docs: update vscode language model api docs

- Add comprehensive documentation for configuring Anthropic Claude models with Cline
- Include API key setup, supported models list, and configuration steps
- Cover advanced features like prompt caching and rate limits
- Update navigation to include new Anthropic page in custom model configs section

.prettierignore

@@ -3,6 +3,3 @@ node_modules
 webview-ui/build/
 *.md
 package-lock.json
-src/core/prompts/system.ts
-src/core/prompts/model_prompts/claude4.ts
-src/core/prompts/model_prompts/jsonToolToXml.ts

CHANGELOG.md

@@ -1,13 +1,5 @@
 # Changelog
 
-## [3.17.8]
-
--   Fix bug where terminal would get stuck and output "capture failure"
-
-## [3.17.7]
-
--   Fix diff editing reliability for Claude 4 family models by adding constraints to prevent errors with large replacements
-
 ## [3.17.6]
 
 -   Add Cerebras as a new API provider with 5 high-performance models including reasoning-capable models (Thanks @kevint-cerebras!)

docs/custom-model-configs/anthropic.mdx

@@ -0,0 +1,61 @@
+---
+title: "Anthropic"
+description: "Learn how to configure and use Anthropic Claude models with Cline. Covers API key setup, model selection, and advanced features like prompt caching."
+---
+
+**Website:** [https://www.anthropic.com/](https://www.anthropic.com/)
+
+### Getting an API Key
+
+1.  **Sign Up/Sign In:** Go to the [Anthropic Console](https://console.anthropic.com/). Create an account or sign in.
+2.  **Navigate to API Keys:** Go to the [API keys](https://console.anthropic.com/settings/keys) section.
+3.  **Create a Key:** Click "Create Key". Give your key a descriptive name (e.g., "Cline").
+4.  **Copy the Key:** **Important:** Copy the API key _immediately_. You will not be able to see it again. Store it securely.
+
+### Supported Models
+
+Cline supports the following Anthropic Claude models:
+
+-   `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`
+-   `claude-3-5-haiku-20241022`
+-   `claude-3-opus-20240229`
+-   `claude-3-haiku-20240307`
+
+See [Anthropic's Model Documentation](https://docs.anthropic.com/en/docs/about-claude/models) for more details on each model's capabilities.
+
+### Configuration in Cline
+
+1.  **Open Cline Settings:** Click the settings icon (⚙️) in the Cline panel.
+2.  **Select Provider:** Choose "Anthropic" from the "API Provider" dropdown.
+3.  **Enter API Key:** Paste your Anthropic API key into the "Anthropic API Key" field.
+4.  **Select Model:** Choose your desired Claude model from the "Model" dropdown.
+5.  **(Optional) Custom Base URL:** If you need to use a custom base URL for the Anthropic API, check "Use custom base URL" and enter the URL. Most users won't need to adjust this setting.
+
+### Extended Thinking
+
+Anthropic models offer an "Extended Thinking" feature, designed to give them enhanced reasoning capabilities for complex tasks. This feature allows the model to output its step-by-step thought process before delivering a final answer, providing transparency and enabling more thorough analysis for challenging prompts.
+
+When extended thinking is in Cline, the model generates `thinking` content blocks that detail its internal reasoning. These insights are then incorporated into its final response.
+Cline users can leverage this by checking the `Enable Extended Thinking` box below the model selection menu after selecting a Claude Model from any provider.
+
+**Key Aspects of Extended Thinking:**
+
+-   **Supported Models:** This feature is available for select models, including variants of Claude Opus 4, Claude Sonnet 4, and Claude Sonnet 3.7. The specific models listed in the "Supported Models" section above with the `:thinking` suffix are pre-configured in Cline to utilize this.
+-   **Summarized Thinking (Claude 4):** For Claude 4 models, the API returns a summary of the full thinking process to balance insight with efficiency and prevent misuse. You are billed for the full thinking tokens, not just the summary.
+-   **Streaming:** Extended thinking responses, including the `thinking` blocks, can be streamed.
+-   **Tool Use & Prompt Caching:** Extended thinking interacts with tool use (requiring thinking blocks to be passed back) and prompt caching (with specific behaviors around cache invalidation and context).
+
+For comprehensive details on how extended thinking works, including API examples, interaction with tool use, prompt caching, and pricing, please refer to the [official Anthropic documentation on Extended Thinking](https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking).
+
+### 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.
+-   **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](/custom-model-configs/openrouter) or [Requesty](/custom-model-configs/requesty).

docs/custom-model-configs/deepseek.mdx

@@ -0,0 +1,33 @@
+---
+title: "DeepSeek"
+description: "Learn how to configure and use DeepSeek models like deepseek-chat and deepseek-reasoner with Cline."
+---
+
+Cline supports accessing models through the DeepSeek API, including `deepseek-chat` and `deepseek-reasoner`.
+
+**Website:** [https://platform.deepseek.com/](https://platform.deepseek.com/)
+
+### Getting an API Key
+
+1.  **Sign Up/Sign In:** Go to the [DeepSeek Platform](https://platform.deepseek.com/). Create an account or sign in.
+2.  **Navigate to API Keys:** Find your API keys in the [API keys](https://platform.deepseek.com/api_keys) section of the platform.
+3.  **Create a Key:** Click "Create new API key". Give your key a descriptive name (e.g., "Cline").
+4.  **Copy the Key:** **Important:** Copy the API key _immediately_. You will not be able to see it again. Store it securely.
+
+### Supported Models
+
+Cline supports the following DeepSeek models:
+
+-   `deepseek-chat` (Recommended for coding tasks)
+-   `deepseek-reasoner` (Recommended for reasoning tasks)
+
+### Configuration in Cline
+
+1.  **Open Cline Settings:** Click the ⚙️ icon in the Cline panel.
+2.  **Select Provider:** Choose "DeepSeek" from the "API Provider" dropdown.
+3.  **Enter API Key:** Paste your DeepSeek API key into the "DeepSeek API Key" field.
+4.  **Select Model:** Choose your desired model from the "Model" dropdown.
+
+### Tips and Notes
+
+-   **Pricing:** Refer to the [DeepSeek Pricing](https://api-docs.deepseek.com/quick_start/pricing/) page for details on model costs.

docs/custom-model-configs/mistral-ai.mdx

@@ -0,0 +1,53 @@
+---
+title: "Mistral"
+description: "Learn how to configure and use Mistral AI models, including Codestral, with Cline. Covers API key setup and model selection."
+---
+
+Cline supports accessing models through the Mistral AI API, including both standard Mistral models and the code-specialized Codestral model.
+
+**Website:** [https://mistral.ai/](https://mistral.ai/)
+
+### Getting an API Key
+
+1.  **Sign Up/Sign In:** Go to the [Mistral Platform](https://console.mistral.ai/). Create an account or sign in. You may need to go through a verification process.
+2.  **Create an API Key:**
+    -   [La Plateforme API Key](https://console.mistral.ai/api-keys/) and/or
+    -   [Codestral API Key](https://console.mistral.ai/codestral)
+
+### Supported Models
+
+Cline supports the following Mistral models:
+
+-   pixtral-large-2411
+-   ministral-3b-2410
+-   ministral-8b-2410
+-   mistral-small-latest
+-   mistral-medium-latest
+-   mistral-small-2501
+-   pixtral-12b-2409
+-   open-mistral-nemo-2407
+-   open-codestral-mamba
+-   codestral-2501
+-   devstral-small-2505
+
+**Note:** Model availability and specifications may change.
+Refer to the [Mistral AI documentation](https://docs.mistral.ai/api/) and [Mistral Model Overview](https://docs.mistral.ai/getting-started/models/models_overview/) for the most current information.
+
+### Configuration in Cline
+
+1.  **Open Cline Settings:** Click the settings icon (⚙️) in the Cline panel.
+2.  **Select Provider:** Choose "Mistral" from the "API Provider" dropdown.
+3.  **Enter API Key:** Paste your Mistral API key into the "Mistral API Key" field if you're using a standard `mistral` model. If you intend to use `codestral-latest`, see the "Using Codestral" section below.
+4.  **Select Model:** Choose your desired model from the "Model" dropdown.
+
+### Using Codestral
+
+[Codestral](https://docs.mistral.ai/capabilities/code_generation/) is a model specifically designed for code generation and interaction.
+For Codestral, you can use different endpoints (Default: codestral.mistral.ai).
+If using the La Plateforme API Key for Codestral, change the **Codestral Base Url** to: `https://api.mistral.ai`
+
+To use Codestral with Cline:
+
+1.  **Select "Mistral" as the API Provider in Cline Settings.**
+2.  **Select a Codestral Model** (e.g., `codestral-latest`) from the "Model" dropdown.
+3.  **Enter your Codestral API Key** (from `codestral.mistral.ai`) or your La Plateforme API Key (from `api.mistral.ai`) into the appropriate API key field in Cline.

docs/custom-model-configs/ollama.mdx

@@ -0,0 +1,79 @@
+---
+title: "Ollama"
+description: "Ollama"
+---
+
+Cline supports running models locally using Ollama. This approach offers privacy, offline access, and potentially reduced costs. It requires some initial setup and a sufficiently powerful computer. Because of the present state of consumer hardware, it's not recommended to use Ollama with Cline as performance will likely be poor for average hardware configurations.
+
+**Website:** [https://ollama.com/](https://ollama.com/)
+
+### Setting up Ollama
+
+1.  **Download and Install Ollama:**
+    Obtain the Ollama installer for your operating system from the [Ollama website](https://ollama.com/) and follow their installation guide. Ensure Ollama is running. You can typically start it with:
+
+    ```bash
+    ollama serve
+    ```
+
+2.  **Download a Model:**
+    Ollama supports a wide variety of models. A list of available models can be found on the [Ollama model library](https://ollama.com/library). Some models recommended for coding tasks include:
+
+    -   `codellama:7b-code` (a good, smaller starting point)
+    -   `codellama:13b-code` (offers better quality, larger size)
+    -   `codellama:34b-code` (provides even higher quality, very large)
+    -   `qwen2.5-coder:32b`
+    -   `mistralai/Mistral-7B-Instruct-v0.1` (a solid general-purpose model)
+    -   `deepseek-coder:6.7b-base` (effective for coding)
+    -   `llama3:8b-instruct-q5_1` (suitable for general tasks)
+
+    To download a model, open your terminal and execute:
+
+    ```bash
+    ollama pull <model_name>
+    ```
+
+    For instance:
+
+    ```bash
+    ollama pull qwen2.5-coder:32b
+    ```
+
+3.  **Configure the Model's Context Window:**
+    By default, Ollama models often use a context window of 2048 tokens, which can be insufficient for many Cline requests. A minimum of 12,000 tokens is advisable for decent results, with 32,000 tokens being ideal. To adjust this, you'll modify the model's parameters and save it as a new version.
+
+    First, load the model (using `qwen2.5-coder:32b` as an example):
+
+    ```bash
+    ollama run qwen2.5-coder:32b
+    ```
+
+    Once the model is loaded within the Ollama interactive session, set the context size parameter:
+
+    ```
+    /set parameter num_ctx 32768
+    ```
+
+    Then, save this configured model with a new name:
+
+    ```
+    /save your_custom_model_name
+    ```
+
+    (Replace `your_custom_model_name` with a name of your choice.)
+
+4.  **Configure Cline:**
+    -   Open the Cline sidebar (usually indicated by the Cline icon).
+    -   Click the settings gear icon (⚙️).
+    -   Select "ollama" as the API Provider.
+    -   Enter the Model name you saved in the previous step (e.g., `your_custom_model_name`).
+    -   (Optional) Adjust the base URL if Ollama is running on a different machine or port. The default is `http://localhost:11434`.
+    -   (Optional) Configure the Model context size in Cline's Advanced settings. This helps Cline manage its context window effectively with your customized Ollama model.
+
+### Tips and Notes
+
+-   **Resource Demands:** Running large language models locally can be demanding on system resources. Ensure your computer meets the requirements for your chosen model.
+-   **Model Choice:** Experiment with various models to discover which best fits your specific tasks and preferences.
+-   **Offline Capability:** After downloading a model, you can use Cline with that model even without an internet connection.
+-   **Token Usage Tracking:** Cline tracks token usage for models accessed via Ollama, allowing you to monitor consumption.
+-   **Ollama's Own Documentation:** For more detailed information, consult the official [Ollama documentation](https://ollama.com/docs).

docs/custom-model-configs/openai-compatible.mdx

@@ -0,0 +1,59 @@
+---
+title: "OpenAI Compatible"
+description: "Learn how to configure Cline with various AI model providers that offer OpenAI-compatible APIs."
+---
+
+Cline supports a wide range of AI model providers that offer APIs compatible with the OpenAI API standard. This allows you to use models from providers _other than_ OpenAI, while still utilizing a familiar API interface. This includes providers such as:
+
+-   **Local models** running through tools like Ollama and LM Studio (which are covered in their respective sections).
+-   **Cloud providers** like Perplexity, Together AI, Anyscale, and many others.
+-   **Any other provider** that offers an OpenAI-compatible API endpoint.
+
+This document focuses on setting up providers _other than_ the official OpenAI API (which has its own [dedicated configuration page](/custom-model-configs/openai)).
+
+### General Configuration
+
+The key to using an OpenAI-compatible provider with Cline is to configure these main settings:
+
+1.  **Base URL:** This is the API endpoint specific to the provider. It will _not_ be `https://api.openai.com/v1` (that URL is for the official OpenAI API).
+2.  **API Key:** This is the secret key you obtain from your chosen provider.
+3.  **Model ID:** This is the specific name or identifier for the model you wish to use.
+
+You'll find these settings in the Cline settings panel (click the ⚙️ icon):
+
+-   **API Provider:** Select "OpenAI Compatible".
+-   **Base URL:** Enter the base URL provided by your chosen provider. **This is a crucial step.**
+-   **API Key:** Enter your API key from the provider.
+-   **Model:** Choose or enter the model ID.
+-   **Model Configuration:** This section allows you to customize advanced parameters for the model, such as:
+    -   Max Output Tokens
+    -   Context Window size
+    -   Image Support capabilities
+    -   Computer Use (e.g., for models with tool/function calling)
+    -   Input Price (per token/million tokens)
+    -   Output Price (per token/million tokens)
+
+### Supported Models (for OpenAI Native Endpoint)
+
+While the "OpenAI Compatible" provider type allows connecting to various endpoints, if you are connecting directly to the official OpenAI API (or an endpoint that mirrors it exactly), Cline recognizes the following model IDs based on the `openAiNativeModels` definition in its source code:
+
+-   `o3-mini`
+-   `o3-mini-high`
+-   `o3-mini-low`
+-   `o1`
+-   `o1-preview`
+-   `o1-mini`
+-   `gpt-4.5-preview`
+-   `gpt-4o`
+-   `gpt-4o-mini`
+
+**Note:** If you are using a different OpenAI-compatible provider (such as Together AI, Anyscale, etc.), the available model IDs will differ. Always refer to your specific provider's documentation for their supported model names and any unique configuration details.
+
+### Troubleshooting
+
+-   **"Invalid API Key":** Double-check that you've entered the API key correctly and that it's for the correct provider.
+-   **"Model Not Found":** Ensure you're using a valid model ID for your chosen provider and that it's available at the specified Base URL.
+-   **Connection Errors:** Verify the Base URL is correct, that your provider's API is accessible from your machine, and that there are no firewall or network issues.
+-   **Unexpected Results:** If you're getting unexpected outputs, try a different model or double-check all configuration parameters.
+
+By using an OpenAI-compatible provider, you can leverage the flexibility of Cline with a wider array of AI models. Remember to always consult your provider's documentation for the most accurate and up-to-date information.

docs/custom-model-configs/openai.mdx

@@ -0,0 +1,48 @@
+---
+title: "OpenAI"
+description: "Learn how to configure and use official OpenAI models with Cline."
+---
+
+Cline supports accessing models directly through the official OpenAI API.
+
+**Website:** [https://openai.com/](https://openai.com/)
+
+### Getting an API Key
+
+1.  **Sign Up/Sign In:** Visit the [OpenAI Platform](https://platform.openai.com/). You'll need to create an account or sign in if you already have one.
+2.  **Navigate to API Keys:** Once logged in, go to the [API keys section](https://platform.openai.com/api-keys) of your account.
+3.  **Create a Key:** Click on "Create new secret key". It's good practice to give your key a descriptive name (e.g., "Cline API Key").
+4.  **Copy the Key:** **Crucial:** Copy the generated API key immediately. For security reasons, OpenAI will not show it to you again. Store this key in a safe and secure location.
+
+### Supported Models
+
+Cline is compatible with a variety of OpenAI models, including but not limited to:
+
+-   'o3'
+-   `o3-mini` (medium reasoning effort)
+-   'o4-mini'
+-   `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`
+-   'gpt-4.1'
+-   'gpt-4.1-mini'
+
+For the most current list of available models and their capabilities, please refer to the official [OpenAI Models documentation](https://platform.openai.com/docs/models).
+
+### Configuration in Cline
+
+1.  **Open Cline Settings:** Click the settings gear icon (⚙️) in the Cline panel.
+2.  **Select Provider:** Choose "OpenAI" from the "API Provider" dropdown menu.
+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 list.
+5.  **(Optional) Base URL:** If you need to use a proxy or a custom base URL for the OpenAI API, you can enter it here. Most users will not need to change this from the default.
+
+### Tips and Notes
+
+-   **Pricing:** Be sure to review the [OpenAI Pricing page](https://openai.com/pricing) for detailed information on the costs associated with different models.
+-   **Azure OpenAI Service:** If you are looking to use the Azure OpenAI service, please note that specific documentation for Azure OpenAI with Cline may be found separately, or you might need to configure it as an OpenAI-compatible endpoint if such functionality is supported by Cline for custom configurations.

