diff --git a/docs/features/api-configuration-profiles.mdx b/docs/features/api-configuration-profiles.mdx index e7cf5a5b..f662a553 100644 --- a/docs/features/api-configuration-profiles.mdx +++ b/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 Model selection interface - 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. Rate limit slider control within API profile settings - 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 Pinning API configuration profiles diff --git a/docs/features/browser-use.mdx b/docs/features/browser-use.mdx index 8070c67d..a250ef6c 100644 --- a/docs/features/browser-use.mdx +++ b/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 diff --git a/docs/features/codebase-indexing.mdx b/docs/features/codebase-indexing.mdx index 5f1fc72a..1f2e6e4b 100644 --- a/docs/features/codebase-indexing.mdx +++ b/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 diff --git a/docs/features/concurrent-file-reads.md b/docs/features/concurrent-file-reads.md index 7794008b..d159f65d 100644 --- a/docs/features/concurrent-file-reads.md +++ b/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 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. Concurrent file reads settings showing limit slider @@ -73,5 +73,5 @@ You can configure the Multi-File Read feature by clicking the -1. **Open Prompts Tab:** Click the 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:** Roo Code Prompts tab showing mode-specific custom instructions interface - * **Open Tab:** Click the 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 diff --git a/docs/features/custom-modes.mdx b/docs/features/custom-modes.mdx index 582d73b6..6389c914 100644 --- a/docs/features/custom-modes.mdx +++ b/docs/features/custom-modes.mdx @@ -32,8 +32,8 @@ Roo Code allows you to create **custom modes** to tailor Roo's behavior to speci
-:::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: diff --git a/docs/features/enhance-prompt.md b/docs/features/enhance-prompt.md index 227d42b2..d18ae421 100644 --- a/docs/features/enhance-prompt.md +++ b/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 () 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 () 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. diff --git a/docs/features/marketplace.mdx b/docs/features/marketplace.mdx index 446a8f85..3c79fde9 100644 --- a/docs/features/marketplace.mdx +++ b/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). MCP tab showing available MCPs with install and remove buttons diff --git a/docs/features/mcp/server-transports.md b/docs/features/mcp/server-transports.md index 5f4ce6eb..f9780ce7 100644 --- a/docs/features/mcp/server-transports.md +++ b/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" + } } } ``` diff --git a/docs/features/mcp/using-mcp-in-roo.mdx b/docs/features/mcp/using-mcp-in-roo.mdx index 1b1c6ed9..78126015 100644 --- a/docs/features/mcp/using-mcp-in-roo.mdx +++ b/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. Network Timeout pulldown diff --git a/docs/features/message-queueing.md b/docs/features/message-queueing.md index fae933dd..af5be02b 100644 --- a/docs/features/message-queueing.md +++ b/docs/features/message-queueing.md @@ -22,7 +22,9 @@ No more waiting! Type your follow-up thoughts, corrections, or additional reques ## Overview -Message queueing lets you type and send messages while Roo is still working. Just type your message and hit Enter - it gets queued and will be processed as soon as Roo is ready for your next input. When a queued message is processed, Roo implicitly approves whatever would normally require your confirmation (tool calls, file writes, running commands)—even if auto-approval is disabled. This is useful for quick corrections or additions when you want to keep work moving without manual prompts. +Message queueing lets you type and send messages while Roo is still working. Just type your message and hit Enter - it gets queued and will be processed as soon as Roo is ready for your next input. + +If Roo is currently waiting on an approval prompt (for example: tool use, command execution, browser session launch, or MCP server use), the next queued message will be used to proceed past that prompt (equivalent to clicking “Approve”), even if auto-approval is disabled. --- @@ -33,7 +35,7 @@ While Roo is working: 1. **Type your message** as normal 2. **Press Enter** or click Send 3. **Message gets queued** and appears with "Queued Messages:" label -4. **Roo processes the queued message** as soon as it's ready for your next input and implicitly approves the next pending action (e.g., a tool call, file write, or command)—even if auto-approval is disabled +4. **Roo processes the queued message** as soon as it's ready for your next input. If Roo is blocked on an approval prompt, this may also implicitly approve the next pending approval prompt (e.g., tool use, command execution, browser session launch, or MCP server use)—even if auto-approval is disabled Message queueing interface showing active processing and three queued messages @@ -45,9 +47,11 @@ While Roo is working: The input field stays active so you can type anytime - just hit Enter to queue your message. -:::warning Queued Messages Implicitly Approve -Queued messages act as approval for the next action. When a queued message is processed, Roo proceeds with whatever would normally require confirmation (tool calls, file writes, running commands)—even if auto-approval is disabled. +:::warning Queued Messages Can Implicitly Approve +If Roo is blocked on an approval prompt, processing a queued message can act like clicking “Approve” for that prompt (for example: tool use, command execution, browser session launch, or MCP server use)—even if auto-approval is disabled. + Editing or deleting a queued message requires clicking it before it's processed. In fast workflows this window can be extremely short; if you need a manual review step, avoid queueing until you're ready to approve. + Note: This behavior is distinct from [Auto-Approving Actions](/features/auto-approving-actions) and is not controlled by its settings. ::: @@ -63,10 +67,10 @@ A: There is no hard limit on the number of messages you can queue. The queue siz A: No, messages are always processed in the order they were sent (FIFO). **Q: Do queued messages require approval?