v3.18.11 Release Notes (#4814)

* Fix: Ensure Cline client is initialized with the latest auth token

The Cline client was not being re-initialized with the latest authentication token after the user signs in. This resulted in the client using an outdated or non-existent token, leading to authentication errors when making API requests.

This commit ensures that the Cline client is initialized with the most recent authentication token by setting the `apiKey` property of the `OpenAI` client instance to the current auth token retrieved from `AuthService` before every request. This guarantees that the client always uses the valid and up-to-date token for authentication.

* changeset

* move this._authService.getAuthToken() to ensureClient

---------

Co-authored-by: abeatrix <beatrix@cline.bot>

.eslintrc.json

@@ -22,6 +22,7 @@
 		"react-hooks/exhaustive-deps": "off",
 		"eslint-rules/no-protobuf-object-literals": "error",
 		"eslint-rules/no-grpc-client-object-literals": "error",
+		"eslint-rules/no-direct-vscode-api": "warn",
 		"no-restricted-syntax": [
 			"error",
 			{

.gitignore

@@ -7,6 +7,7 @@ tmp
 *.vsix
 
 .DS_Store
+.idea
 
 pnpm-lock.yaml
 
@@ -37,4 +38,4 @@ src/hosts/vscode/*/methods.ts
 src/hosts/vscode/*/index.ts
 src/hosts/vscode/client/host-grpc-client.ts
 src/hosts/vscode/host-grpc-service-config.ts
-src/standalone/server-setup.ts
+src/standalone/server-setup.ts

.vscode/launch.json

@@ -23,19 +23,20 @@
 			"request": "launch",
 			"runtimeExecutable": "${execPath}",
 			"args": [
+				"--user-data-dir=${workspaceFolder}/dist/tmp/user",
 				"--profile-temp",
-				"--sync",
-				"off",
+				"--sync=off",
 				"--disable-extensions",
 				"--extensionDevelopmentPath=${workspaceFolder}",
 				"${workspaceFolder}"
 			],
 			"outFiles": ["${workspaceFolder}/dist/**/*.js"],
-			"preLaunchTask": "clean-sandbox",
+			"preLaunchTask": "clean-tmp-user",
 			"internalConsoleOptions": "openOnSessionStart",
 			"postDebugTask": "stop",
 			"env": {
 				"IS_DEV": "true",
+				"TEMP_PROFILE": "true",
 				"DEV_WORKSPACE_FOLDER": "${workspaceFolder}"
 			}
 		},

.vscode/tasks.json

@@ -233,10 +233,10 @@
 			"type": "shell"
 		},
 		{
-			"label": "clean-sandbox",
+			"label": "clean-tmp-user",
 			"type": "shell",
 			"dependsOn": ["watch"],
-			"command": "rm -rf .vscode-dev"
+			"command": "rm -rf ${workspaceFolder}/dist/tmp/user && mkdir -p ${workspaceFolder}/dist/tmp/user"
 		}
 	],
 	"inputs": [

.vscodeignore

@@ -2,8 +2,10 @@
 .vscode/**
 .vscode-test/**
 out/**
+dist-standalone/**
 node_modules/**
 src/**
+standalone/**
 .gitignore
 .yarnrc
 esbuild.js
@@ -13,6 +15,7 @@ vsc-extension-quickstart.md
 **/*.map
 **/*.ts
 **/.vscode-test.*
+eslint-rules/**
 
 # Custom
 demo.gif
@@ -32,15 +35,12 @@ webview-ui/node_modules/**
 
 # Ignore docs
 docs/**
+old_docs/**
 
 # Fix issue where codicons don't get packaged (https://github.com/microsoft/vscode-extension-samples/issues/692)
 !node_modules/@vscode/codicons/dist/codicon.css
 !node_modules/@vscode/codicons/dist/codicon.ttf
 
-# Include KaTeX CSS and fonts for LaTeX rendering
-!webview-ui/node_modules/katex/dist/katex.min.css
-!webview-ui/node_modules/katex/dist/fonts/**
-
 # Include default themes JSON files used in getTheme
 !src/integrations/theme/default-themes/**
 