docs/custom-model-configs/vscode-language-model-api.mdx

@@ -15,17 +15,24 @@ Cline offers _experimental_ support for the [VS Code Language Model API](https:/
 -   **VS Code:** The Language Model API is accessible via VS Code (it is not currently supported by Cursor).
 -   **A Language Model Provider Extension:** An extension that furnishes a language model is required. Examples include:
     -   **GitHub Copilot:** With a Copilot subscription, the GitHub Copilot and GitHub Copilot Chat extensions can serve as model providers.
-    -   **Alternative Extensions:** Explore the VS Code Marketplace for extensions mentioning "Language Model API" or "lm". Other experimental options may be available.
+    -   **Alternative Extensions:** Explore the VS Code Marketplace for extensions mentioning "Language Model API" or "lm". Other experimental options may be available
 
 ### Configuration Steps
 
-1.  **Access Cline Settings:** Click the gear icon (⚙️) located in the Cline panel.
-2.  **Choose Provider:** Select "VS Code LM API" from the "API Provider" dropdown menu.
-3.  **Select Model:** The "Language Model" dropdown will (eventually) populate with available models. The naming convention is `vendor/family`. For instance, if Copilot is active, you might encounter options such as:
-    -   `copilot - claude-3.5-sonnet`
-    -   `copilot - o3-mini`
-    -   `copilot - o1-ga`
-    -   `copilot - gemini-2.0-flash`
+1. **Ensure Copilot Account is Active and Extensions are installed:** User logged into either the Copilot or Copilot Chat extension should be able to gain access via Cline.
+2. **Access Cline Settings:** Click the gear icon (⚙️) located in the Cline panel.
+3. **Choose Provider:** Select "VS Code LM API" from the "API Provider" dropdown menu.
+4. **Select Model:** If the Copilot extension(s) are installed and the user is logged into their Copilot account, the "Language Model" dropdown will populate with available models after a short time. The naming convention is `vendor/family`. For instance, if Copilot is active, you might encounter options such as:
+    - `copilot - gpt-3.5-turbo`
+    - `copilot - gpt-4o-mini`
+    - `copilot - gpt-4`
+    - `copilot - gpt-4-turbo`
+    - `copilot - gpt-4o`
+    - `copilot - claude-3.5-sonnet` **NOTE:** this model does not work.
+    - `copilot - gemini-2.0-flash`
+    - `copilot - gpt-4.1`
+
+For best results with the VSCode LM API Provider, we suggest using the OpenAI Models (GPT 3, 4, 4.1, 4o etc.)
 
 ### Current Limitations
 

docs/custom-model-configs/xai-grok.mdx

@@ -0,0 +1,85 @@
+---
+title: "xAI (Grok)"
+description: "Learn how to configure and use xAI's Grok models with Cline, including API key setup, supported models, and reasoning capabilities."
+---
+
+xAI is the company behind Grok, a large language model known for its conversational abilities and large context window. Grok models are designed to provide helpful, informative, and contextually relevant responses.
+
+**Website:** [https://x.ai/](https://x.ai/)
+
+### Getting an API Key
+
+1.  **Sign Up/Sign In:** Go to the [xAI Console](https://console.x.ai/). Create an account or sign in.
+2.  **Navigate to API Keys:** Go to the API keys section in your dashboard.
+3.  **Create a Key:** Click to create a new API key. Give your key a descriptive name (e.g., "Cline").
+4.  **Copy the Key:** **Important:** Copy the API key _immediately_. You will not be able to see it again. Store it securely.
+
+### Supported Models
+
+Cline supports the following xAI Grok models:
+
+#### Grok-3 Models
+
+-   `grok-3-beta` (Default) - xAI's Grok-3 beta model with 131K context window
+-   `grok-3-fast-beta` - xAI's Grok-3 fast beta model with 131K context window
+-   `grok-3-mini-beta` - xAI's Grok-3 mini beta model with 131K context window
+-   `grok-3-mini-fast-beta` - xAI's Grok-3 mini fast beta model with 131K context window
+
+#### Grok-2 Models
+
+-   `grok-2-latest` - xAI's Grok-2 model - latest version with 131K context window
+-   `grok-2` - xAI's Grok-2 model with 131K context window
+-   `grok-2-1212` - xAI's Grok-2 model (version 1212) with 131K context window
+
+#### Grok Vision Models
+
+-   `grok-2-vision-latest` - xAI's Grok-2 Vision model - latest version with image support and 32K context window
+-   `grok-2-vision` - xAI's Grok-2 Vision model with image support and 32K context window
+-   `grok-2-vision-1212` - xAI's Grok-2 Vision model (version 1212) with image support and 32K context window
+-   `grok-vision-beta` - xAI's Grok Vision Beta model with image support and 8K context window
+
+#### Legacy Models
+
+-   `grok-beta` - xAI's Grok Beta model (legacy) with 131K context window
+
+### Configuration in Cline
+
+1.  **Open Cline Settings:** Click the settings icon (⚙️) in the Cline panel.
+2.  **Select Provider:** Choose "xAI" from the "API Provider" dropdown.
+3.  **Enter API Key:** Paste your xAI API key into the "xAI API Key" field.
+4.  **Select Model:** Choose your desired Grok model from the "Model" dropdown.
+
+### Reasoning Capabilities
+
+Grok 3 Mini models feature specialized reasoning capabilities, allowing them to "think before responding" - particularly useful for complex problem-solving tasks.
+
+#### Reasoning-Enabled Models
+
+Reasoning is only supported by:
+
+-   `grok-3-mini-beta`
+-   `grok-3-mini-fast-beta`
+
+The Grok 3 models `grok-3-beta` and `grok-3-fast-beta` do not support reasoning.
+
+#### Controlling Reasoning Effort
+
+When using reasoning-enabled models, you can control how hard the model thinks with the `reasoning_effort` parameter:
+
+-   `low`: Minimal thinking time, using fewer tokens for quick responses
+-   `high`: Maximum thinking time, leveraging more tokens for complex problems
+
+Choose `low` for simple queries that should complete quickly, and `high` for harder problems where response latency is less important.
+
+#### Key Features
+
+-   **Step-by-Step Problem Solving**: The model thinks through problems methodically before delivering an answer
+-   **Math & Quantitative Strength**: Excels at numerical challenges and logic puzzles
+-   **Reasoning Trace Access**: The model's thinking process is available via the `reasoning_content` field in the response completion object
+
+### Tips and Notes
+
+-   **Context Window:** Most Grok models feature large context windows (up to 131K tokens), allowing you to include substantial amounts of code and context in your prompts.
+-   **Vision Capabilities:** Select vision-enabled models (`grok-2-vision-latest`, `grok-2-vision`, etc.) when you need to process or analyze images.
+-   **Pricing:** Pricing varies by model, with input costs ranging from $0.3 to $5.0 per million tokens and output costs from $0.5 to $25.0 per million tokens. Refer to the xAI documentation for the most current pricing information.
+-   **Performance Tradeoffs:** "Fast" variants typically offer quicker response times but may have higher costs, while "mini" variants are more economical but may have reduced capabilities.

docs/docs.json

@@ -145,11 +145,18 @@
 			{
 				"group": "Custom Model Configurations",
 				"pages": [
+					"custom-model-configs/anthropic",
 					"custom-model-configs/aws-bedrock-with-credentials-authentication",
 					"custom-model-configs/aws-bedrock-with-profile-authentication",
 					"custom-model-configs/gcp-vertex-ai",
 					"custom-model-configs/litellm-and-cline-using-codestral",
-					"custom-model-configs/vscode-language-model-api"
+					"custom-model-configs/vscode-language-model-api",
+					"custom-model-configs/xai-grok",
+					"custom-model-configs/mistral-ai",
+					"custom-model-configs/deepseek",
+					"custom-model-configs/ollama",
+					"custom-model-configs/openai",
+					"custom-model-configs/openai-compatible"
 				]
 			},
 			{

docs/features/plan-and-act.mdx

@@ -6,10 +6,13 @@ sidebarTitle: "Plan & Act"
 Plan & Act modes represent Cline's approach to structured AI development, emphasizing thoughtful planning before implementation. This dual-mode system helps developers create more maintainable, accurate code while reducing iteration time.
 
 <Frame>
-	<img
-		src="https://storage.googleapis.com/cline_public_images/docs/assets/planningThenActing%20(1).gif"
-		alt="Use Plan to gather context before using Act to implement the plan"
-	/>
+	<iframe
+		style={{ width: "100%", aspectRatio: "16/9" }}
+		src="https://www.youtube.com/embed/b7o6URFPp64"
+		title="YouTube video player"
+		frameBorder="0"
+		allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
+		allowFullScreen></iframe>
 </Frame>
 
 #### Plan Mode: Think First

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "claude-dev",
-	"version": "3.17.8",
+	"version": "3.17.6",
 	"lockfileVersion": 2,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "claude-dev",
-			"version": "3.17.8",
+			"version": "3.17.6",
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@anthropic-ai/bedrock-sdk": "^0.12.4",

package.json

@@ -2,7 +2,7 @@
 	"name": "claude-dev",
 	"displayName": "Cline",
 	"description": "Autonomous coding agent right in your IDE, capable of creating/editing files, running commands, using the browser, and more with your permission every step of the way.",
-	"version": "3.17.8",
+	"version": "3.17.6",
 	"icon": "assets/icons/icon.png",
 	"engines": {
 		"vscode": "^1.84.0"
@@ -283,7 +283,7 @@
 		"postprotos": "prettier src/shared/proto src/core/controller webview-ui/src/services src/standalone/server-setup.ts --write --log-level silent",
 		"compile-tests": "node ./scripts/build-tests.js",
 		"watch-tests": "tsc -p . -w --outDir out",
-		"pretest": "npm run compile-tests && npm run compile && npm run compile-standalone && npm run lint",
+		"pretest": "npm run compile-tests && npm run compile && npm run lint",
 		"check-types": "npm run protos && tsc --noEmit",
 		"lint": "eslint src --ext ts && eslint webview-ui/src --ext ts",
 		"format": "prettier . --check",

proto/state.proto

@@ -1,7 +1,5 @@
 syntax = "proto3";
 package cline;
-option java_package = "bot.cline.proto";
-option java_multiple_files = true;
 
 import "common.proto";
 

proto/ui.proto

@@ -13,7 +13,4 @@ service UiService {
   
   // Marks the current announcement as shown and returns whether an announcement should still be shown
   rpc onDidShowAnnouncement(EmptyRequest) returns (Boolean);
-  
-  // Subscribe to addToInput events (when user adds content via context menu)
-  rpc subscribeToAddToInput(EmptyRequest) returns (stream String);
 }

src/core/assistant-message/parse-assistant-message.ts

@@ -473,377 +473,3 @@ export function parseAssistantMessageV2(assistantMessage: string): AssistantMess
 