** -A: No. When processed, a queued message implicitly approves the next pending action (tool calls, file writes, running commands), even if auto-approval is disabled. If you need a manual review step, do not queue the message; wait for the approval prompt and confirm manually. +A: No. If Roo is blocked on an approval prompt, processing a queued message can implicitly approve that prompt (for example: tool use, command execution, browser session launch, or MCP server use)—even if auto-approval is disabled. If you need a manual review step, do not queue the message; wait for the approval prompt and confirm manually. **Q: Why are my queued messages triggering auto-approval?** -A: This isn’t the Auto-Approving Actions setting. Queueing a message tells Roo to proceed without pausing for confirmations, so the queued message implicitly approves the next action. To avoid this, don’t queue when you need a manual review—wait for the approval prompt and confirm manually. See [Auto-Approving Actions](/features/auto-approving-actions) for settings-based approvals. +A: This isn’t the Auto-Approving Actions setting. Queueing a message can let Roo proceed past an approval prompt without pausing. To avoid this, don’t queue when you need a manual review—wait for the approval prompt and confirm manually. See [Auto-Approving Actions](/features/auto-approving-actions) for settings-based approvals. **Q: What happens if Roo encounters an error?** A: Queued messages remain in the queue. You can choose to cancel them or let processing continue. diff --git a/docs/features/model-temperature.md b/docs/features/model-temperature.md index 57f2ac8c..6583a2b6 100644 --- a/docs/features/model-temperature.md +++ b/docs/features/model-temperature.md @@ -10,10 +10,11 @@ keywords: --- import KangarooIcon from '@site/src/components/KangarooIcon'; +import Codicon from '@site/src/components/Codicon'; # Model Temperature -Temperature controls the randomness of AI model outputs. Adjusting this setting optimizes results for different tasks - from precise code generation to creative brainstorming. Temperature is one of the most powerful parameters for controlling AI behavior. A well-tuned temperature setting can dramatically improve the quality and appropriateness of responses for specific tasks. +Temperature controls how random or predictable an AI model’s output is. Adjust it to optimize results for different tasks—from precise code generation to creative brainstorming. Animation showing temperature slider adjustment @@ -36,9 +37,9 @@ Temperature controls output randomness, not code quality or accuracy directly. K ## Default Values in Roo Code -Roo Code uses a default temperature of 0.0 for most models, optimizing for maximum determinism and precision in code generation. This applies to OpenAI models, Anthropic models (non-thinking variants), LM Studio models, and most other providers. +Roo Code falls back to a default temperature of 0.0 unless the selected model/provider defines its own `defaultTemperature`. -Some models use higher default temperatures - DeepSeek R1 models and certain reasoning-focused models default to 0.6, providing a balance between determinism and creative exploration. +Some models use higher default temperatures — for example, DeepSeek R1 models default to 0.3. Models with thinking capabilities (where the AI shows its reasoning process) require a fixed temperature of 1.0 which cannot be changed, as this setting ensures optimal performance of the thinking mechanism. This applies to any model with the ":thinking" flag enabled. diff --git a/docs/features/more-features.md b/docs/features/more-features.md index 74d472bd..61b60069 100644 --- a/docs/features/more-features.md +++ b/docs/features/more-features.md @@ -20,9 +20,9 @@ This page describes additional features in Roo Code that enhance your developmen ## Suggested Responses -Roo Code provides suggested responses to questions, saving you time typing. These suggestions appear as buttons below the chat input box after you ask a question. Click a suggestion to quickly use it as your next prompt. +For details and screenshots, see [Suggested Responses](/features/suggested-responses). -This feature aims to streamline your workflow by anticipating your potential follow-up questions and providing one-click access to relevant prompts. +Suggested responses appear as one-click buttons under the chat input to help you continue the conversation quickly. --- @@ -30,7 +30,7 @@ This feature aims to streamline your workflow by anticipating your potential fol Roo Code includes a Text-to-Speech (TTS) feature that reads out the AI responses, allowing you to listen to the information instead of reading it. This can be helpful for accessibility, learning, or simply for a change of pace. -To use Text-to-Speech, simply enable it in the Roo Code settings. Once enabled, a speaker icon will appear next to each AI response in the chat. Click the icon to start listening. +To use Text-to-Speech, enable it in the Roo Code settings. When enabled, Roo automatically reads new assistant messages aloud, and a stop control appears in the chat input area while audio is playing. --- diff --git a/docs/features/rooignore.md b/docs/features/rooignore.md index a9988515..01088cc8 100644 --- a/docs/features/rooignore.md +++ b/docs/features/rooignore.md @@ -80,7 +80,7 @@ These tools directly check `.rooignore` before any file operation. If a file is ## User Experience and Notifications -* **Visual Cue (🔒)**: In file listings and `@directory` attachments, files ignored by `.rooignore` may be marked with a lock symbol (🔒), depending on the `showRooIgnoredFiles` setting (defaults to `true`). +* **Visual Cue (🔒)**: In file listings and `@directory` attachments, files ignored by `.rooignore` may be marked with a lock symbol (🔒), depending on the `showRooIgnoredFiles` setting (default may depend on whether the setting has been saved yet). * **Ignore Messages**: Single file mentions return "(File is ignored by .rooignore)" instead of content. * **Error Messages**: If a tool operation is blocked, Roo receives an error: `"Access to [file_path] is blocked by the .rooignore file settings. You must try to continue in the task without using this file, or ask the user to update the .rooignore file."