Fix Changeset

* Run pretest in CI to build all tests

* Alias paths when running tests

* Bundle ES modules with esbuild

* alias packages

.changeset/breezy-items-bake.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-improving search and replace edit failure behaviors

.changeset/bright-knives-wait.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+updated drag and drop text to say "drop" instead of "drag"

.changeset/bright-zebras-sip.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Add markdown copy to chat

.changeset/chatty-scissors-rescue.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Update Google Gemini API key link

.changeset/custom-timeout-setting.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+Add support for custom API request timeout. Previously, timeouts were hardcoded to 30 seconds for providers like Ollama or 15 seconds for OpenRouter and Cline. Now users can set a custom timeout value in milliseconds through the settings interface.

.changeset/dirty-rice-film.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-added telemetry to track replace_in_file tool failures

.changeset/fair-papayas-learn.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Minor UX improvement to drag and drop ux

.changeset/fluffy-pants-jog.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-feat(extension): add access to history, mcp, and new task buttons in popout view

.changeset/kind-pears-invent.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Add dependsOn to more blocks in the tasks.json

.changeset/little-tomatoes-drive.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-Support connecting to SSE servers

.changeset/long-cheetahs-love.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Adding args to allow Cursor to open workspaces (for checkpoint testing/development)

.changeset/loud-spies-deny.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+add truncation notice when truncating manually

.changeset/mighty-pants-sort.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Move the MCP Restart and Delete buttons and add an auto-approve all toggle

.changeset/nasty-radios-dance.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-updated gemini-2.0-pro-exp-02-05 to gemini-2.5-pro-exp-03-25 for Vertex AI

.changeset/nine-rings-shout.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+add checkpoints after more messages

.changeset/ninety-numbers-decide.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Introduce UI library for future UI development

.changeset/rare-ladybugs-talk.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+add newrule slash command

.changeset/serious-baboons-train.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+protobus migration for openImage

.changeset/shy-buckets-itch.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+add cache ui for open router and cline provider

.changeset/silent-sheep-nail.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-adding task id to request headers

.changeset/six-hairs-rush.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+showing expanded task by default

.changeset/sweet-toes-bake.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+Refactor to not pass a message for showing the MCP View from the servers modal

.changeset/tall-ghosts-help.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+Migrate the addRemoteServer to protobus

.changeset/tall-rivers-knock.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-Add toggle disabled for remote servers

.changeset/thick-rice-rush.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Lowering Gemini cache TTL time

.changeset/thirty-feet-rule.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Adding UI to show openrouter balance next to provider

.changeset/twenty-comics-enjoy.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+fix cost calculation

.changeset/wicked-dryers-grab.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-added task feedback thumbs up thumbs down telemetry

.clinerules/cline-overview.md

@@ -8,16 +8,18 @@ Cline is a VSCode extension that provides AI assistance through a combination of
 
 ```mermaid
 graph TB
-    subgraph VSCode Extension Host
-        subgraph Core Extension
+    subgraph VSCodeExtensionHost[VSCode Extension Host]
+        subgraph CoreExtension[Core Extension]
             ExtensionEntry[Extension Entry<br/>src/extension.ts]
-            ClineProvider[ClineProvider<br/>src/core/webview/ClineProvider.ts]
-            ClineClass[Cline Class<br/>src/core/Cline.ts]
+            WebviewProvider[WebviewProvider<br/>src/core/webview/index.ts]
+            Controller[Controller<br/>src/core/controller/index.ts]
+            Task[Task<br/>src/core/task/index.ts]
             GlobalState[VSCode Global State]
             SecretsStorage[VSCode Secrets Storage]
+            McpHub[McpHub<br/>src/services/mcp/McpHub.ts]
         end
 
-        subgraph Webview UI
+        subgraph WebviewUI[Webview UI]
             WebviewApp[React App<br/>webview-ui/src/App.tsx]
             ExtStateContext[ExtensionStateContext<br/>webview-ui/src/context/ExtensionStateContext.tsx]
             ReactComponents[React Components]
@@ -27,45 +29,101 @@ graph TB
             TaskStorage[Task Storage<br/>Per-Task Files & History]
             CheckpointSystem[Git-based Checkpoints]
         end
+
+        subgraph apiProviders[API Providers]
+            AnthropicAPI[Anthropic]
+            OpenRouterAPI[OpenRouter]
+            BedrockAPI[AWS Bedrock]
+            OtherAPIs[Other Providers]
+        end
+
+        subgraph MCPServers[MCP Servers]
+            ExternalMcpServers[External MCP Servers]
+        end
     end
 
     %% Core Extension Data Flow
-    ExtensionEntry --> ClineProvider
-    ClineProvider --> ClineClass
-    ClineClass --> GlobalState
-    ClineClass --> SecretsStorage
-    ClineClass --> TaskStorage
-    ClineClass --> CheckpointSystem
+    ExtensionEntry --> WebviewProvider
+    WebviewProvider --> Controller
+    Controller --> Task
+    Controller --> McpHub
+    Task --> GlobalState
+    Task --> SecretsStorage
+    Task --> TaskStorage
+    Task --> CheckpointSystem
+    Task --> |API Requests| apiProviders
+    McpHub --> |Connects to| ExternalMcpServers
+    Task --> |Uses| McpHub
 
     %% Webview Data Flow
     WebviewApp --> ExtStateContext
     ExtStateContext --> ReactComponents
 
     %% Bidirectional Communication
-    ClineProvider <-->|postMessage| ExtStateContext
+    WebviewProvider <-->|postMessage| ExtStateContext
 
     style GlobalState fill:#f9f,stroke:#333,stroke-width:2px
     style SecretsStorage fill:#f9f,stroke:#333,stroke-width:2px
     style ExtStateContext fill:#bbf,stroke:#333,stroke-width:2px
-    style ClineProvider fill:#bfb,stroke:#333,stroke-width:2px
+    style WebviewProvider fill:#bfb,stroke:#333,stroke-width:2px
+    style McpHub fill:#bfb,stroke:#333,stroke-width:2px
+    style apiProviders fill:#fdb,stroke:#333,stroke-width:2px
 ```
 
 ## Definitions 
 
-- core extension: Anything inside the src folder starting with the Cline.ts file
-- core extension state: Managed by the ClineProvider class in src/core/webview/ClineProvider.ts, which serves as the single source of truth for the extension's state. It manages multiple types of persistent storage (global state, workspace state, and secrets), handles state distribution to both the core extension and webview components, and coordinates state across multiple extension instances. This includes managing API configurations, task history, settings, and MCP configurations.
-- webview: Anything inside the webview-ui. All the react or view's seen by the user and user interaction compone
-- webview state: Managed by ExtensionStateContext in webview-ui/src/context/ExtensionStateContext.tsx, which provides React components with access to the extension's state through a context provider pattern. It maintains local state for UI components, handles real-time updates through message events, manages partial message updates, and provides methods for state modifications. The context includes extension version, messages, task history, theme, API configurations, MCP servers, marketplace catalog, and workspace file paths. It synchronizes with the core extension through VSCode's message passing system and provides type-safe access to state through a custom hook (useExtensionState).
+- **Core Extension**: Anything inside the src folder, organized into modular components
+- **Core Extension State**: Managed by the Controller class in src/core/controller/index.ts, which serves as the single source of truth for the extension's state. It manages multiple types of persistent storage (global state, workspace state, and secrets), handles state distribution to both the core extension and webview components, and coordinates state across multiple extension instances. This includes managing API configurations, task history, settings, and MCP configurations.
+- **Webview**: Anything inside the webview-ui. All the react or view's seen by the user and user interaction components
+- **Webview State**: Managed by ExtensionStateContext in webview-ui/src/context/ExtensionStateContext.tsx, which provides React components with access to the extension's state through a context provider pattern. It maintains local state for UI components, handles real-time updates through message events, manages partial message updates, and provides methods for state modifications. The context includes extension version, messages, task history, theme, API configurations, MCP servers, marketplace catalog, and workspace file paths. It synchronizes with the core extension through VSCode's message passing system and provides type-safe access to state through a custom hook (useExtensionState).
+
+### Core Extension Architecture
+
+The core extension follows a clear hierarchical structure:
+
+1. **WebviewProvider** (src/core/webview/index.ts): Manages the webview lifecycle and communication
+2. **Controller** (src/core/controller/index.ts): Handles webview messages and task management
+3. **Task** (src/core/task/index.ts): Executes API requests and tool operations
+
+This architecture provides clear separation of concerns:
+- WebviewProvider focuses on VSCode webview integration
+- Controller manages state and coordinates tasks
+- Task handles the execution of AI requests and tool operations
+
+### WebviewProvider Implementation
+
+The WebviewProvider class in `src/core/webview/index.ts` is responsible for:
+
+- Managing multiple active instances through a static set (`activeInstances`)
+- Handling webview lifecycle events (creation, visibility changes, disposal)
+- Implementing HTML content generation with proper CSP headers
+- Supporting Hot Module Replacement (HMR) for development
+- Setting up message listeners between the webview and extension
+
+The WebviewProvider maintains a reference to the Controller and delegates message handling to it. It also handles the creation of both sidebar and tab panel webviews, allowing Cline to be used in different contexts within VSCode.
 
 ### Core Extension State
 
-The `ClineProvider` class manages multiple types of persistent storage:
+The `Controller` class manages multiple types of persistent storage:
 
 - **Global State:** Stored across all VSCode instances. Used for settings and data that should persist globally.
 - **Workspace State:** Specific to the current workspace. Used for task-specific data and settings.
 - **Secrets:** Secure storage for sensitive information like API keys.
 
-The `ClineProvider` handles the distribution of state to both the core extension and webview components. It also coordinates state across multiple extension instances, ensuring consistency.
+The `Controller` handles the distribution of state to both the core extension and webview components. It also coordinates state across multiple extension instances, ensuring consistency.
+
+State synchronization between instances is handled through:
+- File-based storage for task history and conversation data
+- VSCode's global state API for settings and configuration
+- Secrets storage for sensitive information
+- Event listeners for file changes and configuration updates
+
+The Controller implements methods for:
+- Saving and loading task state
+- Managing API configurations
+- Handling user authentication
+- Coordinating MCP server connections
+- Managing task history and checkpoints
 
 ### Webview State
 
@@ -82,16 +140,65 @@ The `ExtensionStateContext` in `webview-ui/src/context/ExtensionStateContext.tsx
 
 It synchronizes with the core extension through VSCode's message passing system and provides type-safe access to the state via a custom hook (`useExtensionState`).
 
-## Core Extension (Cline.ts)
+The ExtensionStateContext handles:
+- Real-time updates through message events
+- Partial message updates for streaming content
+- State modifications through setter methods
+- Type-safe access to state through a custom hook
 
-The Cline class is the heart of the extension, managing task execution, state persistence, and tool coordination. Each task runs in its own instance of the Cline class, ensuring isolation and proper state management.
+## API Provider System
+
+Cline supports multiple AI providers through a modular API provider system. Each provider is implemented as a separate module in the `src/api/providers/` directory and follows a common interface.
+
+### API Provider Architecture
+
+The API system consists of:
+
+1. **API Handlers**: Provider-specific implementations in `src/api/providers/`
+2. **API Transformers**: Stream transformation utilities in `src/api/transform/`
+3. **API Configuration**: User settings for API keys and endpoints
+4. **API Factory**: Builder function to create the appropriate handler
+
+Key providers include:
+- **Anthropic**: Direct integration with Claude models
+- **OpenRouter**: Meta-provider supporting multiple model providers
+- **AWS Bedrock**: Integration with Amazon's AI services
+- **Gemini**: Google's AI models
+- **Ollama**: Local model hosting
+- **LM Studio**: Local model hosting
+- **VSCode LM**: VSCode's built-in language models
+
+### API Configuration Management
+
+API configurations are stored securely:
+- API keys are stored in VSCode's secrets storage
+- Model selections and non-sensitive settings are stored in global state
+- The Controller manages switching between providers and updating configurations
+
+The system supports:
+- Secure storage of API keys
+- Model selection and configuration
+- Automatic retry and error handling
+- Token usage tracking and cost calculation
+- Context window management
+
+### Plan/Act Mode API Configuration
+
+Cline supports separate model configurations for Plan and Act modes:
+- Different models can be used for planning vs. execution
+- The system preserves model selections when switching modes
+- The Controller handles the transition between modes and updates the API configuration accordingly
+
+## Task Execution System
+
+The Task class is responsible for executing AI requests and tool operations. Each task runs in its own instance of the Task class, ensuring isolation and proper state management.
 
 ### Task Execution Loop
 
 The core task execution loop follows this pattern:
 
 ```typescript
-class Cline {
+class Task {
   async initiateTaskLoop(userContent: UserContent, isNewTask: boolean) {
     while (!this.abort) {
       // 1. Make API request and stream response
@@ -126,7 +233,7 @@ class Cline {
 The streaming system handles real-time updates and partial content:
 
 ```typescript
-class Cline {
+class Task {
   async presentAssistantMessage() {
     // Handle streaming locks to prevent race conditions
     if (this.presentAssistantMessageLocked) {
@@ -161,7 +268,7 @@ class Cline {
 Tools follow a strict execution pattern:
 
 ```typescript
-class Cline {
+class Task {
   async executeToolWithApproval(block: ToolBlock) {
     // 1. Check auto-approval settings
     if (this.shouldAutoApproveTool(block.name)) {
@@ -193,7 +300,7 @@ class Cline {
 The system includes robust error handling:
 
 ```typescript
-class Cline {
+class Task {
   async handleError(action: string, error: Error) {
     // 1. Check if task was abandoned
     if (this.abandoned) return
@@ -216,23 +323,23 @@ class Cline {
 
 ### API Request & Token Management
 
-The Cline class handles API requests with built-in retry, streaming, and token management:
+The Task class handles API requests with built-in retry, streaming, and token management:
 
 ```typescript
-class Cline {
+class Task {
   async *attemptApiRequest(previousApiReqIndex: number): ApiStream {
     // 1. Wait for MCP servers to connect
-    await pWaitFor(() => this.providerRef.deref()?.mcpHub?.isConnecting !== true)
+    await pWaitFor(() => this.controllerRef.deref()?.mcpHub?.isConnecting !== true)
 
     // 2. Manage context window
     const previousRequest = this.clineMessages[previousApiReqIndex]
     if (previousRequest?.text) {
-      const { tokensIn, tokensOut } = JSON.parse(previousRequest.text)
+      const { tokensIn, tokensOut } = JSON.parse(previousRequest.text || "{}")
       const totalTokens = (tokensIn || 0) + (tokensOut || 0)
       
       // Truncate conversation if approaching context limit
       if (totalTokens >= maxAllowedSize) {
-        this.conversationHistoryDeletedRange = getNextTruncationRange(
+        this.conversationHistoryDeletedRange = this.contextManager.getNextTruncationRange(
           this.apiConversationHistory,
           this.conversationHistoryDeletedRange,
           totalTokens / 2 > maxAllowedSize ? "quarter" : "half"
@@ -299,16 +406,32 @@ Key features:
    - Cost calculation
    - Cache hit monitoring
 
+### Context Management System
+
+The Context Management System handles conversation history truncation to prevent context window overflow errors. Implemented in the `ContextManager` class, it ensures long-running conversations remain within model context limits while preserving critical context.
+
+Key features:
+
+1. **Model-Aware Sizing**: Dynamically adjusts based on different model context windows (64K for DeepSeek, 128K for most models, 200K for Claude).
+
+2. **Proactive Truncation**: Monitors token usage and preemptively truncates conversations when approaching limits, maintaining buffers of 27K-40K tokens depending on the model.
+
+3. **Intelligent Preservation**: Always preserves the original task message and maintains the user-assistant conversation structure when truncating.
+
+4. **Adaptive Strategies**: Uses different truncation strategies based on context pressure - removing half of the conversation for moderate pressure or three-quarters for severe pressure.
+
+5. **Error Recovery**: Includes specialized detection for context window errors from different providers with automatic retry and more aggressive truncation when needed.
+
 ### Task State & Resumption
 
-The Cline class provides robust task state management and resumption capabilities:
+The Task class provides robust task state management and resumption capabilities:
 
 ```typescript
-class Cline {
+class Task {
   async resumeTaskFromHistory() {
     // 1. Load saved state
-    this.clineMessages = await this.getSavedClineMessages()
-    this.apiConversationHistory = await this.getSavedApiConversationHistory()
+    this.clineMessages = await getSavedClineMessages(this.getContext(), this.taskId)
+    this.apiConversationHistory = await getSavedApiConversationHistory(this.getContext(), this.taskId)
 
     // 2. Handle interrupted tool executions
     const lastMessage = this.apiConversationHistory[this.apiConversationHistory.length - 1]
@@ -338,14 +461,14 @@ class Cline {
 
   private async saveTaskState() {
     // Save conversation history
-    await this.saveApiConversationHistory()
-    await this.saveClineMessages()
+    await saveApiConversationHistory(this.getContext(), this.taskId, this.apiConversationHistory)
+    await saveClineMessages(this.getContext(), this.taskId, this.clineMessages)
     
     // Create checkpoint
     const commitHash = await this.checkpointTracker?.commit()
     
     // Update task history
-    await this.providerRef.deref()?.updateTaskHistory({
+    await this.controllerRef.deref()?.updateTaskHistory({
       id: this.taskId,
       ts: lastMessage.ts,
       task: taskMessage.text,
@@ -381,11 +504,54 @@ Key aspects of task state management:
    - Resources are cleaned up properly
    - User is notified of state changes
 
+## Plan/Act Mode System
+
+Cline implements a dual-mode system that separates planning from execution:
+
+### Mode Architecture
+
+The Plan/Act mode system consists of:
+
+1. **Mode State**: Stored in `chatSettings.mode` in the Controller's state
+2. **Mode Switching**: Handled by `togglePlanActModeWithChatSettings` in the Controller
+3. **Mode-specific Models**: Optional configuration to use different models for each mode
+4. **Mode-specific Prompting**: Different system prompts for planning vs. execution
+
+### Mode Switching Process
+
+When switching between modes:
+
+1. The current model configuration is saved to mode-specific state
+2. The previous mode's model configuration is restored
+3. The Task instance is updated with the new mode
+4. The webview is notified of the mode change
+5. Telemetry events are captured for analytics
+
+### Plan Mode
+
+Plan mode is designed for:
+- Information gathering and context building
+- Asking clarifying questions
+- Creating detailed execution plans
+- Discussing approaches with the user
+
+In Plan mode, the AI uses the `plan_mode_respond` tool to engage in conversational planning without executing actions.
+
+### Act Mode
+
+Act mode is designed for:
+- Executing the planned actions
+- Using tools to modify files, run commands, etc.
+- Implementing the solution
+- Providing results and completion feedback
+
+In Act mode, the AI has access to all tools except `plan_mode_respond` and focuses on implementation rather than discussion.
+
 ## Data Flow & State Management
 
 ### Core Extension Role
 
-The core extension (ClineProvider) acts as the single source of truth for all persistent state. It:
+The Controller acts as the single source of truth for all persistent state. It:
 - Manages VSCode global state and secrets storage
 - Coordinates state updates between components
 - Ensures state consistency across webview reloads
@@ -394,10 +560,10 @@ The core extension (ClineProvider) acts as the single source of truth for all pe
 
 ### Terminal Management
 
-The Cline class manages terminal instances and command execution:
+The Task class manages terminal instances and command execution:
 
 ```typescript
-class Cline {
+class Task {
   async executeCommandTool(command: string): Promise<[boolean, ToolResponse]> {
     // 1. Get or create terminal
     const terminalInfo = await this.terminalManager.getOrCreateTerminal(cwd)
@@ -453,10 +619,10 @@ Key features:
 
 ### Browser Session Management
 
-The Cline class handles browser automation through Puppeteer:
+The Task class handles browser automation through Puppeteer:
 
 ```typescript
-class Cline {
+class Task {
   async executeBrowserAction(action: BrowserAction): Promise<BrowserActionResult> {
     switch (action) {
       case "launch":
@@ -493,13 +659,93 @@ Key aspects:
    - Screenshot capture
    - Error recovery
 
+## MCP (Model Context Protocol) Integration
+
+### MCP Architecture
+
+The MCP system consists of:
+
+1. **McpHub Class**: Central manager in `src/services/mcp/McpHub.ts`
+2. **MCP Connections**: Manages connections to external MCP servers
+3. **MCP Settings**: Configuration stored in a JSON file
+4. **MCP Marketplace**: Online catalog of available MCP servers
+5. **MCP Tools & Resources**: Capabilities exposed by connected servers
+
+The McpHub class:
+- Manages the lifecycle of MCP server connections
+- Handles server configuration through a settings file
+- Provides methods for calling tools and accessing resources
+- Implements auto-approval settings for MCP tools
+- Monitors server health and handles reconnection
+
+### MCP Server Types
+
+Cline supports two types of MCP server connections:
+- **Stdio**: Command-line based servers that communicate via standard I/O
+- **SSE**: HTTP-based servers that communicate via Server-Sent Events
+
+### MCP Server Management
+
+The McpHub class provides methods for:
+- Discovering and connecting to MCP servers
+- Monitoring server health and status
+- Restarting servers when needed
+- Managing server configurations
+- Setting timeouts and auto-approval rules
+
+### MCP Tool Integration
+
+MCP tools are integrated into the Task execution system:
+- Tools are discovered and registered at connection time
+- The Task class can call MCP tools through the McpHub
+- Tool results are streamed back to the AI
+- Auto-approval settings can be configured per tool
+
+### MCP Marketplace
+
+The MCP Marketplace provides:
+- A catalog of available MCP servers
+- One-click installation
+- README previews
+- Server status monitoring
+
+The Controller class manages MCP servers through the McpHub service:
+
+```typescript
+class Controller {
+  mcpHub?: McpHub
+
+  constructor(context: vscode.ExtensionContext, outputChannel: vscode.OutputChannel, webviewProvider: WebviewProvider) {
+    this.mcpHub = new McpHub(this)
+  }
+
+  async downloadMcp(mcpId: string) {
+    // Fetch server details from marketplace
+    const response = await axios.post<McpDownloadResponse>(
+      "https://api.cline.bot/v1/mcp/download",
+      { mcpId },
+      {
+        headers: { "Content-Type": "application/json" },
+        timeout: 10000,
+      }
+    )
+
+    // Create task with context from README
+    const task = `Set up the MCP server from ${mcpDetails.githubUrl}...`
+
+    // Initialize task and show chat view
+    await this.initClineWithTask(task)
+  }
+}
+```
+
 ## Conclusion
 
 This guide provides a comprehensive overview of the Cline extension architecture, with special focus on state management, data persistence, and code organization. Following these patterns ensures robust feature implementation with proper state handling across the extension's components.
 
 Remember:
 - Always persist important state in the extension
-- The core extension exists in the src/ folder
+- The core extension follows a WebviewProvider -> Controller -> Task flow
 - Use proper typing for all state and messages
 - Handle errors and edge cases
 - Test state persistence across webview reloads

.codespellrc

@@ -0,0 +1,6 @@
+[codespell]
+# Ref: https://github.com/codespell-project/codespell#using-a-config-file
+skip = .git*,*.svg,package-lock.json,*.css,.codespellrc,locales
+check-hidden = true
+ignore-regex = (\b(optIn|isTaller)\b|https://\S+)
+# ignore-words-list =

.github/CODEOWNERS

@@ -1 +1 @@
-*       @saoudrizwan @ocasta181 @NightTrek @pashpashpash @dcbartlett @saito-sv
+*       @saoudrizwan @ocasta181 @NightTrek @pashpashpash @dcbartlett @saito-sv @Garoth

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -31,6 +31,14 @@ body:
           label: Relevant API REQUEST output
           description: Please copy and paste any relevant output. This will be automatically formatted into code, so no need for backticks.
           render: shell
+    - type: input
+      id: provider-model
+      attributes:
+          label: Provider/Model
+          description: What provider and model were you using when the issue occurred?
+          placeholder: "e.g., cline:anthropic/claude-3.7-sonnet, gemini:gemini-2.5-pro-exp-03-25"
+      validations:
+          required: true
     - type: input
       id: operating-system
       attributes:

.github/pull_request_template.md

@@ -13,7 +13,10 @@
 -   [ ] 🐛 Bug fix (non-breaking change which fixes an issue)
 -   [ ] ✨ New feature (non-breaking change which adds functionality)
 -   [ ] 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)
+-   [ ] ♻️ Refactor Changes
+-   [ ] 💅 Cosmetic Changes
 -   [ ] 📚 Documentation update
+-   [ ] 🏃 Workflow Changes
 
 ### Pre-flight Checklist
 

.github/scripts/coverage_check/__init__.py

@@ -0,0 +1,19 @@
+"""
+Coverage utility package for GitHub Actions workflows.
+This package handles extracting coverage percentages, comparing them, and generating PR comments.
+"""
+
+# Import external dependencies
+import requests
+
+# Import main function for CLI usage
+from .__main__ import main
+
+# Import functions from extraction module
+from .extraction import extract_coverage, compare_coverage, run_coverage, set_verbose
+
+# Import functions from github_api module
+from .github_api import generate_comment, post_comment, set_github_output
+
+# Import functions from workflow module
+from .workflow import process_coverage_workflow

.github/scripts/coverage_check/__main__.py

@@ -0,0 +1,154 @@
+"""
+Main module.
+This module provides the CLI interface for the coverage utility script.
+"""
+
+import sys
+import argparse
+
+from .extraction import extract_coverage, compare_coverage, run_coverage, set_verbose
+from .github_api import generate_comment, post_comment, set_github_output
+from .workflow import process_coverage_workflow
+from .util import log
+
+def setup_verbose_mode(args):
+    """
+    Set up verbose mode based on command line arguments.
+    
+    Args:
+        args: Parsed command line arguments
+    """
+    if getattr(args, 'verbose', False):
+        set_verbose(True)
+        log("Verbose mode enabled")
+
+def main():
+    # Create parent parser with common arguments
+    parent_parser = argparse.ArgumentParser(add_help=False)
+    parent_parser.add_argument('-v', '--verbose', action='store_true', help='Enable verbose output')
+
+    # Create main parser that inherits common arguments
+    parser = argparse.ArgumentParser(description='Coverage utility script for GitHub Actions workflows', parents=[parent_parser])
+    subparsers = parser.add_subparsers(dest='command', help='Command to run')
+    
+    # extract-coverage command - used directly in workflow
+    extract_parser = subparsers.add_parser('extract-coverage', help='Extract coverage percentage from a file', parents=[parent_parser])
+    extract_parser.add_argument('file_path', help='Path to the coverage report file')
+    extract_parser.add_argument('--type', choices=['extension', 'webview'], default='extension',
+                               help='Type of coverage report')
+    extract_parser.add_argument('--github-output', action='store_true', help='Output in GitHub Actions format')
+    
+    # compare-coverage command - used by process-workflow
+    compare_parser = subparsers.add_parser('compare-coverage', help='Compare coverage percentages', parents=[parent_parser])
+    compare_parser.add_argument('base_cov', help='Base branch coverage percentage')
+    compare_parser.add_argument('pr_cov', help='PR branch coverage percentage')
+    compare_parser.add_argument('--output-prefix', default='', help='Prefix for GitHub Actions output variables')
+    compare_parser.add_argument('--github-output', action='store_true', help='Output in GitHub Actions format')
+    
+    # generate-comment command - used by process-workflow
+    comment_parser = subparsers.add_parser('generate-comment', help='Generate PR comment with coverage comparison', parents=[parent_parser])
+    comment_parser.add_argument('base_ext_cov', help='Base branch extension coverage')
+    comment_parser.add_argument('pr_ext_cov', help='PR branch extension coverage')
+    comment_parser.add_argument('ext_decreased', help='Whether extension coverage decreased (true/false)')
+    comment_parser.add_argument('ext_diff', help='Extension coverage difference')
+    comment_parser.add_argument('base_web_cov', help='Base branch webview coverage')
+    comment_parser.add_argument('pr_web_cov', help='PR branch webview coverage')
+    comment_parser.add_argument('web_decreased', help='Whether webview coverage decreased (true/false)')
+    comment_parser.add_argument('web_diff', help='Webview coverage difference')
+    
+    # post-comment command - used by process-workflow
+    post_parser = subparsers.add_parser('post-comment', help='Post a comment to a GitHub PR', parents=[parent_parser])
+    post_parser.add_argument('comment_path', help='Path to the file containing the comment text')
+    post_parser.add_argument('pr_number', help='PR number')
+    post_parser.add_argument('repo', help='Repository in the format "owner/repo"')
+    post_parser.add_argument('--token', help='GitHub token')
+    
+    # run-coverage command - used by process-workflow
+    run_parser = subparsers.add_parser('run-coverage', help='Run a coverage command and extract the coverage percentage', parents=[parent_parser])
+    run_parser.add_argument('coverage_cmd', help='Command to run')
+    run_parser.add_argument('output_file', help='File to save the output to')
+    run_parser.add_argument('--type', choices=['extension', 'webview'], default='extension',
+                           help='Type of coverage report')
+    run_parser.add_argument('--github-output', action='store_true', help='Output in GitHub Actions format')
+    
+    # process-workflow command - used directly in workflow
+    workflow_parser = subparsers.add_parser('process-workflow', help='Process the entire coverage workflow', parents=[parent_parser])
+    workflow_parser.add_argument('--base-branch', required=True, help='Base branch name')
+    workflow_parser.add_argument('--pr-number', help='PR number')
+    workflow_parser.add_argument('--repo', help='Repository in the format "owner/repo"')
+    workflow_parser.add_argument('--token', help='GitHub token')
+    
+    # set-github-output command - used by process-workflow
+    output_parser = subparsers.add_parser('set-github-output', help='Set GitHub Actions output variable', parents=[parent_parser])
+    output_parser.add_argument('name', help='Output variable name')
+    output_parser.add_argument('value', help='Output variable value')
+    
+    args = parser.parse_args()
+    
+    # Set up verbose mode
+    setup_verbose_mode(args)
+    
+    if args.command == 'extract-coverage':
+        log(f"Extracting coverage from file: {args.file_path} (type: {args.type})")
+        coverage_pct = extract_coverage(args.file_path, args.type)
+        if args.github_output:
+            set_github_output(f"{args.type}_coverage", coverage_pct)
+        else:
+            log(f"Coverage: {coverage_pct}%")
+        
+    elif args.command == 'compare-coverage':
+        log(f"Comparing coverage: base={args.base_cov}%, PR={args.pr_cov}%")
+        decreased, diff = compare_coverage(args.base_cov, args.pr_cov)
+        if args.github_output:
+            prefix = args.output_prefix
+            set_github_output(f"{prefix}decreased", str(decreased).lower())
+            set_github_output(f"{prefix}diff", diff)
+            log(f"Coverage difference: {diff}%")
+            log(f"Coverage decreased: {decreased}")
+        else:
+            log(f"decreased={str(decreased).lower()}")
+            log(f"diff={diff}")
+        
+    elif args.command == 'generate-comment':
+        log("Generating coverage comparison comment")
+        comment = generate_comment(
+            args.base_ext_cov, args.pr_ext_cov, args.ext_decreased, args.ext_diff,
+            args.base_web_cov, args.pr_web_cov, args.web_decreased, args.web_diff
+        )
+        # Output the comment to stdout
+        log(comment)
+        
+    elif args.command == 'post-comment':
+        log(f"Posting comment from {args.comment_path} to PR #{args.pr_number} in {args.repo}")
+        post_comment(args.comment_path, args.pr_number, args.repo, args.token)
+        
+    elif args.command == 'run-coverage':
+        log(f"Running coverage command: {args.coverage_cmd}")
+        log(f"Output file: {args.output_file}")
+        log(f"Coverage type: {args.type}")
+        coverage_pct = run_coverage(args.coverage_cmd, args.output_file, args.type)
+        if args.github_output:
+            set_github_output(f"{args.type}_coverage", coverage_pct)
+        else:
+            log(f"Coverage: {coverage_pct}%")
+        
+    elif args.command == 'process-workflow':
+        log("Processing coverage workflow")
+        log(f"Base branch: {args.base_branch}")
+        if args.pr_number:
+            log(f"PR number: {args.pr_number}")
+        if args.repo:
+            log(f"Repository: {args.repo}")
+        process_coverage_workflow(args)
+        
+    elif args.command == 'set-github-output':
+        log(f"Setting GitHub output: {args.name}={args.value}")
+        set_github_output(args.name, args.value)
+    
+    else:
+        log("No command specified")
+        parser.print_help()
+        sys.exit(1)
+
+if __name__ == "__main__":
+    main()

