specific custom instructions interface" width="600" />
-    * **Open Tab:** Click the <Codicon name="notebook" /> icon in the Roo Code top menu bar
+    * **Open Tab:** Click the notebook icon in the Roo Code top menu bar
     * **Select Mode:** Under the Modes heading, click the button for the mode you want to customize
     * **Enter Instructions:** Enter your instructions in the text area under "Mode-specific Custom Instructions (optional)"
     * **Save Changes:** Click "Done" to save your changes
@@ -278,10 +278,10 @@ Rules:
 * **Recursive Reading:** Rules directories are read recursively, including all files in subdirectories
 * **File Filtering:** System automatically excludes cache and temporary files (`.DS_Store`, `*.bak`, `*.cache`, `*.log`, `*.tmp`, `Thumbs.db`, etc.)
 * **Empty Files:** Empty or missing rule files are silently skipped
-* **Source Headers:** Directory-based rules include per-file headers `# Rules from {absolute path}:`, while file-based rules include `# Rules from {filename}:` headers
+* **Source Headers:** Directory-based rules include per-file headers `# Rules from {relative path}:`, while file-based rules include `# Rules from {filename}:` headers
 * **Aggregation:** Both global and workspace rules directories are aggregated for mode-specific and generic rules (not either-or)
 * **Sorting:** Files are sorted by basename only, case-insensitive
-* **Header Paths:** Header paths are absolute and follow symlinks
+* **Header Paths:** Header paths are shown relative to the workspace; symlinks are resolved for reading (max depth 5)
 * **Rule Interaction:** Mode-specific rules complement global rules rather than replacing them
 * **Symbolic Links:** Fully supported for both files and directories, with a maximum resolution depth of 5 to prevent infinite loops
 

docs/features/custom-modes.mdx

@@ -32,8 +32,8 @@ Roo Code allows you to create **custom modes** to tailor Roo's behavior to speci
 
 <br />
 
-:::tip Sticky Models for Efficient Workflow
-Each mode—including custom ones—features **Sticky Models**. This means Roo Code automatically remembers and selects the last model you used with a particular mode. This lets you assign different preferred models to different tasks without constant reconfiguration, as Roo switches between models when you change modes.
+:::tip Sticky API Config per mode
+Each mode—including custom ones—remembers and restores the last **API configuration / provider profile** you used with that mode. This lets you assign different preferred provider/model/settings to different tasks without constant reconfiguration.
 :::
 
 :::info Discover Community Modes
@@ -113,6 +113,8 @@ Roo packages the mode's configuration and any rules found in the project's `.roo
 
 **Note:** When exporting modes with rules, all file paths are normalized to use forward slashes for cross-platform compatibility. This ensures modes can be shared between team members using different operating systems.
 
+**Note:** Export includes rule files found directly inside the rules folder (not nested subfolders).
+
 ---
 
 ### Exported YAML file format:

docs/features/enhance-prompt.md

@@ -19,7 +19,7 @@ The "Enhance Prompt" feature in Roo Code helps you improve the quality and effec
 ## Why Use Enhance Prompt?
 
 *   **Improved Clarity:**  Roo Code can rephrase your prompt to make it more understandable for the AI model.
-*   **Added Context:**  The enhancement process can add relevant context to your prompt, such as the current file path or selected code.
+*   **Added Context:** The enhancement process can add relevant context to your prompt, such as recent conversation history (when enabled).
 *   **Better Instructions:**  Roo Code can add instructions to guide the AI towards a more helpful response (e.g., requesting specific formatting or a particular level of detail).
 *   **Reduced Ambiguity:**  Enhance Prompt helps to eliminate ambiguity and ensure that Roo Code understands your intent.
 *   **Consistency**: Roo will consistently format prompts the same way to the AI.
@@ -32,7 +32,7 @@ The "Enhance Prompt" feature in Roo Code helps you improve the quality and effec
 1.  **Type your initial prompt:**  Enter your request in the Roo Code chat input box as you normally would.  This can be a simple question, a complex task description, or anything in between.
 2.  **Click the Wand Icon:**  Instead of pressing Enter, click the wand icon located in the top right corner of the chat input box. While Roo processes your enhancement request, the wand icon will spin to indicate it's working.
 3.  **Review the Enhanced Prompt:**  Roo Code will replace your original prompt with an enhanced version.  Review the enhanced prompt to make sure it accurately reflects your intent. You can further refine the enhanced prompt before sending. Changed your mind? You can undo the enhancement using Ctrl+Z (Cmd+Z on Mac) to restore your original prompt.
-4.  **Send the Enhanced Prompt:**  Press Enter or click the Send icon (<Codicon name="send" />) to send the enhanced prompt to Roo Code.
+4.  **Send the Enhanced Prompt:** Press Enter or click the Send button to send the enhanced prompt to Roo Code.
 