CHANGELOG.md

@@ -1,5 +1,58 @@
 # Changelog
 
+## [3.18.11]
+
+-   Fix authentication issues with Cline provider by ensuring the client always uses the latest auth token
+
+## [3.18.10]
+
+-   Update recommended fast & cheap model to Grok 4 in OpenRouter model picker
+-   Fix Gemini 2.5 Pro thinking budget slider and add support for Gemini 2.5 Flash Lite Preview model (Thanks @arafatkatze!)
+
+## [3.18.9]
+
+-   Fix streaming reliability issues with Cline provider that could cause connection problems during long conversations
+-   Fix authentication error handling for Cline provider to show clearer error messages when not signed in and prevent recursive failed requests
+-   Remove incorrect pricing display for SAP AI Core provider since it uses non-USD "Capacity Units" that cannot be directly converted (Thanks @ncryptedV1!)
+
+## [3.18.8]
+
+-   Update pricing for Grok 3 model because the promotion ended
+
+## [3.18.7]
+
+-   Remove promotional "free" messaging for Grok 3 model in UI
+
+## [3.18.6]
+
+-   Update request header to include `"ai-client-type": "Cline"` to SAP Api Provider
+-   Add organization organization accounts
+
+## [3.18.5]
+
+-   Fix Plan/Act mode persistence across sessions and multi-workspace conflicts
+-   Improve provider switching performance by 18x (from 550ms to 30ms) with batched storage operations
+-   Improve SAP AI Core provider model organization and fix exception handling (Thanks @schardosin!)
+
+## [3.18.4]
+
+-   Add support for Gemini 2.5 Pro and Flash to SAP AI Core Provider
+-   Fix logging in with Cline account not getting past welcome screen
+
+## [3.18.3]
+
+-   Improve Cerebras Qwen model performance by removing thinking tokens from model input (Thanks @kevint-cerebras!)
+-   Improve Claude Code provider with better error handling and performance optimizations (Thanks @BarreiroT!)
+
+## [3.18.2]
+
+-   Fix issue where terminal output would not be captured if shell integration fails by falling back to capturing the terminal content.
+-   Add confirmation popup when deleting tasks
+-   Add support for Claude Sonnet 4 and Opus 4 model in SAP AI Core provider (Thanks @lizzzcai!)
+-   Add support for `litellm_session_id` to group requests in a single session (Thanks @jorgegarciarey!)
+-   Add "Thinking Budget" customization for Claude Code (Thanks @BarreiroT!)
+-   Fix issue where the extension would use the user's environment variables for authentication when using Claude Code (Thanks @BarreiroT!)
+
 ## [3.18.1]
 
 -   Add support for Claude 4 Sonnet in SAP AI Core provider (Thanks @GTxx!)

docs/docs.json

@@ -170,6 +170,10 @@
 					"running-models-locally/ollama"
 				]
 			},
+			{
+				"group": "Troubleshooting",
+				"pages": ["troubleshooting/terminal-quick-fixes", "troubleshooting/terminal-integration-guide"]
+			},
 			{
 				"group": "More Info",
 				"pages": ["more-info/telemetry"]

docs/features/at-mentions/terminal-mentions.mdx

@@ -58,3 +58,16 @@ When you use the terminal mention in your message, here's what happens behind th
 6. The AI can now "see" the complete terminal output with all formatting preserved
 
 This process happens automatically whenever you use the terminal mention, giving the AI access to your command results, error messages, and other terminal output without you having to copy it manually.
+
+## Troubleshooting Terminal Issues
+
+If you're experiencing issues with terminal mentions or terminal integration in general (such as "Shell Integration Unavailable" or commands not showing output), please refer to our comprehensive [Terminal Integration Troubleshooting Guide](/troubleshooting/terminal-integration-guide).
+
+Common issues include:
+
+-   Terminal mentions not capturing output
+-   "Shell Integration Unavailable" messages in Cline chat
+-   Commands executing but output not visible to Cline
+-   Terminal integration working inconsistently
+
+The troubleshooting guide provides platform-specific solutions and detailed configuration steps to resolve these issues.

docs/features/commands-and-shortcuts/terminal-integration.mdx

@@ -74,8 +74,25 @@ This approach ensures that all terminal output, including colors and formatting,
 
 -   **Select specific output when needed**: By default, the integration captures all terminal content, but you can also select specific lines before right-clicking to focus on just the relevant output.
 
--   **Combine with file mentions**: After sending terminal output to Cline, you can enhance your question by mentioning relevant files using the @ mentions feature.
+-   **Combine terminal outputs with file mentions**: After sending terminal output to Cline, you can enhance your question by mentioning relevant files using the @ mentions feature.
 
--   **Use for build and test output**: Terminal integration is particularly useful for understanding complex build errors or test failures that span multiple lines.
+-   **Contextualize build & test outputs with the terminal**: Terminal integration is particularly useful for understanding complex build errors or test failures that span multiple lines.
 
 Next time you're staring at a cryptic error message in your terminal, try using Cline's terminal integration instead of copying and pasting. You'll get more accurate help because Cline can see the complete terminal context with proper formatting.
+
+## Troubleshooting Terminal Issues
+
+If you're experiencing issues with terminal integration, such as "Shell Integration Unavailable" or commands not showing output, please refer to our comprehensive [Terminal Integration Troubleshooting Guide](/troubleshooting/terminal-integration-guide).
+
+The troubleshooting guide covers:
+
+-   Common terminal integration issues and quick fixes
+-   Platform-specific solutions for Windows, macOS, and Linux
+-   Shell-specific configurations for zsh, bash, PowerShell, and more
+-   Advanced debugging techniques
+-   Terminal settings optimization
+
+<Tip>
+	**Quick Fix**: Most terminal issues can be resolved by switching to bash in the Cline settings and increasing the shell
+	integration timeout to 10 seconds.
+</Tip>