.github/scripts/coverage_check/extraction.py

@@ -0,0 +1,265 @@
+"""
+Coverage extraction module.
+This module handles extracting coverage percentages from coverage report files.
+"""
+
+import os
+import re
+import sys
+import shlex
+import subprocess
+import traceback
+from .util import log, file_exists, get_file_size, list_directory, is_safe_command, run_command
+
+# Global verbose flag
+verbose = False
+
+def set_verbose(value):
+    """Set the global verbose flag."""
+    global verbose
+    verbose = value
+
+def print_debug_output(content, coverage_type):
+    """
+    Print debug information about the coverage output.
+    
+    Args:
+        content: The content of the coverage file
+        coverage_type: Type of coverage report (extension or webview)
+    """
+    if not verbose:
+        return
+
+    # Extract and print only the coverage summary section
+    if coverage_type == "extension":
+        # Look for the coverage summary section
+        summary_match = re.search(r'=============================== Coverage summary ===============================\n(.*?)\n=+', content, re.DOTALL)
+        if summary_match:
+            sys.stdout.write("\n##[group]EXTENSION COVERAGE SUMMARY\n")
+            sys.stdout.write("=============================== Coverage summary ===============================\n")
+            sys.stdout.write(summary_match.group(1) + "\n")
+            sys.stdout.write("================================================================================\n")
+            sys.stdout.write("##[endgroup]\n")
+            sys.stdout.flush()
+        else:
+            sys.stdout.write("\n##[warning]No coverage summary found in extension coverage file\n")
+            sys.stdout.flush()
+    else:  # webview
+        # Look for the coverage table - specifically the "All files" row
+        table_match = re.search(r'% Coverage report from v8.*?-+\|.*?\n.*?\n(All files.*?)(?:\n[^\n]*\|)', content, re.DOTALL)
+        if table_match:
+            sys.stdout.write("\n##[group]WEBVIEW COVERAGE SUMMARY\n")
+            sys.stdout.write("% Coverage report from v8\n")
+            sys.stdout.write("-------------------|---------|----------|---------|---------|-------------------\n")
+            sys.stdout.write("File               | % Stmts | % Branch | % Funcs | % Lines | Uncovered Line #s \n")
+            sys.stdout.write("-------------------|---------|----------|---------|---------|-------------------\n")
+            sys.stdout.write(table_match.group(1) + "\n")
+            sys.stdout.write("-------------------|---------|----------|---------|---------|-------------------\n")
+            sys.stdout.write("##[endgroup]\n")
+            sys.stdout.flush()
+        else:
+            sys.stdout.write("\n##[warning]No coverage table found in webview coverage file\n")
+            sys.stdout.flush()
+
+def extract_coverage(file_path, coverage_type="extension"):
+    """
+    Extract coverage percentage from a coverage report file.
+    
+    Args:
+        file_path: Path to the coverage report file
+        coverage_type: Type of coverage report (extension or webview)
+        
+    Returns:
+        Coverage percentage as a float
+    """
+    
+    # Always print file path for debugging
+    log(f"Checking coverage file: {file_path}")
+    
+    # Check if file exists and get its size
+    if not file_exists(file_path):
+        sys.stdout.write(f"\n##[error]File {file_path} does not exist\n")
+        sys.stdout.flush()
+        log(f"Error: File {file_path} does not exist")
+        
+        # Check if the directory exists
+        dir_path = os.path.dirname(file_path)
+        if not os.path.exists(dir_path):
+            sys.stdout.write(f"\n##[error]Directory {dir_path} does not exist\n")
+            sys.stdout.flush()
+            log(f"Error: Directory {dir_path} does not exist")
+        else:
+            # List directory contents for debugging
+            log(f"Directory {dir_path} exists, listing contents:")
+            try:
+                dir_contents = list_directory(dir_path)
+                for name, size in dir_contents:
+                    log(f"  {name} - {size}")
+                    sys.stdout.write(f"  {name} - {size}\n")
+                sys.stdout.flush()
+            except Exception as e:
+                log(f"Error listing directory: {e}")
+        
+        return 0.0
+    
+    file_size = get_file_size(file_path)
+    log(f"File size: {file_size} bytes")
+    sys.stdout.write(f"\n##[info]Coverage file {file_path} exists, size: {file_size} bytes\n")
+    sys.stdout.flush()
+    
+    if file_size == 0:
+        sys.stdout.write(f"\n##[warning]File {file_path} is empty\n")
+        sys.stdout.flush()
+        log(f"Warning: File {file_path} is empty")
+        return 0.0
+    
+    # List directory contents for debugging
+    dir_path = os.path.dirname(file_path)
+    log(f"Directory contents of {dir_path}:")
+    try:
+        dir_contents = list_directory(dir_path)
+        for name, size in dir_contents:
+            log(f"  {name} - {size}")
+    except Exception as e:
+        log(f"Error listing directory: {e}")
+    
+    with open(file_path, 'r') as f:
+        content = f.read()
+    
+    # Print debug information if verbose
+    print_debug_output(content, coverage_type)
+    
+    # Extract coverage percentage based on coverage type
+    if coverage_type == "extension":
+        # Extract the percentage from the "Lines" row in the coverage summary
+        # Pattern: Lines : xx.xx% ( xxxxxxx/xxxxxxx )
+        lines_match = re.search(r'Lines\s*:\s*(\d+\.\d+)%', content)
+        if lines_match:
+            coverage_pct = float(lines_match.group(1))
+            if verbose:
+                sys.stdout.write(f"Pattern matched (Lines percentage): {coverage_pct}\n")
+                sys.stdout.flush()
+            return coverage_pct
+        else:
+            # No coverage data found, log full content for debugging
+            log("No coverage data found. Full file content:")
+            log("=== Full file content ===")
+            log(content)
+            log("=== End file content ===")
+    else:  # webview
+        # Extract the percentage from the "% Lines" column in the "All files" row
+        # Pattern: All files | xx.xx | xx.xx | xx.xx | xx.xx |
+        all_files_match = re.search(r'All files\s+\|\s+\d+\.\d+\s+\|\s+\d+\.\d+\s+\|\s+\d+\.\d+\s+\|\s+(\d+\.\d+)', content)
+        if all_files_match:
+            coverage_pct = float(all_files_match.group(1))
+            if verbose:
+                sys.stdout.write(f"Pattern matched (All files % Lines): {coverage_pct}\n")
+                sys.stdout.flush()
+            return coverage_pct
+        else:
+            # No coverage data found, log full content for debugging
+            log("No coverage data found. Full file content:")
+            log("=== Full file content ===")
+            log(content)
+            log("=== End file content ===")
+    
+    # If no match found, return 0.0
+    return 0.0
+
+def compare_coverage(base_cov, pr_cov):
+    """
+    Compare coverage percentages between base and PR branches.
+    
+    Args:
+        base_cov: Base branch coverage percentage
+        pr_cov: PR branch coverage percentage
+        
+    Returns:
+        Tuple of (decreased, diff)
+    """
+    try:
+        base_cov = float(base_cov)
+        pr_cov = float(pr_cov)
+    except ValueError:
+        sys.stdout.write(f"Error: Invalid coverage values - base: {base_cov}, PR: {pr_cov}\n")
+        sys.stdout.flush()
+        return False, 0
+    
+    diff = pr_cov - base_cov
+    decreased = diff < 0
+    
+    return decreased, abs(diff)
+
+def run_coverage(command, output_file, coverage_type="extension"):
+    """
+    Run a coverage command and extract the coverage percentage.
+    
+    Args:
+        command: Command to run
+        output_file: File to save the output to
+        coverage_type: Type of coverage report (extension or webview)
+        
+    Returns:
+        Coverage percentage as a float
+    
+    Raises:
+        SystemExit: If the output file is not created or is empty
+    """
+    
+    try:
+        # Run the command and capture output
+        if not is_safe_command(command):
+            error_msg = f"ERROR: Unsafe command detected: {command}"
+            log(error_msg)
+            sys.stdout.write(f"\n##[error]{error_msg}\n")
+            sys.stdout.flush()
+            sys.exit(1)
+
+        # Run command using safe execution from util
+        returncode, stdout, stderr = run_command(command)
+        
+        # Log command result
+        log(f"Command exit code: {returncode}")
+        log(f"Command stdout length: {len(stdout)} bytes")
+        log(f"Command stderr length: {len(stderr)} bytes")
+        
+        # Save output to file
+        log(f"Saving command output to {output_file}")
+        with open(output_file, 'w') as f:
+            f.write(stdout)
+            if stderr:
+                f.write("\n\n=== STDERR ===\n")
+                f.write(stderr)
+        
+        # Verify file was created and has content
+        if not file_exists(output_file):
+            error_msg = f"ERROR: Output file {output_file} was not created"
+            log(error_msg)
+            sys.stdout.write(f"\n##[error]{error_msg}\n")
+            sys.stdout.flush()
+            sys.exit(1)  # Exit with error code to fail the workflow
+            
+        file_size = get_file_size(output_file)
+        if file_size == 0:
+            error_msg = f"ERROR: Output file {output_file} is empty"
+            log(error_msg)
+            sys.stdout.write(f"\n##[error]{error_msg}\n")
+            sys.stdout.flush()
+            sys.exit(1)  # Exit with error code to fail the workflow
+            
+        log(f"Output file size: {file_size} bytes")
+        
+        # Extract coverage percentage
+        coverage_pct = extract_coverage(output_file, coverage_type)
+        
+        log(f"{coverage_type.capitalize()} coverage: {coverage_pct}%")
+        return coverage_pct
+    
+    except Exception as e:
+        error_msg = f"Error running coverage command: {e}"
+        log(error_msg)
+        sys.stdout.write(f"\n##[error]{error_msg}\n")
+        sys.stdout.flush()
+        # Print stack trace for debugging
+        log(traceback.format_exc())
+        sys.exit(1)  # Exit with error code to fail the workflow

.github/scripts/coverage_check/github_api.py

@@ -0,0 +1,177 @@
+"""
+GitHub API module.
+This module handles interactions with the GitHub API for posting comments to PRs.
+"""
+
+import os
+import requests
+from .util import log, file_exists
+
+def generate_comment(base_ext_cov, pr_ext_cov, ext_decreased, ext_diff, 
+                    base_web_cov, pr_web_cov, web_decreased, web_diff):
+    """
+    Generate a PR comment with coverage comparison.
+    
+    Args:
+        base_ext_cov: Base branch extension coverage
+        pr_ext_cov: PR branch extension coverage
+        ext_decreased: Whether extension coverage decreased
+        ext_diff: Extension coverage difference
+        base_web_cov: Base branch webview coverage
+        pr_web_cov: PR branch webview coverage
+        web_decreased: Whether webview coverage decreased
+        web_diff: Webview coverage difference
+        
+    Returns:
+        Comment text
+    """
+    from datetime import datetime
+    
+    # Convert string inputs to appropriate types
+    try:
+        base_ext_cov = float(base_ext_cov)
+        pr_ext_cov = float(pr_ext_cov)
+        # Handle ext_decreased as either string or boolean
+        if isinstance(ext_decreased, str):
+            ext_decreased = ext_decreased.lower() == 'true'
+        else:
+            ext_decreased = bool(ext_decreased)
+        ext_diff = float(ext_diff)
+        base_web_cov = float(base_web_cov)
+        pr_web_cov = float(pr_web_cov)
+        # Handle web_decreased as either string or boolean
+        if isinstance(web_decreased, str):
+            web_decreased = web_decreased.lower() == 'true'
+        else:
+            web_decreased = bool(web_decreased)
+        web_diff = float(web_diff)
+    except ValueError as e:
+        log(f"Error converting input values: {e}")
+        return ""
+    
+    # Add a unique identifier to find this comment later
+    comment = '<!-- COVERAGE_REPORT -->\n'
+    comment += '## Coverage Report\n\n'
+
+    # Extension coverage
+    comment += '### Extension Coverage\n\n'
+    comment += f'Base branch: {base_ext_cov:.0f}%\n\n'
+    comment += f'PR branch: {pr_ext_cov:.0f}%\n\n'
+
+    if ext_decreased:
+        comment += f'⚠️ **Warning: Coverage decreased by {ext_diff:.2f}%**\n\n'
+        comment += 'Consider adding tests to cover your changes.\n\n'
+    else:
+        comment += '✅ Coverage increased or remained the same\n\n'
+
+    # Webview coverage
+    comment += '### Webview Coverage\n\n'
+    comment += f'Base branch: {base_web_cov:.0f}%\n\n'
+    comment += f'PR branch: {pr_web_cov:.0f}%\n\n'
+
+    if web_decreased:
+        comment += f'⚠️ **Warning: Coverage decreased by {web_diff:.2f}%**\n\n'
+        comment += 'Consider adding tests to cover your changes.\n\n'
+    else:
+        comment += '✅ Coverage increased or remained the same\n\n'
+
+    # Overall assessment
+    comment += '### Overall Assessment\n\n'
+    if ext_decreased or web_decreased:
+        comment += '⚠️ **Test coverage has decreased in this PR**\n\n'
+        comment += 'Please consider adding tests to maintain or improve coverage.\n\n'
+    else:
+        comment += '✅ **Test coverage has been maintained or improved**\n\n'
+
+    # Add timestamp
+    comment += f'\n\n<sub>Last updated: {datetime.now().isoformat()}</sub>'
+    
+    return comment
+
+def post_comment(comment_path, pr_number, repo, token=None):
+    """
+    Post a comment to a GitHub PR.
+    
+    Args:
+        comment_path: Path to the file containing the comment text
+        pr_number: PR number
+        repo: Repository in the format "owner/repo"
+        token: GitHub token
+    """
+    if not file_exists(comment_path):
+        log(f"Error: Comment file {comment_path} does not exist")
+        return
+    
+    with open(comment_path, 'r') as f:
+        comment_body = f.read()
+    
+    if not token:
+        token = os.environ.get('GITHUB_TOKEN')
+        if not token:
+            log("Error: GitHub token not provided")
+            return
+    
+    # Find existing comment
+    headers = {
+        'Authorization': f'token {token}',
+        'Accept': 'application/vnd.github.v3+json'
+    }
+    
+    # Get all comments
+    comments_url = f'https://api.github.com/repos/{repo}/issues/{pr_number}/comments'
+    log(f"Getting comments from: {comments_url}")
+    response = requests.get(comments_url, headers=headers)
+    
+    if response.status_code != 200:
+        log(f"Error getting comments: {response.status_code} - {response.text}")
+        return
+    
+    comments = response.json()
+    log(f"Found {len(comments)} existing comments")
+    
+    # Find comment with our identifier
+    comment_id = None
+    for comment in comments:
+        if '<!-- COVERAGE_REPORT -->' in comment['body']:
+            comment_id = comment['id']
+            log(f"Found existing coverage report comment with ID: {comment_id}")
+            break
+    
+    if comment_id:
+        # Update existing comment
+        update_url = f'https://api.github.com/repos/{repo}/issues/comments/{comment_id}'
+        log(f"Updating existing comment at: {update_url}")
+        response = requests.patch(update_url, headers=headers, json={'body': comment_body})
+        
+        if response.status_code == 200:
+            log(f"Successfully updated existing comment: {comment_id}")
+        else:
+            log(f"Error updating comment: {response.status_code} - {response.text}")
+    else:
+        # Create new comment
+        log(f"Creating new comment at: {comments_url}")
+        response = requests.post(comments_url, headers=headers, json={'body': comment_body})
+        
+        if response.status_code == 201:
+            log("Successfully created new comment")
+        else:
+            log(f"Error creating comment: {response.status_code} - {response.text}")
+
+def set_github_output(name, value):
+    """
+    Set GitHub Actions output variable.
+    
+    Args:
+        name: Output variable name
+        value: Output variable value
+    """
+    # Write to the GitHub output file if available
+    if 'GITHUB_OUTPUT' in os.environ:
+        with open(os.environ['GITHUB_OUTPUT'], 'a') as f:
+            f.write(f"{name}={value}\n")
+    else:
+        # Fallback to the deprecated method for backward compatibility
+        log(f"::set-output name={name}::{value}")
+    
+    # Also print for human readability
+    log(f"{name}: {value}")

.github/scripts/coverage_check/util.py

@@ -0,0 +1,245 @@
+"""
+Utility module.
+This module provides utility functions used across the coverage check scripts.
+"""
+
+import os
+import sys
+import re
+import shlex
+import subprocess
+import traceback
+from typing import List, Tuple, Dict, Any, Optional, Union
+
+# List of allowed commands and their arguments
+ALLOWED_COMMANDS = {
+    'xvfb-run': ['-a'],
+    'npm': ['run', 'test:coverage', 'ci', 'install', '--no-save', '@vitest/coverage-v8', 'check-types', 'lint', 'format', 'compile'],
+    'cd': ['webview-ui'],
+    'python': ['-m', 'coverage_check'],
+    'git': ['fetch', 'checkout', 'origin'],
+}
+
+def is_safe_command(command: Union[str, List[str]]) -> bool:
+    """
+    Check if a command is safe to execute.
+    
+    Args:
+        command: Command to check (string or list)
+        
+    Returns:
+        True if command is safe, False otherwise
+    """
+    # Convert string command to list
+    if isinstance(command, str):
+        try:
+            cmd_parts = shlex.split(command)
+        except ValueError:
+            return False
+    else:
+        cmd_parts = command
+
+    if not cmd_parts:
+        return False
+
+    # Get base command
+    base_cmd = os.path.basename(cmd_parts[0])
+    
+    # Check if command is in allowed list
+    if base_cmd not in ALLOWED_COMMANDS:
+        return False
+        
+    # For each argument, check for suspicious patterns
+    for arg in cmd_parts[1:]:
+        # Check for shell metacharacters
+        if re.search(r'[;&|`$]', arg):
+            return False
+        # Check for path traversal
+        if '..' in arg and not (base_cmd == 'npm' and arg.startswith('@')):
+            return False
+            
+    return True
+
+def log(message: str) -> None:
+    """
+    Write a message to stdout and flush.
+    
+    Args:
+        message: The message to write
+    """
+    sys.stdout.write(f"{message}\n")
+    sys.stdout.flush()
+
+def file_exists(file_path: str) -> bool:
+    """
+    Check if a file exists.
+    
+    Args:
+        file_path: Path to the file
+        
+    Returns:
+        True if the file exists, False otherwise
+    """
+    return os.path.exists(file_path) and os.path.isfile(file_path)
+
+def get_file_size(file_path: str) -> int:
+    """
+    Get the size of a file in bytes.
+    
+    Args:
+        file_path: Path to the file
+        
+    Returns:
+        Size of the file in bytes, or 0 if the file doesn't exist
+    """
+    if file_exists(file_path):
+        return os.path.getsize(file_path)
+    return 0
+
+def list_directory(dir_path: str) -> List[Tuple[str, Union[int, str]]]:
+    """
+    List the contents of a directory.
+    
+    Args:
+        dir_path: Path to the directory
+        
+    Returns:
+        List of (name, size) tuples for each file/directory in the directory
+    """
+    if not os.path.exists(dir_path) or not os.path.isdir(dir_path):
+        return []
+    
+    contents = []
+    for item in os.listdir(dir_path):
+        item_path = os.path.join(dir_path, item)
+        if os.path.isfile(item_path):
+            contents.append((item, os.path.getsize(item_path)))
+        else:
+            contents.append((item, "DIR"))
+    
+    return contents
+
+def read_file_content(file_path: str, default: str = "") -> str:
+    """
+    Read file content with error handling.
+    
+    Args:
+        file_path: Path to the file
+        default: Default value to return if file cannot be read
+        
+    Returns:
+        File content or default value
+    """
+    if not file_exists(file_path):
+        log(f"File does not exist: {file_path}")
+        return default
+    
+    try:
+        with open(file_path, 'r') as f:
+            return f.read()
+    except Exception as e:
+        log(f"Error reading file {file_path}: {e}")
+        return default
+
+def write_file_content(file_path: str, content: str) -> bool:
+    """
+    Write content to file with error handling.
+    
+    Args:
+        file_path: Path to the file
+        content: Content to write
+        
+    Returns:
+        True if successful, False otherwise
+    """
+    try:
+        # Create directory if it doesn't exist
+        os.makedirs(os.path.dirname(file_path), exist_ok=True)
+        
+        with open(file_path, 'w') as f:
+            f.write(content)
+        return True
+    except Exception as e:
+        log(f"Error writing to file {file_path}: {e}")
+        return False
+
+def run_command(command: Union[str, List[str]], capture_output: bool = True) -> Tuple[int, str, str]:
+    """
+    Run a command and return the result.
+    
+    Args:
+        command: Command to run (string or list)
+        capture_output: Whether to capture stdout/stderr
+        
+    Returns:
+        Tuple of (returncode, stdout, stderr)
+    """
+    if not is_safe_command(command):
+        error_msg = f"Unsafe command detected: {command}"
+        log(error_msg)
+        return 1, "", error_msg
+        
+    log(f"Running command: {command}")
+    try:
+        # Convert string command to list
+        if isinstance(command, str):
+            cmd_list = shlex.split(command)
+        else:
+            cmd_list = command
+            
+        result = subprocess.run(
+            cmd_list,
+            shell=False,  # Never use shell=True for security
+            capture_output=capture_output,
+            text=True
+        )
+        log(f"Command exit code: {result.returncode}")
+        return result.returncode, result.stdout, result.stderr
+    except Exception as e:
+        log(f"Error running command: {e}")
+        log(traceback.format_exc())
+        return 1, "", str(e)
+
+def find_pattern(content: str, pattern: str, group: int = 0, 
+                default: Optional[str] = None) -> Optional[str]:
+    """
+    Find a pattern in content and return the specified group.
+    
+    Args:
+        content: Text content to search
+        pattern: Regex pattern to search for
+        group: Group number to return (default: 0 for entire match)
+        default: Default value to return if pattern not found
+        
+    Returns:
+        Matched text or default value
+    """
+    match = re.search(pattern, content, re.DOTALL)
+    if match:
+        return match.group(group)
+    return default
+
+def get_env_var(name: str, default: Optional[str] = None) -> Optional[str]:
+    """
+    Get environment variable with default value.
+    
+    Args:
+        name: Environment variable name
+        default: Default value if not set
+        
+    Returns:
+        Environment variable value or default
+    """
+    return os.environ.get(name, default)
+
+def format_exception(e: Exception) -> str:
+    """
+    Format an exception with traceback for logging.
+    
+    Args:
+        e: Exception to format
+        
+    Returns:
+        Formatted exception string
+    """
+    return f"{type(e).__name__}: {str(e)}\n{traceback.format_exc()}"

.github/scripts/coverage_check/workflow.py

@@ -0,0 +1,432 @@
+"""
+Workflow module.
+This module handles the main workflow logic for running coverage tests and processing results.
+"""
+
+import os
+import re
+import sys
+import subprocess
+import traceback
+
+from .extraction import run_coverage, compare_coverage, extract_coverage
+from .github_api import generate_comment, post_comment, set_github_output
+from .util import log, file_exists, get_file_size, list_directory, run_command
+
+def is_valid_branch_name(branch_name: str) -> bool:
+    """
+    Validate a git branch name.
+    
+    Args:
+        branch_name: Branch name to validate
+        
+    Returns:
+        True if valid, False otherwise
+    """
+    # Check for common branch name patterns
+    if not re.match(r'^[a-zA-Z0-9_\-./]+$', branch_name):
+        return False
+    
+    # Check for path traversal
+    if '..' in branch_name:
+        return False
+        
+    # Check for shell metacharacters
+    if re.search(r'[;&|`$]', branch_name):
+        return False
+        
+    return True
+
+def checkout_branch(branch_name: str) -> None:
+    """
+    Checkout a branch for testing.
+    
+    Args:
+        branch_name: Branch name to checkout
+        
+    Raises:
+        RuntimeError: If branch checkout fails
+        ValueError: If branch name is invalid
+    """
+    if not is_valid_branch_name(branch_name):
+        raise ValueError(f"Invalid branch name: {branch_name}")
+        
+    log(f"=== Checking out branch: {branch_name} ===")
+    
+    # Fetch the branch
+    returncode, stdout, stderr = run_command(['git', 'fetch', 'origin', branch_name])
+    if returncode != 0:
+        log(f"ERROR: Failed to fetch branch {branch_name}")
+        log(f"Error details: {stderr}")
+        raise RuntimeError(f"Git fetch failed: {stderr}")
+    
+    # Checkout the branch
+    returncode, stdout, stderr = run_command(['git', 'checkout', branch_name])
+    if returncode != 0:
+        log(f"ERROR: Failed to checkout branch {branch_name}")
+        log(f"Error details: {stderr}")
+        raise RuntimeError(f"Git checkout failed: {stderr}")
+    
+    log(f"Successfully checked out branch: {branch_name}")
+
+def extract_extension_coverage_from_file(file_path):
+    """Extract extension coverage from file when run_coverage returns 0."""
+    if not file_exists(file_path):
+        log(f"File {file_path} does not exist, cannot extract extension coverage")
+        return 0.0
+    
+    file_size = get_file_size(file_path)
+    if file_size == 0:
+        log(f"File {file_path} is empty, cannot extract extension coverage")
+        return 0.0
+        
+    log(f"Extension coverage is 0.0, trying to read from file directly: {file_path} (size: {file_size} bytes)")
+    with open(file_path, 'r') as f:
+        content = f.read()
+        # Extract the percentage from the "Lines" row in the coverage summary
+        # Pattern: Lines : xx.xx% ( xxxxxxx/xxxxxxx )
+        lines_match = re.search(r'Lines\s*:\s*(\d+\.\d+)%', content)
+        if lines_match:
+            coverage = float(lines_match.group(1))
+            log(f"Found extension coverage in file: {coverage}%")
+            return coverage
+    return 0.0
+
+def extract_webview_coverage_from_file(file_path):
+    """Extract webview coverage from file when run_coverage returns 0."""
+    if not file_exists(file_path):
+        log(f"File {file_path} does not exist, cannot extract webview coverage")
+        return 0.0
+    
+    file_size = get_file_size(file_path)
+    if file_size == 0:
+        log(f"File {file_path} is empty, cannot extract webview coverage")
+        return 0.0
+        
+    log(f"Webview coverage is 0.0, trying to read from file directly: {file_path} (size: {file_size} bytes)")
+    with open(file_path, 'r') as f:
+        content = f.read()
+        # Extract the percentage from the "% Lines" column in the "All files" row
+        # Pattern: All files | xx.xx | xx.xx | xx.xx | xx.xx |
+        all_files_match = re.search(r'All files\s+\|\s+\d+\.\d+\s+\|\s+\d+\.\d+\s+\|\s+\d+\.\d+\s+\|\s+(\d+\.\d+)', content)
+        if all_files_match:
+            coverage = float(all_files_match.group(1))
+            log(f"Found webview coverage in file: {coverage}%")
+            return coverage
+    return 0.0
+
+def run_extension_coverage(branch_name=None):
+    """Run extension coverage tests and extract results."""
+    prefix = 'base_' if branch_name else ''
+    file_path = f"{prefix}extension_coverage.txt"
+    
+    # Run coverage tests
+    ext_cov = run_coverage(
+        ["xvfb-run", "-a", "npm", "run", "test:coverage"], 
+        file_path, 
+        "extension"
+    )
+    
+    # If coverage is 0.0, try to extract from file directly
+    if ext_cov == 0.0:
+        ext_cov = extract_extension_coverage_from_file(file_path)
+        
+    return ext_cov
+
+def run_webview_coverage(branch_name=None):
+    """Run webview coverage tests and extract results."""
+    prefix = 'base_' if branch_name else ''
+    file_path = f"{prefix}webview_coverage.txt"
+    
+    # Save current directory
+    original_dir = os.getcwd()
+    
+    try:
+        # Change to webview-ui directory
+        os.chdir('webview-ui')
+        
+        # Install coverage dependency
+        returncode, stdout, stderr = run_command(["npm", "install", "--no-save", "@vitest/coverage-v8"])
+        if returncode != 0:
+            log(f"Failed to install coverage dependency: {stderr}")
+            return 0.0
+        
+        # Run coverage tests from webview-ui directory
+        web_cov = run_coverage(
+            ["npm", "run", "test:coverage"],
+            os.path.join('..', file_path),
+            "webview"
+        )
+    finally:
+        # Always change back to original directory
+        os.chdir(original_dir)
+    
+    # If coverage is 0.0, try to extract from file directly
+    if web_cov == 0.0:
+        web_cov = extract_webview_coverage_from_file(file_path)
+        
+    return web_cov
+
+def run_branch_coverage(branch_name=None):
+    """
+    Run coverage tests for a branch.
+    
+    Args:
+        branch_name: Name of the branch to checkout before running tests (optional)
+        
+    Returns:
+        Tuple of (extension_coverage, webview_coverage)
+    """
+    # Checkout branch if specified
+    if branch_name:
+        checkout_branch(branch_name)
+    
+    # Run coverage tests
+    log(f"=== Running coverage tests{' for ' + branch_name if branch_name else ''} ===")
+    
+    # Run extension and webview coverage
+    ext_cov = run_extension_coverage(branch_name)
+    web_cov = run_webview_coverage(branch_name)
+    
+    return ext_cov, web_cov
+
+def find_potential_coverage_files():
+    """Find potential coverage files in the current directory and webview-ui."""
+    log("Searching for potential coverage files...")
+    
+    # Find files in current directory
+    current_dir_files = list_directory('.')
+    for name, size in current_dir_files:
+        if 'coverage' in name.lower() and size != "DIR":
+            log(f"Found potential coverage file: {name} (size: {size} bytes)")
+    
+    # Find files in webview-ui directory
+    if os.path.exists('webview-ui') and os.path.isdir('webview-ui'):
+        webview_files = list_directory('webview-ui')
+        for name, size in webview_files:
+            if 'coverage' in name.lower() and size != "DIR":
+                log(f"Found potential webview coverage file: webview-ui/{name} (size: {size} bytes)")
+    else:
+        log("webview-ui directory not found")
+
+def generate_warnings(base_ext_cov, pr_ext_cov, ext_decreased, ext_diff, 
+                     base_web_cov, pr_web_cov, web_decreased, web_diff):
+    """Generate warnings for coverage decreases."""
+    if not (ext_decreased or web_decreased):
+        return []
+        
+    warnings = [
+        "Test coverage has decreased in this PR",
+        f"Extension coverage: {base_ext_cov}% -> {pr_ext_cov}% (Diff: {ext_diff}%)",
+        f"Webview coverage: {base_web_cov}% -> {pr_web_cov}% (Diff: {web_diff}%)"
+    ]
+    
+    # Additional warning for significant decrease (more than 1%)
+    if ext_decreased and ext_diff > 1.0:
+        warnings.append(f"Extension coverage decreased by more than 1% ({ext_diff}%). Consider adding tests to cover your changes.")
+    
+    if web_decreased and web_diff > 1.0:
+        warnings.append(f"Webview coverage decreased by more than 1% ({web_diff}%). Consider adding tests to cover your changes.")
+        
+    return warnings
+
+def output_warnings(warnings):
+    """Output warnings to GitHub step summary and console."""
+    if not warnings:
+        return
+        
+    # Get the GitHub step summary file path from environment variable
+    github_step_summary = os.environ.get('GITHUB_STEP_SUMMARY')
+    
+    # Write to GitHub step summary if available
+    if github_step_summary:
+        with open(github_step_summary, 'a') as f:
+            f.write("## Coverage Warnings\n\n")
+            for warning in warnings:
+                f.write(f"⚠️ {warning}\n\n")
+    
+    # Also output to console with ::warning:: syntax for backward compatibility
+    for warning in warnings:
+        log(f"::warning::{warning}")
+
+def output_github_results(pr_ext_cov, pr_web_cov, base_ext_cov, base_web_cov, 
+                         ext_decreased, ext_diff, web_decreased, web_diff):
+    """Output results for GitHub Actions."""
+    set_github_output("pr_extension_coverage", pr_ext_cov)
+    set_github_output("pr_webview_coverage", pr_web_cov)
+    set_github_output("base_extension_coverage", base_ext_cov)
+    set_github_output("base_webview_coverage", base_web_cov)
+    set_github_output("extension_decreased", str(ext_decreased).lower())
+    set_github_output("extension_diff", ext_diff)
+    set_github_output("webview_decreased", str(web_decreased).lower())
+    set_github_output("webview_diff", web_diff)
+
+def extract_pr_coverage_from_artifacts():
+    """
+    Extract PR branch coverage from artifact files.
+    
+    Returns:
+        Tuple of (extension_coverage, webview_coverage)
+        
+    Raises:
+        SystemExit: If the coverage files don't exist
+    """
+    log("=== Extracting PR branch coverage from artifacts ===")
+    
+    # Check if the coverage files exist
+    ext_file_path = "extension_coverage.txt"
+    web_file_path = "webview-ui/webview_coverage.txt"
+    
+    # Extract extension coverage
+    log(f"Extracting extension coverage from {ext_file_path}")
+    if not file_exists(ext_file_path):
+        error_msg = f"ERROR: PR extension coverage file {ext_file_path} not found"
+        log(error_msg)
+        
+        # List directory contents for debugging
+        log("Current directory contents:")
+        try:
+            dir_contents = list_directory('.')
+            for name, size in dir_contents:
+                log(f"  {name} - {size}\n")
+        except Exception as e:
+            log(f"Error listing directory: {e}")
+        
+        sys.exit(1)  # Exit with error code to fail the workflow
+    
+    ext_cov = extract_extension_coverage_from_file(ext_file_path)
+    log(f"PR extension coverage from artifact: {ext_cov}%")
+    
+    # Extract webview coverage
+    log(f"Extracting webview coverage from {web_file_path}")
+    if not file_exists(web_file_path):
+        error_msg = f"ERROR: PR webview coverage file {web_file_path} not found"
+        log(error_msg)
+        
+        # Check if the webview-ui directory exists
+        if not os.path.exists('webview-ui'):
+            log("ERROR: webview-ui directory not found")
+        else:
+            # List webview-ui directory contents for debugging
+            log("webview-ui directory contents:")
+            try:
+                dir_contents = list_directory('webview-ui')
+                for name, size in dir_contents:
+                    log(f"  {name} - {size}")
+            except Exception as e:
+                log(f"Error listing directory: {e}")
+        
+        sys.exit(1)  # Exit with error code to fail the workflow
+    
+    web_cov = extract_webview_coverage_from_file(web_file_path)
+    log(f"PR webview coverage from artifact: {web_cov}%")
+    
+    return ext_cov, web_cov
+
+def process_coverage_workflow(args):
+    """
+    Process the entire coverage workflow.
+    
+    Args:
+        args: Command line arguments
+    """
+    # Initialize all variables at the start
+    pr_ext_cov = 0.0
+    pr_web_cov = 0.0
+    base_ext_cov = 0.0
+    base_web_cov = 0.0
+    ext_decreased = False
+    ext_diff = 0.0
+    web_decreased = False
+    web_diff = 0.0
+    
+    try:
+        # Validate branch name
+        if not is_valid_branch_name(args.base_branch):
+            raise ValueError(f"Invalid base branch name: {args.base_branch}")
+        
+        # Check if we're running in GitHub Actions
+        is_github_actions = 'GITHUB_ACTIONS' in os.environ
+        if is_github_actions:
+            log("Running in GitHub Actions environment")
+        
+        # Extract PR branch coverage from artifacts (from test job)
+        pr_ext_cov, pr_web_cov = extract_pr_coverage_from_artifacts()
+        
+        # Verify PR coverage values
+        if pr_ext_cov == 0.0:
+            log("WARNING: PR extension coverage is 0.0, this may indicate an issue with the coverage report")
+            find_potential_coverage_files()
+        
+        if pr_web_cov == 0.0:
+            log("WARNING: PR webview coverage is 0.0, this may indicate an issue with the coverage report")
+            find_potential_coverage_files()
+        
+        # Run base branch coverage
+        log(f"=== Running base branch coverage for {args.base_branch} ===")
+        base_ext_cov, base_web_cov = run_branch_coverage(args.base_branch)
+        
+        # Verify base coverage values
+        if base_ext_cov == 0.0:
+            log("WARNING: Base extension coverage is 0.0, this may indicate an issue with the coverage report")
+        
+        if base_web_cov == 0.0:
+            log("WARNING: Base webview coverage is 0.0, this may indicate an issue with the coverage report")
+        
+        # Compare coverage
+        log("=== Comparing extension coverage ===")
+        ext_decreased, ext_diff = compare_coverage(base_ext_cov, pr_ext_cov)
+        
+        log("=== Comparing webview coverage ===")
+        web_decreased, web_diff = compare_coverage(base_web_cov, pr_web_cov)
+        
+        # Print summary of coverage values
+        log("\n=== Coverage Summary ===")
+        log(f"PR extension coverage: {pr_ext_cov}%")
+        log(f"Base extension coverage: {base_ext_cov}%")
+        log(f"Extension coverage change: {'+' if not ext_decreased else '-'}{ext_diff}%")
+        log(f"PR webview coverage: {pr_web_cov}%")
+        log(f"Base webview coverage: {base_web_cov}%")
+        log(f"Webview coverage change: {'+' if not web_decreased else '-'}{web_diff}%")
+        
+        # Generate and output warnings
+        warnings = generate_warnings(
+            base_ext_cov, pr_ext_cov, ext_decreased, ext_diff,
+            base_web_cov, pr_web_cov, web_decreased, web_diff
+        )
+        output_warnings(warnings)
+        
+        # Generate comment
+        log("=== Generating comment ===")
+        comment = generate_comment(
+            base_ext_cov, pr_ext_cov, str(ext_decreased).lower(), ext_diff,
+            base_web_cov, pr_web_cov, str(web_decreased).lower(), web_diff
+        )
+        
+        # Save comment to file
+        with open("coverage_comment.md", "w") as f:
+            f.write(comment)
+        
+        # Post comment if PR number is provided
+        if args.pr_number:
+            log(f"=== Posting comment to PR #{args.pr_number} ===")
+            post_comment("coverage_comment.md", args.pr_number, args.repo, args.token)
+        
+        # Output results for GitHub Actions
+        output_github_results(
+            pr_ext_cov, pr_web_cov, base_ext_cov, base_web_cov,
+            ext_decreased, ext_diff, web_decreased, web_diff
+        )
+        
+    except Exception as e:
+        log(f"ERROR in process_coverage_workflow: {e}")
+        traceback.print_exc()
+        
+        # Try to output results even if there was an error
+        try:
+            output_github_results(
+                pr_ext_cov, pr_web_cov, base_ext_cov, base_web_cov,
+                ext_decreased, ext_diff, web_decreased, web_diff
+            )
+        except Exception as e2:
+            log(f"ERROR outputting GitHub results: {e2}")