 ---
 
@@ -54,7 +54,7 @@ The "Enhance Prompt" feature uses a customizable prompt template. You can modify
 
 ### Accessing Prompts Settings
 
-1.  **Open Settings:** Click the gear icon (<Codicon name="gear" />) in the Roo Code panel or use the settings command.
+1.  **Open Settings:** Click the gear icon in the Roo Code panel or use the settings command.
 2.  **Navigate to Prompts:** Go to the "Prompts" tab in the settings.
 3.  **Select "ENHANCE":** From the dropdown menu, select "ENHANCE" to view and edit the enhancement prompt.
 

docs/features/marketplace.mdx

@@ -57,7 +57,7 @@ The Roo Code Marketplace is available directly within the Roo Code extension in
 The marketplace offers two types of items:
 
 ### MCPs (Model Context Protocol)
-MCPs allow Roo Code to connect to and interact with various AI models, APIs, and other external tools. By installing an MCP, you can configure Roo Code to use different language models (like those from OpenAI, Anthropic, or others) or to integrate with other services. Learn more about [What is MCP?](/features/mcp/what-is-mcp) and [how to use MCP in Roo Code](/features/mcp/using-mcp-in-roo).
+MCP servers allow Roo Code to discover and call external **tools/resources** (via MCP), such as ticketing systems, databases, or internal services. Learn more about [What is MCP?](/features/mcp/what-is-mcp) and [how to use MCP in Roo Code](/features/mcp/using-mcp-in-roo).
 
 <img src="/img/marketplace/marketplace-1.png" alt="MCP tab showing available MCPs with install and remove buttons" width="500" />
 

docs/features/mcp/server-transports.md

@@ -112,12 +112,15 @@ Streamable HTTP transport is ideal for:
 
 ### Streamable HTTP Implementation Example
 
-Configuration in `settings.json`:
+In Roo Code, MCP servers are configured in `mcp_settings.json` (global) or `.roo/mcp.json` (project):
+
 ```json
-"mcp.servers": {
-  "StreamableHTTPMCPName": {
-    "type": "streamable-http",
-    "url": "http://localhost:8080/mcp"
+{
+  "mcpServers": {
+    "StreamableHTTPMCPName": {
+      "type": "streamable-http",
+      "url": "http://localhost:8080/mcp"
+    }
   }
 }
 ```

docs/features/mcp/using-mcp-in-roo.mdx

@@ -209,7 +209,7 @@ Streamable HTTP configuration example:
 
   SSE (Legacy) configuration parameters:
 
-  *   `type` (optional, but recommended for clarity): Should be set to `"sse"` if providing a `url` for an SSE server, to distinguish from Streamable HTTP. If `url` is present and `type` is omitted, Roo Code might try to infer, but explicit declaration is safer.
+  *   `type` (required when `url` is present): Must be explicitly set to either `"sse"` or `"streamable-http"`.
   *   `url` (required): The base URL for the remote MCP server. For legacy SSE, this usually implies separate paths like `/events` (for SSE stream) and `/message` (for POST requests) will be derived or expected by the server.
   *   `headers` (optional): An object containing custom HTTP headers to send with requests (e.g., for authentication tokens).
   *   `alwaysAllow` (optional): An array of tool names from this server to automatically approve.
@@ -310,7 +310,7 @@ Each MCP server has its own configuration panel where you can modify settings, m
 
 To set the maximum time to wait for a response after a tool call to the MCP server:
 
-1. Click the `Network Timeout` pulldown at the bottom of the individual MCP server's config box and change the time. Default is 1 minute but it can be set between 30 seconds and 5 minutes.
+1. Click the `Network Timeout` pulldown at the bottom of the individual MCP server's config box and change the time. Default is 1 minute; you can choose values from 15 seconds up to 60 minutes.
 
 <img src="/img/using-mcp-in-roo/using-mcp-in-roo-6.png" alt="Network Timeout pulldown" width="400" />