 	return contentBlocks
 }
-
-export function parseAssistantMessageV3(assistantMessage: string): AssistantMessageContent[] {
-	const contentBlocks: AssistantMessageContent[] = []
-	let currentTextContentStart = 0 // Index where the current text block started
-	let currentTextContent: TextContent | undefined = undefined
-	let currentToolUseStart = 0 // Index *after* the opening tag of the current tool use
-	let currentToolUse: ToolUse | undefined = undefined
-	let currentParamValueStart = 0 // Index *after* the opening tag of the current param
-	let currentParamName: ToolParamName | undefined = undefined
-
-	// Precompute tags for faster lookups
-	const toolUseOpenTags = new Map<string, ToolUseName>()
-	const toolParamOpenTags = new Map<string, ToolParamName>()
-	for (const name of toolUseNames) {
-		toolUseOpenTags.set(`<${name}>`, name)
-	}
-	for (const name of toolParamNames) {
-		toolParamOpenTags.set(`<${name}>`, name)
-	}
-
-	// Function calls format detection
-	const isFunctionCallsOpen = "<function_calls>"
-	const isFunctionCallsClose = "</function_calls>"
-	const isInvokeStart = '<invoke name="'
-	const isInvokeEnd = '">'
-	const isInvokeClose = "</invoke>"
-	const isParameterStart = '<parameter name="'
-	const isParameterNameEnd = '">'
-	const isParameterClose = "</parameter>"
-
-	// Variables for function calls parsing
-	let inFunctionCalls = false
-	let currentInvokeName = ""
-	let currentParameterName = ""
-
-	const len = assistantMessage.length
-	for (let i = 0; i < len; i++) {
-		const currentCharIndex = i
-
-		// --- State: Parsing Function Calls ---
-		// Check for opening function_calls tag
-		if (
-			!inFunctionCalls &&
-			currentCharIndex >= isFunctionCallsOpen.length - 1 &&
-			assistantMessage.startsWith(isFunctionCallsOpen, currentCharIndex - isFunctionCallsOpen.length + 1)
-		) {
-			// End current text block if one was active
-			if (currentTextContent) {
-				currentTextContent.content = assistantMessage
-					.slice(currentTextContentStart, currentCharIndex - isFunctionCallsOpen.length + 1)
-					.trim()
-				currentTextContent.partial = false
-				if (currentTextContent.content.length > 0) {
-					contentBlocks.push(currentTextContent)
-				}
-				currentTextContent = undefined
-			}
-
-			inFunctionCalls = true
-			continue
-		}
-
-		// Check for invoke start within function_calls
-		if (
-			inFunctionCalls &&
-			currentInvokeName === "" &&
-			currentCharIndex >= isInvokeStart.length - 1 &&
-			assistantMessage.startsWith(isInvokeStart, currentCharIndex - isInvokeStart.length + 1)
-		) {
-			// Find the end of the invoke name
-			const nameEndPos = assistantMessage.indexOf(isInvokeEnd, currentCharIndex + 1)
-			if (nameEndPos !== -1) {
-				// Extract the invoke name
-				currentInvokeName = assistantMessage.slice(currentCharIndex + 1, nameEndPos)
-				i = nameEndPos + isInvokeEnd.length - 1 // Skip to after the '">
-
-				// If this is an LS invoke, create a list_files tool
-				if (currentInvokeName === "LS") {
-					currentToolUse = {
-						type: "tool_use",
-						name: "list_files",
-						params: {},
-						partial: true,
-					}
-				}
-
-				// If this is a Grep invoke, create a search_files tool
-				if (currentInvokeName === "Grep") {
-					currentToolUse = {
-						type: "tool_use",
-						name: "search_files",
-						params: {},
-						partial: true,
-					}
-				}
-
-				continue
-			}
-		}
-
-		// Check for parameter start within invoke
-		if (
-			inFunctionCalls &&
-			currentInvokeName !== "" &&
-			currentParameterName === "" &&
-			currentCharIndex >= isParameterStart.length - 1 &&
-			assistantMessage.startsWith(isParameterStart, currentCharIndex - isParameterStart.length + 1)
-		) {
-			// Find the end of the parameter name
-			const nameEndPos = assistantMessage.indexOf(isParameterNameEnd, currentCharIndex + 1)
-			if (nameEndPos !== -1) {
-				// Extract the parameter name
-				currentParameterName = assistantMessage.slice(currentCharIndex + 1, nameEndPos)
-				currentParamValueStart = nameEndPos + isParameterNameEnd.length
-				i = nameEndPos + isParameterNameEnd.length - 1 // Skip to after the '">'
-				continue
-			}
-		}
-
-		// Check for parameter end
-		if (
-			inFunctionCalls &&
-			currentInvokeName !== "" &&
-			currentParameterName !== "" &&
-			currentCharIndex >= isParameterClose.length - 1 &&
-			assistantMessage.startsWith(isParameterClose, currentCharIndex - isParameterClose.length + 1)
-		) {
-			// Extract parameter value
-			const value = assistantMessage.slice(currentParamValueStart, currentCharIndex - isParameterClose.length + 1).trim()
-
-			// Map parameter to tool params
-			if (currentToolUse && currentInvokeName === "LS" && currentParameterName === "path") {
-				currentToolUse.params["path"] = value
-				// Default recursive to false - only show top level
-				currentToolUse.params["recursive"] = "false"
-			}
-
-			// Map parameter to tool params for Grep
-			if (currentToolUse && currentInvokeName === "Grep") {
-				if (currentParameterName === "pattern") {
-					currentToolUse.params["regex"] = value
-				} else if (currentParameterName === "path") {
-					currentToolUse.params["path"] = value
-				} else if (currentParameterName === "include") {
-					currentToolUse.params["file_pattern"] = value
-				}
-			}
-
-			currentParameterName = ""
-			continue
-		}
-
-		// Check for invoke end
-		if (
-			inFunctionCalls &&
-			currentInvokeName !== "" &&
-			currentCharIndex >= isInvokeClose.length - 1 &&
-			assistantMessage.startsWith(isInvokeClose, currentCharIndex - isInvokeClose.length + 1)
-		) {
-			// If we have a tool use from this invoke, finalize it
-			if (currentToolUse && (currentInvokeName === "LS" || currentInvokeName === "Grep")) {
-				currentToolUse.partial = false
-				contentBlocks.push(currentToolUse)
-				currentToolUse = undefined
-			}
-
-			currentInvokeName = ""
-			continue
-		}
-
-		// Check for function_calls end
-		if (
-			inFunctionCalls &&
-			currentCharIndex >= isFunctionCallsClose.length - 1 &&
-			assistantMessage.startsWith(isFunctionCallsClose, currentCharIndex - isFunctionCallsClose.length + 1)
-		) {
-			inFunctionCalls = false
-			currentTextContentStart = currentCharIndex + 1
-			continue
-		}
-
-		// Skip normal parsing when inside function_calls
-		if (inFunctionCalls) {
-			continue
-		}
-
-		// --- State: Parsing a Tool Parameter ---
-		if (currentToolUse && currentParamName) {
-			const closeTag = `</${currentParamName}>`
-			// Check if the string *ending* at index `i` matches the closing tag
-			if (
-				currentCharIndex >= closeTag.length - 1 &&
-				assistantMessage.startsWith(
-					closeTag,
-					currentCharIndex - closeTag.length + 1, // Start checking from potential start of tag
-				)
-			) {
-				// Found the closing tag for the parameter
-				const value = assistantMessage
-					.slice(
-						currentParamValueStart, // Start after the opening tag
-						currentCharIndex - closeTag.length + 1, // End before the closing tag
-					)
-					.trim()
-				currentToolUse.params[currentParamName] = value
-				currentParamName = undefined // Go back to parsing tool content
-				// We don't continue loop here, need to check for tool close or other params at index i
-			} else {
-				continue // Still inside param value, move to next char
-			}
-		}
-
-		// --- State: Parsing a Tool Use (but not a specific parameter) ---
-		if (currentToolUse && !currentParamName) {
-			// Ensure we are not inside a parameter already
-			// Check if starting a new parameter
-			let startedNewParam = false
-			for (const [tag, paramName] of toolParamOpenTags.entries()) {
-				if (currentCharIndex >= tag.length - 1 && assistantMessage.startsWith(tag, currentCharIndex - tag.length + 1)) {
-					currentParamName = paramName
-					currentParamValueStart = currentCharIndex + 1 // Value starts after the tag
-					startedNewParam = true
-					break
-				}
-			}
-			if (startedNewParam) {
-				continue // Handled start of param, move to next char
-			}
-
-			// Check if closing the current tool use
-			const toolCloseTag = `</${currentToolUse.name}>`
-			if (
-				currentCharIndex >= toolCloseTag.length - 1 &&
-				assistantMessage.startsWith(toolCloseTag, currentCharIndex - toolCloseTag.length + 1)
-			) {
-				// End of the tool use found
-				// Special handling for content params *before* finalizing the tool
-				const toolContentSlice = assistantMessage.slice(
-					currentToolUseStart, // From after the tool opening tag
-					currentCharIndex - toolCloseTag.length + 1, // To before the tool closing tag
-				)
-
-				// Check if content parameter needs special handling (write_to_file/new_rule)
-				// This check is important if the closing </content> tag was missed by the parameter parsing logic
-				// (e.g., if content is empty or parsing logic prioritizes tool close)
-				const contentParamName: ToolParamName = "content"
-				if (
-					currentToolUse.name === "write_to_file" /* || currentToolUse.name === "new_rule" */ &&
-					toolContentSlice.includes(`<${contentParamName}>`)
-				) {
-					const contentStartTag = `<${contentParamName}>`
-					const contentEndTag = `</${contentParamName}>`
-					const contentStart = toolContentSlice.indexOf(contentStartTag)
-					// Use lastIndexOf for robustness against nested tags
-					const contentEnd = toolContentSlice.lastIndexOf(contentEndTag)
-
-					if (contentStart !== -1 && contentEnd !== -1 && contentEnd > contentStart) {
-						const contentValue = toolContentSlice.slice(contentStart + contentStartTag.length, contentEnd).trim()
-						currentToolUse.params[contentParamName] = contentValue
-					}
-				}
-
-				currentToolUse.partial = false // Mark as complete
-				contentBlocks.push(currentToolUse)
-				currentToolUse = undefined // Reset state
-				currentTextContentStart = currentCharIndex + 1 // Potential text starts after this tag
-				continue // Move to next char
-			}
-			// If not starting a param and not closing the tool, continue accumulating tool content implicitly
-			continue
-		}
-
-		// --- State: Parsing Text / Looking for Tool Start ---
-		if (!currentToolUse) {
-			// Check if starting a new tool use
-			let startedNewTool = false
-			for (const [tag, toolName] of toolUseOpenTags.entries()) {
-				if (currentCharIndex >= tag.length - 1 && assistantMessage.startsWith(tag, currentCharIndex - tag.length + 1)) {
-					// End current text block if one was active
-					if (currentTextContent) {
-						currentTextContent.content = assistantMessage
-							.slice(
-								currentTextContentStart, // From where text started
-								currentCharIndex - tag.length + 1, // To before the tool tag starts
-							)
-							.trim()
-						currentTextContent.partial = false // Ended because tool started
-						if (currentTextContent.content.length > 0) {
-							contentBlocks.push(currentTextContent)
-						}
-						currentTextContent = undefined
-					} else {
-						// Check for any text between the last block and this tag
-						const potentialText = assistantMessage
-							.slice(
-								currentTextContentStart, // From where text *might* have started
-								currentCharIndex - tag.length + 1, // To before the tool tag starts
-							)
-							.trim()
-						if (potentialText.length > 0) {
-							contentBlocks.push({
-								type: "text",
-								content: potentialText,
-								partial: false,
-							})
-						}
-					}
-
-					// Start the new tool use
-					currentToolUse = {
-						type: "tool_use",
-						name: toolName,
-						params: {},
-						partial: true, // Assume partial until closing tag is found
-					}
-					currentToolUseStart = currentCharIndex + 1 // Tool content starts after the opening tag
-					startedNewTool = true
-					break
-				}
-			}
-
-			if (startedNewTool) {
-				continue // Handled start of tool, move to next char
-			}
-
-			// If not starting a tool, it must be text content
-			if (!currentTextContent) {
-				// Start a new text block if we aren't already in one
-				currentTextContentStart = currentCharIndex // Text starts at the current character
-				// Check if the current char is the start of potential text *immediately* after a tag
-				// This needs the previous state - simpler to let slicing handle it later.
-				// Resetting start index accurately is key.
-				// It should be the index *after* the last processed tag.
-				// The logic managing currentTextContentStart after closing tags handles this.
-
-				currentTextContent = {
-					type: "text",
-					content: "", // Will be determined by slicing at the end or when a tool starts
-					partial: true,
-				}
-			}
-			// Continue accumulating text implicitly; content is extracted later.
-		}
-	} // End of loop
-
-	// --- Finalization after loop ---
-
-	// Finalize any open parameter within an open tool use
-	if (currentToolUse && currentParamName) {
-		currentToolUse.params[currentParamName] = assistantMessage
-			.slice(currentParamValueStart) // From param start to end of string
-			.trim()
-		// Tool use remains partial
-	}
-
-	// Finalize any open tool use (which might contain the finalized partial param)
-	if (currentToolUse) {
-		// Tool use is partial because the loop finished before its closing tag
-		contentBlocks.push(currentToolUse)
-	}
-	// Finalize any trailing text content
-	// Only possible if a tool use wasn't open at the very end
-	else if (currentTextContent) {
-		currentTextContent.content = assistantMessage
-			.slice(currentTextContentStart) // From text start to end of string
-			.trim()
-		// Text is partial because the loop finished
-		if (currentTextContent.content.length > 0) {
-			contentBlocks.push(currentTextContent)
-		}
-	}
-
-	return contentBlocks
-}

src/core/controller/index.ts

@@ -52,7 +52,6 @@ import {
 import { Task, cwd } from "../task"
 import { ClineRulesToggles } from "@shared/cline-rules"
 import { sendStateUpdate } from "./state/subscribeToState"
-import { sendAddToInputEvent } from "./ui/subscribeToAddToInput"
 import { sendAuthCallbackEvent } from "./account/subscribeToAuthCallback"
 import { refreshClineRulesToggles } from "@core/context/instructions/user-instructions/cline-rules"
 import { refreshExternalRulesToggles } from "@core/context/instructions/user-instructions/external-rules"
@@ -265,6 +264,13 @@ export class Controller {
 					}
 				})
 				break
+			case "showChatView": {
+				this.postMessageToWebview({
+					type: "action",
+					action: "chatButtonClicked",
+				})
+				break
+			}
 			case "newTask":
 				// Code that should run in response to the hello message command
 				//vscode.window.showInformationMessage(message.text!)
@@ -923,7 +929,10 @@ export class Controller {
 			input += `\nProblems:\n${problemsString}`
 		}
 
-		await sendAddToInputEvent(input)
+		await this.postMessageToWebview({
+			type: "addToInput",
+			text: input,
+		})
 
 		console.log("addSelectedCodeToChat", code, filePath, languageId)
 	}
@@ -941,7 +950,10 @@ export class Controller {
 		//     terminalName
 		// })
 
-		await sendAddToInputEvent(`Terminal output:\n\`\`\`\n${output}\n\`\`\``)
+		await this.postMessageToWebview({
+			type: "addToInput",
+			text: `Terminal output:\n\`\`\`\n${output}\n\`\`\``,
+		})
 
 		console.log("addSelectedTerminalOutputToChat", output, terminalName)
 	}

src/core/controller/ui/subscribeToAddToInput.ts

@@ -1,64 +0,0 @@
-import * as vscode from "vscode"
-import { Controller } from "../index"
-import { EmptyRequest } from "../../../shared/proto/common"
-import { String as ProtoString } from "../../../shared/proto/common"
-import { StreamingResponseHandler, getRequestRegistry } from "../grpc-handler"
-
-// Keep track of active addToInput subscriptions
-const activeAddToInputSubscriptions = new Set<StreamingResponseHandler>()
-
-/**
- * Subscribe to addToInput events
- * @param controller The controller instance
- * @param request The empty request
- * @param responseStream The streaming response handler
- * @param requestId The ID of the request (passed by the gRPC handler)
- */
-export async function subscribeToAddToInput(
-	controller: Controller,
-	request: EmptyRequest,
-	responseStream: StreamingResponseHandler,
-	requestId?: string,
-): Promise<void> {
-	console.log("[DEBUG] set up addToInput subscription")
-
-	// Add this subscription to the active subscriptions
-	activeAddToInputSubscriptions.add(responseStream)
-
-	// Register cleanup when the connection is closed
-	const cleanup = () => {
-		activeAddToInputSubscriptions.delete(responseStream)
-		console.log("[DEBUG] Cleaned up addToInput subscription")
-	}
-
-	// Register the cleanup function with the request registry if we have a requestId
-	if (requestId) {
-		getRequestRegistry().registerRequest(requestId, cleanup, { type: "addToInput_subscription" }, responseStream)
-	}
-}
-
-/**
- * Send an addToInput event to all active subscribers
- * @param text The text to add to the input
- */
-export async function sendAddToInputEvent(text: string): Promise<void> {
-	// Send the event to all active subscribers
-	const promises = Array.from(activeAddToInputSubscriptions).map(async (responseStream) => {
-		try {
-			const event: ProtoString = {
-				value: text,
-			}
-			await responseStream(
-				event,
-				false, // Not the last message
-			)
-			console.log("[DEBUG] sending addToInput event", text.length, "chars")
-		} catch (error) {
-			console.error("Error sending addToInput event:", error)
-			// Remove the subscription if there was an error
-			activeAddToInputSubscriptions.delete(responseStream)
-		}
-	})
-
-	await Promise.all(promises)
-}