.github/scripts/tests/coverage_check_test.py

@@ -0,0 +1,282 @@
+#!/usr/bin/env python3
+"""
+Tests for coverage_check script.
+"""
+
+import os
+import sys
+import unittest
+import subprocess
+import tempfile
+from unittest.mock import patch, MagicMock, call, mock_open
+
+# Add parent directory to path so we can import coverage modules
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+from coverage_check import extract_coverage, compare_coverage, set_verbose, generate_comment, post_comment, set_github_output
+from coverage_check.util import log, file_exists, get_file_size, list_directory
+
+
+class TestCoverage(unittest.TestCase):
+    # Class variables to store coverage files
+    temp_dir = None
+    extension_coverage_file = None
+    webview_coverage_file = None
+    
+    @classmethod
+    def setUpClass(cls):
+        """Set up test environment once for all tests."""
+        # Create temporary directory for test files
+        cls.temp_dir = tempfile.TemporaryDirectory()
+        cls.extension_coverage_file = os.path.join(cls.temp_dir.name, 'extension_coverage.txt')
+        cls.webview_coverage_file = os.path.join(cls.temp_dir.name, 'webview_coverage.txt')
+        
+        # Run actual tests to generate coverage reports
+        cls.generate_coverage_reports()
+        
+        # Verify files exist and are not empty
+        assert os.path.exists(cls.extension_coverage_file), \
+            f"Extension coverage file {cls.extension_coverage_file} does not exist"
+        assert os.path.getsize(cls.extension_coverage_file) > 0, \
+            f"Extension coverage file {cls.extension_coverage_file} is empty"
+        assert os.path.exists(cls.webview_coverage_file), \
+            f"Webview coverage file {cls.webview_coverage_file} does not exist"
+        assert os.path.getsize(cls.webview_coverage_file) > 0, \
+            f"Webview coverage file {cls.webview_coverage_file} is empty"
+
+    @classmethod
+    def tearDownClass(cls):
+        """Clean up test environment after all tests."""
+        if cls.temp_dir:
+            cls.temp_dir.cleanup()
+
+    @classmethod
+    def generate_coverage_reports(cls):
+        """Generate real coverage reports by running tests."""
+        log("Generating coverage reports (this may take a while)...")
+        
+        # Run extension tests with coverage
+        try:
+            # Get absolute paths
+            root_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), '../../..'))
+            webview_dir = os.path.join(root_dir, 'webview-ui')
+            
+            # Use xvfb-run on Linux
+            if sys.platform.startswith('linux'):
+                cmd = f"cd {root_dir} && xvfb-run -a npm run test:coverage > {cls.extension_coverage_file} 2>&1"
+            else:
+                cmd = f"cd {root_dir} && npm run test:coverage > {cls.extension_coverage_file} 2>&1"
+            
+            log("Running extension tests...")
+            log(f"Command: {cmd}")
+            result = subprocess.run(cmd, shell=True, check=False, capture_output=True, text=True)
+            log(f"Extension tests exit code: {result.returncode}")
+            
+            # Run webview tests with coverage
+            log("Running webview tests...")
+            cmd = f"cd {webview_dir} && npm run test:coverage > {cls.webview_coverage_file} 2>&1"
+            log(f"Command: {cmd}")
+            result = subprocess.run(cmd, shell=True, check=False, capture_output=True, text=True)
+            log(f"Webview tests exit code: {result.returncode}")
+            
+            # Verify files were created
+            if file_exists(cls.extension_coverage_file):
+                ext_size = get_file_size(cls.extension_coverage_file)
+                log(f"Extension coverage file created: {cls.extension_coverage_file} (size: {ext_size} bytes)")
+            else:
+                log(f"WARNING: Extension coverage file was not created: {cls.extension_coverage_file}")
+                
+            if file_exists(cls.webview_coverage_file):
+                web_size = get_file_size(cls.webview_coverage_file)
+                log(f"Webview coverage file created: {cls.webview_coverage_file} (size: {web_size} bytes)")
+            else:
+                log(f"WARNING: Webview coverage file was not created: {cls.webview_coverage_file}")
+            
+            log("Coverage reports generation completed.")
+        except Exception as e:
+            log(f"Error generating coverage reports: {e}")
+            import traceback
+            log(traceback.format_exc())
+            
+            # Create empty files if tests fail
+            log("Creating fallback coverage files...")
+            with open(cls.extension_coverage_file, 'w') as f:
+                f.write("No coverage data available")
+            with open(cls.webview_coverage_file, 'w') as f:
+                f.write("No coverage data available")
+
+    def test_extract_coverage(self):
+        """Test extract_coverage function with both extension and webview coverage."""
+        # Check if verbose mode is enabled
+        if '-v' in sys.argv or '--verbose' in sys.argv:
+            set_verbose(True)
+        
+        # Verify files exist before testing
+        self.assertTrue(file_exists(self.extension_coverage_file), 
+                       f"Extension coverage file does not exist: {self.extension_coverage_file}")
+        self.assertTrue(file_exists(self.webview_coverage_file), 
+                       f"Webview coverage file does not exist: {self.webview_coverage_file}")
+        
+        # Log file sizes
+        ext_size = get_file_size(self.extension_coverage_file)
+        web_size = get_file_size(self.webview_coverage_file)
+        log(f"Extension coverage file size: {ext_size} bytes")
+        log(f"Webview coverage file size: {web_size} bytes")
+        
+        # Test extension coverage
+        log("Testing extension coverage extraction...")
+        ext_coverage_pct = extract_coverage(self.extension_coverage_file, 'extension')
+        
+        # Check that coverage percentage is a float
+        self.assertIsInstance(ext_coverage_pct, float)
+        
+        # Check that coverage percentage is between 0 and 100
+        self.assertGreaterEqual(ext_coverage_pct, 0)
+        self.assertLessEqual(ext_coverage_pct, 100)
+        
+        # Log coverage percentage for debugging
+        log(f"Extension coverage: {ext_coverage_pct}%")
+        
+        # Test webview coverage
+        log("Testing webview coverage extraction...")
+        web_coverage_pct = extract_coverage(self.webview_coverage_file, 'webview')
+        
+        # Convert to float if it's an integer
+        if isinstance(web_coverage_pct, int):
+            web_coverage_pct = float(web_coverage_pct)
+        
+        # Check that coverage percentage is a float
+        self.assertIsInstance(web_coverage_pct, float)
+        
+        # Check that coverage percentage is between 0 and 100
+        self.assertGreaterEqual(web_coverage_pct, 0)
+        self.assertLessEqual(web_coverage_pct, 100)
+        
+        # Log coverage percentage for debugging
+        log(f"Webview coverage: {web_coverage_pct}%")
+
+    def test_compare_coverage(self):
+        """Test compare_coverage function."""
+        # Test with coverage increase
+        decreased, diff = compare_coverage(80, 90)
+        self.assertFalse(decreased)
+        self.assertEqual(diff, 10)
+        
+        # Test with coverage decrease
+        decreased, diff = compare_coverage(90, 80)
+        self.assertTrue(decreased)
+        self.assertEqual(diff, 10)
+        
+        # Test with no change
+        decreased, diff = compare_coverage(80, 80)
+        self.assertFalse(decreased)
+        self.assertEqual(diff, 0)
+
+    def test_generate_comment(self):
+        """Test generate_comment function."""
+        comment = generate_comment(
+            80, 90, 'false', 10,
+            70, 75, 'false', 5
+        )
+        
+        # Check that comment contains expected sections
+        self.assertIn('Coverage Report', comment)
+        self.assertIn('Extension Coverage', comment)
+        self.assertIn('Webview Coverage', comment)
+        self.assertIn('Overall Assessment', comment)
+        
+        # Check that comment contains coverage percentages
+        self.assertIn('Base branch: 80%', comment)
+        self.assertIn('PR branch: 90%', comment)
+        self.assertIn('Base branch: 70%', comment)
+        self.assertIn('PR branch: 75%', comment)
+        
+        # Check that comment contains correct assessment
+        self.assertIn('Coverage increased or remained the same', comment)
+        self.assertIn('Test coverage has been maintained or improved', comment)
+
+    @patch('coverage_check.requests.get')
+    @patch('coverage_check.requests.post')
+    @patch('coverage_check.requests.patch')
+    def test_post_comment_new(self, mock_patch, mock_post, mock_get):
+        """Test post_comment function when creating a new comment."""
+        # Create a temporary comment file
+        comment_file = os.path.join(self.temp_dir.name, 'comment.md')
+        with open(comment_file, 'w') as f:
+            f.write('<!-- COVERAGE_REPORT -->\nTest comment')
+        
+        # Mock the API responses
+        mock_get.return_value = MagicMock(status_code=200, json=lambda: [])
+        mock_post.return_value = MagicMock(status_code=201)
+        
+        # Test post_comment function
+        post_comment(comment_file, '123', 'owner/repo', 'token')
+        
+        # Check that the correct API calls were made
+        mock_get.assert_called_once()
+        mock_post.assert_called_once()
+        mock_patch.assert_not_called()
+
+    @patch('coverage_check.requests.get')
+    @patch('coverage_check.requests.post')
+    @patch('coverage_check.requests.patch')
+    def test_post_comment_update(self, mock_patch, mock_post, mock_get):
+        """Test post_comment function when updating an existing comment."""
+        # Create a temporary comment file
+        comment_file = os.path.join(self.temp_dir.name, 'comment.md')
+        with open(comment_file, 'w') as f:
+            f.write('<!-- COVERAGE_REPORT -->\nTest comment')
+        
+        # Mock the API responses
+        mock_get.return_value = MagicMock(
+            status_code=200, 
+            json=lambda: [{'id': 456, 'body': '<!-- COVERAGE_REPORT -->\nOld comment'}]
+        )
+        mock_patch.return_value = MagicMock(status_code=200)
+        
+        # Test post_comment function
+        post_comment(comment_file, '123', 'owner/repo', 'token')
+        
+        # Check that the correct API calls were made
+        mock_get.assert_called_once()
+        mock_patch.assert_called_once()
+        mock_post.assert_not_called()
+
+    def test_set_github_output(self):
+        """Test set_github_output function."""
+        # Capture stdout
+        with patch('sys.stdout', new=MagicMock()) as mock_stdout:
+            # Mock environment without GITHUB_OUTPUT
+            with patch.dict('os.environ', {}, clear=True):
+                set_github_output('test_name', 'test_value')
+                
+                # Check that the correct output was printed to stdout
+                mock_stdout.assert_has_calls([
+                    # GitHub Actions output format (deprecated method)
+                    call.write('::set-output name=test_name::test_value\n'),
+                    call.flush(),
+                    # Human readable format
+                    call.write('test_name: test_value\n'),
+                    call.flush()
+                ], any_order=False)
+                
+                # Reset mock for next test
+                mock_stdout.reset_mock()
+            
+            # Test with GITHUB_OUTPUT environment variable
+            with patch.dict('os.environ', {'GITHUB_OUTPUT': '/tmp/github_output'}), \
+                 patch('builtins.open', mock_open()) as mock_file:
+                set_github_output('test_name', 'test_value')
+                
+                # Check that file was written to
+                mock_file.assert_called_once_with('/tmp/github_output', 'a')
+                mock_file().write.assert_called_once_with('test_name=test_value\n')
+                
+                # Check that human readable output was printed
+                mock_stdout.assert_has_calls([
+                    call.write('test_name: test_value\n'),
+                    call.flush()
+                ], any_order=False)
+
+
+if __name__ == '__main__':
+    unittest.main()

.github/workflows/changeset-converter.yml

@@ -2,6 +2,7 @@ name: Changeset Converter
 run-name: Changeset Conversion
 
 on:
+    workflow_dispatch:
     pull_request:
         types: [closed]
 
@@ -13,16 +14,36 @@ env:
 jobs:
     # Job 1: Create version bump PR when changesets are merged to main
     changeset-pr-version-bump:
-        if: >
-            github.event_name == 'pull_request' &&
-            github.event.pull_request.merged == true &&
-            github.event.pull_request.base.ref == 'main' &&
-            github.actor != 'github-actions'
+        if: |
+            github.event_name == 'workflow_dispatch' ||
+            (
+                github.event_name == 'pull_request' &&
+                github.event.pull_request.merged == true &&
+                github.event.pull_request.base.ref == 'main' &&
+                github.actor != 'github-actions'
+            )
         runs-on: ubuntu-latest
         permissions:
             contents: write
             pull-requests: write
         steps:
+            - name: Check user for team affiliation
+              id: team_check
+              if: github.event_name == 'workflow_dispatch'
+              uses: morfien101/actions-authorized-user@4a3cfbf0bcb3cafe4a71710a278920c5d94bb38b
+              with:
+                  username: ${{ github.actor }}
+                  team: "deployer"
+                  github_token: ${{ secrets.GITHUB_TOKEN }}
+
+            - name: Check if user is authorized
+              if: github.event_name == 'workflow_dispatch'
+              run: |
+                  if [ "${{ steps.team_check.outputs.authorized }}" != "true" ]; then
+                      echo "User is not authorized to run this workflow."
+                      exit 1
+                  fi
+
             - name: Git Checkout
               uses: actions/checkout@v4
               with:

.github/workflows/codespell.yml

@@ -0,0 +1,27 @@
+# Codespell configuration is within .codespellrc
+---
+name: Codespell
+
+on:
+    push:
+        branches: [main]
+    pull_request:
+        branches: [main]
+
+permissions:
+    contents: read
+
+jobs:
+    codespell:
+        name: Check for spelling errors
+        runs-on: ubuntu-latest
+
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v4
+            - name: Annotate locations with typos
+              uses: codespell-project/codespell-problem-matcher@v1
+            - name: Codespell
+              uses: codespell-project/actions-codespell@v2
+              with:
+                  only_warn: 1

.github/workflows/pull-request.yml

@@ -0,0 +1,177 @@
+name: Create Linear Issue on Pull Request
+
+on:
+    workflow_dispatch:
+    pull_request:
+        branches: [main]
+        types: [opened]
+
+permissions:
+    pull-requests: write
+
+jobs:
+    create-linear-issue-on-pull-request:
+        runs-on: ubuntu-latest
+        steps:
+            - name: Check for existing Linear link
+              id: check-linear
+              uses: actions/github-script@v6
+              with:
+                  result-encoding: string
+                  script: |
+                      const pr = context.payload.pull_request;
+                      // 1) PR body
+                      if (/https?:\/\/linear\.app/.test(pr.body||"")) {
+                        return "true";
+                      }
+                      // 2) Any linked GitHub issues?
+                      const res = await github.graphql(
+                        `query($owner:String!,$repo:String!,$prNumber:Int!){
+                           repository(owner:$owner,name:$repo){
+                             pullRequest(number:$prNumber){
+                               closingIssuesReferences(first:10){
+                                 nodes{number}
+                               }
+                             }
+                           }
+                         }`,
+                        {
+                          owner: context.repo.owner,
+                          repo: context.repo.repo,
+                          prNumber: pr.number
+                        }
+                      );
+                      for (const {number} of res.repository.pullRequest.closingIssuesReferences.nodes) {
+                        const comments = await github.rest.issues.listComments({
+                          owner: context.repo.owner,
+                          repo: context.repo.repo,
+                          issue_number: number
+                        });
+                        if (comments.data.some(c=>/https?:\/\/linear\.app/.test(c.body))) {
+                          return "true";
+                        }
+                      }
+                      return "false";
+
+            - name: Find or create Linear issue via GraphQL
+              if: steps.check-linear.outputs.result == 'false'
+              id: linear
+              uses: actions/github-script@v6
+              env:
+                  LINEAR_API_KEY: ${{ secrets.LINEAR_API_KEY }}
+              with:
+                  result-encoding: string
+                  script: |
+                      const API = 'https://api.linear.app/graphql';
+                      const apiKey = process.env.LINEAR_API_KEY;
+
+                      // Check if API key exists
+                      if (!apiKey) {
+                        core.setFailed('LINEAR_API_KEY is not set. Please add it to your repository secrets.');
+                        core.setOutput('error', 'true');
+                        core.setOutput('error-message', 'LINEAR_API_KEY is not set. Please add it to your repository secrets.');
+                        return;
+                      }
+
+                      // Helper to call Linear with error handling
+                      async function gql(q, v) {
+                        try {
+                          const r = await fetch(API, {
+                            method:'POST',
+                            headers:{
+                              'Content-Type':'application/json',
+                              'Authorization': apiKey
+                            },
+                            body: JSON.stringify({ query: q, variables: v })
+                          });
+                          
+                          if (!r.ok) {
+                            throw new Error(`Linear API responded with status ${r.status}: ${await r.text()}`);
+                          }
+                          
+                          const json = await r.json();
+                          
+                          // Check for GraphQL errors
+                          if (json.errors && json.errors.length > 0) {
+                            const errorMessages = json.errors.map(e => e.message).join(', ');
+                            throw new Error(`Linear GraphQL errors: ${errorMessages}`);
+                          }
+                          
+                          return json.data;
+                        } catch (error) {
+                          core.error(`Error calling Linear API: ${error.message}`);
+                          throw error;
+                        }
+                      }
+
+                      try {
+                        // 1) Set team ID
+                        const teamId = "19b9c1b2-5f58-498c-b1bf-23ee8f52a677"
+
+                        // 2) Look for existing issue by PR URL
+                        const pr = context.payload.pull_request;
+                        const searchData = await gql(
+                          `query($team:ID!,$q:String!){
+                              issues(filter: { team: { id: { eq: $team } } attachments: { some: { url: { eq: $q } } } }){nodes{id,url}}
+                            }`,
+                          { team: teamId, q: pr.html_url }
+                        );
+                        let issue = searchData.issues.nodes[0];
+
+                        // 3) Create if missing
+                        if (!issue) {
+                          const createData = await gql(
+                            `mutation($input:IssueCreateInput!){
+                                issueCreate(input:$input){issue{id,url}}
+                              }`,
+                            {
+                              input: {
+                                teamId,
+                                title: `[GITHUB] ${pr.title}`,
+                                description: `${pr.body||''}\n\n${pr.html_url}`,
+                                stateId: "4d9bcba2-6712-47e3-b577-6ec1ee023dc2",
+                                labelIds: ["504e7d60-5037-483f-a9b8-7e298bdf116f"]
+                              }
+                            }
+                          );
+                          issue = createData.issueCreate.issue;
+                        }
+
+                        // Set output for next steps
+                        core.setOutput('linear-issue-url', issue.url);
+                        core.setOutput('error', 'false');
+                      } catch (error) {
+                        core.setOutput('error', 'true');
+                        core.setOutput('error-message', error.message);
+                        core.setFailed(`Failed to create or find Linear issue: ${error.message}`);
+                      }
+
+            - name: Comment PR with Linear link
+              if: steps.check-linear.outputs.result == 'false'
+              uses: actions/github-script@v6
+              with:
+                  script: |
+                      const pr = context.payload.pull_request;
+                      const url = `${{ steps.linear.outputs.linear-issue-url }}`;
+                      const body = `🔗 Linear issue created: ${url}`;
+                      // Fetch existing comments
+                      const { data: comments } = await github.rest.issues.listComments({
+                        ...context.repo,
+                        issue_number: pr.number
+                      });
+                      const botComment = comments.find(c =>
+                        c.user.type === "Bot" && c.body.startsWith("🔗 Linear issue created:")
+                      );
+                      if (botComment) {
+                        await github.rest.issues.updateComment({
+                          ...context.repo,
+                          comment_id: botComment.id,
+                          body
+                        });
+                      } else {
+                        await github.rest.issues.createComment({
+                          ...context.repo,
+                          issue_number: pr.number,
+                          body
+                        });
+                      }

.github/workflows/test.yml

@@ -23,7 +23,18 @@ jobs:
             - name: Setup Node.js environment
               uses: actions/setup-node@v4
               with:
-                  node-version: 20.15.1
+                  node-version: 22
+
+            # Setup Python for coverage script
+            - name: Setup Python
+              uses: actions/setup-python@v4
+              with:
+                  python-version: "3.10"
+
+            - name: Install Python dependencies
+              run: |
+                  python -m pip install --upgrade pip
+                  pip install requests
 
             # Cache root dependencies - only reuse if package-lock.json exactly matches
             - name: Cache root dependencies
@@ -58,5 +69,130 @@ jobs:
             - name: Prettier / Format Check
               run: npm run format
 
-            - name: Extension Tests
-              run: xvfb-run -a npm run test
+            # Build the extension before running tests
+            - name: Build Tests and Extension
+              run: npm run pretest
+
+            - name: Unit Tests
+              run: npm run test:unit
+
+            # Run extension tests with coverage
+            - name: Extension Tests with Coverage
+              id: extension_coverage
+              continue-on-error: true
+              run: |
+                  xvfb-run -a npm run test:coverage > extension_coverage.txt 2>&1
+                  PYTHONPATH=.github/scripts python -m coverage_check extract-coverage extension_coverage.txt --type=extension --github-output --verbose
+
+            # Run webview tests with coverage
+            - name: Webview Tests with Coverage
+              id: webview_coverage
+              continue-on-error: true
+              run: |
+                  cd webview-ui
+                  # Ensure coverage dependency is installed
+                  npm install --no-save @vitest/coverage-v8
+                  npm run test:coverage > webview_coverage.txt 2>&1 || true
+                  cd ..
+                  PYTHONPATH=.github/scripts python -m coverage_check extract-coverage webview-ui/webview_coverage.txt --type=webview --github-output --verbose
+
+            # Save coverage reports as artifacts (workflow-scoped)
+            - name: Save Coverage Reports
+              uses: actions/upload-artifact@v4
+              with:
+                  name: pr-coverage-reports
+                  path: |
+                      extension_coverage.txt
+                      webview-ui/webview_coverage.txt
+                  retention-period: workflow # Artifacts are automatically deleted when the workflow completes
+
+            # Set the check as failed if any of the tests failed
+            - name: Check for test failures
+              run: |
+                  # Check if any of the test steps failed
+                  # https://docs.github.com/en/actions/writing-workflows/choosing-what-your-workflow-does/accessing-contextual-information-about-workflow-runs#steps-context
+                  if [ "${{ steps.extension_coverage.outcome }}" != "success" ] || [ "${{ steps.webview_coverage.outcome }}" != "success" ]; then
+                      echo "Tests failed."
+                      cat extension_coverage.txt
+                      cat webview-ui/webview_coverage.txt
+                      exit 1
+                  fi
+
+    coverage:
+        needs: test
+        runs-on: ubuntu-latest
+        # Only run on PRs to main branch
+        if: github.event_name == 'pull_request' && github.base_ref == 'main'
+        steps:
+            - name: Checkout code
+              uses: actions/checkout@v4
+              with:
+                  fetch-depth: 0 # Fetch all history for accurate comparison
+
+            # Setup Python for coverage script
+            - name: Setup Python
+              uses: actions/setup-python@v4
+              with:
+                  python-version: "3.10"
+
+            - name: Install Python dependencies
+              run: |
+                  python -m pip install --upgrade pip
+                  pip install requests
+
+            - name: Setup Node.js environment
+              uses: actions/setup-node@v4
+              with:
+                  node-version: 22
+
+            # Cache root dependencies - only reuse if package-lock.json exactly matches
+            - name: Cache root dependencies
+              uses: actions/cache@v4
+              id: root-cache
+              with:
+                  path: node_modules
+                  key: ${{ runner.os }}-npm-${{ hashFiles('package-lock.json') }}
+
+            # Cache webview-ui dependencies - only reuse if package-lock.json exactly matches
+            - name: Cache webview-ui dependencies
+              uses: actions/cache@v4
+              id: webview-cache
+              with:
+                  path: webview-ui/node_modules
+                  key: ${{ runner.os }}-npm-webview-${{ hashFiles('webview-ui/package-lock.json') }}
+
+            - name: Install root dependencies
+              if: steps.root-cache.outputs.cache-hit != 'true'
+              run: npm ci
+
+            - name: Install webview-ui dependencies
+              if: steps.webview-cache.outputs.cache-hit != 'true'
+              run: cd webview-ui && npm ci
+
+            # Build the extension before running tests
+            - name: Build Extension
+              run: npm run compile
+
+            # Download coverage artifacts from test job
+            - name: Download Coverage Reports
+              uses: actions/download-artifact@v4
+              with:
+                  name: pr-coverage-reports
+                  path: . # Download to root directory to match expected paths
+
+            # Process coverage workflow
+            - name: Process coverage workflow
+              id: coverage
+              run: |
+                  # Extract PR number from GITHUB_REF
+                  PR_NUMBER=$(echo "$GITHUB_REF" | sed -e 's/refs\/pull\///' -e 's/\/merge//')
+
+                  # Run the coverage workflow from root directory
+                  PYTHONPATH=.github/scripts python -m coverage_check process-workflow \
+                    --base-branch ${{ github.base_ref }} \
+                    --pr-number $PR_NUMBER \
+                    --repo $GITHUB_REPOSITORY \
+                    --token ${{ secrets.GITHUB_TOKEN }} \
+                    --verbose
+              env:
+                  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -1,5 +1,4 @@
 out
-coverage
 dist
 node_modules
 tmp
@@ -10,4 +9,13 @@ tmp
 
 pnpm-lock.yaml
 
-.clineignore
+.clineignore
+.venv
+.actrc
+
+# Ignore coverage directories and files
+coverage
+# But don't ignore the coverage scripts in .github/scripts/
+!.github/scripts/coverage/
+
+*evals.env

