feat: add release notes for versions 3.25.9 and 3.25.10, including GPT-5 support and bug fixes; update sidebars configuration

Author: hannesrudolph

docs/providers/openai.md

@@ -1,8 +1,9 @@
 ---
 sidebar_label: OpenAI
-description: Connect Roo Code to OpenAI's official API for access to GPT-4o, o1, and o3-mini models with advanced reasoning capabilities.
+description: Connect Roo Code to OpenAI's official API for access to GPT-5, GPT-4o, o1, and o3 models with advanced reasoning capabilities and verbosity control.
 keywords:
   - OpenAI
+  - GPT-5
   - GPT-4o
   - o1 models
   - o3-mini
@@ -11,12 +12,14 @@ keywords:
   - reasoning models
   - API key
   - official OpenAI API
+  - verbosity
+  - reasoning effort
 image: /img/social-share.jpg
 ---
 
 # Using OpenAI With Roo Code
 
-Roo Code supports accessing models directly through the official OpenAI API.
+Roo Code supports accessing models directly through the official OpenAI API, including the latest GPT-5 family with advanced features like reasoning effort control and verbosity settings.
 
 **Website:** [https://openai.com/](https://openai.com/)
 
@@ -33,32 +36,104 @@ Roo Code supports accessing models directly through the official OpenAI API.
 
 ## Supported Models
 
-Roo Code supports a variety of OpenAI models, including:
+### GPT-5 Family (Latest)
+The GPT-5 models are OpenAI's most advanced, offering superior coding capabilities and agentic task performance:
 
-*	`o3-mini` (medium reasoning effort)
-*	`o3-mini-high` (high reasoning effort)
+* **`gpt-5-2025-08-07`** (default) - Best model for coding and agentic tasks
+* **`gpt-5-mini-2025-08-07`** - Faster, cost-efficient for well-defined tasks
+* **`gpt-5-nano-2025-08-07`** - Fastest, most cost-efficient option
+
+### GPT-4.1 Family
+Advanced multimodal models with balanced capabilities:
+
+* `gpt-4.1` - Advanced multimodal model
+* `gpt-4.1-mini` - Balanced performance
+* `gpt-4.1-nano` - Lightweight option
+
+### o3 Reasoning Models
+Models with configurable reasoning effort for complex problem-solving:
+
+* `o3`, `o3-high`, `o3-low` - Different reasoning effort presets
+* `o3-mini` (medium reasoning effort)
+* `o3-mini-high` (high reasoning effort)
 * `o3-mini-low` (low reasoning effort)
-* `o1`
-* `o1-preview`
-*	`o1-mini`
-*   `gpt-4.5-preview`
-* `gpt-4o`
-* `gpt-4o-mini`
+
+### o4 Models
+Latest mini reasoning models:
+
+* `o4-mini`, `o4-mini-high`, `o4-mini-low`
+
+### o1 Family
+Original reasoning models:
+
+* `o1` - Original reasoning model
+* `o1-preview` - Preview version
+* `o1-mini` - Smaller variant
+
+### GPT-4o Family
+Optimized GPT-4 models:
+
+* `gpt-4.5-preview`
+* `gpt-4o` - Optimized GPT-4
+* `gpt-4o-mini` - Smaller optimized variant
 
 Refer to the [OpenAI Models documentation](https://platform.openai.com/docs/models) for the most up-to-date list of models and capabilities.
 
 ---
 
 ## Configuration in Roo Code
 
+### Setup
+
 1.  **Open Roo Code Settings:** Click the gear icon (<Codicon name="gear" />) in the Roo Code panel.
 2.  **Select Provider:** Choose "OpenAI" from the "API Provider" dropdown.
 3.  **Enter API Key:** Paste your OpenAI API key into the "OpenAI API Key" field.
-4.  **Select Model:** Choose your desired model from the "Model" dropdown.
+4.  **Select Model:** Choose your desired model from the "Model" dropdown (defaults to `gpt-5-2025-08-07`).
 5.  **(Optional) Base URL:** If you need to use a custom base URL, enter the URL. Most people won't need to adjust this.
 
 ---
 
+## Advanced Features
+
+### Reasoning Effort Control
+
+For models that support reasoning (GPT-5, o1, o3, o4 families), you can control how deeply the model thinks:
+
+**GPT-5 Models:**
+- `minimal` - Fastest responses with basic reasoning
+- `low` - Quick responses with light reasoning
+- `medium` (default) - Balanced reasoning and response time
+- `high` - Deep reasoning for complex problems
+
+**o1/o3/o4 Models:**
+- `low` - Minimal thinking time
+- `medium` - Balanced approach
+- `high` - Maximum thinking for complex problems
+
+Some models have preset reasoning levels (e.g., `o3-high` always uses high reasoning).
+
+### Verbosity Control
+
+Available for GPT-5 models and select others, verbosity controls the detail level of responses:
+
+- `low` - Concise, direct responses
+- `medium` (default) - Balanced detail
+- `high` - Comprehensive, detailed responses
+
+### Temperature Settings
+
+Temperature controls output randomness (0.0 to 2.0):
+
+- **GPT-5 models:** Default 1.0 for balanced creativity
+- **Other models:** Default 0.0 for deterministic output
+- **Note:** Not available for o1/o3 reasoning models
+
+### Conversation Continuity (GPT-5)
+
+GPT-5 models maintain conversation context efficiently through response IDs, reducing token usage while preserving context. This happens automatically - no configuration needed.
+
+---
+
 ## Tips and Notes
 
 *   **Pricing:** Refer to the [OpenAI Pricing](https://openai.com/pricing) page for details on model costs.