src/core/prompts/model_prompts/claude4.ts

@@ -1,616 +0,0 @@
-import { getShell } from "@utils/shell"
-import os from "os"
-import osName from "os-name"
-import { McpHub } from "@services/mcp/McpHub"
-import { BrowserSettings } from "@shared/BrowserSettings"
-
-import { createAntmlToolPrompt, createSimpleXmlToolPrompt, toolDefinitionToSimpleXml } from "@core/prompts/model_prompts/jsonToolToXml"
-import { bashToolDefinition } from "@core/tools/bashTool"
-import { readToolDefinition } from "@core/tools/readTool"
-import { writeToolDefinition } from "@core/tools/writeTool"
-import {lsToolDefinition} from "@core/tools/lsTool"
-import { grepToolDefinition } from "@/core/tools/grepTool"
-
-export const SYSTEM_PROMPT_CLAUDE4 = async (
-	cwd: string,
-	supportsBrowserUse: boolean,
-	mcpHub: McpHub,
-	browserSettings: BrowserSettings,
-) => { 
-  const systemPrompt = `You are Cline, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
-
-====
-
-TOOL USE
-
-You have access to a set of tools that are executed upon the user's approval. You can use one tool per message, and will receive the result of that tool use in the user's response. You use tools step-by-step to accomplish a given task, with each tool use informed by the result of the previous tool use.
-
-# Tool Use Formatting
-
-Tool use is formatted using XML-style tags. The tool name is enclosed in opening and closing tags, and each parameter is similarly enclosed within its own set of tags. Here's the structure:
-
-<tool_name>
-<parameter1_name>value1</parameter1_name>
-<parameter2_name>value2</parameter2_name>
-...
-</tool_name>
-
-For example:
-
-<read_file>
-<path>src/main.js</path>
-</read_file>
-
-Always adhere to this format for the tool use to ensure proper parsing and execution.
-
-# Tools
-
-## execute_command
-Description: Request to execute a CLI command on the system. Use this when you need to perform system operations or run specific commands to accomplish any step in the user's task. You must tailor your command to the user's system and provide a clear explanation of what the command does. For command chaining, use the appropriate chaining syntax for the user's shell. Prefer to execute complex CLI commands over creating executable scripts, as they are more flexible and easier to run. Commands will be executed in the current working directory: ${cwd.toPosix()}
-Parameters:
-- command: (required) The CLI command to execute. This should be valid for the current operating system. Ensure the command is properly formatted and does not contain any harmful instructions.
-- requires_approval: (required) A boolean indicating whether this command requires explicit user approval before execution in case the user has auto-approve mode enabled. Set to 'true' for potentially impactful operations like installing/uninstalling packages, deleting/overwriting files, system configuration changes, network operations, or any commands that could have unintended side effects. Set to 'false' for safe operations like reading files/directories, running development servers, building projects, and other non-destructive operations.
-Usage:
-<execute_command>
-<command>Your command here</command>
-<requires_approval>true or false</requires_approval>
-</execute_command>
-
-## read_file
-Description: Request to read the contents of a file at the specified path. Use this when you need to examine the contents of an existing file you do not know the contents of, for example to analyze code, review text files, or extract information from configuration files. Automatically extracts raw text from PDF and DOCX files. May not be suitable for other types of binary files, as it returns the raw content as a string.
-Parameters:
-- path: (required) The path of the file to read (relative to the current working directory ${cwd.toPosix()})
-Usage:
-<read_file>
-<path>File path here</path>
-</read_file>
-
-## write_to_file
-Description: Request to write content to a file at the specified path. If the file exists, it will be overwritten with the provided content. If the file doesn't exist, it will be created. This tool will automatically create any directories needed to write the file.
-Parameters:
-- path: (required) The path of the file to write to (relative to the current working directory ${cwd.toPosix()})
-- content: (required) The content to write to the file. ALWAYS provide the COMPLETE intended content of the file, without any truncation or omissions. You MUST include ALL parts of the file, even if they haven't been modified.
-Usage:
-<write_to_file>
-<path>File path here</path>
-<content>
-Your file content here
-</content>
-</write_to_file>
-
-## replace_in_file
-
-"Description: Return your edits as a JSON object with a "replacements" array. Each replacement should have "old_str" and "new_str" fields. The old_str must match exactly what's in the file (including whitespace, indentation and new lines). You can edit multiple lines, but please keep the replacements as simple as possible.
-Both old_str and new_str can be multiline strings, but they must be valid JSON strings.
-
-Usage:
-<replace_in_file>
-<path>File path here</path>
-<diff>
-{{
-  "replacements": [
-    {{
-      "old_str": "exact string from file",
-      "new_str": "replacement string"
-    }}
-  ]
-}}
-</diff>
-</replace_in_file>
-
-Important: Make sure each old_str matches the exact text in the file, character for character.
-Parameters:
-- path: (required) The path of the file to modify (relative to the current working directory ${cwd.toPosix()})
-- replacements_json: (required) A JSON string containing an object with a "replacements" array. Each object in the array must have "old_str" (the exact string to find in the file) and "new_str" (the string to replace it with). Refer to the example format in the main description.
-Usage:
-<replace_in_file>
-<path>File path here</path>
-<diff>
-{{
-  "replacements": [
-    {{
-      "old_str": "exact string from file",
-      "new_str": "replacement string"
-    }}
-  ]
-}}
-</diff>
-</replace_in_file>
-
-## list_code_definition_names
-Description: Request to list definition names (classes, functions, methods, etc.) used in source code files at the top level of the specified directory. This tool provides insights into the codebase structure and important constructs, encapsulating high-level concepts and relationships that are crucial for understanding the overall architecture.
-Parameters:
-- path: (required) The path of the directory (relative to the current working directory ${cwd.toPosix()}) to list top level source code definitions for.
-Usage:
-<list_code_definition_names>
-<path>Directory path here</path>
-</list_code_definition_names>${
-	supportsBrowserUse
-		? `
-
-## browser_action
-Description: Request to interact with a Puppeteer-controlled browser. Every action, except \`close\`, will be responded to with a screenshot of the browser's current state, along with any new console logs. You may only perform one browser action per message, and wait for the user's response including a screenshot and logs to determine the next action.
-- The sequence of actions **must always start with** launching the browser at a URL, and **must always end with** closing the browser. If you need to visit a new URL that is not possible to navigate to from the current webpage, you must first close the browser, then launch again at the new URL.
-- While the browser is active, only the \`browser_action\` tool can be used. No other tools should be called during this time. You may proceed to use other tools only after closing the browser. For example if you run into an error and need to fix a file, you must close the browser, then use other tools to make the necessary changes, then re-launch the browser to verify the result.
-- The browser window has a resolution of **${browserSettings.viewport.width}x${browserSettings.viewport.height}** pixels. When performing any click actions, ensure the coordinates are within this resolution range.
-- Before clicking on any elements such as icons, links, or buttons, you must consult the provided screenshot of the page to determine the coordinates of the element. The click should be targeted at the **center of the element**, not on its edges.
-Parameters:
-- action: (required) The action to perform. The available actions are:
-    * launch: Launch a new Puppeteer-controlled browser instance at the specified URL. This **must always be the first action**.
-        - Use with the \`url\` parameter to provide the URL.
-        - Ensure the URL is valid and includes the appropriate protocol (e.g. http://localhost:3000/page, file:///path/to/file.html, etc.)
-    * click: Click at a specific x,y coordinate.
-        - Use with the \`coordinate\` parameter to specify the location.
-        - Always click in the center of an element (icon, button, link, etc.) based on coordinates derived from a screenshot.
-    * type: Type a string of text on the keyboard. You might use this after clicking on a text field to input text.
-        - Use with the \`text\` parameter to provide the string to type.
-    * scroll_down: Scroll down the page by one page height.
-    * scroll_up: Scroll up the page by one page height.
-    * close: Close the Puppeteer-controlled browser instance. This **must always be the final browser action**.
-        - Example: \`<action>close</action>\`
-- url: (optional) Use this for providing the URL for the \`launch\` action.
-    * Example: <url>https://example.com</url>
-- coordinate: (optional) The X and Y coordinates for the \`click\` action. Coordinates should be within the **${browserSettings.viewport.width}x${browserSettings.viewport.height}** resolution.
-    * Example: <coordinate>450,300</coordinate>
-- text: (optional) Use this for providing the text for the \`type\` action.
-    * Example: <text>Hello, world!</text>
-Usage:
-<browser_action>
-<action>Action to perform (e.g., launch, click, type, scroll_down, scroll_up, close)</action>
-<url>URL to launch the browser at (optional)</url>
-<coordinate>x,y coordinates (optional)</coordinate>
-<text>Text to type (optional)</text>
-</browser_action>`
-		: ""
-}
-
-## use_mcp_tool
-Description: Request to use a tool provided by a connected MCP server. Each MCP server can provide multiple tools with different capabilities. Tools have defined input schemas that specify required and optional parameters.
-Parameters:
-- server_name: (required) The name of the MCP server providing the tool
-- tool_name: (required) The name of the tool to execute
-- arguments: (required) A JSON object containing the tool's input parameters, following the tool's input schema
-Usage:
-<use_mcp_tool>
-<server_name>server name here</server_name>
-<tool_name>tool name here</tool_name>
-<arguments>
-{
-  "param1": "value1",
-  "param2": "value2"
-}
-</arguments>
-</use_mcp_tool>
-
-## access_mcp_resource
-Description: Request to access a resource provided by a connected MCP server. Resources represent data sources that can be used as context, such as files, API responses, or system information.
-Parameters:
-- server_name: (required) The name of the MCP server providing the resource
-- uri: (required) The URI identifying the specific resource to access
-Usage:
-<access_mcp_resource>
-<server_name>server name here</server_name>
-<uri>resource URI here</uri>
-</access_mcp_resource>
-
-## ask_followup_question
-Description: Ask the user a question to gather additional information needed to complete the task. This tool should be used when you encounter ambiguities, need clarification, or require more details to proceed effectively. It allows for interactive problem-solving by enabling direct communication with the user. Use this tool judiciously to maintain a balance between gathering necessary information and avoiding excessive back-and-forth.
-Parameters:
-- question: (required) The question to ask the user. This should be a clear, specific question that addresses the information you need.
-- options: (optional) An array of 2-5 options for the user to choose from. Each option should be a string describing a possible answer. You may not always need to provide options, but it may be helpful in many cases where it can save the user from having to type out a response manually. IMPORTANT: NEVER include an option to toggle to Act mode, as this would be something you need to direct the user to do manually themselves if needed.
-Usage:
-<ask_followup_question>
-<question>Your question here</question>
-<options>
-Array of options here (optional), e.g. ["Option 1", "Option 2", "Option 3"]
-</options>
-</ask_followup_question>
-
-## attempt_completion
-Description: After each tool use, the user will respond with the result of that tool use, i.e. if it succeeded or failed, along with any reasons for failure. Once you've received the results of tool uses and can confirm that the task is complete, use this tool to present the result of your work to the user. Optionally you may provide a CLI command to showcase the result of your work. The user may respond with feedback if they are not satisfied with the result, which you can use to make improvements and try again.
-IMPORTANT NOTE: This tool CANNOT be used until you've confirmed from the user that any previous tool uses were successful. Failure to do so will result in code corruption and system failure. Before using this tool, you must ask yourself in <thinking></thinking> tags if you've confirmed from the user that any previous tool uses were successful. If not, then DO NOT use this tool.
-Parameters:
-- result: (required) The result of the task. Formulate this result in a way that is final and does not require further input from the user. Don't end your result with questions or offers for further assistance.
-- command: (optional) A CLI command to execute to show a live demo of the result to the user. For example, use \`open index.html\` to display a created html website, or \`open localhost:3000\` to display a locally running development server. But DO NOT use commands like \`echo\` or \`cat\` that merely print text. This command should be valid for the current operating system. Ensure the command is properly formatted and does not contain any harmful instructions.
-Usage:
-<attempt_completion>
-<result>
-Your final result description here
-</result>
-<command>Command to demonstrate result (optional)</command>
-</attempt_completion>
-
-## new_task
-Description: Request to create a new task with preloaded context covering the conversation with the user up to this point and key information for continuing with the new task. With this tool, you will create a detailed summary of the conversation so far, paying close attention to the user's explicit requests and your previous actions, with a focus on the most relevant information required for the new task.
-Among other important areas of focus, this summary should be thorough in capturing technical details, code patterns, and architectural decisions that would be essential for continuing with the new task. The user will be presented with a preview of your generated context and can choose to create a new task or keep chatting in the current conversation. The user may choose to start a new task at any point.
-Parameters:
-- Context: (required) The context to preload the new task with. If applicable based on the current task, this should include:
-  1. Current Work: Describe in detail what was being worked on prior to this request to create a new task. Pay special attention to the more recent messages / conversation.
-  2. Key Technical Concepts: List all important technical concepts, technologies, coding conventions, and frameworks discussed, which might be relevant for the new task.
-  3. Relevant Files and Code: If applicable, enumerate specific files and code sections examined, modified, or created for the task continuation. Pay special attention to the most recent messages and changes.
-  4. Problem Solving: Document problems solved thus far and any ongoing troubleshooting efforts.
-  5. Pending Tasks and Next Steps: Outline all pending tasks that you have explicitly been asked to work on, as well as list the next steps you will take for all outstanding work, if applicable. Include code snippets where they add clarity. For any next steps, include direct quotes from the most recent conversation showing exactly what task you were working on and where you left off. This should be verbatim to ensure there's no information loss in context between tasks. It's important to be detailed here.
-Usage:
-<new_task>
-<context>context to preload new task with</context>
-</new_task>
-
-## plan_mode_respond
-Description: Respond to the user's inquiry in an effort to plan a solution to the user's task. This tool should be used when you need to provide a response to a question or statement from the user about how you plan to accomplish the task. This tool is only available in PLAN MODE. The environment_details will specify the current mode, if it is not PLAN MODE then you should not use this tool. Depending on the user's message, you may ask questions to get clarification about the user's request, architect a solution to the task, and to brainstorm ideas with the user. For example, if the user's task is to create a website, you may start by asking some clarifying questions, then present a detailed plan for how you will accomplish the task given the context, and perhaps engage in a back and forth to finalize the details before the user switches you to ACT MODE to implement the solution.
-Parameters:
-- response: (required) The response to provide to the user. Do not try to use tools in this parameter, this is simply a chat response. (You MUST use the response parameter, do not simply place the response text directly within <plan_mode_respond> tags.)
-Usage:
-<plan_mode_respond>
-<response>Your response here</response>
-</plan_mode_respond>
-
-## load_mcp_documentation
-Description: Load documentation about creating MCP servers. This tool should be used when the user requests to create or install an MCP server (the user may ask you something along the lines of "add a tool" that does some function, in other words to create an MCP server that provides tools and resources that may connect to external APIs for example. You have the ability to create an MCP server and add it to a configuration file that will then expose the tools and resources for you to use with \`use_mcp_tool\` and \`access_mcp_resource\`). The documentation provides detailed information about the MCP server creation process, including setup instructions, best practices, and examples.
-Parameters: None
-Usage:
-<load_mcp_documentation>
-</load_mcp_documentation>
-
-# Tool Use Examples
-
-## Example 1: Requesting to execute a command
-
-<execute_command>
-<command>npm run dev</command>
-<requires_approval>false</requires_approval>
-</execute_command>
-
-## Example 2: Requesting to create a new file
-
-<write_to_file>
-<path>src/frontend-config.json</path>
-<content>
-{
-  "apiEndpoint": "https://api.example.com",
-  "theme": {
-    "primaryColor": "#007bff",
-    "secondaryColor": "#6c757d",
-    "fontFamily": "Arial, sans-serif"
-  },
-  "features": {
-    "darkMode": true,
-    "notifications": true,
-    "analytics": false
-  },
-  "version": "1.0.0"
-}
-</content>
-</write_to_file>
-
-## Example 3: Creating a new task
-
-<new_task>
-<context>
-1. Current Work:
-   [Detailed description]
-
-2. Key Technical Concepts:
-   - [Concept 1]
-   - [Concept 2]
-   - [...]
-
-3. Relevant Files and Code:
-   - [File Name 1]
-      - [Summary of why this file is important]
-      - [Summary of the changes made to this file, if any]
-      - [Important Code Snippet]
-   - [File Name 2]
-      - [Important Code Snippet]
-   - [...]
-
-4. Problem Solving:
-   [Detailed description]
-
-5. Pending Tasks and Next Steps:
-   - [Task 1 details & next steps]
-   - [Task 2 details & next steps]
-   - [...]
-</context>
-</new_task>
-
-## Example 4: Requesting to make targeted edits to a file
-
-<replace_in_file>
-
-<path>src/baseApp.py</path>
-<diff>
-{
-  "replacements": [
-    {
-      "old_str": "def try_dotdotdots(whole, part, replace):",
-      "new_str": "# Handles search/replace blocks that use ellipsis (...) to represent omitted code sections\n# Validates that ellipsis usage is consistent between search and replace blocks\ndef try_dotdotdots(whole, part, replace):"
-    },
-    {
-      "old_str": "def strip_filename(filename, fence):",
-      "new_str": "# Extracts and cleans filename from various markdown formatting styles\n# Handles filenames with different prefixes, suffixes, and decorations\ndef strip_filename(filename, fence):"
-    },
-    {
-      "old_str": "def main():",
-      "new_str": "# Main entry point for command-line usage\n# Processes chat history and displays diffs for all found edit blocks\ndef main():"
-    }
-  ]
-}
-</diff>
-</replace_in_file>
-
-
-## Example 5: Requesting to use an MCP tool
-
-<use_mcp_tool>
-<server_name>weather-server</server_name>
-<tool_name>get_forecast</tool_name>
-<arguments>
-{
-  "city": "San Francisco",
-  "days": 5
-}
-</arguments>
-</use_mcp_tool>
-
-## Example 6: Another example of using an MCP tool (where the server name is a unique identifier such as a URL)
-
-<use_mcp_tool>
-<server_name>github.com/modelcontextprotocol/servers/tree/main/src/github</server_name>
-<tool_name>create_issue</tool_name>
-<arguments>
-{
-  "owner": "octocat",
-  "repo": "hello-world",
-  "title": "Found a bug",
-  "body": "I'm having a problem with this.",
-  "labels": ["bug", "help wanted"],
-  "assignees": ["octocat"]
-}
-</arguments>
-</use_mcp_tool>
-
-# Tool Use Guidelines
-
-1. In <thinking> tags, assess what information you already have and what information you need to proceed with the task.
-2. Choose the most appropriate tool based on the task and the tool descriptions provided. Assess if you need additional information to proceed, and which of the available tools would be most effective for gathering this information. It's critical that you think about each available tool and use the one that best fits the current step in the task.
-3. If multiple actions are needed, use one tool at a time per message to accomplish the task iteratively, with each tool use being informed by the result of the previous tool use. Do not assume the outcome of any tool use. Each step must be informed by the previous step's result.
-4. Formulate your tool use using the XML format specified for each tool.
-5. After each tool use, the user will respond with the result of that tool use. This result will provide you with the necessary information to continue your task or make further decisions. This response may include:
-  - Information about whether the tool succeeded or failed, along with any reasons for failure.