.mocharc.json

@@ -0,0 +1,6 @@
+{
+	"extension": ["ts"],
+	"spec": "src/**/__tests__/*.ts",
+	"require": ["ts-node/register", "source-map-support/register", "./src/test/requires.ts"],
+	"recursive": true
+}

.vscode-test.mjs

@@ -6,6 +6,10 @@ export default defineConfig({
 	mocha: {
 		ui: "bdd",
 		timeout: 20000, // Maximum time (in ms) that a test can run before failing
+		/** Set up alias path resolution during tests
+		 * @See {@link file://./test-setup.js}
+		 */
+		require: ["./test-setup.js"],
 	},
 	workspaceFolder: "test-workspace",
 	version: "stable",

.vscode/launch.json

@@ -9,7 +9,7 @@
 			"name": "Run Extension",
 			"type": "extensionHost",
 			"request": "launch",
-			"args": ["--extensionDevelopmentPath=${workspaceFolder}"],
+			"args": ["--extensionDevelopmentPath=${workspaceFolder}", "--disable-workspace-trust", "${workspaceFolder}"],
 			"outFiles": ["${workspaceFolder}/dist/**/*.js"],
 			"preLaunchTask": "${defaultBuildTask}",
 			"env": {

.vscode/tasks.json

@@ -4,16 +4,45 @@
 	"version": "2.0.0",
 	"tasks": [
 		{
-			"label": "watch",
-			"dependsOn": ["npm: build:webview", "npm: dev:webview", "npm: watch:tsc", "npm: watch:esbuild"],
+			"label": "npm: protos",
+			"type": "npm",
+			"script": "protos",
+			"problemMatcher": [],
+			"isBackground": false,
 			"presentation": {
-				"reveal": "never"
+				"reveal": "always"
+			},
+			"options": {
+				"env": {
+					"IS_DEV": "true"
+				}
+			}
+		},
+		{
+			"label": "watch",
+			"dependsOn": ["npm: protos", "npm: build:webview", "npm: dev:webview", "npm: watch:tsc", "npm: watch:esbuild"],
+			"presentation": {
+				"reveal": "always"
 			},
 			"group": {
 				"kind": "build",
 				"isDefault": true
 			}
 		},
+		{
+			"label": "watch:test",
+			"dependsOn": [
+				"npm: protos",
+				"npm: build:webview:test",
+				"npm: dev:webview",
+				"npm: watch:tsc",
+				"npm: watch:esbuild:test"
+			],
+			"presentation": {
+				"reveal": "always"
+			},
+			"group": "build"
+		},
 		{
 			"type": "npm",
 			"script": "build:webview",
@@ -21,10 +50,10 @@
 			"problemMatcher": [],
 			"isBackground": true,
 			"label": "npm: build:webview",
+			"dependsOn": ["npm: protos"],
 			"presentation": {
 				"group": "watch",
-				"reveal": "never",
-				"close": true
+				"reveal": "always"
 			},
 			"options": {
 				"env": {
@@ -32,6 +61,25 @@
 				}
 			}
 		},
+		{
+			"type": "npm",
+			"script": "build:webview:test",
+			"group": "build",
+			"problemMatcher": [],
+			"isBackground": true,
+			"label": "npm: build:webview:test",
+			"dependsOn": ["npm: protos"],
+			"presentation": {
+				"group": "watch",
+				"reveal": "always"
+			},
+			"options": {
+				"env": {
+					"IS_DEV": "true",
+					"IS_TEST": "true"
+				}
+			}
+		},
 		{
 			"type": "npm",
 			"script": "dev:webview",
@@ -55,10 +103,10 @@
 			],
 			"isBackground": true,
 			"label": "npm: dev:webview",
+			"dependsOn": ["npm: protos"],
 			"presentation": {
 				"group": "watch",
-				"reveal": "never",
-				"close": true
+				"reveal": "always"
 			},
 			"options": {
 				"env": {
@@ -73,10 +121,34 @@
 			"problemMatcher": "$esbuild-watch",
 			"isBackground": true,
 			"label": "npm: watch:esbuild",
+			"dependsOn": ["npm: protos"],
 			"presentation": {
 				"group": "watch",
-				"reveal": "never",
-				"close": true
+				"reveal": "always"
+			},
+			"options": {
+				"env": {
+					"IS_DEV": "true"
+				}
+			}
+		},
+		{
+			"type": "npm",
+			"script": "watch:esbuild:test",
+			"group": "build",
+			"problemMatcher": "$esbuild-watch",
+			"isBackground": true,
+			"label": "npm: watch:esbuild:test",
+			"dependsOn": ["npm: protos"],
+			"presentation": {
+				"group": "watch",
+				"reveal": "always"
+			},
+			"options": {
+				"env": {
+					"IS_DEV": "true",
+					"IS_TEST": "true"
+				}
 			}
 		},
 		{
@@ -86,10 +158,10 @@
 			"problemMatcher": "$tsc-watch",
 			"isBackground": true,
 			"label": "npm: watch:tsc",
+			"dependsOn": ["npm: protos"],
 			"presentation": {
 				"group": "watch",
-				"reveal": "never",
-				"close": true
+				"reveal": "always"
 			}
 		},
 		{
@@ -97,15 +169,16 @@
 			"script": "watch-tests",
 			"problemMatcher": "$tsc-watch",
 			"isBackground": true,
+			"dependsOn": ["npm: protos"],
 			"presentation": {
-				"reveal": "never",
+				"reveal": "always",
 				"group": "watchers"
 			},
 			"group": "build"
 		},
 		{
 			"label": "tasks: watch-tests",
-			"dependsOn": ["npm: watch", "npm: watch-tests"],
+			"dependsOn": ["npm: protos", "npm: watch", "npm: watch-tests"],
 			"problemMatcher": []
 		},
 		{

CHANGELOG.md

@@ -1,5 +1,145 @@
 # Changelog
 
+## [3.13.3]
+
+-   Add download counts to MCP marketplace items
+-   Add `/compact` command
+-   Add prompt caching to gemini models in cline / openrouter providers
+-   Add tooltips to bottom row menu
+
+## [3.13.2]
+
+-   Add Gemini 2.5 Flash model to Vertex and Gemini Providers (Thanks monotykamary!)
+-   Add Caching to gemini provider (Thanks arafatkatze!)
+-   Add thinking budget support to Gemini Models (Thanks monotykamary!)
+-   Add !include .file directive support for .clineignore (Thanks watany-dev!)
+-   Improve slash command functionality
+-   Improve prompting for new task tool
+-   Fix o1 temperature being passed to the azure api (Thanks treeleaves30760!)
+-   Fix to make "add new rule file" button functional
+-   Fix Ollama provider timeout, allowing for a larger loading time (Thanks suvarchal!)
+-   Fix Non-UTF-8 File Handling: Improve Encoding Detection to Prevent Garbled Text and Binary Misclassification (Thanks yt3trees!)
+-   Fix settings to not reset by changing providers
+-   Fix terminal outputs missing commas
+-   Fix terminal errors caused by starting non-alphanumeric outputs
+-   Fix auto approve settings becoming unset
+-   Fix Mermaid syntax error in documentation (Thanks tuki0918!)
+-   Remove supportsComputerUse restriction and support browser use through any model that supports images (Thanks arafatkatze!)
+
+## [3.13.1]
+
+-   Fix bug where task cancellation during thinking stream would result in error state
+
+## [3.13.0]
+
+-   Add Cline rules popover under the chat field, allowing you to easily add, enable & disable workspace level or global rule files
+-   Add new slash command menu letting you type “/“ to do quick actions like creating new tasks
+-   Add ability to edit past messages, with options to restore your workspace back to that point
+-   Allow sending a message when selecting an option provided by the question or plan tool
+-   Add command to jump to Cline's chat input
+-   Add support for OpenAI o3 & 4o-mini (Thanks @PeterDaveHello and @arafatkatze!)
+-   Add baseURL option for Google Gemini provider (Thanks @owengo and @olivierhub!)
+-   Add support for Azure's DeepSeek model. (Thanks @yt3trees!)
+-   Add ability for models that support it to receive image responses from MCP servers (Thanks @rikaaa0928!)
+-   Improve search and replace diff editing by making it more flexible with models that fail to follow structured output instructions. (Thanks @chi-cat!)
+-   Add detection of Ctrl+C termination in terminal, improving output reading issues
+-   Fix issue where some commands with large output would cause UI to freeze
+-   Fix token usage tracking issues with vertex provider (Thanks @mzsima!)
+-   Fix issue with xAI reasoning content not being parsed (Thanks @mrubens!)
+
+## [3.12.3]
+
+-   Add copy button to MermaidBlock component (Thanks @cacosub7!)
+-   Add the ability to fetch from global cline rules files
+-   Add icon to indicate when a file outside of the users workspace is edited
+
+## [3.12.2]
+
+-   Add gpt-4.1
+
+## [3.12.1]
+
+-   Use visual checkpoint indicator to make it clear when checkpoints are created
+-   Big shoutout to @samuel871211 for numerous code quality improvements, refactoring contributions, and webview performance improvements!
+-   Use improved context manager
+
+## [3.12.0]
+
+-   Add favorite toggles for models when using the Cline & OpenRouter providers
+-   Add auto-approve options for edits/reads outside of the workspace
+-   Improve diff editing animation for large files
+-   Add indicator showing number of diff edits when Cline edits a file
+-   Add streaming support and reasoning effort option to xAI's Grok 3 Mini
+-   Add settings button to MCP popover to easily modify installed servers
+-   Fix bug where browser tool actions would show unparsed results in the chat view
+-   Fix issue with new checkpoints popover hiding too quickly
+-   Fix duplicate checkpoints bug
+-   Improve Ollama provider with retry mechanism, timeout handling, and improved error handling (thanks suvarchal!)
+
+## [3.11.0]
+
+-   Redesign checkpoint UI to declutter chat view by using a subtle indicator line that expands to a popover on hover, with a new date indicator for when it was created
+-   Add support for xAI's provider's Grok 3 models
+-   Add more robust error tracking for users opted in to telemetry (thank you for helping us make Cline better!)
+
+## [3.10.1]
+
+-   Add CMD+' keyboard shortcut to add selected text to Cline
+-   Cline now auto focuses the text field when using 'Add to Cline' shortcut
+-   Add new 'Create New Task' tool to let Cline start a new task autonomously!
+-   Fix Mermaid diagram issues
+-   Fix Gemini provider cost calculation to take new tiered pricing structure into account
+
+## [3.10.0]
+
+-   Add setting to let browser tool use local Chrome via remote debugging, enabling session-based browsing. Replaces sessionless Chromium, unlocking debugging and productivity workflows tied to your real browser state.
+-   Add new auto-approve option to approve _ALL_ commands (use at your own risk!)
+-   Add modal in the chat area to more easily enable or disable MCP servers
+-   Add drag and drop of file/folders into cline chat (Thanks eljapi!)
+-   Add prompt caching for LiteLLM + Claude (Thanks sammcj!)
+-   Add Improved context management
+-   Fix MCP auto approve toggle issues being out of sync with settings
+
+## [3.9.2]
+
+-   Add recommended models for Cline provider
+-   Add ability to detect when user edits files manually so Cline knows to re-read, leading to reduced diff edit errors
+-   Add improvements to file mention searching for faster searching
+-   Add scoring logic to file mentions to sort and exclude results based on relevance
+-   Add Support for Bytedance Doubao (Thanks Tunixer!)
+-   Fix to prevent duplicate BOM (Thanks bamps53!)
+
+## [3.9.1]
+
+-   Add Gemini 2.5 Pro Preview 03-25 to Google Provider
+
+## [3.9.0]
+
+-   Add Enable extended thinking for LiteLLM provider (Thanks @jorgegarciarey!)
+-   Add a tab for configuring local MCP Servers
+-   Fix issue with DeepSeek API provider token counting + context management
+-   Fix issues with checkpoints hanging under certain conditions
+
+## [3.8.6]
+
+-   Add UI for adding remote servers
+-   Add Mentions Feature Guide and update related documentation
+-   Fix bug where menu would open in sidebar and open tab
+-   Fix issue with Cline accounts not showing user info in popout tabs
+-   Fix bug where menu buttons wouldn't open view in sidebar
+
+## [3.8.5]
+
+-   Add support for remote MCP Servers using SSE
+-   Add gemini-2.5-pro-exp-03-25 to Vertex AI (thanks @arri-cc!)
+-   Add access to history, mcp, and new task buttons in popout view
+-   Add task feedback telemetry (thumbs up/down on task completion)
+-   Add toggle disabled for remote servers
+-   Move the MCP Restart and Delete buttons and add an auto-approve all toggle
+-   Update Requestly UX for model selection (thanks @arafatkatze!)
+-   Add escape for html content for gemini when running commands
+-   Improve search and replace edit failure behaviors
+
 ## [3.8.4]
 
 -   Add Sambanova Deepseek-V3-0324
@@ -210,8 +350,8 @@
 ## [3.1.0]
 
 -   Added checkpoints: Snapshots of workspace are automatically created whenever Cline uses a tool
-    -   Compare changes: Hover over any tool use to see a diff between the snapshot and current workspace state
-    -   Restore options: Choose to restore just the task state, just the workspace files, or both
+-   Compare changes: Hover over any tool use to see a diff between the snapshot and current workspace state
+-   Restore options: Choose to restore just the task state, just the workspace files, or both
 -   New 'See new changes' button appears after task completion, providing an overview of all workspace changes
 -   Task header now shows disk space usage with a delete button to help manage snapshot storage
 
@@ -393,10 +533,10 @@
 ## [1.8.0]
 
 -   You can now use '@' in the textarea to add context!
-    -   @url: Paste in a URL for the extension to fetch and convert to markdown, useful when you want to give Claude the latest docs!
-    -   @problems: Add workspace errors and warnings for Claude to fix, no more back-and-forth about debugging
-    -   @file: Adds a file's contents so you don't have to waste API requests approving read file (+ type to search files)
-    -   @folder: Adds folder's files all at once to speed up your workflow even more
+-   @url: Paste in a URL for the extension to fetch and convert to markdown, useful when you want to give Claude the latest docs!
+-   @problems: Add workspace errors and warnings for Claude to fix, no more back-and-forth about debugging
+-   @file: Adds a file's contents so you don't have to waste API requests approving read file (+ type to search files)
+-   @folder: Adds folder's files all at once to speed up your workflow even more
 
 ## [1.7.0]
 
@@ -443,7 +583,7 @@
 -   Adds "Always allow read-only operations" setting to let Claude read files and view directories without needing approval (off by default)
 -   Implement sliding window context management to keep tasks going past 200k tokens
 -   Adds Google Cloud Vertex AI support and updates Claude 3.5 Sonnet max output to 8192 tokens for all providers.
--   Improves system prompt to gaurd against lazy edits (less "//rest of code here")
+-   Improves system prompt to guard against lazy edits (less "//rest of code here")
 
 ## [1.3.0]
 

README.md

@@ -24,7 +24,7 @@ English | <a href="https://github.com/cline/cline/blob/main/locales/es/README.md
 <a href="https://github.com/cline/cline/discussions/categories/feature-requests?discussions_q=is%3Aopen+category%3A%22Feature+Requests%22+sort%3Atop" target="_blank"><strong>Feature Requests</strong></a>
 </td>
 <td align="center">
-<a href="https://docs.cline.bot/getting-started/getting-started-new-coders" target="_blank"><strong>Getting Started</strong></a>
+<a href="https://docs.cline.bot/getting-started/for-new-coders" target="_blank"><strong>Getting Started</strong></a>
 </td>
 </tbody>
 </table>

docs/README.md

@@ -18,6 +18,7 @@ Welcome to the Cline documentation - your comprehensive guide to using and exten
 -   **Understand Cline's capabilities:**
 
     -   [Cline Tools Guide](tools/cline-tools-guide.md)
+    -   [Mentions Feature Guide](tools/mentions-guide.md)
 
 -   **Extend Cline with MCP Servers:**
     -   [MCP Overview](mcp/README.md)

docs/architecture/extension-architecture.mmd

@@ -1,41 +1,67 @@
-graph TB
-    subgraph VSCode Extension Host
-        subgraph Core Extension
-            ExtensionEntry[Extension Entry<br/>src/extension.ts]
-            ClineProvider[ClineProvider<br/>src/core/webview/ClineProvider.ts]
-            ClineClass[Cline Class<br/>src/core/Cline.ts]
-            GlobalState[VSCode Global State]
-            SecretsStorage[VSCode Secrets Storage]
+flowchart TB
+    subgraph "VSCode Extension Host"
+        subgraph "Core Extension"
+            ExtensionEntry["Extension Entry<br/>src/extension.ts"]
+            WebviewProvider["WebviewProvider<br/>src/core/webview/index.ts"]
+            Controller["Controller<br/>src/core/controller/index.ts"]
+            Task["Task<br/>src/core/task/index.ts"]
+            GlobalState["VSCode Global State"]
+            SecretsStorage["VSCode Secrets Storage"]
+            McpHub["McpHub<br/>src/services/mcp/McpHub.ts"]
         end
 
-        subgraph Webview UI
-            WebviewApp[React App<br/>webview-ui/src/App.tsx]
-            ExtStateContext[ExtensionStateContext<br/>webview-ui/src/context/ExtensionStateContext.tsx]
-            ReactComponents[React Components]
+        subgraph "Webview UI"
+            WebviewApp["React App<br/>webview-ui/src/App.tsx"]
+            ExtStateContext["ExtensionStateContext<br/>webview-ui/src/context/ExtensionStateContext.tsx"]
+            ReactComponents["React Components"]
         end
 
-        subgraph Storage
-            TaskStorage[Task Storage<br/>Per-Task Files & History]
-            CheckpointSystem[Git-based Checkpoints]
+        subgraph "Storage"
+            TaskStorage["Task Storage<br/>Per-Task Files & History"]
+            CheckpointSystem["Git-based Checkpoints"]
+        end
+
+        subgraph "API Providers"
+            AnthropicAPI["Anthropic"]
+            OpenRouterAPI["OpenRouter"]
+            BedrockAPI["AWS Bedrock"]
+            OtherAPIs["Other Providers"]
+        end
+
+        subgraph "MCP Servers"
+            ExternalMcpServers["External MCP Servers"]
         end
     end
 
     %% Core Extension Data Flow
-    ExtensionEntry --> ClineProvider
-    ClineProvider --> ClineClass
-    ClineClass --> GlobalState
-    ClineClass --> SecretsStorage
-    ClineClass --> TaskStorage
-    ClineClass --> CheckpointSystem
+    ExtensionEntry --> WebviewProvider
+    WebviewProvider --> Controller
+    Controller --> Task
+    Controller --> McpHub
+    Task --> GlobalState
+    Task --> SecretsStorage
+    Task --> TaskStorage
+    Task --> CheckpointSystem
+    Task --> |"API Requests"| AnthropicAPI
+    Task --> |"API Requests"| OpenRouterAPI
+    Task --> |"API Requests"| BedrockAPI
+    Task --> |"API Requests"| OtherAPIs
+    McpHub --> |"Connects to"| ExternalMcpServers
+    Task --> |"Uses"| McpHub
 
     %% Webview Data Flow
     WebviewApp --> ExtStateContext
     ExtStateContext --> ReactComponents
 
     %% Bidirectional Communication
-    ClineProvider <-->|postMessage| ExtStateContext
+    WebviewProvider <--> |"postMessage"| ExtStateContext
 
-    style GlobalState fill:#ff0066,stroke:#333,stroke-width:2px,color:#ffffff
-    style SecretsStorage fill:#ff0066,stroke:#333,stroke-width:2px,color:#ffffff
-    style ExtStateContext fill:#0066ff,stroke:#333,stroke-width:2px,color:#ffffff
-    style ClineProvider fill:#00cc66,stroke:#333,stroke-width:2px,color:#ffffff
+    classDef vscodeState fill:#f9f,stroke:#333,stroke-width:2px
+    classDef contextClass fill:#bbf,stroke:#333,stroke-width:2px
+    classDef providerClass fill:#bfb,stroke:#333,stroke-width:2px
+    classDef apiClass fill:#fdb,stroke:#333,stroke-width:2px
+
+    class GlobalState,SecretsStorage vscodeState
+    class ExtStateContext contextClass
+    class WebviewProvider,McpHub providerClass
+    class AnthropicAPI,OpenRouterAPI,BedrockAPI,OtherAPIs apiClass

docs/tools/cline-tools-guide.md

@@ -20,8 +20,9 @@ Cline is your AI assistant that can:
 
 2. **Provide Context**
 
-    - Use @ mentions to add files, folders, or URLs
-    - Example: "@file:src/components/App.tsx"
+    - Use @ mentions to add files, folders, URLs, diagnostics, terminal output, and more
+    - Example: "@/src/components/App.tsx"
+    - See the [Mentions Feature Guide](./mentions-guide.md) for details
 
 3. **Review Changes**
     - Cline will show diffs before making changes
@@ -54,7 +55,7 @@ Cline is your AI assistant that can:
 
 ## Available Tools
 
-For the most up-to-date implementation details, you can view the full source code in the [Cline repository](https://github.com/cline/cline/blob/main/src/core/Cline.ts).
+For the most up-to-date implementation details, you can view the full source code in the [Cline repository](https://github.com/cline/cline/blob/main/src/core/task/index.ts).
 
 Cline has access to the following tools for various tasks:
 
@@ -81,6 +82,7 @@ Cline has access to the following tools for various tasks:
 4. **Interaction Tools**
     - `ask_followup_question`: Ask user for clarification
     - `attempt_completion`: Present final results
+    - `new_task`: Start a new task with preloaded context
 
 Each tool has specific parameters and usage patterns. Here are some examples:
 
@@ -113,6 +115,21 @@ Each tool has specific parameters and usage patterns. Here are some examples:
     </execute_command>
     ```
 
+-   Start a new task with context (new_task):
+    ```xml
+    <new_task>
+    <context>
+    We've completed the backend API with these endpoints:
+    - GET /api/tasks
+    - POST /api/tasks
+    - PUT /api/tasks/:id
+    - DELETE /api/tasks/:id
+
+    Now we need to implement the React frontend.
+    </context>
+    </new_task>
+    ```
+
 ## Common Tasks
 
 1. **Create a New Component**

docs/tools/mentions-guide.md

@@ -0,0 +1,205 @@
+# Cline Mentions Feature Guide
+
+## Overview
+
+The mentions feature is a powerful capability that allows you to reference various resources in your conversations with Cline using the "@" symbol. This includes file contents, directory structures, webpage URLs, VSCode diagnostic information, terminal output, Git change status, and more - all easily incorporated into your conversations.
+
+By using this feature, Cline can gain more accurate context and provide more relevant assistance for your tasks.
+
+## Basic Syntax
+
+Mentions always start with the "@" symbol, followed by the path or identifier of the resource you want to reference:
+
+```
+@resource_identifier
+```
+
+You can place mentions anywhere in your user messages, and Cline will automatically retrieve the referenced content.
+
+## Supported Mention Types
+
+### 1. File References
+
+To reference file contents, use `@/` followed by the relative path within your project:
+
+```
+@/path/to/file.js
+```
+
+**Example:**
+```
+Please analyze the implementation in @/src/components/Button.tsx
+```
+
+In this example, Cline automatically retrieves the contents of Button.tsx and uses it to perform the analysis.
+
+### 2. Directory References
+
+To reference directory contents, use `@/` followed by the relative path of the directory, ending with a trailing `/`:
+
+```
+@/path/to/directory/
+```
+
+**Example:**
+```
+What components are available in the @/src/components/ directory?
+```
+
+In this example, Cline retrieves a listing of the components directory and its contents.
+
+### 3. URL References
+
+To reference web page contents, use `@` followed by the URL:
+
+```
+@https://example.com
+```
+
+**Example:**
+```
+Please parse the JSON response from @https://api.github.com/users/octocat
+```
+
+In this example, Cline fetches the response from the GitHub API and analyzes the JSON.
+
+### 4. Diagnostic References
+
+To reference VSCode diagnostic information (errors and warnings) in the current workspace, use `@problems`:
+
+```
+@problems
+```
+
+**Example:**
+```
+Check @problems and tell me which errors I should prioritize fixing
+```
+
+In this example, Cline retrieves the current errors and warnings from your workspace and identifies high-priority issues.
+
+### 5. Terminal Output References
+
+To reference the latest terminal output, use `@terminal`:
+
+```
+@terminal
+```
+
+**Example:**
+```
+Please identify the cause of the error in the @terminal output
+```
+
+In this example, Cline examines the latest terminal output and analyzes the error's cause.
+
+### 6. Git Working Directory References
+
+To reference the current Git working directory change status, use `@git-changes`:
+
+```
+@git-changes
+```
+
+**Example:**
+```
+Review the @git-changes and summarize the important changes that should be committed
+```
+
+In this example, Cline retrieves the list of changed files in the current Git working directory and identifies candidates for commit.
+
+### 7. Git Commit References
+
+To reference information about a specific Git commit, use `@` followed by the commit hash:
+
+```
+@commit_hash
+```
+
+**Example:**
+```
+Analyze the commit @abcd123 and explain what changes were made
+```
+
+In this example, Cline retrieves information about the specified commit hash and analyzes the changes made in that commit.
+
+## Usage Scenarios
+
+### Code Review
+
+```
+Check @/src/components/Form.jsx and suggest improvements from a performance perspective. Also, if there are any @problems, please suggest how to fix them.
+```
+
+### Debugging Assistance
+
+```
+My npm install failed. Please examine the @terminal output and suggest a solution to the problem.
+```
+
+### Project Analysis
+
+```
+Analyze the code in the @/src/models/ directory and explain the relationships between the data models. Also, tell me how the utility functions in @/src/utils/ are used with these models.
+```
+
+### Code Generation
+
+```
+Create a new Input.tsx component using the same design language as @/src/components/Button.tsx
+```
+
+### Version Control Integration
+
+```
+Review the @git-changes and suggest a commit message for the feature I'm working on.
+```
+
+## Combining Multiple Mentions
+
+You can combine multiple mentions to provide more complex context:
+
+```
+There seems to be a bug in @/src/api/users.js. Please check @problems and @terminal to identify and fix the issue.
+```
+
+## Limitations and Considerations
+
+1. **Large Files**: Referencing very large files may take time to process and could consume a significant amount of tokens.
+
+2. **Binary Files**: Binary files (such as images) will not be properly processed and will show a "Binary file" message.
+
+3. **Directory Structure**: Directory references will only show top-level files and directories, not recursively showing the contents of subdirectories.
+
+4. **URL Limitations**: Some websites may block automated crawling, which could prevent accurate content retrieval.
+
+5. **Path Syntax**: File paths or URLs with special characters (such as spaces) may not be recognized correctly.
+
+## Troubleshooting
+
+### Mentions Not Recognized
+
+If your mentions aren't being recognized correctly, check that:
+
+- There's no space after the `@` symbol
+- File paths are accurate (case-sensitive)
+- URLs include the full format (with `https://`)
+
+### Content Not Retrieved
+
+If the content of referenced resources can't be retrieved:
+
+- Verify the file exists
+- Ensure you have access permissions for the file
+- Check that the file isn't too large or the URL too complex
+
+### Performance Issues
+
+If mention processing is slow:
+
+- Reference smaller files or specific file sections
+- Reduce the number of mentions used at once
+
+## Conclusion
+
+Mastering the mentions feature makes your communication with Cline more efficient. By providing appropriate context, Cline can deliver more accurate assistance, significantly improving your development workflow.

esbuild.js

@@ -8,6 +8,60 @@ const watch = process.argv.includes("--watch")
 /**
  * @type {import('esbuild').Plugin}
  */
+const aliasResolverPlugin = {
+	name: "alias-resolver",
+	setup(build) {
+		const aliases = {
+			"@": path.resolve(__dirname, "src"),
+			"@api": path.resolve(__dirname, "src/api"),
+			"@core": path.resolve(__dirname, "src/core"),
+			"@integrations": path.resolve(__dirname, "src/integrations"),
+			"@services": path.resolve(__dirname, "src/services"),
+			"@shared": path.resolve(__dirname, "src/shared"),
+			"@utils": path.resolve(__dirname, "src/utils"),
+			"@packages": path.resolve(__dirname, "src/packages"),
+		}
+
+		// For each alias entry, create a resolver
+		Object.entries(aliases).forEach(([alias, aliasPath]) => {
+			const aliasRegex = new RegExp(`^${alias}($|/.*)`)
+			build.onResolve({ filter: aliasRegex }, (args) => {
+				const importPath = args.path.replace(alias, aliasPath)
+
+				// First, check if the path exists as is
+				if (fs.existsSync(importPath)) {
+					const stats = fs.statSync(importPath)
+					if (stats.isDirectory()) {
+						// If it's a directory, try to find index files
+						const extensions = [".ts", ".tsx", ".js", ".jsx"]
+						for (const ext of extensions) {
+							const indexFile = path.join(importPath, `index${ext}`)
+							if (fs.existsSync(indexFile)) {
+								return { path: indexFile }
+							}
+						}
+					} else {
+						// It's a file that exists, so return it
+						return { path: importPath }
+					}
+				}
+
+				// If the path doesn't exist, try appending extensions
+				const extensions = [".ts", ".tsx", ".js", ".jsx"]
+				for (const ext of extensions) {
+					const pathWithExtension = `${importPath}${ext}`
+					if (fs.existsSync(pathWithExtension)) {
+						return { path: pathWithExtension }
+					}
+				}
+
+				// If nothing worked, return the original path and let esbuild handle the error
+				return { path: importPath }
+			})
+		})
+	},
+}
+
 const esbuildProblemMatcherPlugin = {
 	name: "esbuild-problem-matcher",
 
