feat: add Doubao and SambaNova providers; enhance prompt suggestions …

.roo/rules-release-notes-writer/2_formatting_standards.xml

@@ -196,7 +196,6 @@ Concluding sentence about the benefit.
       <step>Map new changes to appropriate sections</step>
       <step>Strip PR references from new items</step>
       <step>Use apply_diff to insert items at the end of each section</step>
-      <step>See 9_combined_notes_integration.xml for detailed workflow</step>
     </integration_approach>
   </combined_notes_updates>
 

docs/features/custom-modes.mdx

@@ -37,6 +37,10 @@ Roo Code allows you to create **custom modes** to tailor Roo's behavior to speci
 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.
 :::
 
+:::info Discover Community Modes
+Looking for ready-to-use custom modes? Visit the [Roo Code Marketplace](/features/marketplace) to browse and install community-contributed modes with a single click. The marketplace offers specialized modes for various tasks like React development, documentation writing, testing, and more—all created and shared by the Roo Code community.
+:::
+
 ---
 
 ## Why Use Custom Modes?
@@ -661,5 +665,3 @@ In addition to mode-specific rules directories, there's also a generic `.roo/rul
 - **Invalid regex patterns:** If your `fileRegex` pattern is invalid, you'll receive an error message. Test your patterns using online regex testers before applying them.
 - **Precedence confusion:** Remember that project modes completely override global modes with the same slug - no properties are merged.
 
-## Community Resources
-Ready to explore more? Check out the [Community Projects](/community) page to discover tools and projects that extend Roo Code's capabilities, including sophisticated custom mode collections like [Roo Commander](/community/roo-commander) and [Maestro](/community/maestro).

docs/features/enhance-prompt.md

@@ -13,7 +13,7 @@ image: /img/social-share.jpg
 
 # Enhance Prompt
 
-The "Enhance Prompt" feature in Roo Code helps you improve the quality and effectiveness of your prompts before sending them to the AI model.  By clicking the <Codicon name="wand" /> icon in the chat input, you can automatically refine your initial request, making it clearer, more specific, and more likely to produce the desired results.
+The "Enhance Prompt" feature in Roo Code helps you improve the quality and effectiveness of your prompts before sending them to the AI model. By clicking the wand icon in the chat input, you can automatically refine your initial request, making it clearer, more specific, and more likely to produce the desired results.
 
 ---
 
@@ -24,38 +24,115 @@ The "Enhance Prompt" feature in Roo Code helps you improve the quality and effec
 *   **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.
+*   **Context-Aware Suggestions:** When enabled, uses your recent conversation history to generate more relevant and accurate enhancements.
 
 ---
 
 ## How to Use Enhance Prompt
 
 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 <Codicon name="wand" /> Icon:**  Instead of pressing Enter, click the <Codicon name="wand" /> icon located in the bottom right of the chat input box.
-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.
+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.
 
 ---
 
+## Special Behaviors
+
+### Empty Prompt Enhancement
+
+If you click the enhance button with an empty prompt, Roo will show you a helpful message explaining how the feature works. This is a great way to learn about the enhancement feature if you're new to it.
+
+### Message Queueing Support
+
+The enhance button remains enabled even when message sending is disabled. This allows you to enhance prompts that will be queued for later sending.
+
+---
+
 ## Customizing the Enhancement Process
 
-The "Enhance Prompt" feature uses a customizable prompt template.  You can modify this template to tailor the enhancement process to your specific needs.
+The "Enhance Prompt" feature uses a customizable prompt template. You can modify this template to tailor the enhancement process to your specific needs.
+
+### Accessing Prompts Settings
 
-1.  **Open the Prompts Tab:** Click the <Codicon name="notebook" /> icon in the Roo Code top menu bar.
-2.  **Select "ENHANCE" Tab:** You should see listed out support prompts, including "ENHANCE". Click on this tab.
-3.  **Edit the Prompt Template:** Modify the text in the "Prompt" field.
+1.  **Open Settings:** Click the gear icon (<Codicon name="gear" />) 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.
 
-The default prompt template includes the placeholder `${userInput}`, which will be replaced with your original prompt. You can modify this to fit the model's prompt format, and instruct it how to enhance your request.
+### Editing the Enhancement Prompt
+
+The default enhancement prompt template is:
+
+```
+Generate an enhanced version of this prompt (reply with only the enhanced prompt - no conversation, explanations, lead-in, bullet points, placeholders, or surrounding quotes):
+
+${userInput}
+```
+
+The `${userInput}` placeholder will be replaced with your original prompt. You can modify this template to fit your needs and the model's prompt format.
+
+### Testing Your Custom Prompt
+
+The Prompts settings include a test area where you can preview how your custom enhancement prompt works:
+
+1. After editing your enhancement prompt, look for the "Test Enhancement" section
+2. Enter a sample prompt to test
+3. Click "Test" to see how your custom prompt would enhance it
+4. Adjust your enhancement prompt as needed based on the results
 