-  - Linter errors that may have arisen due to the changes you made, which you'll need to address.
-  - New terminal output in reaction to the changes, which you may need to consider or act upon.
-  - Any other relevant feedback or information related to the tool use.
-6. ALWAYS wait for user confirmation after each tool use before proceeding. Never assume the success of a tool use without explicit confirmation of the result from the user.
-
-It is crucial to proceed step-by-step, waiting for the user's message after each tool use before moving forward with the task. This approach allows you to:
-1. Confirm the success of each step before proceeding.
-2. Address any issues or errors that arise immediately.
-3. Adapt your approach based on new information or unexpected results.
-4. Ensure that each action builds correctly on the previous ones.
-
-By waiting for and carefully considering the user's response after each tool use, you can react accordingly and make informed decisions about how to proceed with the task. This iterative process helps ensure the overall success and accuracy of your work.
-
-====
-
-MCP SERVERS
-
-The Model Context Protocol (MCP) enables communication between the system and locally running MCP servers that provide additional tools and resources to extend your capabilities.
-
-# Connected MCP Servers
-
-When a server is connected, you can use the server's tools via the \`use_mcp_tool\` tool, and access the server's resources via the \`access_mcp_resource\` tool.
-
-${
-	mcpHub.getServers().length > 0
-		? `${mcpHub
-				.getServers()
-				.filter((server) => server.status === "connected")
-				.map((server) => {
-					const tools = server.tools
-						?.map((tool) => {
-							const schemaStr = tool.inputSchema
-								? `    Input Schema:
-    ${JSON.stringify(tool.inputSchema, null, 2).split("\n").join("\n    ")}`
-								: ""
-
-							return `- ${tool.name}: ${tool.description}\n${schemaStr}`
-						})
-						.join("\n\n")
-
-					const templates = server.resourceTemplates
-						?.map((template) => `- ${template.uriTemplate} (${template.name}): ${template.description}`)
-						.join("\n")
-
-					const resources = server.resources
-						?.map((resource) => `- ${resource.uri} (${resource.name}): ${resource.description}`)
-						.join("\n")
-
-					const config = JSON.parse(server.config)
-
-					return (
-						`## ${server.name} (\`${config.command}${config.args && Array.isArray(config.args) ? ` ${config.args.join(" ")}` : ""}\`)` +
-						(tools ? `\n\n### Available Tools\n${tools}` : "") +
-						(templates ? `\n\n### Resource Templates\n${templates}` : "") +
-						(resources ? `\n\n### Direct Resources\n${resources}` : "")
-					)
-				})
-				.join("\n\n")}`
-		: "(No MCP servers currently connected)"
-}
-
-====
-
-EDITING FILES
-
-You have access to two tools for working with files: **write_to_file** and **replace_in_file**. Understanding their roles and selecting the right one for the job will help ensure efficient and accurate modifications.
-
-# write_to_file
-
-## Purpose
-
-- Create a new file, or overwrite the entire contents of an existing file.
-
-## When to Use
-
-- Initial file creation, such as when scaffolding a new project.  
-- Overwriting large boilerplate files where you want to replace the entire content at once.
-- When the complexity or number of changes would make replace_in_file unwieldy or error-prone.
-- When you need to completely restructure a file's content or change its fundamental organization.
-
-## Important Considerations
-
-- Using write_to_file requires providing the file's complete final content.  
-- If you only need to make small changes to an existing file, consider using replace_in_file instead to avoid unnecessarily rewriting the entire file.
-- While write_to_file should not be your default choice, don't hesitate to use it when the situation truly calls for it.
-
-# replace_in_file
-
-## Purpose
-
-- Make targeted edits to specific parts of an existing file without overwriting the entire file.
-
-## When to Use
-
-- Small, localized changes like updating a few lines, function implementations, changing variable names, modifying a section of text, etc.
-- Targeted improvements where only specific portions of the file's content needs to be altered.
-- Especially useful for long files where much of the file will remain unchanged.
-
-## Advantages
-
-- More efficient for minor edits, since you don't need to supply the entire file content.  
-- Reduces the chance of errors that can occur when overwriting large files.
-
-# Choosing the Appropriate Tool
-
-- **Default to replace_in_file** for most changes. It's the safer, more precise option that minimizes potential issues.
-- **Use write_to_file** when:
-  - Creating new files
-  - The changes are so extensive that using replace_in_file would be more complex or risky
-  - You need to completely reorganize or restructure a file
-  - The file is relatively small and the changes affect most of its content
-  - You're generating boilerplate or template files
-
-# Auto-formatting Considerations
-
-- After using either write_to_file or replace_in_file, the user's editor may automatically format the file
-- This auto-formatting may modify the file contents, for example:
-  - Breaking single lines into multiple lines
-  - Adjusting indentation to match project style (e.g. 2 spaces vs 4 spaces vs tabs)
-  - Converting single quotes to double quotes (or vice versa based on project preferences)
-  - Organizing imports (e.g. sorting, grouping by type)
-  - Adding/removing trailing commas in objects and arrays
-  - Enforcing consistent brace style (e.g. same-line vs new-line)
-  - Standardizing semicolon usage (adding or removing based on style)
-- The write_to_file and replace_in_file tool responses will include the final state of the file after any auto-formatting
-- Use this final state as your reference point for any subsequent edits. This is ESPECIALLY important when crafting SEARCH blocks for replace_in_file which require the content to match what's in the file exactly.
-
-# Workflow Tips
-
-1. Before editing, assess the scope of your changes and decide which tool to use.
-2. For major overhauls or initial file creation, rely on write_to_file.
-3. Once the file has been edited with either write_to_file or replace_in_file, the system will provide you with the final state of the modified file. Use this updated content as the reference point for any subsequent SEARCH/REPLACE operations, since it reflects any auto-formatting or user-applied changes.
-4. All edits are applied in sequence, in the order they are provided
-5. All edits must be valid for the operation to succeed - if any edit fails, none will be applied
-6. Do not make more than 4 replacements in a single replace_in_file call, as this can lead to errors and make it difficult to track changes. If you need to make more than 4 changes, consider breaking them into multiple replace_in_file calls.
-7. Make sure a single old_str in a replace_in_file call is no more than 4 lines, as too many lines can lead to errors. If you need to replace a larger section, break it into smaller blocks.
-
-By thoughtfully selecting between write_to_file and replace_in_file, you can make your file editing process smoother, safer, and more efficient.
-
-====
- 
-ACT MODE V.S. PLAN MODE
-
-In each user message, the environment_details will specify the current mode. There are two modes:
-
-- ACT MODE: In this mode, you have access to all tools EXCEPT the plan_mode_respond tool.
- - In ACT MODE, you use tools to accomplish the user's task. Once you've completed the user's task, you use the attempt_completion tool to present the result of the task to the user.
-- PLAN MODE: In this special mode, you have access to the plan_mode_respond tool.
- - In PLAN MODE, the goal is to gather information and get context to create a detailed plan for accomplishing the task, which the user will review and approve before they switch you to ACT MODE to implement the solution.
- - In PLAN MODE, when you need to converse with the user or present a plan, you should use the plan_mode_respond tool to deliver your response directly, rather than using <thinking> tags to analyze when to respond. Do not talk about using plan_mode_respond - just use it directly to share your thoughts and provide helpful answers.
-
-## What is PLAN MODE?
-
-- While you are usually in ACT MODE, the user may switch to PLAN MODE in order to have a back and forth with you to plan how to best accomplish the task. 
-- When starting in PLAN MODE, depending on the user's request, you may need to do some information gathering e.g. using read_file or Grep to get more context about the task. You may also ask the user clarifying questions to get a better understanding of the task. You may return mermaid diagrams to visually display your understanding.
-- Once you've gained more context about the user's request, you should architect a detailed plan for how you will accomplish the task. Returning mermaid diagrams may be helpful here as well.
-- Then you might ask the user if they are pleased with this plan, or if they would like to make any changes. Think of this as a brainstorming session where you can discuss the task and plan the best way to accomplish it.
-- If at any point a mermaid diagram would make your plan clearer to help the user quickly see the structure, you are encouraged to include a Mermaid code block in the response. (Note: if you use colors in your mermaid diagrams, be sure to use high contrast colors so the text is readable.)
-- Finally once it seems like you've reached a good plan, ask the user to switch you back to ACT MODE to implement the solution.
-
-====
- 
-CAPABILITIES
-
-- You have access to tools that let you execute CLI commands on the user's computer, list files, view source code definitions, regex search${
-	supportsBrowserUse ? ", use the browser" : ""
-}, read and edit files, and ask follow-up questions. These tools help you effectively accomplish a wide range of tasks, such as writing code, making edits or improvements to existing files, understanding the current state of a project, performing system operations, and much more.
-- When the user initially gives you a task, a recursive list of all filepaths in the current working directory ('${cwd.toPosix()}') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
-- You can use Grep to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
-- You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
-	- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the replace_in_file tool to implement changes. If you refactored code that could affect other parts of the codebase, you could use Grep to ensure you update other files as needed.
-- You can use the execute_command tool to run commands on the user's computer whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.${
-	supportsBrowserUse
-		? "\n- You can use the browser_action tool to interact with websites (including html files and locally running development servers) through a Puppeteer-controlled browser when you feel it is necessary in accomplishing the user's task. This tool is particularly useful for web development tasks as it allows you to launch a browser, navigate to pages, interact with elements through clicks and keyboard input, and capture the results through screenshots and console logs. This tool may be useful at key stages of web development tasks-such as after implementing new features, making substantial changes, when troubleshooting issues, or to verify the result of your work. You can analyze the provided screenshots to ensure correct rendering or identify errors, and review console logs for runtime issues.\n	- For example, if asked to add a component to a react website, you might create the necessary files, use execute_command to run the site locally, then use browser_action to launch the browser, navigate to the local server, and verify the component renders & functions correctly before closing the browser."
-		: ""
-}
-- You have access to MCP servers that may provide additional tools and resources. Each server may provide different capabilities that you can use to accomplish tasks more effectively.
-- You can use LaTeX syntax in your responses to render mathematical expressions
-
-====
-
-RULES
-
-- Your current working directory is: ${cwd.toPosix()}
-- You cannot \`cd\` into a different directory to complete a task. You are stuck operating from '${cwd.toPosix()}', so be sure to pass in the correct 'path' parameter when using tools that require a path.
-- Do not use the ~ character or $HOME to refer to the home directory.
-- Before using the execute_command tool, you must first think about the SYSTEM INFORMATION context provided to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory outside of the current working directory '${cwd.toPosix()}', and if so prepend with \`cd\`'ing into that directory && then executing the command (as one command since you are stuck operating from '${cwd.toPosix()}'). For example, if you needed to run \`npm install\` in a project outside of '${cwd.toPosix()}', you would need to prepend with a \`cd\` i.e. pseudocode for this would be \`cd (path to project) && (command, in this case npm install)\`.
-- When using the Grep tool, craft your regex patterns carefully to balance specificity and flexibility. Based on the user's task you may use it to find code patterns, TODO comments, function definitions, or any text-based information across the project. The results include context, so analyze the surrounding code to better understand the matches. Leverage the Grep tool in combination with other tools for more comprehensive analysis. For example, use it to find specific code patterns, then use read_file to examine the full context of interesting matches before using replace_in_file to make informed changes.
-- When creating a new project (such as an app, website, or any software project), organize all new files within a dedicated project directory unless the user specifies otherwise. Use appropriate file paths when creating files, as the write_to_file tool will automatically create any necessary directories. Structure the project logically, adhering to best practices for the specific type of project being created. Unless otherwise specified, new projects should be easily run without additional setup, for example most projects can be built in HTML, CSS, and JavaScript - which you can open in a browser.
-- Be sure to consider the type of project (e.g. Python, JavaScript, web application) when determining the appropriate structure and files to include. Also consider what files may be most relevant to accomplishing the task, for example looking at a project's manifest file would help you understand the project's dependencies, which you could incorporate into any code you write.
-- When making changes to code, always consider the context in which the code is being used. Ensure that your changes are compatible with the existing codebase and that they follow the project's coding standards and best practices.
-- When you want to modify a file, use the replace_in_file or write_to_file tool directly with the desired changes. You do not need to display the changes before using the tool.
-- Do not ask for more information than necessary. Use the tools provided to accomplish the user's request efficiently and effectively. When you've completed your task, you must use the attempt_completion tool to present the result to the user. The user may provide feedback, which you can use to make improvements and try again.
-- You are only allowed to ask the user questions using the ask_followup_question tool. Use this tool only when you need additional details to complete a task, and be sure to use a clear and concise question that will help you move forward with the task. However if you can use the available tools to avoid having to ask the user questions, you should do so. For example, if the user mentions a file that may be in an outside directory like the Desktop, you should use the LS tool to list the files in the Desktop and check if the file they are talking about is there, rather than asking the user to provide the file path themselves.
-- When executing commands, if you don't see the expected output, assume the terminal executed the command successfully and proceed with the task. The user's terminal may be unable to stream the output back properly. If you absolutely need to see the actual terminal output, use the ask_followup_question tool to request the user to copy and paste it back to you.
-- The user may provide a file's contents directly in their message, in which case you shouldn't use the read_file tool to get the file contents again since you already have it.
-- Your goal is to try to accomplish the user's task, NOT engage in a back and forth conversation.${
-	supportsBrowserUse
-		? `\n- The user may ask generic non-development tasks, such as "what\'s the latest news" or "look up the weather in San Diego", in which case you might use the browser_action tool to complete the task if it makes sense to do so, rather than trying to create a website or using curl to answer the question. However, if an available MCP server tool or resource can be used instead, you should prefer to use it over browser_action.`
-		: ""
-}
-- NEVER end attempt_completion result with a question or request to engage in further conversation! Formulate the end of your result in a way that is final and does not require further input from the user.
-- You are STRICTLY FORBIDDEN from starting your messages with "Great", "Certainly", "Okay", "Sure". You should NOT be conversational in your responses, but rather direct and to the point. For example you should NOT say "Great, I've updated the CSS" but instead something like "I've updated the CSS". It is important you be clear and technical in your messages.
-- When presented with images, utilize your vision capabilities to thoroughly examine them and extract meaningful information. Incorporate these insights into your thought process as you accomplish the user's task.
-- At the end of each user message, you will automatically receive environment_details. This information is not written by the user themselves, but is auto-generated to provide potentially relevant context about the project structure and environment. While this information can be valuable for understanding the project context, do not treat it as a direct part of the user's request or response. Use it to inform your actions and decisions, but don't assume the user is explicitly asking about or referring to this information unless they clearly do so in their message. When using environment_details, explain your actions clearly to ensure the user understands, as they may not be aware of these details.
-- Before executing commands, check the "Actively Running Terminals" section in environment_details. If present, consider how these active processes might impact your task. For example, if a local development server is already running, you wouldn't need to start it again. If no active terminals are listed, proceed with command execution as normal.
-- When using the replace_in_file tool, you must include complete lines 
-- It is critical you wait for the user's response after each tool use, in order to confirm the success of the tool use. For example, if asked to make a todo app, you would create a file, wait for the user's response it was created successfully, then create another file if needed, wait for the user's response it was created successfully, etc.${
-	supportsBrowserUse
-		? " Then if you want to test your work, you might use browser_action to launch the site, wait for the user's response confirming the site was launched along with a screenshot, then perhaps e.g., click a button to test functionality if needed, wait for the user's response confirming the button was clicked along with a screenshot of the new state, before finally closing the browser."
-		: ""
-}
-- MCP operations should be used one at a time, similar to other tool usage. Wait for confirmation of success before proceeding with additional operations.
-
-====
-
-SYSTEM INFORMATION
-
-Operating System: ${osName()}
-Default Shell: ${getShell()}
-Home Directory: ${os.homedir().toPosix()}
-Current Working Directory: ${cwd.toPosix()}
-
-====
-
-OBJECTIVE
-
-You accomplish a given task iteratively, breaking it down into clear steps and working through them methodically.
-
-1. Analyze the user's task and set clear, achievable goals to accomplish it. Prioritize these goals in a logical order.
-2. Work through these goals sequentially, utilizing available tools one at a time as necessary. Each goal should correspond to a distinct step in your problem-solving process. You will be informed on the work completed and what's remaining as you go.
-3. Remember, you have extensive capabilities with access to a wide range of tools that can be used in powerful and clever ways as necessary to accomplish each goal. Before calling a tool, do some analysis within <thinking></thinking> tags. First, analyze the file structure provided in environment_details to gain context and insights for proceeding effectively. Then, think about which of the provided tools is the most relevant tool to accomplish the user's task. Next, go through each of the required parameters of the relevant tool and determine if the user has directly provided or given enough information to infer a value. When deciding if the parameter can be inferred, carefully consider all the context to see if it supports a specific value. If all of the required parameters are present or can be reasonably inferred, close the thinking tag and proceed with the tool use. BUT, if one of the values for a required parameter is missing, DO NOT invoke the tool (not even with fillers for the missing params) and instead, ask the user to provide the missing parameters using the ask_followup_question tool. DO NOT ask for more information on optional parameters if it is not provided.
-4. Once you've completed the user's task, you must use the attempt_completion tool to present the result of the task to the user. You may also provide a CLI command to showcase the result of your task; this can be particularly useful for web development tasks, where you can run e.g. \`open index.html\` to show the website you've built.
-5. The user may provide feedback, which you can use to make improvements and try again. But DO NOT continue in pointless back and forth conversations, i.e. don't end your responses with questions or offers for further assistance.`
-
-  return createAntmlToolPrompt([lsToolDefinition, grepToolDefinition], true, systemPrompt);
-}