docs/troubleshooting/terminal-integration-guide.mdx

@@ -0,0 +1,399 @@
+---
+title: "Terminal Integration Troubleshooting Guide"
+sidebarTitle: "Terminal Troubleshooting"
+description: "Complete guide to resolving terminal integration issues in Cline"
+---
+
+This guide helps you resolve terminal integration issues in Cline. Terminal integration is crucial for Cline to execute commands and read their output, enabling it to understand errors, test results, and command responses.
+
+<Tip>
+	If you're experiencing terminal issues, try switching to a simpler shell like `bash` in the Cline settings, under "Terminal Settings"
+
+    This resolves most terminal integration problems.
+
+</Tip>
+
+## Quick Diagnosis Flowchart
+
+Follow this flowchart to quickly identify your issue:
+
+```mermaid
+graph TD
+    A[Terminal Issue] --> B{Can Cline execute commands?}
+    B -->|No| C[Shell Integration Unavailable]
+    B -->|Yes| D{Can Cline see the output?}
+    D -->|No| E[Output Capture Failed]
+    D -->|Yes| F{Is the output corrupted?}
+    F -->|Yes| G[Character Filtering Issue]
+    F -->|No| H{Does the command hang?}
+    H -->|Yes| I[Long-Running Command Issue]
+    H -->|No| J[Check Terminal Settings]
+
+    C --> K[Try Solution 1]
+    E --> L[Try Solution 2]
+    G --> M[Try Solution 3]
+    I --> N[Try Solution 4]
+
+    style A fill:#f9f,stroke:#333,stroke-width:2px
+    style K fill:#9f9,stroke:#333,stroke-width:2px
+    style L fill:#9f9,stroke:#333,stroke-width:2px
+    style M fill:#9f9,stroke:#333,stroke-width:2px
+    style N fill:#9f9,stroke:#333,stroke-width:2px
+```
+
+## Common Issues & Quick Solutions
+
+### 1. Shell Integration Unavailable
+
+**Symptoms:**
+
+-   Message: "Shell Integration Unavailable"
+-   Commands execute but Cline can't read output
+-   Terminal works fine manually but not with Cline
+
+**Quick Solutions:**
+
+#### macOS
+
+-   **Switch to bash**
+
+    1. Go to Cline Settings
+    2. Left-Click the **"Terminal Settings"** tab
+    3. Navigate to **"Default Terminal Profile"** and select **"bash"** from the drop-down menu
+
+-   **Disable Oh-My-Zsh temporarily**:
+
+    1. If using zsh, enter `mv ~/.zshrc ~/.zshrc.backup` into the terminal
+    2. Restart VSCode
+
+-   **Set environment**:
+    1.a For Zsh users, use one of the following Zsh commands to edit your shell profile:
+
+          - `nano ~/.zshrc`
+          - `vim ~/.zshrc`
+          - `code ~/.zshrc`
+
+    1.b For Bash users
+
+          - nano ~/.bash_profile
+
+    2. Add the following to your shell config: `export TERM=xterm-256color`
+    3. Save your configuration
+
+#### Windows
+
+-   **Use PowerShell 7**
+
+    1. Install from Microsoft Store
+    2. Go to Cline Settings
+    3. Left-Click the **"Terminal Settings"** tab
+    4. Navigate to **"Default Terminal Profile"** and select **"PowerShell 7"** from the drop-down menu
+
+-   **Disable Windows ConPTY**
+
+    1. Navigate to your VSCode Settings
+    2. Enter "Integrated: Windows Enable Conpty" into the Settings searchbar
+    3. Uncheck the option
+
+-   **Try Command Prompt**
+    1. Go to Cline Settings
+    2. Left-Click the **"Terminal Settings"** tab
+    3. Navigate to **"Default Terminal Profile"** and select **"Command Prompt"** from the drop-down menu
+
+#### Linux
+
+-   **Use bash**
+
+    1. Go to Cline Settings
+    2. Left-Click the **"Terminal Settings"** tab
+    3. Navigate to **"Default Terminal Profile"** and select **"bash"** from the drop-down menu
+
+-   **Check permissions**
+
+    1. Ensure VSCode has terminal access permissions
+
+-   **Disable custom prompts**
+    1. Comment out prompt customizations in `.bashrc`
+
+### 2. Command Output Not Visible
+
+**Symptoms:**
+
+-   Cline states in chat: "[Command is running but producing no output]"
+-   Commands complete but Cline doesn't see results
+-   Commands work sometimes but not consistently
+
+**Solutions:**
+
+-   **Increase Shell Integration Timeout**
+
+    1. Within Cline, left-click the **Settings** button in the top right-hand corner of the chat window
+    2. Once in the **Settings** window, left-click the **"Terminal Settings"** tab from the left-hand column
+    3. Navigate to "Shell integration timeout (seconds)" and enter **"10"** into the text field
+
+-   **Disable Terminal Reuse**
+
+    1. Within Cline, left-click the **Settings** button in the top right-hand corner of the chat window
+    2. Once in the **Settings** window, left-click the **"Terminal Settings"** tab from the left-hand column
+    3. Look for **"Enable aggressive terminal reuse"**, and **uncheck** this option
+
+-   **Check for interfering extensions**
+    1. Disable other terminal-related VSCode extensions
+
+### 3. Character Filtering Issues
+
+**Symptoms:**
+
+-   Commas missing from output (JSON appears corrupted)
+-   Special characters stripped from terminal output
+-   Syntax errors that don't appear when running manually
+
+**Solution:**
+This is a known bug in output processing. Workarounds:
+
+-   Recommend AI to use file output instead
+    1. Tell Cline in chat or Cline rules, to use `command > output.txt` before reading the file/s
+
+<Tip>
+	This family of issues is only partially solved in the latest Cline versions, so if you still face this, create a GitHub issue
+	if it is a persistent problem.
+</Tip>
+
+### 4. Long-Running Commands & Progress Bars
+
+**Symptoms:**
+
+-   Docker builds never complete in Cline
+-   Progress bars consume thousands of tokens
+-   The Cline button "Proceed while running" doesn't work properly in chat
+
+<Tip>
+	This family of issues has been solved in latest Cline versions but if you still face any issues, then create a GitHub issue
+	for this.