@@ -68,8 +122,12 @@ const extensionConfig = {
 	minify: production,
 	sourcemap: !production,
 	logLevel: "silent",
+	define: {
+		"process.env.IS_DEV": JSON.stringify(!production),
+	},
 	plugins: [
 		copyWasmFiles,
+		aliasResolverPlugin,
 		/* add to the end of plugins array */
 		esbuildProblemMatcherPlugin,
 		{

evals/.gitignore

@@ -0,0 +1,3 @@
+repositories
+
+results/evals.db

evals/README.md

@@ -0,0 +1,186 @@
+# Cline Evaluation System
+
+This directory contains the evaluation system for benchmarking Cline against various coding evaluation frameworks.
+
+## Overview
+
+The Cline Evaluation System allows you to:
+
+1. Run Cline against standardized coding benchmarks
+2. Collect comprehensive metrics on performance
+3. Generate detailed reports on evaluation results
+4. Compare performance across different models and benchmarks
+
+## Architecture
+
+The evaluation system consists of two main components:
+
+1. **Test Server**: Enhanced HTTP server in `src/services/test/TestServer.ts` that provides detailed task results
+2. **CLI Tool**: Command-line interface in `evals/cli/` for orchestrating evaluations
+
+## Directory Structure
+
+```
+cline-repo/
+├── src/
+│   ├── services/
+│   │   ├── test/
+│   │   │   ├── TestServer.ts         # Enhanced HTTP server for task execution
+│   │   │   ├── GitHelper.ts          # Git utilities for file tracking
+│   │   │   └── ...
+│   │   └── ...
+│   └── ...
+├── evals/                            # Main directory for evaluation system
+│   ├── cli/                          # CLI tool for orchestrating evaluations
+│   │   ├── src/
+│   │   │   ├── index.ts              # CLI entry point
+│   │   │   ├── commands/             # CLI commands (setup, run, report)
+│   │   │   ├── adapters/             # Benchmark adapters
+│   │   │   ├── db/                   # Database management
+│   │   │   └── utils/                # Utility functions
+│   │   ├── package.json
+│   │   └── tsconfig.json
+│   ├── repositories/                 # Cloned benchmark repositories
+│   │   ├── exercism/                 # Modified Exercism (from pashpashpash/evals)
+│   │   ├── swe-bench/                # SWE-Bench repository
+│   │   ├── swelancer/                # SWELancer repository
+│   │   └── multi-swe/                # Multi-SWE-Bench repository
+│   ├── results/                      # Evaluation results storage
+│   │   ├── runs/                     # Individual run results
+│   │   └── reports/                  # Generated reports
+│   └── README.md                     # This file
+└── ...
+```
+
+## Getting Started
+
+### Prerequisites
+
+- Node.js 16+
+- VSCode with Cline extension installed
+- Git
+
+### Activation Mechanism
+
+The evaluation system uses an `evals.env` file approach to activate test mode in the Cline extension. When an evaluation is run:
+
+1. The CLI creates an `evals.env` file in the workspace directory
+2. The Cline extension activates due to the `workspaceContains:evals.env` activation event
+3. The extension detects this file and automatically enters test mode
+4. After evaluation completes, the file is automatically removed
+
+This approach eliminates the need for environment variables during the build process and allows for targeted activation only when needed for evaluations. The extension remains dormant during normal use, only activating when an evals.env file is present. For more details, see [Evals Env Activation](./docs/evals-env-activation.md).
+
+### Installation
+
+1. Build the CLI tool:
+
+```bash
+cd evals/cli
+npm install
+npm run build
+```
+
+### Usage
+
+#### Setting Up Benchmarks
+
+```bash
+cd evals/cli
+node dist/index.js setup
+```
+
+This will clone and set up all benchmark repositories. You can specify specific benchmarks:
+
+```bash
+node dist/index.js setup --benchmarks exercism
+```
+
+#### Running Evaluations
+
+```bash
+node dist/index.js run --model claude-3-opus-20240229 --benchmark exercism
+```
+
+Options:
+- `--model`: The model to evaluate (default: claude-3-opus-20240229)
+- `--benchmark`: Specific benchmark to run (default: all)
+- `--count`: Number of tasks to run (default: all)
+
+#### Generating Reports
+
+```bash
+node dist/index.js report
+```
+
+Options:
+- `--format`: Report format (json, markdown) (default: markdown)
+- `--output`: Output path for the report
+
+#### Managing Test Mode Activation
+
+The CLI provides a command to manually manage the evals.env file for test mode activation:
+
+```bash
+node dist/index.js evals-env create  # Create evals.env file in current directory
+node dist/index.js evals-env remove  # Remove evals.env file from current directory
+node dist/index.js evals-env check   # Check if evals.env file exists in current directory
+```
+
+Options:
+- `--directory`: Specify a directory other than the current one
+
+## Benchmarks
+
+### Exercism
+
+Modified Exercism exercises from the [pashpashpash/evals](https://github.com/pashpashpash/evals) repository. These are small, focused programming exercises in various languages.
+
+### SWE-Bench (Coming Soon)
+
+Real-world software engineering tasks from the [SWE-bench](https://github.com/SWE-bench/SWE-bench) repository.
+
+### SWELancer (Coming Soon)
+
+Freelance-style programming tasks from the SWELancer benchmark.
+
+### Multi-SWE-Bench (Coming Soon)
+
+Multi-file software engineering tasks from the Multi-SWE-Bench repository.
+
+## Metrics
+
+The evaluation system collects the following metrics:
+
+- **Token Usage**: Input and output tokens
+- **Cost**: Estimated cost of API calls
+- **Duration**: Time taken to complete tasks
+- **Tool Usage**: Number of tool calls and failures
+- **Success Rate**: Percentage of tasks completed successfully
+- **Functional Correctness**: Percentage of tests passed
+
+## Reports
+
+Reports are generated in Markdown or JSON format and include:
+
+- Overall summary
+- Benchmark-specific results
+- Model-specific results
+- Tool usage statistics
+- Charts and visualizations
+
+## Development
+
+### Adding a New Benchmark
+
+1. Create a new adapter in `evals/cli/src/adapters/`
+2. Implement the `BenchmarkAdapter` interface
+3. Register the adapter in `evals/cli/src/adapters/index.ts`
+
+### Extending Metrics
+
+To add new metrics:
+
+1. Update the database schema in `evals/cli/src/db/schema.ts`
+2. Add collection logic in `evals/cli/src/utils/results.ts`
+3. Update report generation in `evals/cli/src/commands/report.ts`

evals/cli/package.json

@@ -0,0 +1,39 @@
+{
+	"name": "cline-evaluation-cli",
+	"version": "0.1.0",
+	"description": "CLI tool for orchestrating Cline evaluations across multiple benchmarks",
+	"main": "dist/index.js",
+	"scripts": {
+		"build": "tsc",
+		"start": "node dist/index.js",
+		"dev": "ts-node src/index.ts",
+		"test": "echo \"Error: no test specified\" && exit 1"
+	},
+	"keywords": [
+		"cline",
+		"evaluation",
+		"benchmark"
+	],
+	"author": "",
+	"license": "MIT",
+	"dependencies": {
+		"better-sqlite3": "^8.0.0",
+		"chalk": "^4.1.2",
+		"commander": "^9.4.1",
+		"execa": "^5.1.1",
+		"node-fetch": "^2.7.0",
+		"ora": "^5.4.1",
+		"sqlite": "^4.1.2",
+		"uuid": "^9.0.0",
+		"yargs": "^17.6.2"
+	},
+	"devDependencies": {
+		"@types/better-sqlite3": "^7.6.3",
+		"@types/node": "^18.11.18",
+		"@types/node-fetch": "^2.6.12",
+		"@types/uuid": "^9.0.0",
+		"@types/yargs": "^17.0.19",
+		"ts-node": "^10.9.1",
+		"typescript": "^4.9.4"
+	}
+}

evals/cli/src/adapters/exercism.ts

@@ -0,0 +1,194 @@
+import * as path from "path"
+import * as fs from "fs"
+import execa from "execa"
+import { BenchmarkAdapter, Task, VerificationResult } from "./types"
+
+const EVALS_DIR = path.resolve(__dirname, "../../../")
+
+/**
+ * Adapter for the modified Exercism benchmark
+ */
+export class ExercismAdapter implements BenchmarkAdapter {
+	name = "exercism"
+
+	/**
+	 * Set up the Exercism benchmark repository
+	 */
+	async setup(): Promise<void> {
+		// Clone repository if needed
+		const exercismDir = path.join(EVALS_DIR, "repositories", "exercism")
+
+		if (!fs.existsSync(exercismDir)) {
+			console.log(`Cloning Exercism repository to ${exercismDir}...`)
+			await execa("git", ["clone", "https://github.com/pashpashpash/evals.git", exercismDir])
+			console.log("Exercism repository cloned successfully")
+		} else {
+			console.log(`Exercism repository already exists at ${exercismDir}`)
+
+			// Pull latest changes
+			console.log("Pulling latest changes...")
+			await execa("git", ["pull"], { cwd: exercismDir })
+			console.log("Repository updated successfully")
+		}
+	}
+
+	/**
+	 * List all available tasks in the Exercism benchmark
+	 */
+	async listTasks(): Promise<Task[]> {
+		const tasks: Task[] = []
+		const exercisesDir = path.join(EVALS_DIR, "repositories", "exercism")
+
+		// Ensure the repository exists
+		if (!fs.existsSync(exercisesDir)) {
+			throw new Error(`Exercism repository not found at ${exercisesDir}. Run setup first.`)
+		}
+
+		// Read language directories
+		const languages = fs
+			.readdirSync(exercisesDir)
+			.filter((dir) => fs.statSync(path.join(exercisesDir, dir)).isDirectory())
+			.filter((dir) => !dir.startsWith(".") && !["node_modules", ".git"].includes(dir))
+
+		for (const language of languages) {
+			const languageDir = path.join(exercisesDir, language)
+
+			// Read exercise directories
+			const exercises = fs.readdirSync(languageDir).filter((dir) => fs.statSync(path.join(languageDir, dir)).isDirectory())
+
+			for (const exercise of exercises) {
+				const exerciseDir = path.join(languageDir, exercise)
+
+				// Read instructions
+				let description = ""
+				const instructionsPath = path.join(exerciseDir, "docs", "instructions.md")
+				if (fs.existsSync(instructionsPath)) {
+					description = fs.readFileSync(instructionsPath, "utf-8")
+				}
+
+				// Determine test commands based on language
+				let testCommands: string[] = []
+				switch (language) {
+					case "javascript":
+						testCommands = ["npm install", "npm test"]
+						break
+					case "python":
+						testCommands = ["python -m pytest -o markers=task *_test.py"]
+						break
+					case "go":
+						testCommands = ["go test"]
+						break
+					case "java":
+						testCommands = ["./gradlew test"]
+						break
+					case "rust":
+						testCommands = ["cargo test"]
+						break
+					default:
+						testCommands = []
+				}
+
+				tasks.push({
+					id: `exercism-${language}-${exercise}`,
+					name: exercise,
+					description,
+					workspacePath: exerciseDir,
+					setupCommands: [],
+					verificationCommands: testCommands,
+					metadata: {
+						language,
+						type: "exercism",
+					},
+				})
+			}
+		}
+
+		return tasks
+	}
+
+	/**
+	 * Prepare a specific task for execution
+	 * @param taskId The ID of the task to prepare
+	 */
+	async prepareTask(taskId: string): Promise<Task> {
+		const tasks = await this.listTasks()
+		const task = tasks.find((t) => t.id === taskId)
+
+		if (!task) {
+			throw new Error(`Task ${taskId} not found`)
+		}
+
+		// Check if Git repository is already initialized
+		const gitDirExists = fs.existsSync(path.join(task.workspacePath, ".git"))
+
+		try {
+			// Initialize Git repository if needed
+			if (!gitDirExists) {
+				await execa("git", ["init"], { cwd: task.workspacePath })
+			}
+
+			// Create a dummy file to ensure there's something to commit
+			const dummyFilePath = path.join(task.workspacePath, ".eval-timestamp")
+			fs.writeFileSync(dummyFilePath, new Date().toISOString())
+
+			// Add all files and commit
+			await execa("git", ["add", "."], { cwd: task.workspacePath })
+
+			try {
+				await execa("git", ["commit", "-m", "Initial commit"], { cwd: task.workspacePath })
+			} catch (error: any) {
+				// If commit fails because there are no changes, that's okay
+				if (!error.stderr?.includes("nothing to commit")) {
+					throw error
+				}
+			}
+		} catch (error: any) {
+			console.warn(`Warning: Git operations failed: ${error.message}`)
+			console.warn("Continuing without Git initialization")
+		}
+
+		return task
+	}
+
+	/**
+	 * Verify the result of a task execution
+	 * @param task The task that was executed
+	 * @param result The result of the task execution
+	 */
+	async verifyResult(task: Task, result: any): Promise<VerificationResult> {
+		// Run verification commands
+		let success = true
+		let output = ""
+
+		for (const command of task.verificationCommands) {
+			try {
+				const [cmd, ...args] = command.split(" ")
+				const { stdout } = await execa(cmd, args, { cwd: task.workspacePath })
+				output += stdout + "\n"
+			} catch (error: any) {
+				success = false
+				if (error.stdout) {
+					output += error.stdout + "\n"
+				}
+				if (error.stderr) {
+					output += error.stderr + "\n"
+				}
+			}
+		}
+
+		// Parse test results
+		const testsPassed = (output.match(/PASS/g) || []).length
+		const testsFailed = (output.match(/FAIL/g) || []).length
+		const testsTotal = testsPassed + testsFailed
+
+		return {
+			success,
+			metrics: {
+				testsPassed,
+				testsFailed,
+				testsTotal,
+				functionalCorrectness: testsTotal > 0 ? testsPassed / testsTotal : 0,
+			},
+		}
+	}
+}

evals/cli/src/adapters/index.ts

@@ -0,0 +1,47 @@
+import { BenchmarkAdapter } from "./types"
+import { ExercismAdapter } from "./exercism"
+import { SWEBenchAdapter } from "./swe-bench"
+import { SWELancerAdapter } from "./swelancer"
+import { MultiSWEAdapter } from "./multi-swe"
+
+// Registry of all available adapters
+const adapters: Record<string, BenchmarkAdapter> = {
+	// Exercism is the primary adapter with real implementation
+	exercism: new ExercismAdapter(),
+
+	// Dummy adapters for testing
+	"swe-bench": new SWEBenchAdapter(),
+	swelancer: new SWELancerAdapter(),
+	"multi-swe": new MultiSWEAdapter(),
+}
+
+/**
+ * Get a specific adapter by name
+ * @param name The name of the adapter to get
+ * @returns The requested adapter
+ * @throws Error if the adapter is not found
+ */
+export function getAdapter(name: string): BenchmarkAdapter {
+	const adapter = adapters[name]
+	if (!adapter) {
+		throw new Error(`Adapter for benchmark '${name}' not found`)
+	}
+	return adapter
+}
+
+/**
+ * Get all available adapters
+ * @returns Array of all registered adapters
+ */
+export function getAllAdapters(): BenchmarkAdapter[] {
+	return Object.values(adapters)
+}
+
+/**
+ * Register a new adapter
+ * @param name The name to register the adapter under
+ * @param adapter The adapter to register
+ */
+export function registerAdapter(name: string, adapter: BenchmarkAdapter): void {
+	adapters[name] = adapter
+}

evals/cli/src/adapters/multi-swe.ts

@@ -0,0 +1,192 @@
+import * as path from "path"
+import * as fs from "fs"
+import execa from "execa"
+import { BenchmarkAdapter, Task, VerificationResult } from "./types"
+
+const EVALS_DIR = path.resolve(__dirname, "../../../")
+
+/**
+ * Dummy adapter for the Multi-SWE-Bench benchmark
+ */
+export class MultiSWEAdapter implements BenchmarkAdapter {
+	name = "multi-swe"
+
+	/**
+	 * Set up the Multi-SWE-Bench benchmark repository (dummy implementation)
+	 */
+	async setup(): Promise<void> {
+		console.log("Multi-SWE-Bench dummy setup completed")
+
+		// Create repositories directory if it doesn't exist
+		const repoDir = path.join(EVALS_DIR, "repositories", "multi-swe")
+		if (!fs.existsSync(repoDir)) {
+			fs.mkdirSync(repoDir, { recursive: true })
+			console.log(`Created dummy Multi-SWE-Bench directory at ${repoDir}`)
+		}
+	}
+
+	/**
+	 * List all available tasks in the Multi-SWE-Bench benchmark (dummy implementation)
+	 */
+	async listTasks(): Promise<Task[]> {
+		return [
+			{
+				id: "multi-swe-task-1",
+				name: "Multi-Language API Integration",
+				description:
+					"Implement a system that integrates a Python backend with a TypeScript frontend and a Rust processing service.",
+				workspacePath: path.join(EVALS_DIR, "repositories", "multi-swe"),
+				setupCommands: [],
+				verificationCommands: [],
+				metadata: {
+					languages: ["python", "typescript", "rust"],
+					complexity: "high",
+					type: "multi-swe",
+				},
+			},
+			{
+				id: "multi-swe-task-2",
+				name: "Cross-Platform Mobile App",
+				description: "Create a cross-platform mobile app using React Native with native modules in Swift and Kotlin.",
+				workspacePath: path.join(EVALS_DIR, "repositories", "multi-swe"),
+				setupCommands: [],
+				verificationCommands: [],
+				metadata: {
+					languages: ["javascript", "swift", "kotlin"],
+					complexity: "medium",
+					type: "multi-swe",
+				},
+			},
+			{
+				id: "multi-swe-task-3",
+				name: "Microservice Architecture",
+				description: "Design and implement a microservice architecture with services written in Go, Node.js, and Java.",
+				workspacePath: path.join(EVALS_DIR, "repositories", "multi-swe"),
+				setupCommands: [],
+				verificationCommands: [],
+				metadata: {
+					languages: ["go", "javascript", "java"],
+					complexity: "high",
+					type: "multi-swe",
+				},
+			},
+		]
+	}
+
+	/**
+	 * Prepare a specific task for execution (dummy implementation)
+	 * @param taskId The ID of the task to prepare
+	 */
+	async prepareTask(taskId: string): Promise<Task> {
+		const tasks = await this.listTasks()
+		const task = tasks.find((t) => t.id === taskId)
+
+		if (!task) {
+			throw new Error(`Task ${taskId} not found`)
+		}
+
+		// Create a dummy workspace for the task
+		const taskDir = path.join(task.workspacePath, taskId)
+		if (!fs.existsSync(taskDir)) {
+			fs.mkdirSync(taskDir, { recursive: true })
+
+			// Create a dummy file for the task
+			fs.writeFileSync(
+				path.join(taskDir, "README.md"),
+				`# ${task.name}\n\n${task.description}\n\nThis is a dummy task for testing purposes.`,
+			)
+
+			// Create additional dummy files based on task type
+			if (task.id === "multi-swe-task-1") {
+				// Python backend
+				fs.mkdirSync(path.join(taskDir, "backend"), { recursive: true })
+				fs.writeFileSync(
+					path.join(taskDir, "backend", "app.py"),
+					`# TODO: Implement Python backend\nfrom flask import Flask\n\napp = Flask(__name__)\n\n@app.route('/')\ndef hello():\n    return "Hello, World!"\n`,
+				)
+
+				// TypeScript frontend
+				fs.mkdirSync(path.join(taskDir, "frontend"), { recursive: true })
+				fs.writeFileSync(
+					path.join(taskDir, "frontend", "app.ts"),
+					`// TODO: Implement TypeScript frontend\nconsole.log('Frontend starting...');\n`,
+				)
+
+				// Rust processing service
+				fs.mkdirSync(path.join(taskDir, "processor"), { recursive: true })
+				fs.writeFileSync(
+					path.join(taskDir, "processor", "main.rs"),
+					`// TODO: Implement Rust processing service\nfn main() {\n    println!("Processor starting...");\n}\n`,
+				)
+			} else if (task.id === "multi-swe-task-2") {
+				// React Native app
+				fs.mkdirSync(path.join(taskDir, "app"), { recursive: true })
+				fs.writeFileSync(
+					path.join(taskDir, "app", "App.js"),
+					`// TODO: Implement React Native app\nimport React from 'react';\nimport { View, Text } from 'react-native';\n\nexport default function App() {\n  return (\n    <View>\n      <Text>Hello, World!</Text>\n    </View>\n  );\n}\n`,
+				)
+
+				// Swift native module
+				fs.mkdirSync(path.join(taskDir, "ios"), { recursive: true })
+				fs.writeFileSync(
+					path.join(taskDir, "ios", "NativeModule.swift"),
+					`// TODO: Implement Swift native module\nimport Foundation\n\n@objc(NativeModule)\nclass NativeModule: NSObject {\n  @objc\n  func hello() -> String {\n    return "Hello from Swift"\n  }\n}\n`,
+				)
+
+				// Kotlin native module
+				fs.mkdirSync(path.join(taskDir, "android"), { recursive: true })
+				fs.writeFileSync(
+					path.join(taskDir, "android", "NativeModule.kt"),
+					`// TODO: Implement Kotlin native module\npackage com.example.app\n\nclass NativeModule {\n  fun hello(): String {\n    return "Hello from Kotlin"\n  }\n}\n`,
+				)
+			} else if (task.id === "multi-swe-task-3") {
+				// Go service
+				fs.mkdirSync(path.join(taskDir, "service-go"), { recursive: true })
+				fs.writeFileSync(
+					path.join(taskDir, "service-go", "main.go"),
+					`// TODO: Implement Go service\npackage main\n\nimport "fmt"\n\nfunc main() {\n\tfmt.Println("Go service starting...")\n}\n`,
+				)
+
+				// Node.js service
+				fs.mkdirSync(path.join(taskDir, "service-node"), { recursive: true })
+				fs.writeFileSync(
+					path.join(taskDir, "service-node", "server.js"),
+					`// TODO: Implement Node.js service\nconsole.log('Node.js service starting...');\n`,
+				)
+
+				// Java service
+				fs.mkdirSync(path.join(taskDir, "service-java"), { recursive: true })
+				fs.writeFileSync(
+					path.join(taskDir, "service-java", "Main.java"),
+					`// TODO: Implement Java service\npublic class Main {\n    public static void main(String[] args) {\n        System.out.println("Java service starting...");\n    }\n}\n`,
+				)
+			}
+		}
+
+		// Update the task's workspace path to the task-specific directory
+		return {
+			...task,
+			workspacePath: taskDir,
+		}
+	}
+
+	/**
+	 * Verify the result of a task execution (dummy implementation)
+	 * @param task The task that was executed
+	 * @param result The result of the task execution
+	 */
+	async verifyResult(task: Task, result: any): Promise<VerificationResult> {
+		// Always return success for dummy implementation
+		return {
+			success: true,
+			metrics: {
+				testsPassed: 1,
+				testsFailed: 0,
+				testsTotal: 1,
+				functionalCorrectness: 1.0,
+				crossLanguageIntegration: 0.9, // Dummy metric specific to Multi-SWE
+				architectureQuality: 0.85, // Dummy metric specific to Multi-SWE
+			},
+		}
+	}
+}

evals/cli/src/adapters/swe-bench.ts

@@ -0,0 +1,125 @@
+import * as path from "path"
+import * as fs from "fs"
+import execa from "execa"
+import { BenchmarkAdapter, Task, VerificationResult } from "./types"
+
+const EVALS_DIR = path.resolve(__dirname, "../../../")
+
+/**
+ * Dummy adapter for the SWE-Bench benchmark
+ */
+export class SWEBenchAdapter implements BenchmarkAdapter {
+	name = "swe-bench"
+
+	/**
+	 * Set up the SWE-Bench benchmark repository (dummy implementation)
+	 */
+	async setup(): Promise<void> {
+		console.log("SWE-Bench dummy setup completed")
+
+		// Create repositories directory if it doesn't exist
+		const repoDir = path.join(EVALS_DIR, "repositories", "swe-bench")
+		if (!fs.existsSync(repoDir)) {
+			fs.mkdirSync(repoDir, { recursive: true })
+			console.log(`Created dummy SWE-Bench directory at ${repoDir}`)
+		}
+	}
+
+	/**
+	 * List all available tasks in the SWE-Bench benchmark (dummy implementation)
+	 */
+	async listTasks(): Promise<Task[]> {
+		return [
+			{
+				id: "swe-bench-task-1",
+				name: "Fix React Component Bug",
+				description: "Fix a bug in a React component where the state is not properly updated.",
+				workspacePath: path.join(EVALS_DIR, "repositories", "swe-bench"),
+				setupCommands: [],
+				verificationCommands: [],
+				metadata: {
+					repository: "facebook/react",
+					issue: "#12345",
+					type: "swe-bench",
+				},
+			},
+			{
+				id: "swe-bench-task-2",
+				name: "Optimize Database Query",
+				description: "Optimize a slow database query in a Django application.",
+				workspacePath: path.join(EVALS_DIR, "repositories", "swe-bench"),
+				setupCommands: [],
+				verificationCommands: [],
+				metadata: {
+					repository: "django/django",
+					issue: "#6789",
+					type: "swe-bench",
+				},
+			},
+			{
+				id: "swe-bench-task-3",
+				name: "Fix Memory Leak",
+				description: "Fix a memory leak in a Node.js application.",
+				workspacePath: path.join(EVALS_DIR, "repositories", "swe-bench"),
+				setupCommands: [],
+				verificationCommands: [],
+				metadata: {
+					repository: "nodejs/node",
+					issue: "#9876",
+					type: "swe-bench",
+				},
+			},
+		]
+	}
+
+	/**
+	 * Prepare a specific task for execution (dummy implementation)
+	 * @param taskId The ID of the task to prepare
+	 */
+	async prepareTask(taskId: string): Promise<Task> {
+		const tasks = await this.listTasks()
+		const task = tasks.find((t) => t.id === taskId)
+
+		if (!task) {
+			throw new Error(`Task ${taskId} not found`)
+		}
+
+		// Create a dummy workspace for the task
+		const taskDir = path.join(task.workspacePath, taskId)
+		if (!fs.existsSync(taskDir)) {
+			fs.mkdirSync(taskDir, { recursive: true })
+
+			// Create a dummy file for the task
+			fs.writeFileSync(
+				path.join(taskDir, "README.md"),
+				`# ${task.name}\n\n${task.description}\n\nThis is a dummy task for testing purposes.`,
+			)
+		}
+
+		// Update the task's workspace path to the task-specific directory
+		return {
+			...task,
+			workspacePath: taskDir,
+		}
+	}
+
+	/**
+	 * Verify the result of a task execution (dummy implementation)
+	 * @param task The task that was executed
+	 * @param result The result of the task execution
+	 */
+	async verifyResult(task: Task, result: any): Promise<VerificationResult> {
+		// Always return success for dummy implementation
+		return {
+			success: true,
+			metrics: {
+				testsPassed: 1,
+				testsFailed: 0,
+				testsTotal: 1,
+				functionalCorrectness: 1.0,
+				performanceImprovement: 0.25, // Dummy metric specific to SWE-Bench
+				codeQuality: 0.9, // Dummy metric specific to SWE-Bench
+			},
+		}
+	}
+}

evals/cli/src/adapters/swelancer.ts

@@ -0,0 +1,143 @@
+import * as path from "path"
+import * as fs from "fs"
+import execa from "execa"
+import { BenchmarkAdapter, Task, VerificationResult } from "./types"
+
+const EVALS_DIR = path.resolve(__dirname, "../../../")
+
+/**
+ * Dummy adapter for the SWELancer benchmark
+ */
+export class SWELancerAdapter implements BenchmarkAdapter {
+	name = "swelancer"
+
+	/**
+	 * Set up the SWELancer benchmark repository (dummy implementation)
+	 */
+	async setup(): Promise<void> {
+		console.log("SWELancer dummy setup completed")
+
+		// Create repositories directory if it doesn't exist
+		const repoDir = path.join(EVALS_DIR, "repositories", "swelancer")
+		if (!fs.existsSync(repoDir)) {
+			fs.mkdirSync(repoDir, { recursive: true })
+			console.log(`Created dummy SWELancer directory at ${repoDir}`)
+		}
+	}
+
+	/**
+	 * List all available tasks in the SWELancer benchmark (dummy implementation)
+	 */
+	async listTasks(): Promise<Task[]> {
+		return [
+			{
+				id: "swelancer-task-1",
+				name: "Create Landing Page",
+				description: "Create a responsive landing page for a new product using HTML, CSS, and JavaScript.",
+				workspacePath: path.join(EVALS_DIR, "repositories", "swelancer"),
+				setupCommands: [],
+				verificationCommands: [],
+				metadata: {
+					client: "TechStartup Inc.",
+					difficulty: "medium",
+					type: "swelancer",
+				},
+			},
+			{
+				id: "swelancer-task-2",
+				name: "Build REST API",
+				description: "Create a RESTful API for a blog application using Node.js and Express.",
+				workspacePath: path.join(EVALS_DIR, "repositories", "swelancer"),
+				setupCommands: [],
+				verificationCommands: [],
+				metadata: {
+					client: "BlogCo",
+					difficulty: "hard",
+					type: "swelancer",
+				},
+			},
+			{
+				id: "swelancer-task-3",
+				name: "Fix CSS Layout Issues",
+				description: "Fix layout issues in a responsive website across different screen sizes.",
+				workspacePath: path.join(EVALS_DIR, "repositories", "swelancer"),
+				setupCommands: [],
+				verificationCommands: [],
+				metadata: {
+					client: "DesignAgency",
+					difficulty: "easy",
+					type: "swelancer",
+				},
+			},
+		]
+	}
+
+	/**
+	 * Prepare a specific task for execution (dummy implementation)
+	 * @param taskId The ID of the task to prepare
+	 */
+	async prepareTask(taskId: string): Promise<Task> {
+		const tasks = await this.listTasks()
+		const task = tasks.find((t) => t.id === taskId)
+
+		if (!task) {
+			throw new Error(`Task ${taskId} not found`)
+		}
+
+		// Create a dummy workspace for the task
+		const taskDir = path.join(task.workspacePath, taskId)
+		if (!fs.existsSync(taskDir)) {
+			fs.mkdirSync(taskDir, { recursive: true })
+
+			// Create a dummy file for the task
+			fs.writeFileSync(
+				path.join(taskDir, "README.md"),
+				`# ${task.name}\n\n${task.description}\n\nThis is a dummy task for testing purposes.`,
+			)
+
+			// Create additional dummy files based on task type
+			if (task.id === "swelancer-task-1") {
+				fs.writeFileSync(
+					path.join(taskDir, "index.html"),
+					`<!DOCTYPE html>\n<html>\n<head>\n  <title>Landing Page</title>\n</head>\n<body>\n  <!-- TODO: Implement landing page -->\n</body>\n</html>`,
+				)
+			} else if (task.id === "swelancer-task-2") {
+				fs.writeFileSync(
+					path.join(taskDir, "server.js"),
+					`// TODO: Implement REST API\nconsole.log('Server starting...');`,
+				)
+			} else if (task.id === "swelancer-task-3") {
+				fs.writeFileSync(
+					path.join(taskDir, "styles.css"),
+					`/* TODO: Fix layout issues */\nbody {\n  margin: 0;\n  padding: 0;\n}`,
+				)
+			}
+		}
+
+		// Update the task's workspace path to the task-specific directory
+		return {
+			...task,
+			workspacePath: taskDir,
+		}
+	}
+
+	/**
+	 * Verify the result of a task execution (dummy implementation)
+	 * @param task The task that was executed
+	 * @param result The result of the task execution
+	 */
+	async verifyResult(task: Task, result: any): Promise<VerificationResult> {
+		// Always return success for dummy implementation
+		return {
+			success: true,
+			metrics: {
+				testsPassed: 1,
+				testsFailed: 0,
+				testsTotal: 1,
+				functionalCorrectness: 1.0,
+				clientSatisfaction: 0.95, // Dummy metric specific to SWELancer
+				timeEfficiency: 0.85, // Dummy metric specific to SWELancer
+			},
+		}
+	}
+}

evals/cli/src/adapters/types.ts

@@ -0,0 +1,31 @@
+/**
+ * Represents a task to be executed
+ */
+export interface Task {
+	id: string
+	name: string
+	description: string
+	workspacePath: string
+	setupCommands: string[]
+	verificationCommands: string[]
+	metadata: Record<string, any>
+}
+
+/**
+ * Result of verifying a task execution
+ */
+export interface VerificationResult {
+	success: boolean
+	metrics: Record<string, any>
+}
+
+/**
+ * Interface for benchmark adapters
+ */
+export interface BenchmarkAdapter {
+	name: string
+	setup(): Promise<void>
+	listTasks(): Promise<Task[]>
+	prepareTask(taskId: string): Promise<Task>
+	verifyResult(task: Task, result: any): Promise<VerificationResult>
+}

evals/cli/src/commands/evals-env.ts

@@ -0,0 +1,53 @@
+import * as path from "path"
+import chalk from "chalk"
+import { createEvalsEnvFile, removeEvalsEnvFile, checkEvalsEnvFile } from "../utils/evals-env"
+
+interface EvalsEnvOptions {
+	action: "create" | "remove" | "check"
+	directory?: string
+}
+
+/**
+ * Handler for the evals-env command
+ * @param options Command options
+ */
+export async function evalsEnvHandler(options: EvalsEnvOptions): Promise<void> {
+	// Determine the directory to use - default to repository root instead of current directory
+	const currentDir = process.cwd()
+	const repoRoot = path.resolve(currentDir, "..", "..") // Navigate up from evals/cli to root
+	const directory = options.directory || repoRoot
+
+	console.log(chalk.blue(`Working with directory: ${directory}`))
+
+	// Perform the requested action
+	switch (options.action) {
+		case "create":
+			console.log(chalk.blue("Creating evals.env file..."))
+			createEvalsEnvFile(directory)
+			console.log(chalk.green("The Cline extension should now detect this file and enter test mode."))
+			console.log(chalk.yellow("Note: You may need to reload VSCode for the changes to take effect."))
+			break
+
+		case "remove":
+			console.log(chalk.blue("Removing evals.env file..."))
+			removeEvalsEnvFile(directory)
+			console.log(chalk.green("The Cline extension should now exit test mode."))
+			console.log(chalk.yellow("Note: You may need to reload VSCode for the changes to take effect."))
+			break
+
+		case "check":
+			console.log(chalk.blue("Checking for evals.env file..."))
+			const exists = checkEvalsEnvFile(directory)
+			if (exists) {
+				console.log(chalk.green("The Cline extension should be in test mode."))
+			} else {
+				console.log(chalk.yellow("The Cline extension should not be in test mode."))
+			}
+			break
+
+		default:
+			console.error(chalk.red(`Unknown action: ${options.action}`))
+			console.log(chalk.yellow("Valid actions are: create, remove, check"))
+			break
+	}
+}