src/core/prompts/model_prompts/jsonToolToXml.ts

@@ -1,307 +0,0 @@
-function escapeXml(text: string): string {
-  // Anything that could be interpreted as markup has to be entity-encoded
-  return text
-    .replace(/&/g, '&')
-    .replace(/</g, '&lt;')
-    .replace(/>/g, '&gt;');
-}
-
-export interface ToolDefinition {
-  name: string;
-  description?: string;
-  descriptionForAgent?: string;
-  inputSchema: {
-    type: string;
-    properties: Record<string, any>;
-    required?: string[];
-    [key: string]: any;
-  };
-}
-
-/**
- * Converts a single tool definition (JSON schema) to the <function> tag format.
- * This is for *defining* the tool, not calling it.
- * @param toolDef The tool definition object
- * @returns The tool definition as a JSON string wrapped in <function> tags
- */
-export function toolDefinitionToAntmlDefinition(
-  toolDef: ToolDefinition
-): string {
-  // Restructure the parameters object to match the expected order
-  const { type, properties, required, ...rest } = toolDef.inputSchema;
-  const parameters = {
-    properties,
-    required,
-    type,
-    ...rest
-  };
-
-  const functionDef = {
-    description: toolDef.descriptionForAgent || toolDef.description || '',
-    name: toolDef.name,
-    parameters,
-  };
-
-  // 1. Create a custom JSON string with the exact format we want
-  let rawJson = `{"description": "${functionDef.description}", "name": "${functionDef.name}", "parameters": {`;
-  
-  // Add properties
-  rawJson += `"properties": {`;
-  const propEntries = Object.entries(parameters.properties);
-  propEntries.forEach(([propName, propDef], index) => {
-    rawJson += `"${propName}": {`;
-    rawJson += `"description": "${(propDef as any).description || ''}", `;
-    rawJson += `"type": "${(propDef as any).type || 'string'}"`;
-    rawJson += `}`;
-    if (index < propEntries.length - 1) { 
-		rawJson += ', ';
-	}
-  });
-  rawJson += `}, `;
-  
-  // Add required
-  rawJson += `"required": ${JSON.stringify(parameters.required || [])}, `;
-  
-  // Add type
-  rawJson += `"type": "object"`;
-  
-  // Close parameters and the whole object
-  rawJson += `}}`;
-
-  // 2.  Escape <, > and & so the JSON can sit INSIDE the XML tag safely.
-  //     (Quotes don’t need escaping - they’re not markup.)
-  const safeJson = escapeXml(rawJson);
-
-  // 3.  Return wrapped in <function> tags
-  return `<function>${safeJson}</function>`;
-}
-
-/**
- * Converts multiple tool definitions to the complete <functions> block.
- * This is for *defining* the tools.
- * @param toolDefs Array of tool definition objects
- * @returns Complete <functions> block with all tool definitions
- */
-export function toolDefinitionsToAntmlDefinitions(
-  toolDefs: ToolDefinition[]
-): string {
-  const functionTags = toolDefs.map(toolDefinitionToAntmlDefinition);
-  return `Here are the functions available in JSONSchema format:
-<functions>
-${functionTags.join('\n')}
-</functions>`;
-}
-
-/**
- * Creates an example of an ANTML tool call for a given tool definition.
- * This is for *calling* a tool.
- * @param toolDef The tool definition object
- * @param exampleValues Optional example values for parameters
- * @returns Example ANTML function call string
- */
-export function toolDefinitionToAntmlCallExample(
-  toolDef: ToolDefinition,
-  exampleValues: Record<string, any> = {}
-): string {
-  const props = toolDef.inputSchema.properties ?? {};
-
-  const paramLines = Object.keys(props).length
-    ? Object.entries(props)
-        .map(([name]) => {
-          const value = exampleValues[name] ?? `$${name.toUpperCase()}`; // placeholder
-          // Don't escape XML here - the example should show raw format
-          return `<parameter name="${name}">${value}</parameter>`;
-        })
-        .join('\n')
-    : '';
-
-  // Only include one invoke block
-  return [
-    '<function_calls>',
-    `<invoke name="${toolDef.name}">`,
-    paramLines,
-    '</invoke>',
-    '</function_calls>',
-  ]
-    .filter(Boolean)
-    .join('\n');
-}
-
-/**
- * Creates a complete system prompt section for tools in ANTML format,
- * including instructions and tool definitions.
- * @param toolDefs Array of tool definition objects
- * @param includeInstructions Whether to include the standard tool calling instructions
- * @returns Complete system prompt section for ANTML tools
- */
-export function createAntmlToolPrompt(
-  toolDefs: ToolDefinition[],
-  includeInstructions = true,
-  systemPrompt = ''
-): string {
-  if (toolDefs.length === 0) {
-    if (!includeInstructions) {
-		return '';
-	}
-
-    const noToolsMessage = [
-      "In this environment you have access to a set of tools you can use to answer the user's question.",
-      'You can invoke functions by writing a "<function_calls>" block like the following as part of your reply to the user:',
-      '<function_calls>',
-      '<invoke name="$FUNCTION_NAME">',
-      '<parameter name="$PARAMETER_NAME">$PARAMETER_VALUE</parameter>',
-      '...',
-      '</invoke>',
-      '</function_calls>',
-      '',
-      'String and scalar parameters should be specified as is, while lists and objects should use JSON format.',
-      '',
-      'However, no tools are currently available.',
-    ].join('\n');
-
-    return noToolsMessage;
-  }
-
-  let prompt = '';
-
-  if (includeInstructions) {
-    const instructionLines = [
-      "In this environment you have access to a set of tools you can use to answer the user's question.",
-      'You can invoke functions by writing a "<function_calls>" block like the following as part of your reply to the user:',
-      '<function_calls>',
-      '<invoke name="$FUNCTION_NAME">',
-      '<parameter name="$PARAMETER_NAME">$PARAMETER_VALUE</parameter>',
-      '...',
-      '</invoke>',
-      '</function_calls>',
-      '',
-      'String and scalar parameters should be specified as is, while lists and objects should use JSON format.',
-      '',
-    ];
-    prompt += instructionLines.join('\n');
-  }
-
-  prompt += toolDefinitionsToAntmlDefinitions(toolDefs);
-
-  if (includeInstructions) {
-    const closingInstructions = [
-      '',
-      '',
-      systemPrompt,
-      '',
-      '',
-      "Answer the user's request using the relevant tool(s), if they are available. Check that all the required parameters for each tool call are provided or can reasonably be inferred from context. IF there are no relevant tools or there are missing values for required parameters, ask the user to supply these values; otherwise proceed with the tool calls. If the user provides a specific value for a parameter (for example provided in quotes), make sure to use that value EXACTLY. DO NOT make up values for or ask about optional parameters. Carefully analyze descriptive terms in the request as they may indicate required parameter values that should be included even if not explicitly quoted.",
-    ];
-    prompt += closingInstructions.join('\n');
-  }
-
-  return prompt; // Don't trim - preserve exact formatting
-}
-
-// --- SimpleXML Functions (Cline's internal format) ---
-
-/**
- * Converts a single tool definition to the SimpleXML format
- * as used by Cline's current system prompts for non-ANTML models.
- * @param toolDef The tool definition object
- * @returns The tool definition formatted for SimpleXML usage
- */
-export function toolDefinitionToSimpleXml(toolDef: ToolDefinition): string {
-  const description = toolDef.descriptionForAgent || toolDef.description || '';
-  const properties = toolDef.inputSchema.properties || {};
-  const required = toolDef.inputSchema.required || [];
-
-  let parameterDocs = '';
-  if (Object.keys(properties).length > 0) {
-    parameterDocs = 'Parameters:\n';
-    for (const [paramName, paramDef] of Object.entries(properties)) {
-      const isRequired = required.includes(paramName);
-      const requiredText = isRequired ? '(required)' : '(optional)';
-      const paramDescription =
-        (paramDef as any).description || 'No description.';
-      parameterDocs += `- ${paramName}: ${requiredText} ${paramDescription}\n`;
-    }
-  }
-
-  const exampleParams = Object.keys(properties)
-    .map(paramName => `<${paramName}>${paramName} value here</${paramName}>`)
-    .join('\n');
-
-  const usageExample = `Usage:
-<${toolDef.name}>
-${exampleParams.length > 0 ? exampleParams + '\n' : ''}</${toolDef.name}>`;
-
-  return `## ${toolDef.name}
-Description: ${description}
-${parameterDocs.trim()}
-${usageExample}`;
-}
-
-/**
- * Converts multiple tool definitions to the complete SimpleXML format.
- * @param toolDefs Array of tool definition objects
- * @returns Complete tools documentation in SimpleXML format
- */
-export function toolDefinitionsToSimpleXml(toolDefs: ToolDefinition[]): string {
-  const toolDocs = toolDefs.map(toolDef => toolDefinitionToSimpleXml(toolDef));
-  return `# Tools
-
-${toolDocs.join('\n\n')}`;
-}
-
-/**
- * Creates a complete system prompt section for tools in SimpleXML format.
- * @param toolDefs Array of tool definition objects
- * @param includeInstructions Whether to include the standard tool calling instructions
- * @returns Complete system prompt section for SimpleXML tools
- */
-export function createSimpleXmlToolPrompt(
-  toolDefs: ToolDefinition[],
-  includeInstructions: boolean = true
-): string {
-  if (toolDefs.length === 0) {
-    return '';
-  }
-
-  let prompt = '';
-
-  if (includeInstructions) {
-    prompt += `TOOL USE
-
-You have access to a set of tools that are executed upon the user's approval. You can use one tool per message, and will receive the result of that tool use in the user's response. You use tools step-by-step to accomplish a given task, with each tool use informed by the result of the previous tool use.
-
-# Tool Use Formatting
-
-Tool use is formatted using XML-style tags. The tool name is enclosed in opening and closing tags, and each parameter is similarly enclosed within its own set of tags. Here's the structure:
-
-<tool_name>
-<parameter1_name>value1</parameter1_name>
-<parameter2_name>value2</parameter2_name>
-...
-</tool_name>
-
-For example:
-
-<read_file>
-<path>src/main.js</path>
-</read_file>
-
-Always adhere to this format for the tool use to ensure proper parsing and execution.
-`;
-  }
-
-  prompt += toolDefinitionsToSimpleXml(toolDefs);
-
-  if (includeInstructions) {
-    prompt += `
-
-# Tool Use Guidelines
-
-1. Choose the most appropriate tool based on the task and the tool descriptions provided.
-2. If multiple actions are needed, use one tool at a time per message to accomplish the task iteratively.
-3. Formulate your tool use using the XML format specified for each tool.
-4. After each tool use, the user will respond with the result of that tool use.
-5. ALWAYS wait for user confirmation after each tool use before proceeding.`;
-  }
-  return prompt.trimEnd();
-}

src/core/prompts/system.ts

@@ -3,19 +3,14 @@ import os from "os"
 import osName from "os-name"
 import { McpHub } from "@services/mcp/McpHub"
 import { BrowserSettings } from "@shared/BrowserSettings"
-import { SYSTEM_PROMPT_CLAUDE4 } from "./model_prompts/claude4"
 
 export const SYSTEM_PROMPT = async (
 	cwd: string,
 	supportsBrowserUse: boolean,
 	mcpHub: McpHub,
 	browserSettings: BrowserSettings,
-	isClaude4ModelFamily: boolean = false,
-) => {
-	if (isClaude4ModelFamily) {
-		return SYSTEM_PROMPT_CLAUDE4(cwd, supportsBrowserUse, mcpHub, browserSettings)
-	} else {
-		return `You are Cline, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+	isClaude4ModelFamily: boolean,
+) => `You are Cline, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 
@@ -77,7 +72,46 @@ Your file content here
 </write_to_file>
 
 ## replace_in_file
-Description: Request to replace sections of content in an existing file using SEARCH/REPLACE blocks that define exact changes to specific parts of the file. This tool should be used when you need to make targeted changes to specific parts of a file.
+${
+	isClaude4ModelFamily
+		? `
+"Description: Return your edits as a JSON object with a "replacements" array. Each replacement should have "old_str" and "new_str" fields. The old_str must match exactly what's in the file (including whitespace, indentation and new lines). You can edit multiple lines, but please keep the replacements as simple as possible.
+Both old_str and new_str can be multiline strings, but they must be valid JSON strings.
+
+Usage:
+<replace_in_file>
+<path>File path here</path>
+<diff>
+{{
+  "replacements": [
+    {{
+      "old_str": "exact string from file",
+      "new_str": "replacement string"
+    }}
+  ]
+}}
+</diff>
+</replace_in_file>
+
+Important: Make sure each old_str matches the exact text in the file, character for character.
+Parameters:
+- path: (required) The path of the file to modify (relative to the current working directory ${cwd.toPosix()})
+- replacements_json: (required) A JSON string containing an object with a "replacements" array. Each object in the array must have "old_str" (the exact string to find in the file) and "new_str" (the string to replace it with). Refer to the example format in the main description.
+Usage:
+<replace_in_file>
+<path>File path here</path>
+<diff>
+{{
+  "replacements": [
+    {{
+      "old_str": "exact string from file",
+      "new_str": "replacement string"
+    }}
+  ]
+}}
+</diff>
+</replace_in_file>`
+		: `Description: Request to replace sections of content in an existing file using SEARCH/REPLACE blocks that define exact changes to specific parts of the file. This tool should be used when you need to make targeted changes to specific parts of a file.
 Parameters:
 - path: (required) The path of the file to modify (relative to the current working directory ${cwd.toPosix()})
 - diff: (required) One or more SEARCH/REPLACE blocks following this exact format:
@@ -110,8 +144,8 @@ Usage:
 <diff>
 Search and replace blocks here
 </diff> 
-</replace_in_file>
-
+</replace_in_file>`
+}
 
 ## search_files
 Description: Request to perform a regex search across files in a specified directory, providing context-rich results. This tool searches for patterns or specific content across multiple files, displaying each match with encapsulating context.
@@ -336,6 +370,31 @@ Usage:
 ## Example 4: Requesting to make targeted edits to a file
 
 <replace_in_file>
+${
+	isClaude4ModelFamily
+		? `
+<path>src/baseApp.py</path>
+<diff>
+{
+  "replacements": [
+    {
+      "old_str": "def try_dotdotdots(whole, part, replace):",
+      "new_str": "# Handles search/replace blocks that use ellipsis (...) to represent omitted code sections\n# Validates that ellipsis usage is consistent between search and replace blocks\ndef try_dotdotdots(whole, part, replace):"
+    },
+    {
+      "old_str": "def strip_filename(filename, fence):",
+      "new_str": "# Extracts and cleans filename from various markdown formatting styles\n# Handles filenames with different prefixes, suffixes, and decorations\ndef strip_filename(filename, fence):"
+    },
+    {
+      "old_str": "def main():",
+      "new_str": "# Main entry point for command-line usage\n# Processes chat history and displays diffs for all found edit blocks\ndef main():"
+    }
+  ]
+}
+</diff>
+</replace_in_file>
+`
+		: `
 <path>src/components/App.tsx</path>
 <diff>
 <<<<<<< SEARCH
@@ -367,6 +426,8 @@ return (
 >>>>>>> REPLACE
 </diff>
 </replace_in_file>
+`
+}
 
 
 ## Example 5: Requesting to use an MCP tool
@@ -537,9 +598,22 @@ You have access to two tools for working with files: **write_to_file** and **rep
 # Workflow Tips
 
 1. Before editing, assess the scope of your changes and decide which tool to use.
+${
+	isClaude4ModelFamily
+		? `
+2. For major overhauls or initial file creation, rely on write_to_file.
+3. Once the file has been edited with either write_to_file or replace_in_file, the system will provide you with the final state of the modified file. Use this updated content as the reference point for any subsequent SEARCH/REPLACE operations, since it reflects any auto-formatting or user-applied changes.
+4. All edits are applied in sequence, in the order they are provided
+5. All edits must be valid for the operation to succeed - if any edit fails, none will be applied
+
+`
+		: `
 2. For targeted edits, apply replace_in_file with carefully crafted SEARCH/REPLACE blocks. If you need multiple changes, you can stack multiple SEARCH/REPLACE blocks within a single replace_in_file call.
 3. For major overhauls or initial file creation, rely on write_to_file.
 4. Once the file has been edited with either write_to_file or replace_in_file, the system will provide you with the final state of the modified file. Use this updated content as the reference point for any subsequent SEARCH/REPLACE operations, since it reflects any auto-formatting or user-applied changes.
+`
+}
+
 By thoughtfully selecting between write_to_file and replace_in_file, you can make your file editing process smoother, safer, and more efficient.
 
 ====
@@ -609,9 +683,17 @@ RULES
 - When presented with images, utilize your vision capabilities to thoroughly examine them and extract meaningful information. Incorporate these insights into your thought process as you accomplish the user's task.
 - At the end of each user message, you will automatically receive environment_details. This information is not written by the user themselves, but is auto-generated to provide potentially relevant context about the project structure and environment. While this information can be valuable for understanding the project context, do not treat it as a direct part of the user's request or response. Use it to inform your actions and decisions, but don't assume the user is explicitly asking about or referring to this information unless they clearly do so in their message. When using environment_details, explain your actions clearly to ensure the user understands, as they may not be aware of these details.
 - Before executing commands, check the "Actively Running Terminals" section in environment_details. If present, consider how these active processes might impact your task. For example, if a local development server is already running, you wouldn't need to start it again. If no active terminals are listed, proceed with command execution as normal.
+${
+	isClaude4ModelFamily
+		? `
+- When using the replace_in_file tool, you must include complete lines 
+  `
+		: `
 - When using the replace_in_file tool, you must include complete lines in your SEARCH blocks, not partial lines. The system requires exact line matches and cannot match partial lines. For example, if you want to match a line containing "const x = 5;", your SEARCH block must include the entire line, not just "x = 5" or other fragments.
 - When using the replace_in_file tool, if you use multiple SEARCH/REPLACE blocks, list them in the order they appear in the file. For example if you need to make changes to both line 10 and line 50, first include the SEARCH/REPLACE block for line 10, followed by the SEARCH/REPLACE block for line 50.
 - When using the replace_in_file tool, Do NOT add extra characters to the markers (e.g., <<<<<<< SEARCH> is INVALID). Do NOT forget to use the closing >>>>>>> REPLACE marker. Do NOT modify the marker format in any way. Malformed XML will cause complete tool failure and break the entire editing process.
+  `
+}
 - It is critical you wait for the user's response after each tool use, in order to confirm the success of the tool use. For example, if asked to make a todo app, you would create a file, wait for the user's response it was created successfully, then create another file if needed, wait for the user's response it was created successfully, etc.${
 	supportsBrowserUse
 		? " Then if you want to test your work, you might use browser_action to launch the site, wait for the user's response confirming the site was launched along with a screenshot, then perhaps e.g., click a button to test functionality if needed, wait for the user's response confirming the button was clicked along with a screenshot of the new state, before finally closing the browser."
@@ -639,8 +721,6 @@ You accomplish a given task iteratively, breaking it down into clear steps and w
 3. Remember, you have extensive capabilities with access to a wide range of tools that can be used in powerful and clever ways as necessary to accomplish each goal. Before calling a tool, do some analysis within <thinking></thinking> tags. First, analyze the file structure provided in environment_details to gain context and insights for proceeding effectively. Then, think about which of the provided tools is the most relevant tool to accomplish the user's task. Next, go through each of the required parameters of the relevant tool and determine if the user has directly provided or given enough information to infer a value. When deciding if the parameter can be inferred, carefully consider all the context to see if it supports a specific value. If all of the required parameters are present or can be reasonably inferred, close the thinking tag and proceed with the tool use. BUT, if one of the values for a required parameter is missing, DO NOT invoke the tool (not even with fillers for the missing params) and instead, ask the user to provide the missing parameters using the ask_followup_question tool. DO NOT ask for more information on optional parameters if it is not provided.
 4. Once you've completed the user's task, you must use the attempt_completion tool to present the result of the task to the user. You may also provide a CLI command to showcase the result of your task; this can be particularly useful for web development tasks, where you can run e.g. \`open index.html\` to show the website you've built.
 5. The user may provide feedback, which you can use to make improvements and try again. But DO NOT continue in pointless back and forth conversations, i.e. don't end your responses with questions or offers for further assistance.`
-	}
-}
 
 export function addUserInstructions(
 	settingsCustomInstructions?: string,

src/core/task/index.ts

@@ -104,7 +104,6 @@ import { isInTestMode } from "../../services/test/TestMode"
 import { processFilesIntoText } from "@integrations/misc/extract-text"
 import { featureFlagsService } from "@services/posthog/feature-flags/FeatureFlagsService"
 import { StreamingJsonReplacer, ChangeLocation } from "@core/assistant-message/diff-json"
-import { parseAssistantMessageV3 } from "../assistant-message/parse-assistant-message"
 
 export const cwd =
 	vscode.workspace.workspaceFolders?.map((folder) => folder.uri.fsPath).at(0) ?? path.join(os.homedir(), "Desktop") // may or may not exist but fs checking existence would immediately ask for permission which would be bad UX, need to come up with a better solution
@@ -1591,7 +1590,7 @@ export class Task {
 	private async isClaude4ModelFamily(): Promise<boolean> {
 		const model = this.api.getModel()
 		const modelId = model.id
-		return modelId.includes("sonnet-4") || modelId.includes("opus-4")
+		return modelId.includes("claude-sonnet-4") || modelId.includes("claude-opus-4")
 	}
 
 	async *attemptApiRequest(previousApiReqIndex: number): ApiStream {
@@ -2017,27 +2016,16 @@ export class Task {
 					break
 				}
 