+</Tip>
+
+## Terminal Settings Explained
+
+Access these in Cline by clicking the settings icon, and navigating to the "Terminal Settings" section:
+
+### Default Terminal Profile
+
+-   **What it does**: Selects which shell Cline uses for commands
+-   **When to change**: If experiencing shell integration issues with your default shell
+-   **Recommended**: - macOS: bash (if zsh has issues) - Windows: PowerShell 7 - Linux: bash
+
+### Shell Integration Timeout
+
+-   **What it does**: How long Cline waits for the terminal to be ready
+-   **Default**: 4 seconds
+-   **When to increase**:
+    -   Slow shell startup (heavy .zshrc/.bashrc)
+    -   WSL environments
+    -   SSH connections
+-   **Recommended**: - Start with 10 seconds if having issues
+
+### Enable Aggressive Terminal Reuse
+
+-   **What it does**: Reuses existing terminals even if not in the correct directory
+-   **When to disable**:
+    -   Commands execute in wrong directory
+    -   Virtual environment issues
+    -   Terminal state corruption
+-   **Trade-off**: - Disabling creates more terminals but ensures clean state
+
+### Terminal Output Line Limit
+
+-   **What it does**: Limits how many lines Cline reads from terminal output
+-   **Default**: 500 lines
+-   **When to adjust**:
+    -   Increase for verbose build outputs
+    -   Decrease if hitting token limits
+    -   Set to 100 for commands with progress bars
+
+## Platform-Specific Solutions
+
+### macOS Issues
+
+#### Oh-My-Zsh Conflicts
+
+Oh-My-Zsh often interferes with shell integration. Solutions:
+
+1. Create a minimal `.zshrc` for VSCode:
+    ```bash
+    # ~/.zshrc-vscode
+    export TERM=xterm-256color
+    export PAGER=cat
+    # Minimal PATH and environment setup
+    ```
+2. Configure VSCode to use it:
+    ```json
+    {
+    	"terminal.integrated.env.osx": {
+    		"ZDOTDIR": "~/.zshrc-vscode"
+    	}
+    }
+    ```
+
+#### macOS 15+ Issues
+
+Recent macOS versions have stricter terminal permissions:
+
+1. System Preferences → Privacy & Security → Developer Tools
+2. Add Visual Studio Code
+3. Restart VSCode completely
+
+### Windows Issues
+
+#### PowerShell Execution Policy
+
+If commands fail silently:
+
+```powershell
+Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
+```
+
+#### WSL Integration
+
+For WSL issues:
+
+1. Use WSL extension for VSCode
+2. Open folder in WSL: `code .` from WSL terminal
+3. Select "WSL Bash" as terminal profile in Cline
+
+#### Path Issues
+
+Windows path problems:
+
+1. Use forward slashes in Cline: `C:/Users/...`
+2. Quote paths with spaces: `"C:/Program Files/..."`
+3. Avoid `~` - use full paths
+
+### Linux/SSH/Container Issues
+
+#### SSH Connections
+
+For remote development:
+
+1. Install Cline on the remote machine, not locally
+2. Use SSH extension's integrated terminal
+3. Increase timeout to 15+ seconds
+
+#### Docker Containers
+
+When developing in containers:
+
+1. Install Cline in the container
+2. Use Dev Containers extension
+3. Ensure shell integration scripts are available
+
+## Shell-Specific Fixes
+
+### Zsh
+
+```bash
+# Add to ~/.zshrc
+export TERM=xterm-256color
+export PAGER=cat
+# Disable fancy prompts for VSCode
+if [[ "$TERM_PROGRAM" == "vscode" ]]; then
+    PS1="%n@%m %1~ %# "
+fi
+```
+
+### Bash
+
+```bash
+# Add to ~/.bashrc
+export TERM=xterm-256color
+export PAGER=cat
+# Simple prompt for VSCode
+if [[ "$TERM_PROGRAM" == "vscode" ]]; then
+    PS1='\u@\h:\w\$ '
+fi
+```
+
+### Fish
+
+```fish
+# Add to ~/.config/fish/config.fish
+set -x TERM xterm-256color
+set -x PAGER cat
+# Disable fancy features in VSCode
+if test "$TERM_PROGRAM" = "vscode"
+    function fish_prompt
+        echo (whoami)'@'(hostname)':'(pwd)'> '
+    end
+end
+```
+
+### PowerShell
+
+```powershell
+# Add to $PROFILE
+$env:PAGER = "cat"
+# Disable progress bars
+$ProgressPreference = 'SilentlyContinue'
+```
+
+## Advanced Troubleshooting
+
+### Debug Mode
+
+Enable terminal debugging to see what's happening:
+
+1. Open VSCode Command Palette (Cmd/Ctrl+Shift+P)
+2. Run: "Developer: Set Log Level..."
+3. Choose "Trace"
+4. Check Output panel → "Cline" for terminal logs
+
+### Manual Shell Integration Test
+
+Test if shell integration works at all:
+
+```bash
+# In VSCode terminal
+echo $TERM_PROGRAM  # Should show "vscode"
+echo $VSCODE_SHELL_INTEGRATION  # Should be "1"
+```
+
+## FAQ
+
+### Why does Cline create so many terminals?
+
+When shell integration fails, Cline can't reuse terminals safely (they might be running long processes). Enable shell integration or adjust the terminal reuse setting.
+
+### Can I use my custom shell (nushell, xonsh, etc.)?
+
+Cline officially supports bash, zsh, fish, and PowerShell. Custom shells may work but aren't guaranteed. Use bash as a fallback.
+
+### Why do some commands work but others don't?
+
+Commands that use interactive features (pagers, progress bars, curses) often fail. Set `PAGER=cat` and use non-interactive flags.
+
+### How do I know if shell integration is working?
+
+Working integration shows command output in Cline's chat. Failed integration shows "Shell Integration Unavailable" or "[Command is running but producing no output]".
+
+## Still Having Issues?
+
+If you've tried everything:
+
+1. **Collect Debug Info**:
+
+    ```bash
+    echo "Shell: $SHELL"
+    echo "Term: $TERM"
+    echo "VSCode: $TERM_PROGRAM"
+    which bash
+    bash --version
+    ```
+
+2. **Report the Issue**:
+    - Use `/reportbug` in Cline github issues
+    - Include your debug info
+    - Mention which solutions you tried
+
+<Tip>
+	Remember: Most terminal issues are resolved by switching to bash and increasing the timeout. Start there before trying complex
+	solutions.
+</Tip>