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
 
+*   [3.25.10](/update-notes/v3.25.10) (2025-08-07)
+*   [3.25.9](/update-notes/v3.25.9) (2025-08-07)
 *   [3.25.8](/update-notes/v3.25.8) (2025-08-06)
 *   [3.25.7](/update-notes/v3.25.7) (2025-08-05)
 *   [3.25.6](/update-notes/v3.25.6) (2025-08-02)

docs/update-notes/v3.25.10.mdx

@@ -0,0 +1,36 @@
+---
+description: Introduces GPT-5 model support with verbosity controls and fixes XML parsing and MCP error display issues.
+keywords:
+  - roo code 3.25.10
+  - gpt-5
+  - openai models
+  - verbosity controls
+  - bug fixes
+image: /img/social-share.jpg
+---
+
+# Roo Code 3.25.10 Release Notes (2025-08-07)
+
+This release introduces support for OpenAI's GPT-5 models with verbosity controls and fixes important bugs in XML parsing and error message display.
+
+## GPT-5 Model Support
+
+We've added support for OpenAI's latest GPT-5 model family ([#6819](https://github.com/RooCodeInc/Roo-Code/pull/6819)):
+
+- **GPT-5 Models**: Three new model variants are now available:
+  - `gpt-5-2025-08-07`: The full GPT-5 model, now set as the default for OpenAI Native provider
+  - `gpt-5-mini-2025-08-07`: A smaller, faster variant for quick responses
+  - `gpt-5-nano-2025-08-07`: The most compact version for resource-constrained scenarios
+
+- **Verbosity Controls**: New settings to control model output detail levels (low, medium, high), allowing you to fine-tune response length and detail based on your needs
+
+- **Experimental Model**: Also includes the experimental `nectarine-alpha` model for testing cutting-edge capabilities
+
+All GPT-5 models support streaming responses for real-time interaction.
+
+> **📚 Documentation**: See [OpenAI Provider Guide](/providers/openai) for detailed information about GPT-5 models and verbosity settings.
+
+## Bug Fixes
+
+* **XML Parsing**: Fixed errors when using the apply_diff tool with complex XML files containing special characters by implementing proper CDATA sections ([#6811](https://github.com/RooCodeInc/Roo-Code/pull/6811))
+* **MCP Error Messages**: Fixed an issue where MCP server errors displayed raw translation keys instead of proper error messages ([#6821](https://github.com/RooCodeInc/Roo-Code/pull/6821))

docs/update-notes/v3.25.9.mdx

@@ -0,0 +1,29 @@
+---
+description: Adds new Fireworks AI models, fixes token calculation, and improves chat input focus.
+keywords:
+  - roo code 3.25.9
+  - fireworks ai models
+  - glm-4.5
+  - bug fixes
+image: /img/social-share.jpg
+---
+
+# Roo Code 3.25.9 Release Notes (2025-08-07)
+
+This release adds new AI models to the Fireworks provider, fixes token calculation issues, and improves the chat creation experience.
+
+## Provider Updates
+
+* **Fireworks AI Models**: Added GLM-4.5 series models (355B and 106B parameters with 128K context) and OpenAI gpt-oss models (20b for edge deployments, 120b for production use) to expand model selection options (thanks alexfarlander!) ([#6784](https://github.com/RooCodeInc/Roo-Code/pull/6784))
+
+## QOL Improvements
+
+* **Chat Input Focus**: The chat input now automatically focuses when creating a new chat via the + button, allowing you to start typing immediately ([#6689](https://github.com/RooCodeInc/Roo-Code/pull/6689))
+
+## Bug Fixes
+
+* **Token Calculation**: Fixed rounding errors that prevented certain models like GLM-4.5 from working properly by ensuring max output tokens are correctly rounded up (thanks markp018!) ([#6808](https://github.com/RooCodeInc/Roo-Code/pull/6808))
+
+## Misc Improvements
+
+* **Cloud Integration**: Reverted to using the npm package version of @roo-code/cloud for improved build stability and maintenance ([#6795](https://github.com/RooCodeInc/Roo-Code/pull/6795))

sidebars.ts

@@ -211,6 +211,8 @@ const sidebars: SidebarsConfig = {
           label: '3.25',
           items: [
             { type: 'doc', id: 'update-notes/v3.25', label: '3.25 Combined' },
+            { type: 'doc', id: 'update-notes/v3.25.10', label: '3.25.10' },
+            { type: 'doc', id: 'update-notes/v3.25.9', label: '3.25.9' },
             { type: 'doc', id: 'update-notes/v3.25.8', label: '3.25.8' },
             { type: 'doc', id: 'update-notes/v3.25.7', label: '3.25.7' },
             { type: 'doc', id: 'update-notes/v3.25.6', label: '3.25.6' },