evals/cli/src/commands/report.ts

@@ -0,0 +1,237 @@
+import * as fs from "fs"
+import * as path from "path"
+import chalk from "chalk"
+import ora from "ora"
+import { ResultsDatabase } from "../db"
+import { generateMarkdownReport } from "../utils/markdown"
+
+interface ReportOptions {
+	format?: "json" | "markdown"
+	output?: string
+}
+
+/**
+ * Handler for the report command
+ * @param options Command options
+ */
+export async function reportHandler(options: ReportOptions): Promise<void> {
+	const format = options.format || "markdown"
+	const db = new ResultsDatabase()
+
+	try {
+		const spinner = ora("Generating report...").start()
+
+		// Get all runs
+		const runs = db.getRuns()
+
+		console.log(chalk.blue(`Found ${runs.length} evaluation runs`))
+
+		if (runs.length === 0) {
+			spinner.fail("No evaluation runs found")
+			return
+		}
+
+		// Generate summary report
+		const summary = {
+			runs: runs.length,
+			models: [...new Set(runs.map((run) => run.model))],
+			benchmarks: [...new Set(runs.map((run) => run.benchmark))],
+			tasks: 0,
+			successRate: 0,
+			averageTokens: 0,
+			averageCost: 0,
+			averageDuration: 0,
+			totalToolCalls: 0,
+			totalToolFailures: 0,
+			toolSuccessRate: 0,
+			toolUsage: {} as Record<string, { calls: number; failures: number }>,
+		}
+
+		let totalTasks = 0
+		let successfulTasks = 0
+		let totalTokens = 0
+		let totalCost = 0
+		let totalDuration = 0
+		let totalToolCalls = 0
+		let totalToolFailures = 0
+
+		for (const run of runs) {
+			const tasks = db.getRunTasks(run.id)
+			totalTasks += tasks.length
+
+			for (const task of tasks) {
+				if (task.success) {
+					successfulTasks++
+				}
+
+				const metrics = db.getTaskMetrics(task.id)
+
+				const tokensIn = metrics.find((m) => m.name === "tokensIn")?.value || 0
+				const tokensOut = metrics.find((m) => m.name === "tokensOut")?.value || 0
+				totalTokens += tokensIn + tokensOut
+
+				totalCost += metrics.find((m) => m.name === "cost")?.value || 0
+				totalDuration += metrics.find((m) => m.name === "duration")?.value || 0
+
+				// Collect tool call metrics
+				totalToolCalls += task.total_tool_calls || 0
+				totalToolFailures += task.total_tool_failures || 0
+
+				// Get detailed tool usage
+				const toolCalls = db.getTaskToolCalls(task.id)
+
+				for (const toolCall of toolCalls) {
+					if (!summary.toolUsage[toolCall.tool_name]) {
+						summary.toolUsage[toolCall.tool_name] = {
+							calls: 0,
+							failures: 0,
+						}
+					}
+
+					summary.toolUsage[toolCall.tool_name].calls += toolCall.call_count
+					summary.toolUsage[toolCall.tool_name].failures += toolCall.failure_count
+				}
+			}
+		}
+
+		// Calculate tool success rate
+		summary.totalToolCalls = totalToolCalls
+		summary.totalToolFailures = totalToolFailures
+		summary.toolSuccessRate = totalToolCalls > 0 ? 1 - totalToolFailures / totalToolCalls : 1.0
+
+		summary.tasks = totalTasks
+		summary.successRate = totalTasks > 0 ? successfulTasks / totalTasks : 0
+		summary.averageTokens = totalTasks > 0 ? totalTokens / totalTasks : 0
+		summary.averageCost = totalTasks > 0 ? totalCost / totalTasks : 0
+		summary.averageDuration = totalTasks > 0 ? totalDuration / totalTasks : 0
+
+		// Generate benchmark-specific reports
+		const benchmarkReports: Record<string, any> = {}
+
+		for (const benchmark of summary.benchmarks) {
+			const benchmarkRuns = runs.filter((run) => run.benchmark === benchmark)
+			const benchmarkSummary = {
+				runs: benchmarkRuns.length,
+				models: [...new Set(benchmarkRuns.map((run) => run.model))],
+				tasks: 0,
+				successRate: 0,
+				averageTokens: 0,
+				averageCost: 0,
+				averageDuration: 0,
+			}
+
+			let benchmarkTasks = 0
+			let benchmarkSuccessfulTasks = 0
+			let benchmarkTotalTokens = 0
+			let benchmarkTotalCost = 0
+			let benchmarkTotalDuration = 0
+
+			for (const run of benchmarkRuns) {
+				const tasks = db.getRunTasks(run.id)
+				benchmarkTasks += tasks.length
+
+				for (const task of tasks) {
+					if (task.success) {
+						benchmarkSuccessfulTasks++
+					}
+
+					const metrics = db.getTaskMetrics(task.id)
+
+					const tokensIn = metrics.find((m) => m.name === "tokensIn")?.value || 0
+					const tokensOut = metrics.find((m) => m.name === "tokensOut")?.value || 0
+					benchmarkTotalTokens += tokensIn + tokensOut
+
+					benchmarkTotalCost += metrics.find((m) => m.name === "cost")?.value || 0
+					benchmarkTotalDuration += metrics.find((m) => m.name === "duration")?.value || 0
+				}
+			}
+
+			benchmarkSummary.tasks = benchmarkTasks
+			benchmarkSummary.successRate = benchmarkTasks > 0 ? benchmarkSuccessfulTasks / benchmarkTasks : 0
+			benchmarkSummary.averageTokens = benchmarkTasks > 0 ? benchmarkTotalTokens / benchmarkTasks : 0
+			benchmarkSummary.averageCost = benchmarkTasks > 0 ? benchmarkTotalCost / benchmarkTasks : 0
+			benchmarkSummary.averageDuration = benchmarkTasks > 0 ? benchmarkTotalDuration / benchmarkTasks : 0
+
+			benchmarkReports[benchmark] = benchmarkSummary
+		}
+
+		// Generate model-specific reports
+		const modelReports: Record<string, any> = {}
+
+		for (const model of summary.models) {
+			const modelRuns = runs.filter((run) => run.model === model)
+			const modelSummary = {
+				runs: modelRuns.length,
+				benchmarks: [...new Set(modelRuns.map((run) => run.benchmark))],
+				tasks: 0,
+				successRate: 0,
+				averageTokens: 0,
+				averageCost: 0,
+				averageDuration: 0,
+			}
+
+			let modelTasks = 0
+			let modelSuccessfulTasks = 0
+			let modelTotalTokens = 0
+			let modelTotalCost = 0
+			let modelTotalDuration = 0
+
+			for (const run of modelRuns) {
+				const tasks = db.getRunTasks(run.id)
+				modelTasks += tasks.length
+
+				for (const task of tasks) {
+					if (task.success) {
+						modelSuccessfulTasks++
+					}
+
+					const metrics = db.getTaskMetrics(task.id)
+
+					const tokensIn = metrics.find((m) => m.name === "tokensIn")?.value || 0
+					const tokensOut = metrics.find((m) => m.name === "tokensOut")?.value || 0
+					modelTotalTokens += tokensIn + tokensOut
+
+					modelTotalCost += metrics.find((m) => m.name === "cost")?.value || 0
+					modelTotalDuration += metrics.find((m) => m.name === "duration")?.value || 0
+				}
+			}
+
+			modelSummary.tasks = modelTasks
+			modelSummary.successRate = modelTasks > 0 ? modelSuccessfulTasks / modelTasks : 0
+			modelSummary.averageTokens = modelTasks > 0 ? modelTotalTokens / modelTasks : 0
+			modelSummary.averageCost = modelTasks > 0 ? modelTotalCost / modelTasks : 0
+			modelSummary.averageDuration = modelTasks > 0 ? modelTotalDuration / modelTasks : 0
+
+			modelReports[model] = modelSummary
+		}
+
+		// Save reports
+		const reportDir = path.join(path.resolve(__dirname, "../../../"), "results", "reports")
+		fs.mkdirSync(reportDir, { recursive: true })
+
+		const timestamp = new Date().toISOString().replace(/:/g, "-")
+
+		if (format === "json") {
+			// Save JSON reports
+			fs.writeFileSync(path.join(reportDir, `summary-${timestamp}.json`), JSON.stringify(summary, null, 2))
+
+			fs.writeFileSync(path.join(reportDir, `benchmarks-${timestamp}.json`), JSON.stringify(benchmarkReports, null, 2))
+
+			fs.writeFileSync(path.join(reportDir, `models-${timestamp}.json`), JSON.stringify(modelReports, null, 2))
+
+			spinner.succeed(`JSON reports generated in ${reportDir}`)
+		} else {
+			// Generate markdown report
+			const outputPath = options.output || path.join(reportDir, `report-${timestamp}.md`)
+
+			generateMarkdownReport(summary, benchmarkReports, modelReports, outputPath)
+
+			spinner.succeed(`Markdown report generated at ${outputPath}`)
+		}
+	} catch (error: any) {
+		console.error(chalk.red(`Error generating report: ${error.message}`))
+		console.error(error.stack)
+	} finally {
+		db.close()
+	}
+}

evals/cli/src/commands/run.ts

@@ -0,0 +1,133 @@
+import * as path from "path"
+import { v4 as uuidv4 } from "uuid"
+import chalk from "chalk"
+import ora from "ora"
+import { getAdapter } from "../adapters"
+import { ResultsDatabase } from "../db"
+import { spawnVSCode, cleanupVSCode } from "../utils/vscode"
+import { sendTaskToServer } from "../utils/task"
+import { storeTaskResult } from "../utils/results"
+
+interface RunOptions {
+	benchmark?: string
+	model: string
+	count?: number
+	apiKey?: string
+}
+
+/**
+ * Handler for the run command
+ * @param options Command options
+ */
+export async function runHandler(options: RunOptions): Promise<void> {
+	// Determine which benchmarks to run
+	const benchmarks = options.benchmark ? [options.benchmark] : ["exercism"] // Default to exercism for now
+	const model = options.model
+	const count = options.count || Infinity
+
+	console.log(chalk.blue(`Running evaluations for model: ${model}`))
+	console.log(chalk.blue(`Benchmarks: ${benchmarks.join(", ")}`))
+
+	// Create a run for each benchmark
+	for (const benchmark of benchmarks) {
+		const runId = uuidv4()
+		const db = new ResultsDatabase()
+
+		console.log(chalk.green(`\nStarting run for benchmark: ${benchmark}`))
+
+		// Create run in database
+		db.createRun(runId, model, benchmark)
+
+		// Get adapter for this benchmark
+		try {
+			const adapter = getAdapter(benchmark)
+
+			// List tasks
+			const spinner = ora("Listing tasks...").start()
+			const tasks = await adapter.listTasks()
+			spinner.succeed(`Found ${tasks.length} tasks for ${benchmark}`)
+
+			// Limit number of tasks if specified
+			const tasksToRun = tasks.slice(0, count)
+
+			console.log(chalk.blue(`Running ${tasksToRun.length} tasks...`))
+
+			// Run each task
+			for (let i = 0; i < tasksToRun.length; i++) {
+				const task = tasksToRun[i]
+
+				console.log(chalk.cyan(`\nTask ${i + 1}/${tasksToRun.length}: ${task.name}`))
+
+				// Prepare task
+				const prepareSpinner = ora("Preparing task...").start()
+				const preparedTask = await adapter.prepareTask(task.id)
+				prepareSpinner.succeed("Task prepared")
+
+				// Spawn VSCode
+				console.log("Spawning VSCode...")
+				await spawnVSCode(preparedTask.workspacePath)
+
+				// Send task to server
+				const sendSpinner = ora("Sending task to server...").start()
+				try {
+					const result = await sendTaskToServer(preparedTask.description, options.apiKey)
+					sendSpinner.succeed("Task completed")
+
+					// Verify result
+					const verifySpinner = ora("Verifying result...").start()
+					const verification = await adapter.verifyResult(preparedTask, result)
+
+					if (verification.success) {
+						verifySpinner.succeed(
+							`Verification successful: ${verification.metrics.testsPassed}/${verification.metrics.testsTotal} tests passed`,
+						)
+					} else {
+						verifySpinner.fail(
+							`Verification failed: ${verification.metrics.testsPassed}/${verification.metrics.testsTotal} tests passed`,
+						)
+					}
+
+					// Store result
+					const storeSpinner = ora("Storing result...").start()
+					await storeTaskResult(runId, preparedTask, result, verification)
+					storeSpinner.succeed("Result stored")
+
+					console.log(chalk.green(`Task completed. Success: ${verification.success}`))
+
+					// Clean up VS Code and temporary files
+					const cleanupSpinner = ora("Cleaning up...").start()
+					try {
+						await cleanupVSCode(preparedTask.workspacePath)
+						cleanupSpinner.succeed("Cleanup completed")
+					} catch (cleanupError: any) {
+						cleanupSpinner.fail(`Cleanup failed: ${cleanupError.message}`)
+						console.error(chalk.yellow(cleanupError.stack))
+					}
+				} catch (error: any) {
+					sendSpinner.fail(`Task failed: ${error.message}`)
+					console.error(chalk.red(error.stack))
+
+					// Clean up VS Code and temporary files even if the task failed
+					const cleanupSpinner = ora("Cleaning up...").start()
+					try {
+						await cleanupVSCode(preparedTask.workspacePath)
+						cleanupSpinner.succeed("Cleanup completed")
+					} catch (cleanupError: any) {
+						cleanupSpinner.fail(`Cleanup failed: ${cleanupError.message}`)
+						console.error(chalk.yellow(cleanupError.stack))
+					}
+				}
+			}
+
+			// Mark run as complete
+			db.completeRun(runId)
+
+			console.log(chalk.green(`\nRun complete for benchmark: ${benchmark}`))
+		} catch (error: any) {
+			console.error(chalk.red(`Error running benchmark ${benchmark}: ${error.message}`))
+			console.error(error.stack)
+		}
+	}
+
+	console.log(chalk.green("\nAll evaluations complete"))
+}

evals/cli/src/commands/setup.ts

@@ -0,0 +1,72 @@
+import * as path from "path"
+import * as fs from "fs"
+import execa from "execa"
+import chalk from "chalk"
+import ora from "ora"
+import { getAllAdapters } from "../adapters/index"
+import { BenchmarkAdapter } from "../adapters/types"
+
+interface SetupOptions {
+	benchmarks: string
+}
+
+/**
+ * Handler for the setup command
+ * @param options Command options
+ */
+export async function setupHandler(options: SetupOptions): Promise<void> {
+	const benchmarks = options.benchmarks.split(",")
+
+	console.log(chalk.blue(`Setting up benchmarks: ${benchmarks.join(", ")}`))
+
+	// Create directories
+	const evalsDir = path.resolve(__dirname, "../../../")
+	const reposDir = path.join(evalsDir, "repositories")
+	const resultsDir = path.join(evalsDir, "results")
+
+	const spinner = ora("Creating directory structure").start()
+
+	try {
+		fs.mkdirSync(reposDir, { recursive: true })
+		fs.mkdirSync(resultsDir, { recursive: true })
+		fs.mkdirSync(path.join(resultsDir, "runs"), { recursive: true })
+		fs.mkdirSync(path.join(resultsDir, "reports"), { recursive: true })
+		spinner.succeed("Directory structure created")
+	} catch (error) {
+		spinner.fail(`Failed to create directory structure: ${(error as Error).message}`)
+		throw error
+	}
+
+	// Set up each benchmark
+	try {
+		const adapters = getAllAdapters().filter((adapter: BenchmarkAdapter) => benchmarks.includes(adapter.name))
+
+		if (adapters.length === 0) {
+			console.warn(chalk.yellow("No valid benchmarks specified. Available benchmarks:"))
+			console.warn(
+				chalk.yellow(
+					getAllAdapters()
+						.map((a: BenchmarkAdapter) => a.name)
+						.join(", "),
+				),
+			)
+			return
+		}
+
+		for (const adapter of adapters) {
+			const setupSpinner = ora(`Setting up ${adapter.name}...`).start()
+			try {
+				await adapter.setup()
+				setupSpinner.succeed(`${adapter.name} setup complete`)
+			} catch (error) {
+				setupSpinner.fail(`Failed to set up ${adapter.name}: ${(error as Error).message}`)
+				throw error
+			}
+		}
+
+		console.log(chalk.green("Setup complete"))
+	} catch (error) {
+		console.error(chalk.red(`Setup failed: ${(error as Error).message}`))
+		throw error
+	}
+}

evals/cli/src/db/index.ts

@@ -0,0 +1,211 @@
+import * as path from "path"
+import * as fs from "fs"
+import Database from "better-sqlite3"
+import { SCHEMA } from "./schema"
+
+const EVALS_DIR = path.resolve(__dirname, "../../../")
+
+/**
+ * Database class for storing evaluation results
+ */
+export class ResultsDatabase {
+	db: Database.Database
+
+	constructor() {
+		// Ensure results directory exists
+		const resultsDir = path.join(EVALS_DIR, "results")
+		fs.mkdirSync(resultsDir, { recursive: true })
+
+		// Create database file
+		const dbPath = path.join(resultsDir, "evals.db")
+		this.db = new Database(dbPath)
+
+		// Initialize schema
+		this.initSchema()
+	}
+
+	/**
+	 * Initialize the database schema
+	 */
+	private initSchema(): void {
+		this.db.exec(SCHEMA)
+	}
+
+	/**
+	 * Create a new evaluation run
+	 * @param id Run ID
+	 * @param model Model name
+	 * @param benchmark Benchmark name
+	 */
+	createRun(id: string, model: string, benchmark: string): void {
+		const stmt = this.db.prepare(`
+      INSERT INTO runs (id, timestamp, model, benchmark)
+      VALUES (?, ?, ?, ?)
+    `)
+
+		stmt.run(id, Date.now(), model, benchmark)
+	}
+
+	/**
+	 * Mark a run as completed
+	 * @param id Run ID
+	 */
+	completeRun(id: string): void {
+		const stmt = this.db.prepare(`
+      UPDATE runs SET completed = 1 WHERE id = ?
+    `)
+
+		stmt.run(id)
+	}
+
+	/**
+	 * Create a new task
+	 * @param id Task ID
+	 * @param runId Run ID
+	 * @param taskId Original task ID
+	 */
+	createTask(id: string, runId: string, taskId: string): void {
+		const stmt = this.db.prepare(`
+      INSERT INTO tasks (id, run_id, task_id, timestamp)
+      VALUES (?, ?, ?, ?)
+    `)
+
+		stmt.run(id, runId, taskId, Date.now())
+	}
+
+	/**
+	 * Mark a task as completed
+	 * @param id Task ID
+	 * @param success Whether the task was successful
+	 * @param toolCalls Total tool calls
+	 * @param toolFailures Total tool failures
+	 */
+	completeTask(id: string, success: boolean, toolCalls: number = 0, toolFailures: number = 0): void {
+		const stmt = this.db.prepare(`
+      UPDATE tasks 
+      SET success = ?, total_tool_calls = ?, total_tool_failures = ? 
+      WHERE id = ?
+    `)
+
+		stmt.run(success ? 1 : 0, toolCalls, toolFailures, id)
+	}
+
+	/**
+	 * Add a metric to a task
+	 * @param taskId Task ID
+	 * @param name Metric name
+	 * @param value Metric value
+	 */
+	addMetric(taskId: string, name: string, value: number): void {
+		const stmt = this.db.prepare(`
+      INSERT INTO metrics (task_id, name, value)
+      VALUES (?, ?, ?)
+    `)
+
+		stmt.run(taskId, name, value)
+	}
+
+	/**
+	 * Add a tool call record
+	 * @param taskId Task ID
+	 * @param toolName Tool name
+	 * @param callCount Number of calls
+	 * @param failureCount Number of failures
+	 */
+	addToolCall(taskId: string, toolName: string, callCount: number, failureCount: number): void {
+		const stmt = this.db.prepare(`
+      INSERT INTO tool_calls (task_id, tool_name, call_count, failure_count)
+      VALUES (?, ?, ?, ?)
+    `)
+
+		stmt.run(taskId, toolName, callCount, failureCount)
+	}
+
+	/**
+	 * Add a file record
+	 * @param taskId Task ID
+	 * @param filePath File path
+	 * @param status File status (created, modified, deleted)
+	 */
+	addFile(taskId: string, filePath: string, status: "created" | "modified" | "deleted"): void {
+		const stmt = this.db.prepare(`
+      INSERT INTO files (task_id, path, status)
+      VALUES (?, ?, ?)
+    `)
+
+		stmt.run(taskId, filePath, status)
+	}
+
+	/**
+	 * Get all runs
+	 * @returns Array of runs
+	 */
+	getRuns(): any[] {
+		const stmt = this.db.prepare(`
+      SELECT * FROM runs ORDER BY timestamp DESC
+    `)
+
+		return stmt.all()
+	}
+
+	/**
+	 * Get all tasks for a run
+	 * @param runId Run ID
+	 * @returns Array of tasks
+	 */
+	getRunTasks(runId: string): any[] {
+		const stmt = this.db.prepare(`
+      SELECT * FROM tasks WHERE run_id = ? ORDER BY timestamp ASC
+    `)
+
+		return stmt.all(runId)
+	}
+
+	/**
+	 * Get all metrics for a task
+	 * @param taskId Task ID
+	 * @returns Array of metrics
+	 */
+	getTaskMetrics(taskId: string): any[] {
+		const stmt = this.db.prepare(`
+      SELECT name, value FROM metrics WHERE task_id = ?
+    `)
+
+		return stmt.all(taskId)
+	}
+
+	/**
+	 * Get all tool calls for a task
+	 * @param taskId Task ID
+	 * @returns Array of tool calls
+	 */
+	getTaskToolCalls(taskId: string): any[] {
+		const stmt = this.db.prepare(`
+      SELECT tool_name, call_count, failure_count 
+      FROM tool_calls 
+      WHERE task_id = ?
+    `)
+
+		return stmt.all(taskId)
+	}
+
+	/**
+	 * Get all files for a task
+	 * @param taskId Task ID
+	 * @returns Array of files
+	 */
+	getTaskFiles(taskId: string): any[] {
+		const stmt = this.db.prepare(`
+      SELECT path, status FROM files WHERE task_id = ?
+    `)
+
+		return stmt.all(taskId)
+	}
+
+	/**
+	 * Close the database connection
+	 */
+	close(): void {
+		this.db.close()
+	}
+}

evals/cli/src/db/schema.ts

@@ -0,0 +1,48 @@
+/**
+ * SQL schema for the evaluation database
+ */
+export const SCHEMA = `
+CREATE TABLE IF NOT EXISTS runs (
+  id TEXT PRIMARY KEY,
+  timestamp INTEGER NOT NULL,
+  model TEXT NOT NULL,
+  benchmark TEXT NOT NULL,
+  completed INTEGER NOT NULL DEFAULT 0
+);
+
+CREATE TABLE IF NOT EXISTS tasks (
+  id TEXT PRIMARY KEY,
+  run_id TEXT NOT NULL,
+  task_id TEXT NOT NULL,
+  timestamp INTEGER NOT NULL,
+  success INTEGER NOT NULL DEFAULT 0,
+  total_tool_calls INTEGER DEFAULT 0,
+  total_tool_failures INTEGER DEFAULT 0,
+  FOREIGN KEY (run_id) REFERENCES runs(id)
+);
+
+CREATE TABLE IF NOT EXISTS metrics (
+  id INTEGER PRIMARY KEY AUTOINCREMENT,
+  task_id TEXT NOT NULL,
+  name TEXT NOT NULL,
+  value REAL NOT NULL,
+  FOREIGN KEY (task_id) REFERENCES tasks(id)
+);
+
+CREATE TABLE IF NOT EXISTS tool_calls (
+  id INTEGER PRIMARY KEY AUTOINCREMENT,
+  task_id TEXT NOT NULL,
+  tool_name TEXT NOT NULL,
+  call_count INTEGER NOT NULL,
+  failure_count INTEGER NOT NULL,
+  FOREIGN KEY (task_id) REFERENCES tasks(id)
+);
+
+CREATE TABLE IF NOT EXISTS files (
+  id INTEGER PRIMARY KEY AUTOINCREMENT,
+  task_id TEXT NOT NULL,
+  path TEXT NOT NULL,
+  status TEXT NOT NULL,
+  FOREIGN KEY (task_id) REFERENCES tasks(id)
+);
+`

evals/cli/src/index.ts

@@ -0,0 +1,86 @@
+#!/usr/bin/env node
+import { Command } from "commander"
+import chalk from "chalk"
+import { setupHandler } from "./commands/setup"
+import { runHandler } from "./commands/run"
+import { reportHandler } from "./commands/report"
+import { evalsEnvHandler } from "./commands/evals-env"
+
+// Create the CLI program
+const program = new Command()
+
+// Set up CLI metadata
+program.name("cline-eval").description("CLI tool for orchestrating Cline evaluations across multiple benchmarks").version("0.1.0")
+
+// Setup command
+program
+	.command("setup")
+	.description("Clone and set up benchmark repositories")
+	.option(
+		"-b, --benchmarks <benchmarks>",
+		"Comma-separated list of benchmarks to set up",
+		"exercism,swe-bench,swelancer,multi-swe",
+	)
+	.action(async (options) => {
+		try {
+			await setupHandler(options)
+		} catch (error) {
+			console.error(chalk.red(`Error during setup: ${error instanceof Error ? error.message : String(error)}`))
+			process.exit(1)
+		}
+	})
+
+// Run command
+program
+	.command("run")
+	.description("Run evaluations")
+	.option("-b, --benchmark <benchmark>", "Specific benchmark to run")
+	.option("-m, --model <model>", "Model to evaluate", "claude-3-opus-20240229")
+	.option("-c, --count <count>", "Number of tasks to run", parseInt)
+	.option("-k, --api-key <apiKey>", "Cline API key to use for evaluations")
+	.action(async (options) => {
+		try {
+			await runHandler(options)
+		} catch (error) {
+			console.error(chalk.red(`Error during run: ${error instanceof Error ? error.message : String(error)}`))
+			process.exit(1)
+		}
+	})
+
+// Report command
+program
+	.command("report")
+	.description("Generate reports")
+	.option("-f, --format <format>", "Report format (json, markdown)", "markdown")
+	.option("-o, --output <path>", "Output path for the report")
+	.action(async (options) => {
+		try {
+			await reportHandler(options)
+		} catch (error) {
+			console.error(chalk.red(`Error generating report: ${error instanceof Error ? error.message : String(error)}`))
+			process.exit(1)
+		}
+	})
+
+// Evals-env command
+program
+	.command("evals-env")
+	.description("Manage evals.env files for test mode activation")
+	.argument("<action>", "Action to perform: create, remove, or check")
+	.option("-d, --directory <directory>", "Directory to create/remove/check evals.env file in (defaults to current directory)")
+	.action(async (action, options) => {
+		try {
+			await evalsEnvHandler({ action, ...options })
+		} catch (error) {
+			console.error(chalk.red(`Error managing evals.env file: ${error instanceof Error ? error.message : String(error)}`))
+			process.exit(1)
+		}
+	})
+
+// Parse command line arguments
+program.parse(process.argv)
+
+// If no arguments provided, show help
+if (process.argv.length === 2) {
+	program.help()
+}

evals/cli/src/utils/evals-env.ts

@@ -0,0 +1,79 @@
+import * as fs from "fs"
+import * as path from "path"
+import chalk from "chalk"
+
+/**
+ * Creates an evals.env file in the specified directory
+ * @param directory The directory where the evals.env file should be created
+ * @returns True if the file was created, false if it already exists
+ */
+export function createEvalsEnvFile(directory: string): boolean {
+	const evalsEnvPath = path.join(directory, "evals.env")
+
+	// Check if the file already exists
+	if (fs.existsSync(evalsEnvPath)) {
+		console.log(chalk.yellow(`evals.env file already exists at ${evalsEnvPath}`))
+		return false
+	}
+
+	// Create the file
+	try {
+		const content = `# This file activates Cline test mode
+# Created at: ${new Date().toISOString()}
+# 
+# This file is automatically detected by the Cline extension
+# and enables test mode for automated evaluations.
+#
+# Delete this file to deactivate test mode.
+`
+		fs.writeFileSync(evalsEnvPath, content)
+		console.log(chalk.green(`Created evals.env file at ${evalsEnvPath}`))
+		return true
+	} catch (error) {
+		console.error(chalk.red(`Error creating evals.env file: ${error}`))
+		return false
+	}
+}
+
+/**
+ * Removes an evals.env file from the specified directory
+ * @param directory The directory where the evals.env file should be removed
+ * @returns True if the file was removed, false if it doesn't exist
+ */
+export function removeEvalsEnvFile(directory: string): boolean {
+	const evalsEnvPath = path.join(directory, "evals.env")
+
+	// Check if the file exists
+	if (!fs.existsSync(evalsEnvPath)) {
+		console.log(chalk.yellow(`No evals.env file found at ${evalsEnvPath}`))
+		return false
+	}
+
+	// Remove the file
+	try {
+		fs.unlinkSync(evalsEnvPath)
+		console.log(chalk.green(`Removed evals.env file from ${evalsEnvPath}`))
+		return true
+	} catch (error) {
+		console.error(chalk.red(`Error removing evals.env file: ${error}`))
+		return false
+	}
+}
+
+/**
+ * Checks if an evals.env file exists in the specified directory
+ * @param directory The directory to check for an evals.env file
+ * @returns True if the file exists, false otherwise
+ */
+export function checkEvalsEnvFile(directory: string): boolean {
+	const evalsEnvPath = path.join(directory, "evals.env")
+	const exists = fs.existsSync(evalsEnvPath)
+
+	if (exists) {
+		console.log(chalk.green(`evals.env file found at ${evalsEnvPath}`))
+	} else {
+		console.log(chalk.yellow(`No evals.env file found at ${evalsEnvPath}`))
+	}
+
+	return exists
+}