docs/troubleshooting/terminal-quick-fixes.mdx

@@ -0,0 +1,51 @@
+---
+title: "Terminal Quick Fixes"
+sidebarTitle: "Terminal Quick Fixes"
+description: "Quick solutions for common terminal issues"
+---
+
+**Here is a list of common fixes, starting with the most applicable:**
+
+-   **Switch to bash** (solves most instances)
+
+    1. Within Cline, left-click the **Settings** button in the top right-hand corner of the chat window
+    2. Once in the **Settings** window, left-click the **"Terminal Settings"** tab from the left-hand column
+    3. Navigate to **"Default Terminal Profile"** and select **"bash"** from the drop-down
+
+-   **Increase timeout**
+
+    1. Within Cline, left-click the **Settings** button in the top right-hand corner of the chat window
+    2. Once in the **Settings** window, left-click the **"Terminal Settings"** tab from the left-hand column
+    3. Navigate to "Shell integration timeout (seconds)" and enter **"10"** into the text field
+
+-   **Disable terminal reuse**
+    1. Within Cline, left-click the **Settings** button in the top right-hand corner of the chat window
+    2. Once in the **Settings** window, left-click the **"Terminal Settings"** tab from the left-hand column
+    3. Look for **"Enable aggressive terminal reuse"**, and **uncheck** this option
+
+## Platform-Specific Fixes
+
+### macOS + Oh-My-Zsh
+
+```bash
+# Create minimal config for VSCode
+echo 'export TERM=xterm-256color' > ~/.zshrc-vscode
+echo 'export PAGER=cat' >> ~/.zshrc-vscode
+```
+
+### Windows PowerShell
+
+```powershell
+# Run as Administrator
+Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
+```
+
+### WSL
+
+-   Open folder from WSL: `code .`
+-   Select **"WSL Bash"** in Cline settings, under **"Terminal Settings"**
+-   Increase **"Shell integration timeout (seconds)"** to **15**
+
+## Full Guide
+
+For detailed troubleshooting, see the [Complete Terminal Troubleshooting Guide](/troubleshooting/terminal-integration-guide).