 ---
 
 ## API Configuration
 
-The API configuration used for Enhance Prompt is, by default, the same one that is selected for Roo Code tasks,
-but it can be changed:
+The API configuration used for Enhance Prompt is, by default, the same one that is selected for Roo Code tasks, but it can be changed:
+
+1.  **Open Settings:** Navigate to Roo Code settings
+2.  **Go to Prompts Tab:** Select the "Prompts" tab
+3.  **Select "ENHANCE":** Choose "ENHANCE" from the dropdown
+4.  **Configure API:** You'll see an "API Configuration" dropdown where you can choose an existing configuration. Future Enhance Prompt requests will be sent to that configured provider/model.
+
+---
+
+## Context-Aware Enhancement
+
+The Enhance Prompt feature can now use your conversation history to generate more relevant suggestions. This helps reduce hallucinations and provides more accurate enhancements based on what you've been working on.
+
+### How It Works
+
+When enabled, the enhancement process includes your last 10 messages from the current conversation as context. This allows the AI to:
+- Understand what you've been working on
+- Maintain consistency with previous discussions
+- Avoid suggesting unrelated or incorrect enhancements
+- Provide more targeted and useful prompt improvements
+
+### Enabling Task History Context
+
+To enable or disable the use of conversation history in prompt enhancement:
+
+1. **Open Settings:** Navigate to Roo Code settings
+2. **Go to Prompts Tab:** Select the "Prompts" tab
+3. **Select "ENHANCE":** Choose "ENHANCE" from the dropdown
+4. **Toggle History Option:** Check or uncheck "Include task history in enhancement" for better context
+
+When disabled, the enhancement will only consider your current prompt without any conversation context.
+
+---
+
+## Visual Feedback and UI Elements
+
+### Button Appearance
+- The wand icon appears semi-transparent (60% opacity) by default
+- Becomes fully opaque (100%) when you hover over it
+- Located in the top-right corner of the chat input box
+- Has a focus ring for keyboard accessibility
+
+### Loading State
+- While processing your enhancement request, the wand icon spins
+- This provides clear visual feedback that Roo is working on your prompt
 
-1.  **Open the Prompts Tab:** Click the <Codicon name="notebook" /> icon in the Roo Code top menu bar.
-2.  **Select "ENHANCE" Tab:** You should see an "API Configuration" dropdown
-3.  **Select an API Configuration:** Choose an existing configuration, and future Enhance Prompt requests will be sent to that configured provider/model.
+### Tooltip
+- Hovering over the button shows: "Enhance prompt with additional context"
+- Helps new users understand the button's purpose
 
 ---
 

docs/providers/claude-code.md

@@ -72,8 +72,6 @@ The provider integrates with Roo Code's interface, giving you the same experienc
 
 ## Configuration
 
-You only need to configure one optional setting:
-
 ### **Claude Code Path**
 - **Setting**: `claudeCodePath`
 - **Description**: Path to your Claude CLI executable.
@@ -83,6 +81,17 @@ You only need to configure one optional setting:
 **Example custom paths:**
 - macOS/Linux: `/usr/local/bin/claude` or `~/bin/claude`
 
+### **Max Output Tokens**
+- **Default**: 16,384 tokens (16k) - increased from previous 8k default
+- **Environment Variable**: `CLAUDE_CODE_MAX_OUTPUT_TOKENS`
+- **Description**: Controls the maximum number of tokens Claude can generate in a single response.
+- **When to change**: If you need longer responses or want to limit output length for cost/performance reasons.
+
+**Example configuration:**
+```bash
+export CLAUDE_CODE_MAX_OUTPUT_TOKENS=32768  # Set to 32k tokens
+```
+
 ---
 
 ## Supported Models
@@ -100,6 +109,17 @@ The specific models available depend on your Claude CLI subscription and plan.
 
 ---
 
+## Output Token Limits
+
+The Claude Code provider now defaults to 16,384 (16k) max output tokens, allowing for longer and more complete responses. This is particularly useful for:
+- Generating large code files
+- Detailed explanations and documentation
+- Complex refactoring operations
+- Multi-file changes
+
+You can customize this limit using the `CLAUDE_CODE_MAX_OUTPUT_TOKENS` environment variable if you need different limits for your use case.
+
+---
 