evals/cli/src/utils/extensions.ts

@@ -0,0 +1,131 @@
+import execa from "execa"
+import * as fs from "fs"
+import * as path from "path"
+import * as os from "os"
+
+/**
+ * List of VSCode extensions to install for evaluation environments
+ * These extensions provide language support and other useful features
+ */
+export const REQUIRED_EXTENSIONS = [
+	"golang.go", // Go language support
+	"dbaeumer.vscode-eslint", // ESLint support
+	"redhat.java", // Java support
+	"ms-python.python", // Python support
+	"rust-lang.rust-analyzer", // Rust support
+	"ms-vscode.cpptools", // C/C++ support
+]
+
+/**
+ * Install required VSCode extensions in the specified extensions directory
+ * @param extensionsDir The directory where extensions should be installed
+ * @returns Promise that resolves when all extensions are installed
+ */
+export async function installRequiredExtensions(extensionsDir: string): Promise<void> {
+	console.log("Installing required VSCode extensions...")
+
+	// Create the extensions directory if it doesn't exist
+	if (!fs.existsSync(extensionsDir)) {
+		fs.mkdirSync(extensionsDir, { recursive: true })
+	}
+
+	// Install each extension
+	for (const extension of REQUIRED_EXTENSIONS) {
+		try {
+			console.log(`Installing extension: ${extension}...`)
+			await execa("code", ["--extensions-dir", extensionsDir, "--install-extension", extension, "--force"])
+			console.log(`✅ Extension ${extension} installed successfully`)
+		} catch (error: any) {
+			console.warn(`⚠️ Failed to install extension ${extension}: ${error.message}`)
+			// Continue with other extensions even if one fails
+		}
+	}
+
+	console.log("✅ All required extensions installed")
+}
+
+/**
+ * Check if a VSCode extension is installed in the specified directory
+ * @param extensionsDir The directory to check for installed extensions
+ * @param extensionId The ID of the extension to check
+ * @returns True if the extension is installed, false otherwise
+ */
+export function isExtensionInstalled(extensionsDir: string, extensionId: string): boolean {
+	// Extensions are installed in directories named publisher.name-version
+	// We need to check if any directory starts with the extensionId
+	const extensionPrefix = extensionId.toLowerCase() + "-"
+
+	try {
+		const files = fs.readdirSync(extensionsDir)
+		return files.some((file) => {
+			const lowerCaseFile = file.toLowerCase()
+			return lowerCaseFile === extensionId.toLowerCase() || lowerCaseFile.startsWith(extensionPrefix)
+		})
+	} catch (error) {
+		return false
+	}
+}
+
+/**
+ * Get the path to the VSCode settings file in the specified user data directory
+ * @param userDataDir The VSCode user data directory
+ * @returns The path to the settings.json file
+ */
+export function getSettingsPath(userDataDir: string): string {
+	const settingsDir = path.join(userDataDir, "User")
+	fs.mkdirSync(settingsDir, { recursive: true })
+	return path.join(settingsDir, "settings.json")
+}
+
+/**
+ * Configure extension settings in the VSCode user data directory
+ * @param userDataDir The VSCode user data directory
+ */
+export function configureExtensionSettings(userDataDir: string): void {
+	const settingsPath = getSettingsPath(userDataDir)
+
+	// Read existing settings if they exist
+	let settings = {}
+	if (fs.existsSync(settingsPath)) {
+		try {
+			settings = JSON.parse(fs.readFileSync(settingsPath, "utf8"))
+		} catch (error) {
+			console.warn(`Error reading settings file: ${error}`)
+		}
+	}
+
+	// Add or update extension-specific settings
+	const updatedSettings = {
+		...settings,
+		// Go extension settings
+		"go.toolsManagement.autoUpdate": false,
+		"go.survey.prompt": false,
+
+		// ESLint settings
+		"eslint.enable": true,
+		"eslint.run": "onSave",
+
+		// Java settings
+		"java.configuration.checkProjectSettingsExclusions": false,
+		"java.configure.checkForOutdatedExtensions": false,
+		"java.help.firstView": false,
+
+		// Python settings
+		"python.experiments.enabled": false,
+		"python.showStartPage": false,
+
+		// Rust settings
+		"rust-analyzer.checkOnSave.command": "check",
+
+		// C/C++ settings
+		"C_Cpp.intelliSenseEngine": "default",
+
+		// General extension settings
+		"extensions.autoUpdate": false,
+		"extensions.ignoreRecommendations": true,
+	}
+
+	// Write updated settings
+	fs.writeFileSync(settingsPath, JSON.stringify(updatedSettings, null, 2))
+	console.log("✅ Extension settings configured")
+}

evals/cli/src/utils/markdown.ts

@@ -0,0 +1,109 @@
+import * as fs from "fs"
+import * as path from "path"
+
+/**
+ * Generate a markdown report from evaluation results
+ * @param summary Overall summary
+ * @param benchmarkReports Benchmark-specific reports
+ * @param modelReports Model-specific reports
+ * @param outputPath Output file path
+ */
+export function generateMarkdownReport(
+	summary: any,
+	benchmarkReports: Record<string, any>,
+	modelReports: Record<string, any>,
+	outputPath: string,
+): void {
+	let markdown = `# Cline Evaluation Report\n\n`
+
+	// Generate summary section
+	markdown += `## Summary\n\n`
+	markdown += `- **Total Runs:** ${summary.runs}\n`
+	markdown += `- **Models:** ${summary.models.join(", ")}\n`
+	markdown += `- **Benchmarks:** ${summary.benchmarks.join(", ")}\n`
+	markdown += `- **Total Tasks:** ${summary.tasks}\n`
+	markdown += `- **Success Rate:** ${(summary.successRate * 100).toFixed(2)}%\n`
+	markdown += `- **Average Tokens:** ${Math.round(summary.averageTokens)}\n`
+	markdown += `- **Average Cost:** $${summary.averageCost.toFixed(4)}\n`
+	markdown += `- **Average Duration:** ${(summary.averageDuration / 1000).toFixed(2)}s\n`
+	markdown += `- **Total Tool Calls:** ${summary.totalToolCalls}\n`
+	markdown += `- **Tool Success Rate:** ${(summary.toolSuccessRate * 100).toFixed(2)}%\n\n`
+
+	// Generate tool usage section
+	markdown += `## Tool Usage\n\n`
+	markdown += `| Tool | Calls | Failures | Success Rate |\n`
+	markdown += `| ---- | ----- | -------- | ------------ |\n`
+
+	for (const [toolName, metrics] of Object.entries(summary.toolUsage)) {
+		const calls = (metrics as any).calls
+		const failures = (metrics as any).failures
+		const successRate = calls > 0 ? (1 - failures / calls) * 100 : 100
+
+		markdown += `| ${toolName} | ${calls} | ${failures} | ${successRate.toFixed(2)}% |\n`
+	}
+
+	// Generate benchmark results section
+	markdown += `\n## Benchmark Results\n\n`
+
+	for (const [benchmark, report] of Object.entries(benchmarkReports)) {
+		markdown += `### ${benchmark}\n\n`
+		markdown += `- **Runs:** ${report.runs}\n`
+		markdown += `- **Models:** ${report.models.join(", ")}\n`
+		markdown += `- **Tasks:** ${report.tasks}\n`
+		markdown += `- **Success Rate:** ${(report.successRate * 100).toFixed(2)}%\n`
+		markdown += `- **Average Tokens:** ${Math.round(report.averageTokens)}\n`
+		markdown += `- **Average Cost:** $${report.averageCost.toFixed(4)}\n`
+		markdown += `- **Average Duration:** ${(report.averageDuration / 1000).toFixed(2)}s\n\n`
+	}
+
+	// Generate model results section
+	markdown += `## Model Results\n\n`
+
+	for (const [model, report] of Object.entries(modelReports)) {
+		markdown += `### ${model}\n\n`
+		markdown += `- **Runs:** ${report.runs}\n`
+		markdown += `- **Benchmarks:** ${report.benchmarks.join(", ")}\n`
+		markdown += `- **Tasks:** ${report.tasks}\n`
+		markdown += `- **Success Rate:** ${(report.successRate * 100).toFixed(2)}%\n`
+		markdown += `- **Average Tokens:** ${Math.round(report.averageTokens)}\n`
+		markdown += `- **Average Cost:** $${report.averageCost.toFixed(4)}\n`
+		markdown += `- **Average Duration:** ${(report.averageDuration / 1000).toFixed(2)}s\n\n`
+	}
+
+	// Add charts using Mermaid
+	markdown += `## Charts\n\n`
+
+	// Success rate by benchmark chart
+	markdown += `### Success Rate by Benchmark\n\n`
+	markdown += "```mermaid\n"
+	markdown += "graph TD\n"
+	markdown += "  title[Success Rate by Benchmark]\n"
+	markdown += "  style title fill:none,stroke:none\n\n"
+
+	for (const [benchmark, report] of Object.entries(benchmarkReports)) {
+		const successRate = (report.successRate * 100).toFixed(2)
+		markdown += `  ${benchmark}[${benchmark}: ${successRate}%]\n`
+	}
+
+	markdown += "```\n\n"
+
+	// Success rate by model chart
+	markdown += `### Success Rate by Model\n\n`
+	markdown += "```mermaid\n"
+	markdown += "graph TD\n"
+	markdown += "  title[Success Rate by Model]\n"
+	markdown += "  style title fill:none,stroke:none\n\n"
+
+	for (const [model, report] of Object.entries(modelReports)) {
+		const successRate = (report.successRate * 100).toFixed(2)
+		markdown += `  ${model.replace(/[-\.]/g, "_")}[${model}: ${successRate}%]\n`
+	}
+
+	markdown += "```\n\n"
+
+	// Add timestamp
+	markdown += `\n\n---\n\nReport generated on ${new Date().toISOString()}\n`
+
+	// Write markdown to file
+	fs.writeFileSync(outputPath, markdown)
+}

evals/cli/src/utils/results.ts

@@ -0,0 +1,79 @@
+import { v4 as uuidv4 } from "uuid"
+import { ResultsDatabase } from "../db"
+import { Task } from "../adapters/types"
+
+/**
+ * Store task result in the database
+ * @param runId The run ID
+ * @param task The task that was executed
+ * @param result The result from the test server
+ * @param verification The verification result
+ */
+export async function storeTaskResult(runId: string, task: Task, result: any, verification: any): Promise<void> {
+	const db = new ResultsDatabase()
+	const taskId = uuidv4()
+
+	try {
+		// Extract metrics from the result
+		const { metrics } = result
+		const totalToolCalls = metrics?.totalToolCalls || 0
+		const totalToolFailures = metrics?.totalToolFailures || 0
+
+		// Create task with tool metrics
+		db.createTask(taskId, runId, task.id)
+		db.completeTask(taskId, verification.success, totalToolCalls, totalToolFailures)
+
+		// Store metrics
+		if (metrics) {
+			// Store token metrics
+			if (metrics.tokensIn) db.addMetric(taskId, "tokensIn", metrics.tokensIn)
+			if (metrics.tokensOut) db.addMetric(taskId, "tokensOut", metrics.tokensOut)
+			if (metrics.cost) db.addMetric(taskId, "cost", metrics.cost)
+			if (metrics.duration) db.addMetric(taskId, "duration", metrics.duration)
+
+			// Store tool call metrics
+			if (metrics.toolCalls) {
+				for (const [toolName, callCount] of Object.entries(metrics.toolCalls)) {
+					const failureCount = metrics.toolFailures?.[toolName] || 0
+					db.addToolCall(taskId, toolName, callCount as number, failureCount)
+				}
+			}
+		}
+
+		// Store verification metrics
+		if (verification.metrics) {
+			for (const [key, value] of Object.entries(verification.metrics)) {
+				if (typeof value === "number") {
+					db.addMetric(taskId, key, value)
+				}
+			}
+		}
+
+		// Store file changes
+		if (result.files) {
+			// Store created files
+			if (result.files.created) {
+				for (const file of result.files.created) {
+					db.addFile(taskId, file, "created")
+				}
+			}
+
+			// Store modified files
+			if (result.files.modified) {
+				for (const file of result.files.modified) {
+					db.addFile(taskId, file, "modified")
+				}
+			}
+
+			// Store deleted files
+			if (result.files.deleted) {
+				for (const file of result.files.deleted) {
+					db.addFile(taskId, file, "deleted")
+				}
+			}
+		}
+	} finally {
+		// Close the database connection
+		db.close()
+	}
+}

evals/cli/src/utils/task.ts

@@ -0,0 +1,52 @@
+import fetch from "node-fetch"
+import chalk from "chalk"
+
+/**
+ * Send a task to the Cline test server
+ * @param task The task description to send
+ * @param apiKey Optional Cline API key to use for the task
+ * @returns The result of the task execution
+ */
+export async function sendTaskToServer(task: string, apiKey?: string): Promise<any> {
+	const SERVER_URL = "http://localhost:9876/task"
+
+	try {
+		console.log(chalk.blue(`Sending task to server: ${task.substring(0, 100)}${task.length > 100 ? "..." : ""}`))
+
+		const response = await fetch(SERVER_URL, {
+			method: "POST",
+			headers: {
+				"Content-Type": "application/json",
+			},
+			body: JSON.stringify({
+				task,
+				apiKey,
+			}),
+		})
+
+		if (!response.ok) {
+			const errorText = await response.text()
+			throw new Error(`Server responded with status ${response.status}: ${errorText}`)
+		}
+
+		const result = await response.json()
+
+		if (!result.success) {
+			throw new Error(`Task execution failed: ${result.error || "Unknown error"}`)
+		}
+
+		if (result.timeout) {
+			throw new Error("Task execution timed out")
+		}
+
+		return result
+	} catch (error: any) {
+		if (error.code === "ECONNREFUSED") {
+			throw new Error(
+				"Could not connect to the test server. Make sure VSCode is running with the Cline extension and the test server is active.",
+			)
+		}
+
+		throw error
+	}
+}

evals/cli/src/utils/vscode.ts

@@ -0,0 +1,615 @@
+import execa from "execa"
+import * as path from "path"
+import * as fs from "fs"
+import fetch from "node-fetch"
+import * as os from "os"
+import { installRequiredExtensions, configureExtensionSettings } from "./extensions"
+
+// Store temporary directories for cleanup
+interface VSCodeResources {
+	tempUserDataDir: string
+	tempExtensionsDir: string
+	vscodePid?: number
+}
+
+// Global map to track resources for each workspace
+const workspaceResources = new Map<string, VSCodeResources>()
+
+/**
+ * Spawn a VSCode instance with the Cline extension
+ * @param workspacePath The workspace path to open
+ * @param vsixPath Optional path to a VSIX file to install
+ * @returns The resources created for this VS Code instance
+ */
+export async function spawnVSCode(workspacePath: string, vsixPath?: string): Promise<VSCodeResources> {
+	// Ensure the workspace path exists
+	if (!fs.existsSync(workspacePath)) {
+		throw new Error(`Workspace path does not exist: ${workspacePath}`)
+	}
+
+	// If no VSIX path is provided, build one with IS_TEST=true
+	if (!vsixPath) {
+		try {
+			// Build the VSIX (no longer need to set IS_TEST=true as we'll use evals.env file)
+			console.log("Building VSIX...")
+			const clineRoot = path.resolve(process.cwd(), "..", "..")
+			await execa("npx", ["vsce", "package"], {
+				cwd: clineRoot,
+				stdio: "inherit",
+			})
+
+			// Find the generated VSIX file(s)
+			const files = fs.readdirSync(clineRoot)
+			const vsixFiles = files.filter((file) => file.endsWith(".vsix"))
+
+			if (vsixFiles.length > 0) {
+				// Get file stats to find the most recent one
+				const vsixFilesWithStats = vsixFiles.map((file) => {
+					const filePath = path.join(clineRoot, file)
+					return {
+						file,
+						path: filePath,
+						mtime: fs.statSync(filePath).mtime,
+					}
+				})
+
+				// Sort by modification time (most recent first)
+				vsixFilesWithStats.sort((a, b) => b.mtime.getTime() - a.mtime.getTime())
+
+				// Use the most recent VSIX
+				vsixPath = vsixFilesWithStats[0].path
+				console.log(`Using most recent VSIX: ${vsixPath} (modified ${vsixFilesWithStats[0].mtime.toISOString()})`)
+
+				// Log all found VSIX files for debugging
+				if (vsixFiles.length > 1) {
+					console.log(`Found ${vsixFiles.length} VSIX files:`)
+					vsixFilesWithStats.forEach((f) => {
+						console.log(`  - ${f.file} (modified ${f.mtime.toISOString()})`)
+					})
+				}
+			} else {
+				console.warn("Could not find generated VSIX file")
+			}
+		} catch (error) {
+			console.warn("Failed to build test VSIX:", error)
+		}
+	}
+
+	// Create a temporary user data directory for this VS Code instance
+	const tempUserDataDir = path.join(os.tmpdir(), `vscode-cline-eval-${Date.now()}`)
+	fs.mkdirSync(tempUserDataDir, { recursive: true })
+	console.log(`Created temporary user data directory: ${tempUserDataDir}`)
+
+	// Create a temporary extensions directory to ensure no other extensions are loaded
+	const tempExtensionsDir = path.join(os.tmpdir(), `vscode-cline-eval-ext-${Date.now()}`)
+	fs.mkdirSync(tempExtensionsDir, { recursive: true })
+	console.log(`Created temporary extensions directory: ${tempExtensionsDir}`)
+
+	// Create evals.env file in the workspace to trigger test mode
+	console.log(`Creating evals.env file in workspace: ${workspacePath}`)
+	const evalsEnvPath = path.join(workspacePath, "evals.env")
+	fs.writeFileSync(
+		evalsEnvPath,
+		`# This file activates Cline test mode
+# Created at: ${new Date().toISOString()}
+# 
+# This file is automatically detected by the Cline extension
+# and enables test mode for automated evaluations.
+#
+# Delete this file to deactivate test mode.
+`,
+	)
+
+	// Create settings.json in the temporary user data directory to disable workspace trust
+	// and configure Cline to auto-open on startup
+	const settingsDir = path.join(tempUserDataDir, "User")
+	fs.mkdirSync(settingsDir, { recursive: true })
+	const settingsPath = path.join(settingsDir, "settings.json")
+	const settings = {
+		// Disable workspace trust
+		"security.workspace.trust.enabled": false,
+		"security.workspace.trust.startupPrompt": "never",
+		"security.workspace.trust.banner": "never",
+		"security.workspace.trust.emptyWindow": true,
+
+		// Configure startup behavior
+		"workbench.startupEditor": "none",
+
+		// Auto-open Cline on startup
+		"cline.autoOpenOnStartup": true,
+
+		// Show the activity bar and sidebar
+		"workbench.activityBar.visible": true,
+		"workbench.sideBar.visible": true,
+		"workbench.view.extension.saoudrizwan.claude-dev-ActivityBar.visible": true,
+		"workbench.view.alwaysShowHeaderActions": true,
+		"workbench.editor.openSideBySideDirection": "right",
+
+		// Disable GitLens from opening automatically
+		"gitlens.views.repositories.autoReveal": false,
+		"gitlens.views.fileHistory.autoReveal": false,
+		"gitlens.views.lineHistory.autoReveal": false,
+		"gitlens.views.compare.autoReveal": false,
+		"gitlens.views.search.autoReveal": false,
+		"gitlens.showWelcomeOnInstall": false,
+		"gitlens.showWhatsNewAfterUpgrades": false,
+
+		// Disable other extensions that might compete for startup focus
+		"extensions.autoUpdate": false,
+	}
+	fs.writeFileSync(settingsPath, JSON.stringify(settings, null, 2))
+	console.log(`Created settings.json to disable workspace trust and auto-open Cline`)
+
+	// Create keybindings.json to automatically open Cline on startup
+	const keybindingsPath = path.join(settingsDir, "keybindings.json")
+	const keybindings = [
+		{
+			key: "alt+c",
+			command: "workbench.view.extension.saoudrizwan.claude-dev-ActivityBar",
+			when: "viewContainer.workbench.view.extension.saoudrizwan.claude-dev-ActivityBar.enabled",
+		},
+		{
+			key: "alt+shift+c",
+			command: "cline.openInNewTab",
+			when: "viewContainer.workbench.view.extension.saoudrizwan.claude-dev-ActivityBar.enabled",
+		},
+	]
+	fs.writeFileSync(keybindingsPath, JSON.stringify(keybindings, null, 2))
+	console.log(`Created keybindings.json to help with Cline activation`)
+
+	// Build the command arguments with custom user data directory
+	const args = [
+		// Use a custom user data directory to isolate this instance
+		"--user-data-dir",
+		tempUserDataDir,
+		// Use a custom extensions directory to ensure only our extension is loaded
+		"--extensions-dir",
+		tempExtensionsDir,
+		// Disable workspace trust
+		"--disable-workspace-trust",
+		"-n",
+		workspacePath,
+		// Force the extension to be activated on startup
+		"--start-up-extension",
+		"saoudrizwan.claude-dev",
+		// Run a command on startup to open Cline
+		"--command",
+		"workbench.view.extension.saoudrizwan.claude-dev-ActivityBar",
+		// Additional flags to help with extension activation
+		"--disable-gpu=false",
+		"--max-memory=4096",
+	]
+
+	// Create a startup script to run commands after VS Code launches
+	const startupScriptPath = path.join(settingsDir, "startup.js")
+	const startupScript = `
+		// This script will be executed when VS Code starts
+		setTimeout(() => {
+			// Try to open Cline in the sidebar
+			require('vscode').commands.executeCommand('workbench.view.extension.saoudrizwan.claude-dev-ActivityBar');
+			
+			// Also try to open Cline in a tab as a fallback
+			setTimeout(() => {
+				require('vscode').commands.executeCommand('cline.openInNewTab');
+			}, 5000);
+		}, 5000);
+	`
+	fs.writeFileSync(startupScriptPath, startupScript)
+	console.log(`Created startup script to activate Cline`)
+
+	// If a VSIX is provided, install it
+	if (vsixPath) {
+		if (!fs.existsSync(vsixPath)) {
+			throw new Error(`VSIX file does not exist: ${vsixPath}`)
+		}
+		args.unshift("--install-extension", vsixPath)
+	}
+
+	// Install required extensions
+	console.log("Installing required VSCode extensions...")
+	await installRequiredExtensions(tempExtensionsDir)
+
+	// Configure extension settings
+	console.log("Configuring extension settings...")
+	configureExtensionSettings(tempUserDataDir)
+
+	// Execute the command
+	try {
+		// We don't need to install extensions globally anymore since we're using a custom user data directory
+		// The VSIX will be installed in the isolated environment if provided in the args
+
+		// Launch VS Code
+		console.log("Launching VS Code...")
+		await execa("code", args, {
+			stdio: "inherit",
+		})
+
+		// Wait longer for VSCode to initialize and extension to load
+		console.log("Waiting for VS Code to initialize...")
+		await new Promise((resolve) => setTimeout(resolve, 30000))
+
+		// Create a JavaScript file that will be loaded as a VS Code extension
+		const extensionDir = path.join(tempExtensionsDir, "cline-activator")
+		fs.mkdirSync(extensionDir, { recursive: true })
+
+		// Create package.json for the extension
+		const packageJsonPath = path.join(extensionDir, "package.json")
+		const packageJson = {
+			name: "cline-activator",
+			displayName: "Cline Activator",
+			description: "Activates Cline and starts the test server",
+			version: "0.0.1",
+			engines: {
+				vscode: "^1.60.0",
+			},
+			main: "./extension.js",
+			activationEvents: ["*"],
+			contributes: {
+				commands: [
+					{
+						command: "cline-activator.activate",
+						title: "Activate Cline",
+					},
+				],
+			},
+		}
+		fs.writeFileSync(packageJsonPath, JSON.stringify(packageJson, null, 2))
+
+		// Create extension.js
+		const extensionJsPath = path.join(extensionDir, "extension.js")
+		const extensionJs = `
+			const vscode = require('vscode');
+			
+			/**
+			 * @param {vscode.ExtensionContext} context
+			 */
+			function activate(context) {
+				console.log('Cline Activator is now active!');
+				
+				// Register the command to activate Cline
+				let disposable = vscode.commands.registerCommand('cline-activator.activate', async function () {
+					try {
+						// Make sure the Cline extension is activated
+						const extension = vscode.extensions.getExtension('saoudrizwan.claude-dev');
+						if (!extension) {
+							console.error('Cline extension not found');
+							return;
+						}
+						
+						if (!extension.isActive) {
+							console.log('Activating Cline extension...');
+							await extension.activate();
+						}
+						
+						// Show the Cline sidebar
+						console.log('Opening Cline sidebar...');
+						await vscode.commands.executeCommand('workbench.view.extension.saoudrizwan.claude-dev-ActivityBar');
+						
+						// Wait a moment for the sidebar to initialize
+						await new Promise(resolve => setTimeout(resolve, 2000));
+						
+						// Also open Cline in a tab as a fallback
+						console.log('Opening Cline in a tab...');
+						await vscode.commands.executeCommand('cline.openInNewTab');
+						
+						// Wait a moment for the tab to initialize
+						await new Promise(resolve => setTimeout(resolve, 2000));
+						
+						// Create the test server if it doesn't exist
+						console.log('Creating test server...');
+						
+						// Get the visible webview instance
+						const clineRootPath = '${path.resolve(process.cwd(), "..", "..")}';
+						const visibleWebview = require(path.join(clineRootPath, 'src', 'core', 'webview')).WebviewProvider.getVisibleInstance();
+						if (visibleWebview) {
+							require(path.join(clineRootPath, 'src', 'services', 'test', 'TestServer')).createTestServer(visibleWebview);
+							console.log('Test server created successfully');
+						} else {
+							console.error('No visible webview instance found');
+						}
+					} catch (error) {
+						console.error('Error activating Cline:', error);
+					}
+				});
+				
+				context.subscriptions.push(disposable);
+				
+				// Automatically run the command after a delay
+				setTimeout(() => {
+					vscode.commands.executeCommand('cline-activator.activate');
+				}, 5000);
+			}
+			
+			function deactivate() {}
+			
+			module.exports = {
+				activate,
+				deactivate
+			}
+		`
+		fs.writeFileSync(extensionJsPath, extensionJs)
+		console.log(`Created Cline Activator extension`)
+
+		// Try multiple approaches to activate the extension
+		let serverStarted = false
+
+		// Create an activation script to run in VS Code
+		const activationScriptPath = path.join(settingsDir, "activate-cline.js")
+		const activationScript = `
+			// This script will be executed to activate Cline and start the test server
+			const vscode = require('vscode');
+			
+			// Execute the cline-activator.activate command
+			vscode.commands.executeCommand('cline-activator.activate');
+		`
+		fs.writeFileSync(activationScriptPath, activationScript)
+		console.log(`Created activation script to run in VS Code`)
+
+		// Execute the activation script
+		try {
+			console.log("Executing activation script to start Cline and test server...")
+			await execa(
+				"code",
+				[
+					"--user-data-dir",
+					tempUserDataDir,
+					"--extensions-dir",
+					tempExtensionsDir,
+					"--folder-uri",
+					`file://${workspacePath}`,
+					"--execute",
+					activationScriptPath,
+				],
+				{
+					stdio: "inherit",
+				},
+			)
+
+			// Wait for the test server to start
+			console.log("Waiting for test server to start...")
+			for (let i = 0; i < 30; i++) {
+				try {
+					// Try to connect to the test server
+					const response = await fetch("http://localhost:9876/task", {
+						method: "OPTIONS",
+						headers: {
+							"Content-Type": "application/json",
+						},
+					})
+
+					if (response.status === 204) {
+						console.log("Test server is running!")
+						serverStarted = true
+						break
+					}
+				} catch (error) {
+					// Server not started yet, wait and try again
+					await new Promise((resolve) => setTimeout(resolve, 1000))
+				}
+			}
+		} catch (error) {
+			console.warn("Failed to execute activation script:", error)
+		}
+
+		if (!serverStarted) {
+			console.warn("Test server did not start after multiple attempts")
+			console.log("You may need to manually open the Cline extension in VS Code")
+		}
+
+		// Store the resources for this workspace
+		const resources: VSCodeResources = {
+			tempUserDataDir,
+			tempExtensionsDir,
+		}
+
+		// Store in the global map
+		workspaceResources.set(workspacePath, resources)
+
+		// Return the resources
+		return resources
+	} catch (error: any) {
+		throw new Error(`Failed to spawn VSCode: ${error.message}`)
+	}
+}
+
+/**
+ * Clean up VS Code resources and shut down the test server
+ * @param workspacePath The workspace path to clean up resources for
+ */
+export async function cleanupVSCode(workspacePath: string): Promise<void> {
+	console.log(`Cleaning up VS Code resources for workspace: ${workspacePath}`)
+
+	// Get the resources for this workspace
+	const resources = workspaceResources.get(workspacePath)
+	if (!resources) {
+		console.log(`No resources found for workspace: ${workspacePath}`)
+		return
+	}
+
+	// Try to shut down the test server
+	try {
+		console.log("Shutting down test server...")
+		await fetch("http://localhost:9876/shutdown", {
+			method: "POST",
+			headers: {
+				"Content-Type": "application/json",
+			},
+		}).catch(() => {
+			// Ignore errors, the server might already be down
+		})
+	} catch (error) {
+		console.warn(`Error shutting down test server: ${error}`)
+	}
+
+	// Try to gracefully close VS Code instead of killing it
+	try {
+		console.log("Attempting to gracefully close VS Code...")
+
+		// Create a settings file that will disable the crash reporter and the exit confirmation dialog
+		const settingsDir = path.join(resources.tempUserDataDir, "User")
+		const settingsPath = path.join(settingsDir, "settings.json")
+
+		// Read existing settings if they exist
+		let settings = {}
+		if (fs.existsSync(settingsPath)) {
+			try {
+				settings = JSON.parse(fs.readFileSync(settingsPath, "utf8"))
+			} catch (error) {
+				console.warn(`Error reading settings file: ${error}`)
+			}
+		}
+
+		// Update settings to disable crash reporter and exit confirmation
+		settings = {
+			...settings,
+			"window.confirmBeforeClose": "never",
+			"telemetry.enableCrashReporter": false,
+			"window.restoreWindows": "none",
+			"window.newWindowDimensions": "default",
+		}
+
+		// Write updated settings
+		fs.writeFileSync(settingsPath, JSON.stringify(settings, null, 2))
+
+		// On macOS, use AppleScript to quit VS Code gracefully
+		if (process.platform === "darwin") {
+			try {
+				// First try AppleScript to quit VS Code gracefully
+				await execa("osascript", ["-e", 'tell application "Visual Studio Code" to quit'])
+
+				// Wait a moment for VS Code to close
+				await new Promise((resolve) => setTimeout(resolve, 2000))
+			} catch (appleScriptError) {
+				console.warn(`Error using AppleScript to quit VS Code: ${appleScriptError}`)
+			}
+		} else if (process.platform === "win32") {
+			// On Windows, try to use taskkill without /F first
+			try {
+				await execa("taskkill", ["/IM", "code.exe"])
+
+				// Wait a moment for VS Code to close
+				await new Promise((resolve) => setTimeout(resolve, 2000))
+			} catch (taskkillError) {
+				console.warn(`Error using taskkill to quit VS Code: ${taskkillError}`)
+			}
+		} else {
+			// On Linux, try to use SIGTERM first
+			try {
+				// Find VS Code processes
+				const { stdout } = await execa("ps", ["aux"])
+				const lines = stdout.split("\n")
+
+				for (const line of lines) {
+					if (line.includes(resources.tempUserDataDir)) {
+						const parts = line.trim().split(/\s+/)
+						const pid = parseInt(parts[1])
+
+						if (pid && !isNaN(pid)) {
+							console.log(`Sending SIGTERM to VS Code process with PID: ${pid}`)
+							try {
+								// Use SIGTERM instead of SIGKILL for a graceful shutdown
+								process.kill(pid, "SIGTERM")
+							} catch (killError) {
+								console.warn(`Failed to terminate process ${pid}: ${killError}`)
+							}
+						}
+					}
+				}
+
+				// Wait a moment for VS Code to close
+				await new Promise((resolve) => setTimeout(resolve, 2000))
+			} catch (psError) {
+				console.warn(`Error listing processes: ${psError}`)
+			}
+		}
+
+		// If graceful methods failed, fall back to forceful termination as a last resort
+		// Check if VS Code is still running with the temp user data dir
+		let vsCodeStillRunning = false
+
+		if (process.platform !== "win32") {
+			try {
+				const { stdout } = await execa("ps", ["aux"])
+				vsCodeStillRunning = stdout.split("\n").some((line) => line.includes(resources.tempUserDataDir))
+			} catch (error) {
+				console.warn(`Error checking if VS Code is still running: ${error}`)
+			}
+		} else {
+			try {
+				const { stdout } = await execa("tasklist", ["/FI", `IMAGENAME eq code.exe`])
+				vsCodeStillRunning = stdout.includes("code.exe")
+			} catch (error) {
+				console.warn(`Error checking if VS Code is still running: ${error}`)
+			}
+		}
+
+		// If VS Code is still running, use forceful termination as a last resort
+		if (vsCodeStillRunning) {
+			console.log("Graceful shutdown failed, falling back to forceful termination...")
+
+			if (process.platform === "win32") {
+				try {
+					await execa("taskkill", ["/IM", "code.exe", "/F"])
+				} catch (error) {
+					console.warn(`Error forcefully terminating VS Code: ${error}`)
+				}
+			} else {
+				try {
+					const { stdout } = await execa("ps", ["aux"])
+					const lines = stdout.split("\n")
+
+					for (const line of lines) {
+						if (line.includes(resources.tempUserDataDir)) {
+							const parts = line.trim().split(/\s+/)
+							const pid = parseInt(parts[1])
+
+							if (pid && !isNaN(pid)) {
+								console.log(`Forcefully killing VS Code process with PID: ${pid}`)
+								try {
+									process.kill(pid, "SIGKILL")
+								} catch (killError) {
+									console.warn(`Failed to kill process ${pid}: ${killError}`)
+								}
+							}
+						}
+					}
+				} catch (error) {
+					console.warn(`Error forcefully terminating VS Code: ${error}`)
+				}
+			}
+		}
+	} catch (error) {
+		console.warn(`Error closing VS Code: ${error}`)
+	}
+
+	// Clean up temporary directories and evals.env file
+	try {
+		console.log(`Removing temporary user data directory: ${resources.tempUserDataDir}`)
+		fs.rmSync(resources.tempUserDataDir, { recursive: true, force: true })
+	} catch (error) {
+		console.warn(`Error removing temporary user data directory: ${error}`)
+	}
+
+	try {
+		console.log(`Removing temporary extensions directory: ${resources.tempExtensionsDir}`)
+		fs.rmSync(resources.tempExtensionsDir, { recursive: true, force: true })
+	} catch (error) {
+		console.warn(`Error removing temporary extensions directory: ${error}`)
+	}
+
+	// Remove the evals.env file
+	try {
+		const evalsEnvPath = path.join(workspacePath, "evals.env")
+		if (fs.existsSync(evalsEnvPath)) {
+			console.log(`Removing evals.env file: ${evalsEnvPath}`)
+			fs.unlinkSync(evalsEnvPath)
+		}
+	} catch (error) {
+		console.warn(`Error removing evals.env file: ${error}`)
+	}
+
+	// Remove from the global map
+	workspaceResources.delete(workspacePath)
+
+	console.log("Cleanup completed")
+}

evals/cli/tsconfig.json

@@ -0,0 +1,17 @@
+{
+	"compilerOptions": {
+		"target": "ES2020",
+		"module": "commonjs",
+		"lib": ["ES2020"],
+		"declaration": true,
+		"outDir": "dist",
+		"rootDir": "src",
+		"strict": true,
+		"esModuleInterop": true,
+		"skipLibCheck": true,
+		"forceConsistentCasingInFileNames": true,
+		"resolveJsonModule": true
+	},
+	"include": ["src/**/*"],
+	"exclude": ["node_modules", "dist"]
+}

locales/ar-sa/README.md

@@ -2,7 +2,7 @@
 العربية | <a href="https://github.com/cline/cline/blob/main/locales/es/README.md" target="_blank">الإسبانية</a> | <a href="https://github.com/cline/cline/blob/main/locales/de/README.md" target="_blank">الألمانية</a> | <a href="https://github.com/cline/cline/blob/main/locales/ja/README.md" target="_blank">اليابانية</a> | <a href="https://github.com/cline/cline/blob/main/locales/zh-cn/README.md" target="_blank">الصينية المبسطة</a> | <a href="https://github.com/cline/cline/blob/main/locales/zh-tw/README.md" target="_blank">الصينية التقليدية</a> | <a href="https://github.com/cline/cline/blob/main/locales/pt-BR/README.md" target="_blank">البرتغالية</a>
 </sub></div>
 