` * **Chat Notifications**: You will typically see a notification in the Roo chat interface when an action is blocked due to `.rooignore`. diff --git a/docs/features/suggested-responses.md b/docs/features/suggested-responses.md index 59ab7411..b98d59e8 100644 --- a/docs/features/suggested-responses.md +++ b/docs/features/suggested-responses.md @@ -42,14 +42,14 @@ You have three options for using suggested responses: * **Result**: The selected answer is immediately sent back to Roo as your response. This is the quickest way to reply if one of the suggestions perfectly matches your intent. 2. **Keyboard Shortcut**: - * **Action**: Use the `roo.acceptInput` command with your configured keyboard shortcut. - * **Result**: The primary (first) suggestion button is automatically selected. + * **Action**: Use the `roo-cline.acceptInput` command with your configured keyboard shortcut. + * **Result**: If Roo is showing action buttons (for example: Approve/Run), this triggers the primary action. It does not specifically select a follow-up suggestion. * **Note**: For setup details, see [Keyboard Shortcuts](/features/keyboard-shortcuts). 3. **Edit Before Sending**: * **Action**: * Hold down `Shift` and click the suggestion button. - * *Alternatively*, hover over the suggestion button and click the pencil icon () that appears. + * *Alternatively*, hover over the suggestion button and click the copy icon that appears. * **Result**: The text of the suggestion is copied into the chat input box. You can then modify the text as needed before pressing Enter to send your customized response. This is useful when a suggestion is close but needs minor adjustments. Chat input box showing text copied from a suggested response, ready for editing diff --git a/docs/features/task-todo-list.mdx b/docs/features/task-todo-list.mdx index 4cf767cd..853ec6a4 100644 --- a/docs/features/task-todo-list.mdx +++ b/docs/features/task-todo-list.mdx @@ -82,29 +82,21 @@ Todo lists appear in multiple places: Interactive todo list tool block in chat -3. **Environment Details**: Todo lists appear as a "REMINDERS" table in the environment_details section, giving the AI persistent access to current todo state. Note: If the `todoListEnabled` setting is disabled, the reminders section will not appear in environment details. +3. **Environment Details**: Todo lists appear as a "REMINDERS" table in the environment_details section, giving the AI persistent access to current todo state. ### Expanded Todo View -When you click on the collapsed todo summary in the task header, a floating panel appears with enhanced functionality: -- **Backdrop overlay**: Click outside the panel to close it -- **Full todo list display**: Shows all todos with their current status indicators -- **Auto-scroll**: Automatically scrolls to the current in-progress task -- **Smooth animations**: Collapse and expand transitions for better user experience -- **Persistent state**: Maintains your scroll position when reopening +Click the todo summary in the task header to expand/collapse an inline list of all todo items. When expanded, Roo auto-scrolls the list to the current in-progress item (or the first incomplete item). ### Understanding Task Status Roo Code automatically manages status progression based on task progress. Each todo item has one of three states: -**Pending**: Shows an empty circle with a border, indicating the task hasn't been started yet -![Pending todo item with empty circle](../../static/img/task-todo-list/task-todo-list-4.png) +**Pending**: Dashed square icon, indicating the task hasn’t been started yet -**In Progress**: Displays a filled yellow circle, showing the task is currently being worked on -![In progress todo item with yellow circle](../../static/img/task-todo-list/task-todo-list-5.png) +**In Progress**: Arrow icon (highlighted), showing the task is currently being worked on -**Completed**: Features a filled green circle, confirming the task is fully finished -![Completed todo item with green circle](../../static/img/task-todo-list/task-todo-list-6.png) +**Completed**: Check icon, confirming the task is finished ### Editing Todo Lists During Approval @@ -119,7 +111,7 @@ When Roo presents a todo list update for approval, you have full control through 3. **Save or Cancel** your changes 4. **Approve or Reject** the overall update -Note: Your edits are staged and only applied when Roo processes the next todo list update. This maintains Roo's control over the workflow while giving you input on task details. +Note: Edits you make in the approval UI are sent back immediately and will be applied if you approve the update. --- @@ -140,7 +132,4 @@ This is an architectural design decision where Roo Code maintains authority over ### Disabling Todo Lists -You can disable todo lists entirely through the `todoListEnabled` setting. When disabled: -- Roo will not create todo lists for any tasks -- The REMINDERS section will not appear in environment details -- Existing todo lists will remain visible but won't be updated \ No newline at end of file +Todo-related behavior can be influenced by settings such as `roo-cline.newTaskRequireTodos` and `roo-cline.preventCompletionWithOpenTodos`. \ No newline at end of file