 ## Common Questions
 

docs/providers/doubao.md

@@ -0,0 +1,56 @@
+---
+sidebar_label: Doubao
+description: Configure ByteDance's Doubao AI models in Roo Code. Access competitive language models with full integration and internationalized support.
+keywords:
+  - doubao
+  - bytedance
+  - bytedance ai
+  - roo code
+  - api provider
+  - doubao models
+  - chinese ai
+  - language models
+image: /img/social-share.jpg
+---
+
+# Using Doubao With Roo Code
+
+Doubao is ByteDance's Chinese AI service, offering competitive language models for various development tasks. The provider includes full API integration with embedding support and internationalized prompts.
+
+**Website:** [https://www.volcengine.com/](https://www.volcengine.com/)
+
+---
+
+## Getting an API Key
+
+1. **Sign Up/Sign In:** Visit the [Volcano Engine Console](https://console.volcengine.com/). Create an account or sign in.
+2. **Navigate to Model Service:** Access the AI model service section in the console.
+3. **Create API Key:** Generate a new API key for the Doubao service.
+4. **Copy the Key:** **Important:** Copy the API key immediately and store it securely. You may not be able to view it again.
+
+---
+
+## Supported Models
+
+Roo Code supports the following Doubao models:
+
+* `doubao-seed-1-6-250615` (Default) - General purpose
+* `doubao-seed-1-6-thinking-250715` - Enhanced reasoning
+* `doubao-seed-1-6-flash-250715` - Speed optimized
+
+All models support:
+- 128,000 token context window
+- 32,768 max output tokens
+- Image inputs
+- Prompt caching with 80% discount on cached reads
+
+---
+
+## Configuration in Roo Code
+
+1. **Open Roo Code Settings:** Click the gear icon (<Codicon name="gear" />) in the Roo Code panel.
+2. **Select Provider:** Choose "Doubao" from the "API Provider" dropdown.
+3. **Enter API Key:** Paste your Doubao API key into the "Doubao API Key" field.
+4. **Select Model:** Choose your desired model from the "Model" dropdown.
+
+**Note:** Doubao uses the base URL `https://ark.cn-beijing.volces.com/api/v3` and servers are located in Beijing, China.

docs/providers/sambanova.md

@@ -0,0 +1,53 @@
+---
+sidebar_label: SambaNova
+description: Configure SambaNova's high-speed AI models in Roo Code. Experience enterprise-grade inference with competitive performance and diverse model selection.
+keywords:
+  - sambanova
+  - sambanova ai
+  - roo code
+  - api provider
+  - high-speed inference
+  - enterprise ai
+  - llm provider
+  - fast inference
+image: /img/social-share.jpg
+---
+
+# Using SambaNova With Roo Code
+
+SambaNova specializes in providing high-speed inference for large language models, utilizing their Reconfigurable Dataflow Units (RDUs) through their SambaCloud portal. This delivers fast response times for supported models.
+
+**Website:** [https://cloud.sambanova.ai/](https://cloud.sambanova.ai/)
+
+---
+
+## Getting an API Key
+
+To use SambaNova with Roo Code, you'll need an API key from the [SambaCloud](https://cloud.sambanova.ai?utm_source=roocode&utm_medium=external&utm_campaign=cloud_signup). After signing up, navigate to the API Keys section in the left panel to create and copy your SambaCloud API key.
+
+---
+
+## Supported Models
+
+Roo Code will attempt to fetch the list of available models from the SambaNova API. Common models available via SambaCloud include:
+
+*   `DeepSeek-R1`
+*   `DeepSeek-V3-0324`
+*   `DeepSeek-R1-Distill-Llama-70B`
+*   `Meta-Llama-3.3-70B-Instruct`
+*   `Meta-Llama-3.1-8B-Instruct`
+*   `Llama-4-Maverick-17B-128E-Instruct`
+*   `Qwen3-32B`
+*   `Llama-3.3-Swallow-70B-Instruct-v0.4`
+
+Refer to the [SambaCloud Documentation](https://docs.sambanova.ai/cloud/docs/get-started/supported-models) for the most up-to-date list of supported models and their capabilities.
+
+---
+
+## Configuration in Roo Code
+
+1. **Open Roo Code Settings:** Click the gear icon (<Codicon name="gear" />) in the Roo Code panel.
+2. **Select Provider:** Choose "SambaNova" from the "API Provider" dropdown.
+3. **Enter API Key:** Paste your SambaNova API key into the "SambaNova API Key" field.
+4. **Select Model:** Choose your desired model from the "Model" dropdown.
+5. **(Optional) Custom Base URL:** If using a private deployment, check "Use custom base URL" and enter your endpoint URL.

docs/update-notes/index.md

@@ -19,6 +19,8 @@ This section contains notes about recent updates to Roo Code, listed by version
 
 ## Version 3.25
 
+*   [3.25.4](/update-notes/v3.25.4) (2025-07-31)
+*   [3.25.3](/update-notes/v3.25.3) (2025-07-30)
 *   [3.25.2](/update-notes/v3.25.2) (2025-07-29)
 *   [3.25.1](/update-notes/v3.25.1) (2025-07-29)
 *   [3.25.0](/update-notes/v3.25.0) (2025-07-29)