-# Cline – \#1 على OpenRouter
+# Cline
 
 <p align="center">
   <img src="https://media.githubusercontent.com/media/cline/cline/main/assets/docs/demo.gif" width="100%" />

locales/de/README.md

@@ -1,4 +1,4 @@
-# Cline – \#1 auf OpenRouter
+# Cline
 
 <p align="center">
         <img src="https://media.githubusercontent.com/media/cline/cline/main/assets/docs/demo.gif" width="100%" />

locales/es/README.md

@@ -1,4 +1,4 @@
-# Cline – #1 en OpenRouter
+# Cline
 
 <p align="center">
         <img src="https://media.githubusercontent.com/media/cline/cline/main/assets/docs/demo.gif" width="100%" />

locales/ja/CONTRIBUTING.md

@@ -1,4 +1,4 @@
-# Clineへの貢献
+# Cline
 
 Clineへの貢献に興味をお持ちいただきありがとうございます。
 

locales/ja/README.md

@@ -1,4 +1,4 @@
-# Cline – OpenRouterでのナンバーワン
+# Cline
 
 <p align="center">
     <img src="https://media.githubusercontent.com/media/cline/cline/main/assets/docs/demo.gif" width="100%" />

locales/ko/CONTRIBUTING.md

@@ -1,4 +1,4 @@
-# Cline에 기여하기
+# Cline
 
 Cline에 기여하는 것에 관심을 가져주셔서 감사합니다! 버그 수정, 기능 추가, 문서 개선 등 모든 기여는 Cline을 더욱 스마트하게 만드는 데 기여합니다. 활기차고 환영하는 커뮤니티를 유지하기 위해 모든 구성원은 [행동 강령](CODE_OF_CONDUCT.md)을 준수해야 합니다.
 

locales/ko/README.md

@@ -1,4 +1,4 @@
-# Cline - 최고의 OpenRouter
+# Cline
 
 <p align="center">
     <img src="https://media.githubusercontent.com/media/cline/cline/main/assets/docs/demo.gif" width="100%" />

locales/pt-BR/README.md

@@ -1,4 +1,4 @@
-# Cline – #1 no OpenRouter
+# Cline
 
 <p align="center">
         <img src="https://media.githubusercontent.com/media/cline/cline/main/assets/docs/demo.gif" width="100%" />

locales/zh-cn/README.md

@@ -1,4 +1,4 @@
-# Cline – OpenRouter 排名第一
+# Cline
 
 <p align="center">
     <img src="https://media.githubusercontent.com/media/cline/cline/main/assets/docs/demo.gif" width="100%" />
@@ -20,25 +20,25 @@
 <a href="https://github.com/cline/cline/discussions/categories/feature-requests?discussions_q=is%3Aopen+category%3A%22Feature+Requests%22+sort%3Atop" target="_blank"><strong>功能请求</strong></a>
 </td>
 <td align="center">
-<a href="https://cline.bot/join-us" target="_blank"><strong>我们正在招聘！</strong></a>
+<a href="https://docs.cline.bot/getting-started/for-new-coders" target="_blank"><strong>新手上路</strong></a>
 </td>
 </tbody>
 </table>
 </div>
 
-认识 Cline，一个可以使用你的 **CLI** 和 **编辑器** 的 AI 助手。
+认识 Cline —— 一个可以使用你的 **终端** 和 **编辑器** 的 AI 助手。
 
-感谢 [Claude 3.7 Sonnet 的代理编码能力](https://www.anthropic.com/claude/sonnet)，Cline 可以一步步处理复杂的软件开发任务。通过允许他创建和编辑文件、探索大型项目、使用浏览器和执行终端命令（在你授予权限后），他可以提供超越代码完成或技术支持的帮助。Cline 甚至可以使用 Model Context Protocol (MCP) 创建新工具并扩展自己的能力。虽然自主 AI 脚本传统上在沙盒环境中运行，但此扩展提供了一个人机交互的 GUI 来批准每个文件更改和终端命令，提供了一种安全且可访问的方式来探索代理 AI 的潜力。
+得益于 [Claude 3.7 Sonnet 的代理式编码能力](https://www.anthropic.com/claude/sonnet)，Cline 能够逐步处理复杂的软件开发任务。借助于一系列工具，他可以创建和编辑文件、浏览大型项目、使用浏览器，并在你授权后执行终端命令，从而在代码补全或技术支持之外提供更深入的帮助。Cline 甚至还能使用 Model Context Protocol（MCP）来创建新工具，并扩展自身的能力。虽然传统的自动化 AI 脚本通常运行在沙盒环境中，但这个扩展提供了一个人类参与审核的图形界面（GUI），用于审批每一次文件变更和终端命令，从而为探索代理式 AI 的潜力提供了一种安全且易于使用的方式。
 
-1. 输入你的任务并添加图像，将模型转换为功能应用程序或通过截图修复错误。
-2. Cline 首先分析你的文件结构和源代码 AST，运行正则表达式搜索，并阅读相关文件以了解现有项目。通过仔细管理添加到上下文中的信息，Cline 即使在大型复杂项目中也能提供有价值的帮助，而不会使上下文窗口过载。
-3. 一旦 Cline 获得所需信息，他可以：
-        - 创建和编辑文件 + 监控 linter/编译器错误，从而主动修复诸如缺少导入和语法错误等问题。
-        - 直接在你的终端中执行命令并监控其输出，从而在编辑文件后对开发服务器问题做出反应。
-        - 对于 Web 开发任务，Cline 可以在无头浏览器中启动网站，点击、输入、滚动并捕获截图和控制台日志，从而修复运行时错误和视觉错误。
-4. 当任务完成时，Cline 将通过终端命令如 `open -a "Google Chrome" index.html` 向你展示结果，你可以通过点击按钮运行该命令。
+1. 输入你的任务，并添加图片，以将界面原型（mockup）转换为功能应用，或通过截图修复 bug。
+2. Cline 会从分析你的文件结构和源代码的抽象语法树（AST）开始，同时执行正则搜索并读取相关文件，以便尽快熟悉项目上下文。通过精细地管理上下文中引入的信息，即使面对大型复杂项目，Cline 也能在不超出上下文窗口限制的前提下提供有效协助。
+3. 一旦获取了所需信息，Cline 能够：
+   - 创建和编辑文件，并在过程中监控 linter 或编译器错误，主动修复诸如缺少导入、语法错误等问题。
+   - 直接在你的终端中执行命令，并在运行过程中监控输出，例如在修改文件后自动响应开发服务器问题。
+   - 针对 Web 开发任务，Cline 可以在无头浏览器中打开网站，进行点击、输入、滚动操作，并采集截图与控制台日志，从而修复运行时错误和界面问题。
+4. 当任务完成后，Cline 会通过类似 `open -a "Google Chrome" index.html` 的终端命令将结果展示给你，你只需点击按钮即可执行。
 
-> [!提示]
+> [!TIP]
 > 使用 `CMD/CTRL + Shift + P` 快捷键打开命令面板并输入 "Cline: Open In New Tab" 将扩展作为标签在编辑器中打开。这让你可以与文件资源管理器并排使用 Cline，更清楚地看到他如何改变你的工作空间。
 
 ---
@@ -49,7 +49,7 @@
 
 Cline 支持 OpenRouter、Anthropic、OpenAI、Google Gemini、AWS Bedrock、Azure 和 GCP Vertex 等 API 提供商。你还可以配置任何兼容 OpenAI 的 API，或通过 LM Studio/Ollama 使用本地模型。如果你使用 OpenRouter，扩展会获取他们的最新模型列表，让你在新模型可用时立即使用。
 
-扩展还会跟踪整个任务循环和单个请求的总令牌和 API 使用成本，让你在每一步都了解支出情况。
+此外，该扩展还会记录整个任务流程中以及每次请求的总 token 数和 API 使用费用，确保你在每一步都能清楚了解花费情况。
 
 <!-- 透明像素以在浮动图像后创建换行 -->
 

locales/zh-tw/README.md

@@ -2,7 +2,7 @@
 <a href="https://github.com/cline/cline/blob/main/README.md" target="_blank">English</a> | <a href="https://github.com/cline/cline/blob/main/locales/es/README.md" target="_blank">Español</a> | <a href="https://github.com/cline/cline/blob/main/locales/de/README.md" target="_blank">Deutsch</a> | <a href="https://github.com/cline/cline/blob/main/locales/ja/README.md" target="_blank">日本語</a> | <a href="https://github.com/cline/cline/blob/main/locales/zh-cn/README.md" target="_blank">简体中文</a> | 繁體中文 | <a href="https://github.com/cline/cline/blob/main/locales/ko/README.md" target="_blank">한국어</a>
 </sub></div>
 
-# Cline – OpenRouter 第一名的 AI 工具
+# Cline
 
 <p align="center">
     <img src="https://media.githubusercontent.com/media/cline/cline/main/assets/docs/demo.gif" width="100%" />
@@ -32,7 +32,7 @@
 
 認識 Cline，一個可以使用您的**命令列介面** (CLI) 和**程式編輯器** (Editor) 的 AI 助理。
 
-感謝 [Claude 3.7 Sonnet 的代理式程式設計能力](https://www.anthropic.com/claude/sonnet)，Cline 能夠逐步處理複雜的軟體開發任務。透過能讓他建立和編輯檔案、探索大型專案、使用瀏覽器，以及執行終端機指令（在您授權後）的工具，他能以超越程式碼自動完成或技術支援的方式協助您。Cline 甚至能使用模型上下文協定（Model Context Protocol，MCP）來建立新工具並擴展自己的功能。雖然自主 AI 腳本傳統上會在沙箱環境中執行，但這個擴充套件提供了人機互動的圖形介面，讓您可以核准每個檔案變更和終端機指令，提供一個安全且容易使用的方式來探索代理式 AI 的潛力。
+感謝 [Claude 3.7 Sonnet 的代理式程式設計能力](https://www.anthropic.com/claude/sonnet)，Cline 能夠逐步處理複雜的軟體開發任務。透過能讓他建立和編輯檔案、探索大型專案、使用瀏覽器，以及執行終端機指令（在您授權後）的工具，從而在程式碼補全或技術支援之外提供更深入的協助。Cline 甚至能使用模型上下文協定（Model Context Protocol，MCP）來建立新工具並擴展自己的功能。雖然自主 AI 腳本傳統上會在沙箱環境中執行，但這個擴充套件提供了人機互動的圖形介面，讓您可以核准每個檔案變更和終端機指令，提供一個安全且容易使用的方式來探索代理式 AI 的潛力。
 
 1. 輸入您的任務，並可以加入圖片來將設計稿轉換成功能性應用程式，或使用截圖來修正錯誤。
 2. Cline 會先分析您的檔案結構和程式碼 AST、執行正規表達式搜尋，並讀取相關檔案，以便在現有專案中快速掌握狀況。透過仔細管理加入上下文的資訊，Cline 可以在不超過上下文視窗的情況下，為大型且複雜的專案提供有價值的協助。

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": "3.8.4",
+	"version": "3.13.3",
 	"icon": "assets/icons/icon.png",
 	"engines": {
 		"vscode": "^1.84.0"
@@ -39,7 +39,9 @@
 		"ai",
 		"llama"
 	],
-	"activationEvents": [],
+	"activationEvents": [
+		"workspaceContains:evals.env"
+	],
 	"main": "./dist/extension.js",
 	"contributes": {
 		"viewsContainers": {
@@ -113,11 +115,21 @@
 				"category": "Cline"
 			},
 			{
-				"command": "cline.fixWithCline",
-				"title": "Fix with Cline",
+				"command": "cline.focusChatInput",
+				"title": "Jump to Chat Input",
 				"category": "Cline"
 			}
 		],
+		"keybindings": [
+			{
+				"command": "cline.addToChat",
+				"key": "cmd+'",
+				"mac": "cmd+'",
+				"win": "ctrl+'",
+				"linux": "ctrl+'",
+				"when": "editorHasSelection"
+			}
+		],
 		"menus": {
 			"view/title": [
 				{
@@ -214,21 +226,6 @@
 					},
 					"description": "Settings for VSCode Language Model API"
 				},
-				"cline.mcp.mode": {
-					"type": "string",
-					"enum": [
-						"full",
-						"server-use-only",
-						"off"
-					],
-					"enumDescriptions": [
-						"Enable all MCP functionality (server use and build instructions)",
-						"Enable MCP server use only (excludes instructions about building MCP servers)",
-						"Disable all MCP functionality"
-					],
-					"default": "full",
-					"description": "Controls MCP inclusion in prompts, reduces token usage if you only need access to certain functionality."
-				},
 				"cline.enableCheckpoints": {
 					"type": "boolean",
 					"default": true,
@@ -294,15 +291,18 @@
 		"watch:esbuild": "node esbuild.js --watch",
 		"watch:tsc": "tsc --noEmit --watch --project tsconfig.json",
 		"package": "npm run build:webview && npm run check-types && npm run lint && node esbuild.js --production",
-		"compile-tests": "tsc -p ./tsconfig.test.json --outDir out",
+		"protos": "node proto/build-proto.js && prettier src/shared/proto --write && prettier src/core/controller --write",
+		"compile-tests": "node ./scripts/build-tests.js",
 		"watch-tests": "tsc -p . -w --outDir out",
 		"pretest": "npm run compile-tests && npm run compile && npm run lint",
 		"check-types": "tsc --noEmit",
 		"lint": "eslint src --ext ts && eslint webview-ui/src --ext ts",
 		"format": "prettier . --check",
 		"format:fix": "prettier . --write",
-		"test": "vscode-test",
+		"test": "npm-run-all test:unit test:integration",
 		"test:ci": "node scripts/test-ci.js",
+		"test:integration": "vscode-test",
+		"test:unit": "TS_NODE_PROJECT='./tsconfig.unit-test.json' mocha",
 		"test:coverage": "vscode-test --coverage",
 		"install:all": "npm install && cd webview-ui && npm install",
 		"dev:webview": "cd webview-ui && npm run dev",
@@ -323,6 +323,7 @@
 		"@types/mocha": "^10.0.7",
 		"@types/node": "20.x",
 		"@types/pdf-parse": "^1.1.4",
+		"@types/proxyquire": "^1.3.31",
 		"@types/should": "^11.2.0",
 		"@types/sinon": "^17.0.4",
 		"@types/turndown": "^5.0.5",
@@ -332,13 +333,20 @@
 		"@vscode/test-cli": "^0.0.9",
 		"@vscode/test-electron": "^2.4.0",
 		"chai": "^4.3.10",
+		"chalk": "^5.3.0",
 		"esbuild": "^0.25.0",
 		"eslint": "^8.57.0",
+		"grpc-tools": "^1.13.0",
 		"husky": "^9.1.7",
 		"npm-run-all": "^4.1.5",
 		"prettier": "^3.3.3",
+		"protoc-gen-ts": "^0.8.7",
+		"proxyquire": "^2.1.3",
 		"should": "^13.2.3",
 		"sinon": "^19.0.2",
+		"ts-node": "^10.9.2",
+		"ts-proto": "^2.6.1",
+		"tsconfig-paths": "^4.2.0",
 		"typescript": "^5.4.5"
 	},
 	"dependencies": {
@@ -346,8 +354,10 @@
 		"@anthropic-ai/sdk": "^0.37.0",
 		"@anthropic-ai/vertex-sdk": "^0.6.4",
 		"@aws-sdk/client-bedrock-runtime": "^3.758.0",
+		"@bufbuild/protobuf": "^2.2.5",
 		"@google-cloud/vertexai": "^1.9.3",
-		"@google/generative-ai": "^0.18.0",
+		"@google/genai": "^0.9.0",
+		"@grpc/grpc-js": "^1.9.15",
 		"@mistralai/mistralai": "^1.5.0",
 		"@modelcontextprotocol/sdk": "^1.7.0",
 		"@opentelemetry/api": "^1.4.1",
@@ -356,20 +366,25 @@
 		"@opentelemetry/sdk-node": "^0.39.1",
 		"@opentelemetry/sdk-trace-node": "^1.30.1",
 		"@opentelemetry/semantic-conventions": "^1.30.0",
+		"@sentry/browser": "^9.12.0",
 		"@vscode/codicons": "^0.0.36",
 		"axios": "^1.8.2",
 		"cheerio": "^1.0.0",
 		"chokidar": "^4.0.1",
+		"chrome-launcher": "^1.1.2",
 		"clone-deep": "^4.0.1",
 		"default-shell": "^2.2.0",
 		"diff": "^5.2.0",
 		"execa": "^9.5.2",
 		"fast-deep-equal": "^3.1.3",
 		"firebase": "^11.2.0",
+		"fzf": "^0.5.2",
 		"get-folder-size": "^5.0.0",
 		"globby": "^14.0.2",
+		"iconv-lite": "^0.6.3",
 		"ignore": "^7.0.3",
 		"isbinaryfile": "^5.0.2",
+		"jschardet": "^3.1.4",
 		"mammoth": "^1.8.0",
 		"monaco-vscode-textmate-theme-converter": "^0.1.7",
 		"ollama": "^0.5.13",

proto/account.proto

@@ -0,0 +1,15 @@
+syntax = "proto3";
+
+package cline;
+option java_package = "bot.cline.proto";
+option java_multiple_files = true;
+
+import "common.proto";
+
+// Service for account-related operations
+service AccountService {
+    // Handles the user clicking the login link in the UI.
+    // Generates a secure nonce for state validation, stores it in secrets,
+    // and opens the authentication URL in the external browser.
+    rpc accountLoginClicked(EmptyRequest) returns (String);
+}

proto/browser.proto

@@ -0,0 +1,50 @@
+syntax = "proto3";
+
+package cline;
+option java_package = "bot.cline.proto";
+option java_multiple_files = true;
+
+import "common.proto";
+
+service BrowserService {
+  rpc getBrowserConnectionInfo(EmptyRequest) returns (BrowserConnectionInfo);
+  rpc testBrowserConnection(StringRequest) returns (BrowserConnection);
+  rpc discoverBrowser(EmptyRequest) returns (BrowserConnection);
+  rpc getDetectedChromePath(EmptyRequest) returns (ChromePath);
+  rpc updateBrowserSettings(UpdateBrowserSettingsRequest) returns (Boolean);
+}
+
+message BrowserConnectionInfo {
+  bool is_connected = 1;
+  bool is_remote = 2;
+  optional string host = 3;
+}
+
+message BrowserConnection {
+  bool success = 1;
+  string message = 2;
+  optional string endpoint = 3;
+}
+
+message ChromePath {
+  string path = 1;
+  bool is_bundled = 2;
+}
+
+message Viewport {
+  int32 width = 1;
+  int32 height = 2;
+}
+
+message BrowserSettings {
+  Viewport viewport = 1;
+  optional string remote_browser_host = 2;
+  optional bool remote_browser_enabled = 3;
+}
+
+message UpdateBrowserSettingsRequest {
+  Metadata metadata = 1;
+  Viewport viewport = 2;
+  optional string remote_browser_host = 3;
+  optional bool remote_browser_enabled = 4;
+}

proto/build-proto.js

@@ -0,0 +1,147 @@
+#!/usr/bin/env node
+
+import * as fs from "fs/promises"
+import * as path from "path"
+import { execSync } from "child_process"
+import { globby } from "globby"
+import chalk from "chalk"
+
+import { createRequire } from "module"
+const require = createRequire(import.meta.url)
+const protoc = path.join(require.resolve("grpc-tools"), "../bin/protoc")
+const tsProtoPlugin = require.resolve("ts-proto/protoc-gen-ts_proto")
+
+// Get script directory and root directory
+const SCRIPT_DIR = path.dirname(new URL(import.meta.url).pathname)
+const ROOT_DIR = path.resolve(SCRIPT_DIR, "..")
+
+async function main() {
+	console.log(chalk.bold.blue("Starting Protocol Buffer code generation..."))
+
+	// Define output directories
+	const TS_OUT_DIR = path.join(ROOT_DIR, "src", "shared", "proto")
+
+	// Create output directory if it doesn't exist
+	await fs.mkdir(TS_OUT_DIR, { recursive: true })
+
+	// Clean up existing generated files
+	console.log(chalk.cyan("Cleaning up existing generated TypeScript files..."))
+	const existingFiles = await globby("**/*.ts", { cwd: TS_OUT_DIR })
+	for (const file of existingFiles) {
+		await fs.unlink(path.join(TS_OUT_DIR, file))
+	}
+
+	// Process all proto files
+	console.log(chalk.cyan("Processing proto files from"), SCRIPT_DIR)
+	const protoFiles = await globby("*.proto", { cwd: SCRIPT_DIR })
+
+	for (const protoFile of protoFiles) {
+		console.log(chalk.cyan(`Generating TypeScript code for ${protoFile}...`))
+
+		// Build the protoc command with proper path handling for cross-platform
+		const protocCommand = [
+			protoc,
+			`--plugin=protoc-gen-ts_proto="${tsProtoPlugin}"`,
+			`--ts_proto_out="${TS_OUT_DIR}"`,
+			"--ts_proto_opt=outputServices=generic-definitions,env=node,esModuleInterop=true,useDate=false,useOptionals=messages",
+			`--proto_path="${SCRIPT_DIR}"`,
+			`"${path.join(SCRIPT_DIR, protoFile)}"`,
+		].join(" ")
+
+		try {
+			const execOptions = {
+				stdio: "inherit",
+			}
+			execSync(protocCommand, execOptions)
+		} catch (error) {
+			console.error(chalk.red(`Error generating TypeScript for ${protoFile}:`), error)
+			process.exit(1)
+		}
+	}
+
+	console.log(chalk.green("Protocol Buffer code generation completed successfully."))
+	console.log(chalk.green(`TypeScript files generated in: ${TS_OUT_DIR}`))
+
+	// Generate method registration files
+	await generateMethodRegistrations()
+
+	// Make the script executable
+	try {
+		await fs.chmod(path.join(SCRIPT_DIR, "build-proto.js"), 0o755)
+	} catch (error) {
+		console.warn(chalk.yellow("Warning: Could not make script executable:"), error)
+	}
+}
+
+async function generateMethodRegistrations() {
+	console.log(chalk.cyan("Generating method registration files..."))
+
+	const serviceDirs = [
+		path.join(ROOT_DIR, "src", "core", "controller", "account"),
+		path.join(ROOT_DIR, "src", "core", "controller", "browser"),
+		path.join(ROOT_DIR, "src", "core", "controller", "checkpoints"),
+		path.join(ROOT_DIR, "src", "core", "controller", "file"),
+		path.join(ROOT_DIR, "src", "core", "controller", "mcp"),
+		path.join(ROOT_DIR, "src", "core", "controller", "task"),
+		// Add more service directories here as needed
+	]
+
+	for (const serviceDir of serviceDirs) {
+		try {
+			await fs.access(serviceDir)
+		} catch (error) {
+			console.log(chalk.gray(`Skipping ${serviceDir} - directory does not exist`))
+			continue
+		}
+
+		const serviceName = path.basename(serviceDir)
+		const registryFile = path.join(serviceDir, "methods.ts")
+
+		console.log(chalk.cyan(`Generating method registrations for ${serviceName}...`))
+
+		// Get all TypeScript files in the service directory
+		const files = await globby("*.ts", { cwd: serviceDir })
+
+		// Filter out index.ts and methods.ts
+		const implementationFiles = files.filter((file) => file !== "index.ts" && file !== "methods.ts")
+
+		// Create the output file with header
+		let content = `// AUTO-GENERATED FILE - DO NOT MODIFY DIRECTLY
+// Generated by proto/build-proto.js
+
+// Import all method implementations
+import { registerMethod } from "./index"\n`
+
+		// Add imports for all implementation files
+		for (const file of implementationFiles) {
+			const baseName = path.basename(file, ".ts")
+			content += `import { ${baseName} } from "./${baseName}"\n`
+		}
+
+		// Add registration function
+		content += `\n// Register all ${serviceName} service methods
+export function registerAllMethods(): void {
+\t// Register each method with the registry\n`
+
+		// Add registration statements
+		for (const file of implementationFiles) {
+			const baseName = path.basename(file, ".ts")
+			content += `\tregisterMethod("${baseName}", ${baseName})\n`
+		}
+
+		// Close the function
+		content += `}`
+
+		// Write the file
+		await fs.writeFile(registryFile, content)
+		console.log(chalk.green(`Generated ${registryFile}`))
+	}
+
+	console.log(chalk.green("Method registration files generated successfully."))
+}
+
+// Run the main function
+main().catch((error) => {
+	console.error(chalk.red("Error:"), error)
+	process.exit(1)
+})

proto/checkpoints.proto

@@ -0,0 +1,19 @@
+syntax = "proto3";
+
+package cline;
+option java_package = "bot.cline.proto";
+option java_multiple_files = true;
+
+import "common.proto";
+
+service CheckpointsService {
+  rpc checkpointDiff(Int64Request) returns (Empty);
+  rpc checkpointRestore(CheckpointRestoreRequest) returns (Empty);
+}
+
+message CheckpointRestoreRequest {
+  Metadata metadata = 1;
+  int64 number = 2;
+  string restore_type = 3;
+  optional int64 offset = 4;
+}

proto/common.proto

@@ -0,0 +1,51 @@
+syntax = "proto3";
+
+package cline;
+option java_package = "bot.cline.proto";
+option java_multiple_files = true;
+
+message Metadata {
+}
+
+message EmptyRequest {
+  Metadata metadata = 1;
+}
+
+message Empty {
+}
+
+message StringRequest {
+  Metadata metadata = 1;
+  string value = 2;
+}
+
+message String {
+  string value = 1;
+}
+
+message Int64Request {
+  Metadata metadata = 1;
+  int64 value = 2;
+}
+
+message Int64 {
+  int64 value = 1;
+}
+
+message BytesRequest {
+  Metadata metadata = 1;
+  bytes value = 2;
+}
+
+message Bytes {
+  bytes value = 1;
+}
+
+message BooleanRequest {
+  Metadata metadata = 1;
+  bool value = 2;
+}
+
+message Boolean {
+  bool value = 1;
+}

proto/file.proto

@@ -0,0 +1,16 @@
+syntax = "proto3";
+
+package cline;
+option java_package = "bot.cline.proto";
+option java_multiple_files = true;
+
+import "common.proto";
+
+// Service for file-related operations
+service FileService {
+  // Opens a file in the editor
+  rpc openFile(StringRequest) returns (Empty);
+  
+  // Opens an image in the system viewer
+  rpc openImage(StringRequest) returns (Empty);
+}

proto/mcp.proto

@@ -0,0 +1,76 @@
+syntax = "proto3";
+
+package cline;
+option java_package = "bot.cline.proto";
+option java_multiple_files = true;
+
+import "common.proto";
+
+service McpService {
+  rpc toggleMcpServer(ToggleMcpServerRequest) returns (McpServers);
+  rpc updateMcpTimeout(UpdateMcpTimeoutRequest) returns (McpServers);
+  rpc addRemoteMcpServer(AddRemoteMcpServerRequest) returns (McpServers);
+}
+
+message ToggleMcpServerRequest {
+  Metadata metadata = 1;
+  string server_name = 2;
+  bool disabled = 3;
+}
+
+message UpdateMcpTimeoutRequest {
+  Metadata metadata = 1;
+  string server_name = 2;
+  int32 timeout = 3;
+}
+
+message AddRemoteMcpServerRequest {
+  Metadata metadata = 1;
+  string server_name = 2;
+  string server_url = 3;
+}
+
+message McpTool {
+  string name = 1;
+  optional string description = 2;
+  optional string input_schema = 3;
+  optional bool auto_approve = 4;
+}
+
+message McpResource {
+  string uri = 1;
+  string name = 2;
+  optional string mime_type = 3;
+  optional string description = 4;
+}
+
+message McpResourceTemplate {
+  string uri_template = 1;
+  string name = 2;
+  optional string mime_type = 3;
+  optional string description = 4;
+}
+
+enum McpServerStatus {
+  // Protobuf enums (in proto3) must have a zero value defined, which serves as the default if the field isn't explicitly set. 
+  // To align with the required nature of the TypeScript type and avoid an unnecessary UNSPECIFIED state, we map one of the existing statuses to this zero value.
+  MCP_SERVER_STATUS_DISCONNECTED = 0; // default
+  MCP_SERVER_STATUS_CONNECTED = 1;
+  MCP_SERVER_STATUS_CONNECTING = 2;
+}
+
+message McpServer {
+  string name = 1;
+  string config = 2;
+  McpServerStatus status = 3;
+  optional string error = 4;
+  repeated McpTool tools = 5;
+  repeated McpResource resources = 6;
+  repeated McpResourceTemplate resource_templates = 7;
+  optional bool disabled = 8;
+  optional int32 timeout = 9;
+}
+
+message McpServers {
+  repeated McpServer mcp_servers = 1;
+}

proto/package.json

@@ -0,0 +1,3 @@
+{
+	"type": "module"
+}