3.25.7 (#298)

Author: hannesrudolph

docs/features/checkpoints.mdx

@@ -61,7 +61,7 @@ Access checkpoint settings in Roo Code settings under the "Checkpoints" section:
 
 ## How Checkpoints Work
 
-Roo Code captures snapshots of your project's state using a shadow Git repository, separate from your main version control system. These snapshots, called checkpoints, automatically record changes throughout your AI-assisted workflow—whenever tasks begin, files change, or commands run.
+Roo Code captures snapshots of your project's state using a shadow Git repository, separate from your main version control system. These snapshots, called checkpoints, are automatically created **before** file modifications occur, ensuring you can always undo unwanted changes. Checkpoints are recorded throughout your AI-assisted workflow—when tasks begin, before files change, and before commands run.
 
 Checkpoints are stored as Git commits in the shadow repository, capturing:
 
@@ -77,12 +77,12 @@ Checkpoints are stored as Git commits in the shadow repository, capturing:
 
 Checkpoints are integrated directly into your workflow through the chat interface.
 
-Checkpoints appear directly in your chat history in two forms:
+Checkpoints appear directly in your chat history:
 
-- **Initial checkpoint** marks your starting project state
-   <img src="/img/checkpoints/checkpoints-1.png" alt="Initial checkpoint indicator in chat" width="500" />
+- **Task checkpoint** marks your starting project state
+   <img src="/img/checkpoints/checkpoints-1.png" alt="Task checkpoint indicator in chat" width="500" />
 
-- **Regular checkpoints** appear after file modifications or command execution
+- **Regular checkpoints** are created before file modifications or command execution, allowing easy undo of any changes
    <img src="/img/checkpoints/checkpoints-2.png" alt="Regular checkpoint indicator in chat" width="500" />
 
 Each checkpoint provides two primary functions:
@@ -128,6 +128,7 @@ To restore a project to a previous checkpoint state:
 - **External changes**: Modifications made outside of tasks (manual edits, other tools) aren't included
 - **Large files**: Very large binary files may impact performance
 - **Unsaved work**: Restoration will overwrite any unsaved changes in your workspace
+- **Timing**: Checkpoints are created before changes are applied, providing a safety net for all modifications
 
 ---
 

docs/features/codebase-indexing.mdx

@@ -139,6 +139,8 @@ The color of the icon indicates the state:
 - 🔴 **Red**: **Error**. An issue has occurred (e.g., failed to connect to Qdrant or the embedding provider). See the Troubleshooting section for help.
 - ⚪ **Gray**: **Standby**. The indexer is waiting for configuration or has been disabled.
 
+**Multi-Folder Workspaces**: In multi-folder workspaces, each folder maintains its own indexing status and configuration. The status icon reflects the combined state of all workspace folders.
+
 ### The Configuration Popover
 
 Clicking the status icon opens the main configuration popover. Here, you can view the detailed status and manage all settings.
@@ -239,6 +241,7 @@ The indexer respects your project's ignore patterns:
 - **Smart Updates**: Only reprocesses modified files
 - **Branch Aware**: Automatically handles Git branch switches
 - **Hash-based Caching**: Avoids reprocessing unchanged content
+- **Multi-Folder Workspaces**: Each folder in a multi-folder workspace maintains its own index with separate settings and status
 
 ---
 
@@ -336,7 +339,6 @@ The tool provides:
 ## Current Limitations
 
 - **File Size**: 1MB maximum per file
-- **Single Workspace**: One workspace indexed at a time
 - **External Dependencies**: Requires embedding provider + Qdrant
 - **Language Support**: Best results with Tree-sitter supported languages
 

docs/features/task-todo-list.mdx

@@ -79,7 +79,7 @@ Todo lists appear in multiple places:
 
    <img src="/img/task-todo-list/task-todo-list-2.png" alt="Interactive todo list tool block in chat" width="600" />
 
-3. **Environment Details**: Todo lists appear as a "REMINDERS" table in the environment_details section, giving the AI persistent access to current todo state
+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.
 