eslint-rules/__tests__/no-direct-vscode-api.test.ts

@@ -0,0 +1,123 @@
+const { RuleTester: DirectApiRuleTester } = require("eslint")
+const noDirectVscodeApiRule = require("../no-direct-vscode-api")
+
+const directApiRuleTester = new DirectApiRuleTester({
+	parser: require.resolve("@typescript-eslint/parser"),
+	parserOptions: {
+		ecmaVersion: 2020,
+		sourceType: "module",
+		ecmaFeatures: {
+			jsx: true,
+		},
+	},
+})
+
+directApiRuleTester.run("no-direct-vscode-api", noDirectVscodeApiRule, {
+	valid: [
+		// Should allow vscode.postMessage in grpc-client-base.ts
+		{
+			code: `vscode.postMessage({ type: "grpc_request", data: {} })`,
+			filename: "grpc-client-base.ts",
+		},
+		{
+			code: `vscode.postMessage({ type: "grpc_request_cancel" })`,
+			filename: "/path/to/grpc-client-base.ts",
+		},
+		// Should allow in exception directories
+		{
+			code: `vscode.workspace.workspaceFolders`,
+			filename: "/src/hosts/vscode/host-bridge.ts",
+		},
+		{
+			code: `vscode.workspace.fs.stat(uri)`,
+			filename: "/standalone/runtime-files/helpers.ts",
+		},
+		// Should allow other vscode API calls
+		{
+			code: `vscode.window.showInformationMessage("Hello")`,
+			filename: "test.ts",
+		},
+		// Should allow postMessage calls on other objects
+		{
+			code: `window.postMessage({ type: "test" }, "*")`,
+			filename: "test.ts",
+		},
+		// Should allow variables named vscode but not calling postMessage
+		{
+			code: `const vscode = { other: "method" }; vscode.other()`,
+			filename: "test.ts",
+		},
+	],
+	invalid: [
+		// Should disallow vscode.postMessage in regular files
+		{
+			code: `vscode.postMessage({ type: "test", data: {} })`,
+			filename: "test.ts",
+			errors: [
+				{
+					messageId: "useGrpcClient",
+				},
+			],
+		},
+		// Should disallow vscode.postMessage in components
+		{
+			code: `vscode.postMessage({ type: "apiConfiguration", apiConfiguration })`,
+			filename: "ApiOptions.tsx",
+			errors: [
+				{
+					messageId: "useGrpcClient",
+				},
+			],
+		},
+		// Should disallow vscode.postMessage in test files
+		{
+			code: `vscode.postMessage({ type: "newTask", text: message.text })`,
+			filename: "test.test.ts",
+			errors: [
+				{
+					messageId: "useGrpcClient",
+				},
+			],
+		},
+		// Should disallow property access for disallowed APIs
+		{
+			code: `const folders = vscode.workspace.workspaceFolders;`,
+			filename: "workspace.ts",
+			errors: [
+				{
+					messageId: "useHostBridge",
+				},
+			],
+		},
+		// Should disallow method calls for disallowed APIs
+		{
+			code: `const relativePath = vscode.workspace.asRelativePath(filePath);`,
+			filename: "path-utils.ts",
+			errors: [
+				{
+					messageId: "usePathUtils",
+				},
+			],
+		},
+		// Should disallow nested property access
+		{
+			code: `const stats = await vscode.workspace.fs.stat(uri);`,
+			filename: "file-utils.ts",
+			errors: [
+				{
+					messageId: "useFsUtils",
+				},
+			],
+		},
+		// Should disallow getting a workspace folder
+		{
+			code: `const folder = vscode.workspace.getWorkspaceFolder(uri);`,
+			filename: "path-helper.ts",
+			errors: [
+				{
+					messageId: "usePathUtils",
+				},
+			],
+		},
+	],
+})