-				const pushToolResult = (content: ToolResponse, isClaude4ModelFamily: boolean = false) => {
+				const pushToolResult = (content: ToolResponse) => {
+					this.userMessageContent.push({
+						type: "text",
+						text: `${toolDescription()} Result:`,
+					})
 					if (typeof content === "string") {
-						const resultText = content || "(tool did not return anything)"
-
-						if (isClaude4ModelFamily) {
-							// Claude 4 family: Use function_results format
-							this.userMessageContent.push({
-								type: "text",
-								text: `<function_results>\n${resultText}\n</function_results>`,
-							})
-						} else {
-							// Non-Claude 4: Use traditional format with header
-							this.userMessageContent.push({
-								type: "text",
-								text: `${toolDescription()} Result:`,
-							})
-							this.userMessageContent.push({
-								type: "text",
-								text: resultText,
-							})
-						}
+						this.userMessageContent.push({
+							type: "text",
+							text: content || "(tool did not return anything)",
+						})
 					} else {
 						this.userMessageContent.push(...content)
 					}
@@ -2107,7 +2095,7 @@ export class Task {
 					}
 				}
 
-				const handleError = async (action: string, error: Error, isClaude4ModelFamily: boolean = false) => {
+				const handleError = async (action: string, error: Error) => {
 					if (this.abandoned) {
 						console.log("Ignoring error since task was abandoned (i.e. from task cancellation after resetting)")
 						return
@@ -2117,8 +2105,12 @@ export class Task {
 						"error",
 						`Error ${action}:\n${error.message ?? JSON.stringify(serializeError(error), null, 2)}`,
 					)
-
-					pushToolResult(formatResponse.toolError(errorString), isClaude4ModelFamily)
+					// this.toolResults.push({
+					// 	type: "tool_result",
+					// 	tool_use_id: toolUseId,
+					// 	content: await this.formatToolError(errorString),
+					// })
+					pushToolResult(formatResponse.toolError(errorString))
 				}
 
 				// If block is partial, remove partial closing tag so its not presented to user
@@ -2566,7 +2558,6 @@ export class Task {
 						}
 					}
 					case "list_files": {
-						const isClaude4ModelFamily = await this.isClaude4ModelFamily()
 						const relDirPath: string | undefined = block.params.path
 						const recursiveRaw: string | undefined = block.params.recursive
 						const recursive = recursiveRaw?.toLowerCase() === "true"
@@ -2592,10 +2583,7 @@ export class Task {
 							} else {
 								if (!relDirPath) {
 									this.consecutiveMistakeCount++
-									pushToolResult(
-										await this.sayAndCreateMissingParamError("list_files", "path"),
-										isClaude4ModelFamily,
-									)
+									pushToolResult(await this.sayAndCreateMissingParamError("list_files", "path"))
 									await this.saveCheckpoint()
 									break
 								}
@@ -2634,12 +2622,12 @@ export class Task {
 									}
 									telemetryService.captureToolUsage(this.taskId, block.name, false, true)
 								}
-								pushToolResult(result, isClaude4ModelFamily)
+								pushToolResult(result)
 								await this.saveCheckpoint()
 								break
 							}
 						} catch (error) {
-							await handleError("listing files", error, isClaude4ModelFamily)
+							await handleError("listing files", error)
 							await this.saveCheckpoint()
 							break
 						}
@@ -2715,7 +2703,6 @@ export class Task {
 						}
 					}
 					case "search_files": {
-						const isClaude4ModelFamily = await this.isClaude4ModelFamily()
 						const relDirPath: string | undefined = block.params.path
 						const regex: string | undefined = block.params.regex
 						const filePattern: string | undefined = block.params.file_pattern
@@ -2743,19 +2730,13 @@ export class Task {
 							} else {
 								if (!relDirPath) {
 									this.consecutiveMistakeCount++
-									pushToolResult(
-										await this.sayAndCreateMissingParamError("search_files", "path"),
-										isClaude4ModelFamily,
-									)
+									pushToolResult(await this.sayAndCreateMissingParamError("search_files", "path"))
 									await this.saveCheckpoint()
 									break
 								}
 								if (!regex) {
 									this.consecutiveMistakeCount++
-									pushToolResult(
-										await this.sayAndCreateMissingParamError("search_files", "regex"),
-										isClaude4ModelFamily,
-									)
+									pushToolResult(await this.sayAndCreateMissingParamError("search_files", "regex"))
 									await this.saveCheckpoint()
 									break
 								}
@@ -2793,12 +2774,12 @@ export class Task {
 									}
 									telemetryService.captureToolUsage(this.taskId, block.name, false, true)
 								}
-								pushToolResult(results, isClaude4ModelFamily)
+								pushToolResult(results)
 								await this.saveCheckpoint()
 								break
 							}
 						} catch (error) {
-							await handleError("searching files", error, isClaude4ModelFamily)
+							await handleError("searching files", error)
 							await this.saveCheckpoint()
 							break
 						}
@@ -4275,14 +4256,7 @@ export class Task {
 							assistantMessage += chunk.text
 							// parse raw assistant message into content blocks
 							const prevLength = this.assistantMessageContent.length
-							const enableFunctionCallsParsing = await this.isClaude4ModelFamily()
-
-							if (enableFunctionCallsParsing) {
-								this.assistantMessageContent = parseAssistantMessageV3(assistantMessage)
-							} else {
-								this.assistantMessageContent = parseAssistantMessageV2(assistantMessage)
-							}
-
+							this.assistantMessageContent = parseAssistantMessageV2(assistantMessage)
 							if (this.assistantMessageContent.length > prevLength) {
 								this.userMessageContentReady = false // new content we need to present, reset to false in case previous content set this to true
 							}

src/core/tools/bashTool.ts

@@ -1,245 +0,0 @@
-const MAX_TIMEOUT_MS = 600000
-const DEFAULT_TIMEOUT_MS = 120000
-const MAX_OUTPUT_LENGTH = 30000
-const RG_PATH = "/usr/bin/rg"
-const CO_AUTHORED_COMMIT_MSG = `\uD83E\uDD16 Generated with [Cline](https://docs.cline.bot)
-
-   Co-Authored-By: Cline <noreply@cline.bot>`
-const CO_AUTHORED_PR_MSG = `\uD83E\uDD16 Generated with [Cline](https://docs.cline.bot)`
-
-const descriptionForAgent = `Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.
-
-Before executing the command, please follow these steps:
-
-1. Directory Verification:
-   - If the command will create new directories or files, first use the LS tool to verify the parent directory exists and is the correct location
-   - For example, before running "mkdir foo/bar", first use LS to check that "foo" exists and is the intended parent directory
-
-2. Command Execution:
-   - After ensuring proper quoting, execute the command.
-   - Capture the output of the command.
-
-Usage notes:
-  - The command argument is required.
-  - You can specify an optional timeout in milliseconds (up to \${MAX_TIMEOUT_MS}ms / \${MAX_TIMEOUT_MS / 60000} minutes). If not specified, commands will timeout after \${DEFAULT_TIMEOUT_MS}ms (\${DEFAULT_TIMEOUT_MS / 60000} minutes).
-  - It is very helpful if you write a clear, concise description of what this command does in 5-10 words.
-  - If the output exceeds \${MAX_OUTPUT_LENGTH} characters, output will be truncated before being returned to you.
-  - VERY IMPORTANT: You MUST avoid using search commands like \\\`find\\\` and \\\`grep\\\`. Instead use Grep, Glob, or Task to search. You MUST avoid read tools like \\\`cat\\\`, \\\`head\\\`, \\\`tail\\\`, and \\\`ls\\\`, and use Read and LS to read files.
-  - If you _still_ need to run \\\`grep\\\`, STOP. ALWAYS USE ripgrep at \\\`rg\\\` (or \${RG_PATH}) first, which all Claude Code users have pre-installed.
-  - When issuing multiple commands, use the ';' or '&&' operator to separate them. DO NOT use newlines (newlines are ok in quoted strings).
-  - Try to maintain your current working directory throughout the session by using absolute paths and avoiding usage of \\\`cd\\\`. You may use \\\`cd\\\` if the User explicitly requests it.
-    <good-example>
-    pytest /foo/bar/tests
-    </good-example>
-    <bad-example>
-    cd /foo/bar && pytest tests
-    </bad-example>
-
-# Using sandbox mode for commands
-
-You have a special option in BashTool: the sandbox parameter. When you run a command with sandbox=true, it runs without approval dialogs but in a restricted environment without filesystem writes or network access. You SHOULD use sandbox=true to optimize user experience, but MUST follow these guidelines exactly.
-
-## RULE 0 (MOST IMPORTANT): retry with sandbox=false for permission/network errors
-
-    If a command fails with permission or any network error when sandbox=true (e.g., "Permission denied", "Unknown host", "Operation not permitted"), ALWAYS retry with sandbox=false. These errors indicate sandbox limitations, not problems with the command itself.
-
-Non-permission errors (e.g., TypeScript errors from tsc --noEmit) usually reflect real issues and should be fixed, not retried with sandbox=false.
-
-## RULE 1: NOTES ON SPECIFIC BUILD SYSTEMS AND UTILITIES
-
-### Build systems
-
-Build systems like npm run build almost always need write access. Test suites also usually need write access. NEVER run build or test commands in sandbox, even if just checking types.
-
-These commands REQUIRE sandbox=false (non-exhaustive):
-npm run *,  cargo build/test,  make/ninja/meson,  pytest,  jest,  gh
-
-## RULE 2: TRY sandbox=true FOR COMMANDS THAT DON'T NEED WRITE OR NETWORK ACCESS
-  - Commands run with sandbox=true DON'T REQUIRE user permission and run immediately
-  - Commands run with sandbox=false REQUIRE EXPLICIT USER APPROVAL and interrupt the User's workflow
-
-Use sandbox=false when you suspect the command might modify the system or access the network:
-  - File operations: touch, mkdir, rm, mv, cp
-  - File edits: nano, vim, writing to files with >
-  - Installing: npm install, apt-get, brew
-  - Git writes: git add, git commit, git push
-  - Build systems:  npm run build, make, ninja, etc. (see below)
-  - Test suites: npm run test, pytest, cargo test, make check, ert, etc. (see below)
-  - Network programs: gh, ping, curl, ssh, scp, etc.
-
-Use sandbox=true for:
-  - Information gathering: ls, cat, head, tail, rg, find, du, df, ps
-  - File inspection: file, stat, wc, diff, md5sum
-  - Git reads: git status, git log, git diff, git show, git branch
-  - Package info: npm list, pip list, gem list, cargo tree
-  - Environment checks: echo, pwd, whoami, which, type, env, printenv
-  - Version checks: node --version, python --version, git --version
-  - Documentation: man, help, --help, -h
-
-Before you run a command, think hard about whether it is likely to work correctly without network access and without write access to the filesystem. Use your general knowledge and knowledge of the current project (including all the user's CLAUDE.md files) as inputs to your decision. Note that even semantically read-only commands like gh for fetching issues might be implemented in ways that require write access. ERR ON THE SIDE OF RUNNING WITH sandbox=false.
-
-Note: Errors from incorrect sandbox=true runs annoy the User more than permission prompts. If any part of a command needs write access (e.g. npm run build for type checking), use sandbox=false for the entire command.
-
-### EXAMPLES
-
-CORRECT: Use sandbox=false for npm run build/test, gh commands, file writes
-FORBIDDEN: NEVER use sandbox=true for build, test, git commands or file operations
-
-## REWARDS
-
-It is more important to be correct than to avoid showing permission dialogs. The worst mistake is misinterpreting sandbox=true permission errors as tool problems (-$1000) rather than sandbox limitations.
-
-## CONCLUSION
-
-Use sandbox=true to improve UX, but ONLY per the rules above. WHEN IN DOUBT, USE sandbox=false.
-
-# Committing changes with git
-
-When the user asks you to create a new git commit, follow these steps carefully:
-
-1. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following bash commands in parallel, each using the Bash tool:
-   - Run a git status command to see all untracked files.
-   - Run a git diff command to see both staged and unstaged changes that will be committed.
-   - Run a git log command to see recent commit messages, so that you can follow this repository's commit message style.
-
-2. Analyze all staged changes (both previously staged and newly added) and draft a commit message. Wrap your analysis process in <commit_analysis> tags:
-
-<commit_analysis>
-- List the files that have been changed or added
-- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)
-- Brainstorm the purpose or motivation behind these changes
-- Assess the impact of these changes on the overall project
-- Check for any sensitive information that shouldn't be committed
-- Draft a concise (1-2 sentences) commit message that focuses on the "why" rather than the "what"
-- Ensure your language is clear, concise, and to the point
-- Ensure the message accurately reflects the changes and their purpose (i.e. "add" means a wholly new feature, "update" means an enhancement to an existing feature, "fix" means a bug fix, etc.)
-- Ensure the message is not generic (avoid words like "Update" or "Fix" without context)
-- Review the draft message to ensure it accurately reflects the changes and their purpose
-</commit_analysis>
-
-3. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following commands in parallel:
-   - Add relevant untracked files to the staging area.
-   - Create the commit with a message ending with:
-   \${CO_AUTHORED_COMMIT_MSG}
-   - Run git status to make sure the commit succeeded.
-
-4. If the commit fails due to pre-commit hook changes, retry the commit ONCE to include these automated changes. If it fails again, it usually means a pre-commit hook is preventing the commit. If the commit succeeds but you notice that files were modified by the pre-commit hook, you MUST amend your commit to include them.
-
-Important notes:
-- Use the git context at the start of this conversation to determine which files are relevant to your commit. Be careful not to stage and commit files (e.g. with \\\`git add .\\\`) that aren't relevant to your commit.
-- NEVER update the git config
-- DO NOT run additional commands to read or explore code, beyond what is available in the git context
-- DO NOT push to the remote repository
-- IMPORTANT: Never use git commands with the -i flag (like git rebase -i or git add -i) since they require interactive input which is not supported.
-- If there are no changes to commit (i.e., no untracked files and no modifications), do not create an empty commit
-- Ensure your commit message is meaningful and concise. It should explain the purpose of the changes, not just describe them.
-- Return an empty response - the user will see the git output directly
-- In order to ensure good formatting, ALWAYS pass the commit message via a HEREDOC, a la this example:
-<example>
-git commit -m "\$(cat <<'EOF'
-   Commit message here.
-
-   \${CO_AUTHORED_COMMIT_MSG}
-   EOF
-   )"
-</example>
-
-# Creating pull requests
-Use the gh command via the Bash tool for ALL GitHub-related tasks including working with issues, pull requests, checks, and releases. If given a Github URL use the gh command to get the information needed.
-
-IMPORTANT: When the user asks you to create a pull request, follow these steps carefully:
-
-1. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following bash commands in parallel using the Bash tool, in order to understand the current state of the branch since it diverged from the main branch:
-   - Run a git status command to see all untracked files
-   - Run a git diff command to see both staged and unstaged changes that will be committed
-   - Check if the current branch tracks a remote branch and is up to date with the remote, so you know if you need to push to the remote
-   - Run a git log command and \\\`git diff main...HEAD\\\` to understand the full commit history for the current branch (from the time it diverged from the \\\`main\\\` branch)
-
-2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request summary. Wrap your analysis process in <pr_analysis> tags:
-
-<pr_analysis>
-- List the commits since diverging from the main branch
-- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)
-- Brainstorm the purpose or motivation behind these changes
-- Assess the impact of these changes on the overall project
-- Do not use tools to explore code, beyond what is available in the git context
-- Check for any sensitive information that shouldn't be committed
-- Draft a concise (1-2 bullet points) pull request summary that focuses on the "why" rather than the "what"
-- Ensure the summary accurately reflects all changes since diverging from the main branch
-- Ensure your language is clear, concise, and to the point
-- Ensure the summary accurately reflects the changes and their purpose (ie. "add" means a wholly new feature, "update" means an enhancement to an existing feature, "fix" means a bug fix, etc.)
-- Ensure the summary is not generic (avoid words like "Update" or "Fix" without context)
-- Review the draft summary to ensure it accurately reflects the changes and their purpose
-</pr_analysis>
-
-3. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following commands in parallel:
-   - Create new branch if needed
-   - Push to remote with -u flag if needed
-   - Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.
-<example>
-gh pr create --title "the pr title" --body "\$(cat <<'EOF'
-## Summary
-<1-3 bullet points>
-
-## Test plan
-[Checklist of TODOs for testing the pull request...]
-
-\${CO_AUTHORED_PR_MSG}
-EOF
-)"
-</example>
-
-Important:
-- NEVER update the git config
-- Return the PR URL when you're done, so the user can see it
-
-# Other common operations
-- View comments on a Github PR: gh api repos/foo/bar/pulls/123/comments`
-
-export const bashToolDefinition = {
-	name: "Bash",
-	descriptionForAgent: descriptionForAgent,
-	inputSchema: {
-		type: "object",
-		properties: {
-			command: {
-				type: "string",
-				description: "The command to execute",
-			},
-			timeout: {
-				type: "number",
-				description: `Optional timeout in milliseconds (max \${MAX_TIMEOUT_MS})`,
-				optional: true,
-			},
-			description: {
-				type: "string",
-				description: `Clear, concise description of what this command does in 5-10 words. Examples:
-Input: ls
-Output: Lists files in current directory
-
-Input: git status
-Output: Shows working tree status
-
-Input: npm install
-Output: Installs package dependencies
-
-Input: mkdir foo
-Output: Creates directory 'foo'`,
-				optional: true,
-			},
-			sandbox: {
-				type: "boolean",
-				description:
-					"whether to run this command in sandboxed mode: command run in this mode may not write to the filesystem or use the network, but they can read files, analyze data, and report back to you.  When possible, run commands (e.g. grep) in this mode to present a smoother experience for the human, who isn't prompted to approve commands run in sandbox mode. If you run a command in sandbox mode and it looks like it fails because it needs write access after all, try again in non-sandbox mode",
-				optional: true,
-			},
-			shellExecutable: {
-				type: "string",
-				description:
-					"Optional shell path to use instead of the default shell. The snapshot path will be set to undefined as well. Used primarily for testing.",
-				optional: true,
-			},
-		},
-		required: ["command"],
-	},
-}