 ### Understanding Task Status
 
@@ -109,7 +109,16 @@ This is an architectural design decision where Roo Code maintains authority over
 
 ---
 
-## Auto-Approving Todo List Updates
+## Configuration
+
+### 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
+
+### Auto-Approving Todo List Updates
 
 You can enable automatic approval of todo list updates to reduce interruptions during long workflows. When enabled, Roo will automatically update task progress without requiring confirmation for each change.
 

docs/providers/anthropic.md

@@ -36,10 +36,9 @@ Anthropic is an AI safety and research company that builds reliable, interpretab
 
 Roo Code supports the following Anthropic Claude models:
 
+*   `claude-opus-4-1-20250805`
 *   `claude-opus-4-20250514`
-*   `claude-opus-4-20250514:thinking` (Extended Thinking variant)
 *   `claude-sonnet-4-20250514` (Recommended)
-*   `claude-sonnet-4-20250514:thinking` (Extended Thinking variant)
 *   `claude-3-7-sonnet-20250219`
 *   `claude-3-7-sonnet-20250219:thinking` (Extended Thinking variant)
 *   `claude-3-5-sonnet-20241022`
@@ -63,7 +62,7 @@ See [Anthropic's Model Documentation](https://docs.anthropic.com/en/docs/about-c
 
 ## Tips and Notes
 
-*   **Prompt Caching:** Claude 3 models support [prompt caching](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching), which can significantly reduce costs and latency for repeated prompts.
+*   **Prompt Caching:** Claude models support [prompt caching](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching), which can significantly reduce costs and latency for repeated prompts.
 *   **Context Window:** Claude models have large context windows (200,000 tokens), allowing you to include a significant amount of code and context in your prompts.
 *   **Pricing:** Refer to the [Anthropic Pricing](https://www.anthropic.com/pricing) page for the latest pricing information.
 *   **Rate Limits:** Anthropic has strict rate limits based on [usage tiers](https://docs.anthropic.com/en/api/rate-limits#requirements-to-advance-tier). If you're repeatedly hitting rate limits, consider contacting Anthropic sales or accessing Claude through a different provider like [OpenRouter](/providers/openrouter) or [Requesty](/providers/requesty).

docs/providers/bedrock.md

@@ -61,6 +61,7 @@ Roo Code supports the following models through Bedrock (based on source code):
     *   `amazon.titan-text-embeddings-v1:0`
     *   `amazon.titan-text-embeddings-v2:0`
 *   **Anthropic:**
+    *   `anthropic.claude-opus-4.1-20250514-v1:0`
     *   `anthropic.claude-opus-4-20250514-v1:0`
     *   `anthropic.claude-sonnet-4-20250514-v1:0`
     *   `anthropic.claude-3-7-sonnet-20250219-v1:0`
@@ -119,7 +120,7 @@ Roo Code supports using the reasoning budget (extended thinking) for Anthropic's
 
 To enable the reasoning budget:
 
-1.  **Select a supported Claude model** (e.g., `anthropic.claude-3-sonnet-20240229-v1:0`).
+1.  **Select a supported Claude model** (e.g., `anthropic.claude-opus-4.1-20250514-v1:0`, `anthropic.claude-3-sonnet-20240229-v1:0`).
 2.  **Enable Reasoning Mode** in the model settings.
 3.  **Adjust the thinking budget** to control how much the model should "think".
 

docs/providers/claude-code.md

@@ -98,11 +98,12 @@ export CLAUDE_CODE_MAX_OUTPUT_TOKENS=32768  # Set to 32k tokens
 
 The Claude Code provider supports these Claude models:
 
-- **Claude Sonnet 4** (latest, recommended)
-- **Claude Opus 4** (most capable)
+- **Claude Opus 4.1** (Most capable)
+- **Claude Opus 4** 
+- **Claude Sonnet 4** (Latest, recommended)
 - **Claude 3.7 Sonnet**
 - **Claude 3.5 Sonnet**
-- **Claude 3.5 Haiku** (fast responses)
+- **Claude 3.5 Haiku** (Fast responses)
 
 The specific models available depend on your Claude CLI subscription and plan.
 