eslint-rules/__tests__/no-vscode-postmessage.test.ts

@@ -1,74 +0,0 @@
-const { RuleTester: VscodeRuleTester } = require("eslint")
-const vscodePostmessageRule = require("../no-vscode-postmessage")
-
-const vscodeRuleTester = new VscodeRuleTester({
-	parser: require.resolve("@typescript-eslint/parser"),
-	parserOptions: {
-		ecmaVersion: 2020,
-		sourceType: "module",
-		ecmaFeatures: {
-			jsx: true,
-		},
-	},
-})
-
-vscodeRuleTester.run("no-vscode-postmessage", vscodePostmessageRule, {
-	valid: [
-		// Should allow vscode.postMessage in grpc-client-base.ts
-		{
-			code: `vscode.postMessage({ type: "grpc_request", data: {} })`,
-			filename: "grpc-client-base.ts",
-		},
-		{
-			code: `vscode.postMessage({ type: "grpc_request_cancel" })`,
-			filename: "/path/to/grpc-client-base.ts",
-		},
-		// Should allow other vscode API calls
-		{
-			code: `vscode.window.showInformationMessage("Hello")`,
-			filename: "test.ts",
-		},
-		// Should allow postMessage calls on other objects
-		{
-			code: `window.postMessage({ type: "test" }, "*")`,
-			filename: "test.ts",
-		},
-		// Should allow variables named vscode but not calling postMessage
-		{
-			code: `const vscode = { other: "method" }; vscode.other()`,
-			filename: "test.ts",
-		},
-	],
-	invalid: [
-		// Should ban vscode.postMessage in regular files
-		{
-			code: `vscode.postMessage({ type: "test", data: {} })`,
-			filename: "test.ts",
-			errors: [
-				{
-					messageId: "useGrpcClient",
-				},
-			],
-		},
-		// Should ban vscode.postMessage in components
-		{
-			code: `vscode.postMessage({ type: "apiConfiguration", apiConfiguration })`,
-			filename: "ApiOptions.tsx",
-			errors: [
-				{
-					messageId: "useGrpcClient",
-				},
-			],
-		},
-		// Should ban vscode.postMessage in test files
-		{
-			code: `vscode.postMessage({ type: "newTask", text: message.text })`,
-			filename: "test.test.ts",
-			errors: [
-				{
-					messageId: "useGrpcClient",
-				},
-			],
-		},
-	],
-})

eslint-rules/index.js

@@ -1,13 +1,13 @@
 // eslint-rules/index.js
 const noProtobufObjectLiterals = require("./no-protobuf-object-literals")
 const noGrpcClientObjectLiterals = require("./no-grpc-client-object-literals")
-const noVscodePostmessage = require("./no-vscode-postmessage")
+const noDirectVscodeApi = require("./no-direct-vscode-api")
 
 module.exports = {
 	rules: {
 		"no-protobuf-object-literals": noProtobufObjectLiterals,
 		"no-grpc-client-object-literals": noGrpcClientObjectLiterals,
-		"no-vscode-postmessage": noVscodePostmessage,
+		"no-direct-vscode-api": noDirectVscodeApi,
 	},
 	configs: {
 		recommended: {
@@ -15,7 +15,7 @@ module.exports = {
 			rules: {
 				"local/no-protobuf-object-literals": "error",
 				"local/no-grpc-client-object-literals": "error",
-				"local/no-vscode-postmessage": "error",
+				"local/no-direct-vscode-api": "warn",
 			},
 		},
 	},