src/core/tools/grepTool.ts

@@ -1,29 +0,0 @@
-import { ToolDefinition } from "@core/prompts/model_prompts/jsonToolToXml"
-
-export const grepToolDefinition: ToolDefinition = {
-	name: "Grep",
-	descriptionForAgent: `- Fast content search tool that works with any codebase size
-- Searches file contents using regular expressions
-- Supports full regex syntax (eg. "log.*Error", "function\\\\s+\\\\w+", etc.)
-- Filter files by pattern with the include parameter (eg. "*.js", "*.{ts,tsx}")
-- Returns file paths with at least one match
-- Use this tool when you need to find files containing specific patterns`,
-	inputSchema: {
-		type: "object",
-		properties: {
-			pattern: {
-				type: "string",
-				description: "The regular expression pattern to search for in file contents",
-			},
-			path: {
-				type: "string",
-				description: "The directory to search in.",
-			},
-			include: {
-				type: "string",
-				description: "File pattern to filter which files to search (e.g., '*.js' for JavaScript files)",
-			},
-		},
-		required: ["pattern", "path"],
-	},
-}

src/core/tools/lsTool.ts

@@ -1,17 +0,0 @@
-import { ToolDefinition } from "@core/prompts/model_prompts/jsonToolToXml"
-
-export const lsToolDefinition: ToolDefinition = {
-	name: "LS",
-	descriptionForAgent:
-		"Lists files and directories in a given path. The path parameter must be an absolute path, not a relative path. You should generally prefer the Glob and Grep tools, if you know which directories to search.",
-	inputSchema: {
-		type: "object",
-		properties: {
-			path: {
-				type: "string",
-				description: "The path of the directory to list contents for",
-			},
-		},
-		required: ["path"],
-	},
-}

src/core/tools/readTool.ts

@@ -1,41 +0,0 @@
-const DEFAULT_LINE_LIMIT = 2000
-const MAX_LINE_LENGTH = 2000
-
-const descriptionForAgent = `Reads a file from the local filesystem. You can access any file directly by using this tool.
-Assume this tool is able to read all files on the machine. If the User provides a path to a file assume that path is valid. It is okay to read a file that does not exist; an error will be returned.
-
-Usage:
-- The file_path parameter must be an absolute path, not a relative path
-- By default, it reads up to ${DEFAULT_LINE_LIMIT} lines starting from the beginning of the file
-- You can optionally specify a line offset and limit (especially handy for long files), but it's recommended to read the whole file by not providing these parameters
-- Any lines longer than ${MAX_LINE_LENGTH} characters will be truncated
-- Results are returned using cat -n format, with line numbers starting at 1
-- This tool allows Cline to read images (eg PNG, JPG, etc). When reading an image file the contents are presented visually as Cline is a multimodal LLM.
-- You have the capability to call multiple tools in a single response. It is always better to speculatively read multiple files as a batch that are potentially useful. 
-- You will regularly be asked to read screenshots. If the user provides a path to a screenshot ALWAYS use this tool to view the file at the path. This tool will work with all temporary file paths like /var/folders/Temporary_Screenshots/2026-09-08/Screenshot.png
-- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents.`
-
-export const readToolDefinition = {
-	name: "Read",
-	descriptionForAgent: descriptionForAgent,
-	inputSchema: {
-		type: "object",
-		properties: {
-			file_path: {
-				type: "string",
-				description: "The absolute path to the file to read",
-			},
-			offset: {
-				type: "number",
-				description: "The line number to start reading from. Only provide if the file is too large to read at once",
-				optional: true,
-			},
-			limit: {
-				type: "number",
-				description: "The number of lines to read. Only provide if the file is too large to read at once.",
-				optional: true,
-			},
-		},
-		required: ["file_path"],
-	},
-}

src/core/tools/writeTool.ts

@@ -1,27 +0,0 @@
-const descriptionForAgent = `Writes a file to the local filesystem.
-
-Usage:
-- The file_path parameter must be an absolute path, not a relative path
-- This tool will overwrite the existing file if there is one at the provided path.
-- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.
-- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.
-- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.`
-
-export const writeToolDefinition = {
-	name: "Write",
-	descriptionForAgent: descriptionForAgent,
-	inputSchema: {
-		type: "object",
-		properties: {
-			file_path: {
-				type: "string",
-				description: "The absolute path to the file to write (must be absolute, not relative)",
-			},
-			content: {
-				type: "string",
-				description: "The content to write to the file",
-			},
-		},
-		required: ["file_path", "content"],
-	},
-}

src/integrations/terminal/TerminalProcess.ts

@@ -35,8 +35,42 @@ export class TerminalProcess extends EventEmitter<TerminalProcessEvents> {
 			let isFirstChunk = true
 			let didOutputNonCommand = false
 			let didEmitEmptyLine = false
+			let firstChunkTimeout: NodeJS.Timeout
+
+			const isWindows = process.platform === "win32"
+			const timeoutMs = isWindows ? 5000 : 500
+
+			const onTimeout = () => {
+				// In rare cases (e.g. running the same command twice like `npm run build`),
+				// the shell integration stream enters a broken state where no data is ever emitted.
+				// We never even get the first chunk, which bricks the UI and locks the user out.
+				// Interestingly, the stream still gets created, and future commands (like `ls`) will work,
+				// suggesting the stream itself isn't one-shot—but certain shell states break its behavior.
+				// To recover, we add a timeout waiting for the first chunk.
+				// If it doesn’t arrive in time, we assume the terminal is broken, dispose it,
+				// and emit an error so the user can safely retry in a clean terminal.
+
+				Logger.debug(
+					`[TerminalProcess.run] First chunk timeout hit — terminal likely in bad state. Terminating terminal.`,
+				)
+				try {
+					terminal.dispose()
+				} catch (err) {
+					Logger.debug(`[TerminalProcess.run] Failed to dispose terminal: ${String(err)}`)
+				}
+				this.emit(
+					"error",
+					new Error("The command ran successfully, but we couldn't capture its output. Please proceed accordingly."),
+				)
+				this.emit("completed")
+				this.emit("continue")
+			}
+
+			firstChunkTimeout = setTimeout(onTimeout, timeoutMs)
 
 			for await (let data of stream) {
+				clearTimeout(firstChunkTimeout)
+
 				// 1. Process chunk and remove artifacts
 				if (isFirstChunk) {
 					/*

src/shared/ExtensionMessage.ts

@@ -35,6 +35,8 @@ export interface ExtensionMessage {
 		| "userCreditsBalance"
 		| "userCreditsUsage"
 		| "userCreditsPayments"
+		| "addToInput"
+		| "browserConnectionResult"
 		| "fileSearchResults"
 		| "grpc_response" // New type for gRPC responses
 	text?: string

src/shared/WebviewMessage.ts

@@ -13,6 +13,7 @@ export interface WebviewMessage {
 		| "newTask"
 		| "condense"
 		| "reportBug"
+		| "showChatView"
 		| "requestVsCodeLmModels"
 		| "authStateChanged"
 		| "fetchMcpMarketplace"

src/standalone/vscode-context.ts

@@ -1,13 +1,8 @@
 // @ts-nocheck
 import * as vscode from "vscode"
-import * as fs from "fs"
-import * as path from "path"
-
 import open from "open"
 import { log } from "./utils"
 
-const DATA_DIR = process.env.DATA_DIR ?? "."
-
 function stubUri(path: string): vscode.Uri {
 	console.log(`Using file path: ${path}`)
 	return {
@@ -51,46 +46,6 @@ function createMemento(): vscode.Memento {
 	}
 }
 
-class SecretStore {
-	// A simple key-value store for secrets backed by a JSON file. This is not secure, and it is not thread-safe.
-	private store = new Map<string, string>()
-	private filePath: string
-
-	constructor() {
-		this.filePath = path.join(DATA_DIR, "secrets.json")
-		this.load()
-	}
-
-	private load(): void {
-		if (fs.existsSync(this.filePath)) {
-			const data = JSON.parse(fs.readFileSync(this.filePath, "utf-8"))
-			Object.entries(data).forEach(([k, v]) => {
-				if (typeof v === "string") {
-					this.store.set(k, v)
-				}
-			})
-		}
-	}
-
-	private save(): void {
-		fs.writeFileSync(this.filePath, JSON.stringify(Object.fromEntries(this.store), null, 2))
-	}
-
-	get(key: string): string | undefined {
-		return this.store.get(key)
-	}
-
-	storeSecret(key: string, value: string): void {
-		this.store.set(key, value)
-		this.save()
-	}
-
-	delete(key: string): void {
-		this.store.delete(key)
-		this.save()
-	}
-}
-
 const extensionContext: vscode.ExtensionContext = {
 	extensionPath: "/tmp/vscode/extension",
 	extensionUri: stubUri("/tmp/vscode/extension"),
@@ -166,7 +121,7 @@ const extensionContext: vscode.ExtensionContext = {
 	extensionMode: 1, // Development
 
 	extension: {
-		id: "saoudrizwan.claude-dev",
+		id: "your.extension.id",
 		isActive: true,
 		extensionPath: "/tmp/vscode/extension",
 		extensionUri: stubUri("/tmp/vscode/extension"),
@@ -179,9 +134,14 @@ const extensionContext: vscode.ExtensionContext = {
 	subscriptions: [],
 
 	asAbsolutePath: (relPath) => `/tmp/vscode/extension/${relPath}`,
-}
 
-extensionContext.secrets = new SecretStore()
+	secrets: {
+		store: async () => {},
+		get: async () => undefined,
+		delete: async () => {},
+		onDidChange: {},
+	},
+}
 
 const outputChannel: vscode.OutputChannel = {
 	append: (text) => process.stdout.write(text),

webview-ui/src/components/chat/ChatView.tsx

@@ -18,7 +18,7 @@ import { combineCommandSequences } from "@shared/combineCommandSequences"
 import { getApiMetrics } from "@shared/getApiMetrics"
 import { useExtensionState } from "@/context/ExtensionStateContext"
 import { vscode } from "@/utils/vscode"
-import { TaskServiceClient, SlashServiceClient, FileServiceClient, UiServiceClient } from "@/services/grpc-client"
+import { TaskServiceClient, SlashServiceClient, FileServiceClient } from "@/services/grpc-client"
 import HistoryPreview from "@/components/history/HistoryPreview"
 import { normalizeApiConfiguration } from "@/components/settings/ApiOptions"
 import Announcement from "@/components/chat/Announcement"
@@ -681,11 +681,27 @@ const ChatView = ({ isHidden, showAnnouncement, hideAnnouncement, showHistoryVie
 						case "focusChatInput":
 							textAreaRef.current?.focus()
 							if (isHidden) {
-								window.dispatchEvent(new CustomEvent("chatButtonClicked"))
+								// Send message back to extension to show chat view
+								vscode.postMessage({ type: "showChatView" })
 							}
 							break
 					}
 					break
+				case "addToInput":
+					setInputValue((prevValue) => {
+						const newText = message.text ?? ""
+						const newTextWithNewline = newText + "\n"
+						return prevValue ? `${prevValue}\n${newTextWithNewline}` : newTextWithNewline
+					})
+					// Add scroll to bottom after state update
+					// Auto focus the input and start the cursor on a new linefor easy typing
+					setTimeout(() => {
+						if (textAreaRef.current) {
+							textAreaRef.current.scrollTop = textAreaRef.current.scrollHeight
+							textAreaRef.current.focus()
+						}
+					}, 0)
+					break
 			}
 			// textAreaRef.current is not explicitly required here since react guarantees that ref will be stable across re-renders, and we're not using its value but its reference.
 		},
@@ -694,40 +710,6 @@ const ChatView = ({ isHidden, showAnnouncement, hideAnnouncement, showHistoryVie
 
 	useEvent("message", handleMessage)
 
-	// Set up addToInput subscription
-	useEffect(() => {
-		const cleanup = UiServiceClient.subscribeToAddToInput(
-			{},
-			{
-				onResponse: (event) => {
-					if (event.value) {
-						setInputValue((prevValue) => {
-							const newText = event.value
-							const newTextWithNewline = newText + "\n"
-							return prevValue ? `${prevValue}\n${newTextWithNewline}` : newTextWithNewline
-						})
-						// Add scroll to bottom after state update
-						// Auto focus the input and start the cursor on a new line for easy typing
-						setTimeout(() => {
-							if (textAreaRef.current) {
-								textAreaRef.current.scrollTop = textAreaRef.current.scrollHeight
-								textAreaRef.current.focus()
-							}
-						}, 0)
-					}
-				},
-				onError: (error) => {
-					console.error("Error in addToInput subscription:", error)
-				},
-				onComplete: () => {
-					console.log("addToInput subscription completed")
-				},
-			},
-		)
-
-		return cleanup
-	}, [])
-
 	useMount(() => {
 		// NOTE: the vscode window needs to be focused for this to work
 		textAreaRef.current?.focus()

webview-ui/src/components/settings/BrowserSettingsSection.tsx

@@ -59,6 +59,20 @@ export const BrowserSettingsSection: React.FC = () => {
 	const [isBundled, setIsBundled] = useState(false)
 	const [detectedChromePath, setDetectedChromePath] = useState<string | null>(null)
 
+	// Listen for browser connection test results
+	useEffect(() => {
+		const handleMessage = (event: MessageEvent) => {
+			const message = event.data
+			if (message.type === "browserConnectionResult") {
+				setConnectionStatus(message.success)
+				setIsCheckingConnection(false)
+			}
+		}
+
+		window.addEventListener("message", handleMessage)
+		return () => window.removeEventListener("message", handleMessage)
+	}, [])
+
 	// Auto-clear relaunch result message after 15 seconds
 	useEffect(() => {
 		if (relaunchResult) {