docs/providers/fireworks.md

@@ -0,0 +1,102 @@
+---
+sidebar_label: Fireworks AI
+description: Use Fireworks AI with Roo Code to access state-of-the-art open-source models like Kimi K2, Qwen3, and DeepSeek with large context windows up to 256K tokens.
+keywords:
+  - fireworks ai
+  - fireworks
+  - kimi k2
+  - qwen3
+  - deepseek
+  - roo code
+  - api provider
+  - open source models
+  - ai models
+  - openai compatible
+image: /img/social-share.jpg
+---
+
+# Using Fireworks AI With Roo Code
+
+Fireworks AI provides access to state-of-the-art open-source language models through their optimized infrastructure. The provider offers cost-effective alternatives to proprietary AI services with context windows up to 256,000 tokens.
+
+**Website:** [https://fireworks.ai/](https://fireworks.ai/)
+
+---
+
+## Getting an API Key
+
+1. **Sign Up/Sign In:** Go to [Fireworks AI](https://fireworks.ai/). Create an account or sign in.
+2. **Navigate to Dashboard:** Access your account dashboard.
+3. **Generate API Key:** Create a new API key from the dashboard.
+4. **Copy the Key:** **Important:** Copy the API key immediately and store it securely.
+
+---
+
+## Supported Models
+
+Fireworks AI offers several high-performance models:
+
+### Kimi K2
+* `accounts/fireworks/models/kimi-k2-instruct` (Default)
+  - 1 trillion total parameters with 32B activated params
+  - 128K context window
+  - Optimized for agentic capabilities
+  - $0.60/M input, $2.50/M output
+
+### Qwen3 Series
+* `accounts/fireworks/models/qwen3-235b-a22b-instruct-2507`
+  - 256K context window
+  - Competitive with closed-source models
+  - $0.22/M input, $0.88/M output
+
+* `accounts/fireworks/models/qwen3-coder-480b-a35b-instruct`
+  - 256K context window
+  - Specialized for coding tasks
+  - $0.45/M input, $1.80/M output
+
+### DeepSeek Series
+* `accounts/fireworks/models/deepseek-r1-0528`
+  - 160K context window
+  - Advanced reasoning with reduced hallucination
+  - Function calling support
+  - $3.00/M input, $8.00/M output
+
+* `accounts/fireworks/models/deepseek-v3`
+  - 128K context window
+  - 671B total parameters with 37B activated
+  - $0.90/M input, $0.90/M output
+
+---
+
+## 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 "Fireworks AI" from the "API Provider" dropdown.
+3. **Enter API Key:** Paste your Fireworks API key into the "Fireworks API Key" field.
+4. **Model Selection:** The default model (Kimi K2) is automatically selected. You can change it from the model dropdown if needed.
+
+---
+
+## Model Selection Guide
+
+Choose models based on your needs:
+
+| Model | Best For | Context | Price |
+|-------|----------|---------|-------|
+| **Kimi K2** | General tasks, balanced performance | 128K | Mid-range |
+| **Qwen3 235B** | Cost-effective general use | 256K | Budget-friendly |
+| **Qwen3 Coder** | Code generation and debugging | 256K | Mid-range |
+| **DeepSeek R1** | Complex reasoning, function calling | 160K | Premium |
+| **DeepSeek V3** | Strong general performance | 128K | Balanced |
+
+---
+
+## Tips and Notes
+
+* **Cost-Effective:** Fireworks AI offers significantly lower pricing than proprietary models while maintaining competitive performance.
+* **Large Context Windows:** Most models support 128K-256K tokens, suitable for processing large documents and maintaining extended conversations.
+* **OpenAI Compatibility:** The provider uses an OpenAI-compatible API format with streaming support and usage tracking.
+* **Text-Only:** All models are text-only without image support or prompt caching capabilities.
+* **Default Temperature:** Uses 0.5 temperature by default for balanced creativity and consistency.
+* **API Keys:** Stored locally on your machine for security.
+* **Pricing:** See the [Fireworks AI pricing page](https://fireworks.ai/pricing) for current rates. Prices shown are per million tokens.

docs/providers/vertex.md

@@ -48,9 +48,8 @@ Roo Code supports the following models through Vertex AI (based on source code):
     *   `gemini-1.5-flash-002`
     *   `gemini-1.5-pro-002`
 *   **Anthropic Claude Models:**
-    *   `claude-opus-4@20250514:thinking`
+    *   `claude-opus-4-1@20250805`
     *   `claude-opus-4@20250514`
-    *   `claude-sonnet-4@20250514:thinking`
     *   `claude-sonnet-4@20250514`
     *   `claude-3-7-sonnet@20250219:thinking`
     *   `claude-3-7-sonnet@20250219`

docs/providers/zai.md

@@ -0,0 +1,79 @@
+---
+sidebar_label: Z AI
+description: Configure Z AI models in Roo Code. Access GLM-4.5 series models with region-aware routing for international and China mainland users.
+keywords:
+  - z ai
+  - zai
+  - zhipu ai
+  - glm-4.5
+  - roo code
+  - api provider
+  - china ai
+  - international ai
+  - openai compatible
+image: /img/social-share.jpg
+---
+
+# Using Z AI With Roo Code
+
+Z AI (Zhipu AI) provides advanced language models with the GLM-4.5 series. The provider offers region-aware routing with separate endpoints for international users and China mainland users.
+
+**Website:** [https://www.z.ai/](https://www.z.ai/) (International) | [https://open.bigmodel.cn/](https://open.bigmodel.cn/) (China)
+
+---
+
+## Getting an API Key
+
+### International Users
+
+1. **Sign Up/Sign In:** Go to [https://www.z.ai/](https://www.z.ai/). Create an account or sign in.
+2. **Navigate to API Keys:** Access your account dashboard and find the API keys section.
+3. **Create a Key:** Generate a new API key for your application.
+4. **Copy the Key:** **Important:** Copy the API key immediately and store it securely.
+
+### China Mainland Users
+
+1. **Sign Up/Sign In:** Go to [https://open.bigmodel.cn/](https://open.bigmodel.cn/). Create an account or sign in.
+2. **Navigate to API Keys:** Access your account dashboard and find the API keys section.
+3. **Create a Key:** Generate a new API key for your application.
+4. **Copy the Key:** **Important:** Copy the API key immediately and store it securely.
+
+---
+
+## Supported Models
+
+Z AI provides different model catalogs based on your selected region:
+
+### International Models
+* GLM-4.5 series models
+* GLM-4.5-Air models
+
+### China Mainland Models
+* GLM-4.5 series models
+* GLM-4.5-Air models
+
+The specific model availability may vary by region. The appropriate models will be available in the dropdown once you select your region.
+
+---
+
+## 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 "Z AI" from the "API Provider" dropdown.
+3. **Select Region:** Choose your region:
+   - "International" for global access
+   - "China" for mainland China access
+4. **Enter API Key:** Paste your Z AI API key into the "Z AI API Key" field.
+5. **Select Model:** Choose your desired model from the "Model" dropdown. Available models depend on your selected region.
+
+---
+
+## Tips and Notes
+
+* **Region Selection:** The region setting determines both the API endpoint and available models:
+  - International: Uses `https://api.z.ai/api/paas/v4`
+  - China: Uses `https://open.bigmodel.cn/api/paas/v4`
+* **OpenAI Compatibility:** Z AI uses an OpenAI-compatible API, providing streaming responses and usage reporting.
+* **Model Selection:** Models are automatically filtered based on your selected region to ensure compatibility.
+* **API Key Required:** A valid API key is required for all requests. Ensure you've obtained one from the appropriate regional platform.
+* **Pricing:** Check the respective regional websites for current pricing information.

docs/update-notes/index.md

@@ -19,6 +19,7 @@ This section contains notes about recent updates to Roo Code, listed by version
 
 ## Version 3.25
 
+*   [3.25.7](/update-notes/v3.25.7) (2025-08-05)
 *   [3.25.6](/update-notes/v3.25.6) (2025-08-02)
 *   [3.25.5](/update-notes/v3.25.5) (2025-08-01)
 *   [3.25.4](/update-notes/v3.25.4) (2025-07-31)