eslint-rules/no-direct-vscode-api.js

@@ -0,0 +1,164 @@
+const { ESLintUtils } = require("@typescript-eslint/utils")
+const path = require("path")
+
+const createRule = ESLintUtils.RuleCreator((name) => `https://cline.bot/eslint-rules/${name}`)
+
+// Configuration of disallowed VSCode APIs and their recommended alternatives
+const disallowedApis = {
+	"vscode.postMessage": {
+		messageId: "useGrpcClient",
+	},
+	"vscode.workspace.fs.stat": {
+		messageId: "useFsUtils",
+	},
+	"vscode.workspace.workspaceFolders": {
+		messageId: "useHostBridge",
+	},
+	"vscode.workspace.asRelativePath": {
+		messageId: "usePathUtils",
+	},
+	"vscode.workspace.getWorkspaceFolder": {
+		messageId: "usePathUtils",
+	},
+}
+
+module.exports = createRule({
+	name: "no-direct-vscode-api",
+	meta: {
+		type: "problem",
+		docs: {
+			description:
+				"Disallow direct VSCode API usage in favor of Cline's abstraction layers, except in src/hosts/vscode and standalone/runtime-files directories",
+			recommended: "error",
+		},
+		messages: {
+			useGrpcClient:
+				"Use gRPC service clients instead of vscode.postMessage().\n" +
+				"Example: AccountServiceClient.methodName(RequestType.create({...})) instead of vscode.postMessage({type: '...'}).\n" +
+				"Found: {{code}}",
+			useFsUtils:
+				"Use utilities in @/utils/fs instead of vscode.workspace.fs.stat.\n" +
+				"Example: import { isDirectory } from '@/utils/fs' or use the file system methods from the host bridge provider.\n" +
+				"Found: {{code}}",
+			useHostBridge:
+				"Use getHostBridgeProvider().workspaceClient.getWorkspacePaths({}) instead of vscode.workspace.workspaceFolders.\n" +
+				"This provides a consistent abstraction across VSCode and standalone environments.\n" +
+				"Found: {{code}}",
+			usePathUtils:
+				"Use path utilities from @/utils/path instead of direct VSCode workspace path methods.\n" +
+				"This provides consistent path handling across different environments.\n" +
+				"Found: {{code}}",
+		},
+		schema: [],
+	},
+	defaultOptions: [],
+
+	create(context) {
+		// Check if current file is in an exception directory or is grpc-client-base.ts
+		const filename = context.filename
+		const isGrpcClientBase = path.basename(filename) === "grpc-client-base.ts"
+
+		// Skip checking files in src/hosts/vscode or standalone/runtime-files
+		const isExceptionDirectory = filename.includes("/src/hosts/vscode/") || filename.includes("/standalone/runtime-files/")
+
+		// Pattern for checking memberExpressions like vscode.workspace.fs.stat
+		function checkMemberExpression(node) {
+			// Skip if this file is in an exception directory or is grpc-client-base.ts
+			if (isGrpcClientBase || isExceptionDirectory) {
+				return
+			}
+
+			// For handling nested properties like vscode.workspace.fs.stat
+			function getFullPropertyPath(node) {
+				if (node.type !== "MemberExpression") {
+					return node.name || ""
+				}
+
+				const objectPart = getFullPropertyPath(node.object)
+				const propertyPart = node.property.name || ""
+
+				return objectPart ? `${objectPart}.${propertyPart}` : propertyPart
+			}
+
+			// Check if the expression matches one of our disallowed patterns
+			if (node.object && node.object.type === "Identifier" && node.object.name === "vscode") {
+				const fullPath = `vscode.${node.property.name}`
+				checkDisallowedApi(fullPath, node)
+			}
+			// Handle nested expressions like vscode.workspace.fs.stat
+			else if (node.object && node.object.type === "MemberExpression") {
+				const fullPath = getFullPropertyPath(node)
+
+				// Only proceed if it starts with vscode
+				if (fullPath.startsWith("vscode.")) {
+					checkDisallowedApi(fullPath, node)
+				}
+			}
+		}
+
+		// Check if an expression matches a disallowed API and report if it does
+		function checkDisallowedApi(expressionPath, node) {
+			// Check exact matches
+			if (disallowedApis[expressionPath]) {
+				reportViolation(expressionPath, node)
+				return
+			}
+
+			// Check prefix matches (for nested properties)
+			for (const disallowedApi in disallowedApis) {
+				// For direct property access like vscode.workspace.workspaceFolders
+				if (expressionPath === disallowedApi) {
+					reportViolation(disallowedApi, node)
+					return
+				}
+
+				// For method calls like vscode.workspace.asRelativePath(...)
+				if (expressionPath.startsWith(`${disallowedApi}.`) || expressionPath.startsWith(`${disallowedApi}(`)) {
+					reportViolation(disallowedApi, node)
+					return
+				}
+			}
+		}
+
+		// Report a violation with the appropriate message
+		function reportViolation(disallowedApi, node) {
+			const sourceCode = context.sourceCode
+			const config = disallowedApis[disallowedApi]
+
+			// For method calls, get the whole call expression
+			let reportNode = node
+			let parentNode = sourceCode.getAncestors(node).pop()
+			if (parentNode && parentNode.type === "CallExpression" && parentNode.callee === node) {
+				reportNode = parentNode
+			}
+
+			const callText = sourceCode.getText(reportNode).trim()
+
+			context.report({
+				node: reportNode,
+				messageId: config.messageId,
+				data: {
+					code: callText,
+				},
+			})
+		}
+
+		return {
+			// Detect basic member expressions (e.g., vscode.postMessage)
+			MemberExpression(node) {
+				checkMemberExpression(node)
+			},
+
+			// Detect property access through destructuring
+			VariableDeclarator(node) {
+				// Skip if this file is in an exception directory or is grpc-client-base.ts
+				if (isGrpcClientBase || isExceptionDirectory) {
+					return
+				}
+
+				// Destructuring pattern checks removed as developers don't use the API this way
+				// They always use direct imports: import * as vscode from "vscode" and direct access: vscode.thing.foo
+			},
+		}
+	},
+})

eslint-rules/no-vscode-postmessage.js

@@ -1,61 +0,0 @@
-const { ESLintUtils } = require("@typescript-eslint/utils")
-const path = require("path")
-
-const createRule = ESLintUtils.RuleCreator((name) => `https://cline.bot/eslint-rules/${name}`)
-
-module.exports = createRule({
-	name: "no-vscode-postmessage",
-	meta: {
-		type: "problem",
-		docs: {
-			description: "Ban vscode.postMessage() calls in favor of gRPC service clients, except in grpc-client-base.ts",
-			recommended: "error",
-		},
-		messages: {
-			useGrpcClient:
-				"Use gRPC service clients instead of vscode.postMessage().\n" +
-				"Example: AccountServiceClient.methodName(RequestType.create({...})) instead of vscode.postMessage({type: '...'}).\n" +
-				"Found: {{code}}",
-		},
-		schema: [],
-	},
-	defaultOptions: [],
-
-	create(context) {
-		// Check if current file is grpc-client-base.ts (exception case)
-		const filename = context.filename
-		const isGrpcClientBase = path.basename(filename) === "grpc-client-base.ts"
-
-		return {
-			// Detect vscode.postMessage calls
-			"CallExpression[callee.type='MemberExpression']"(node) {
-				// Skip if this is grpc-client-base.ts
-				if (isGrpcClientBase) {
-					return
-				}
-
-				const callee = node.callee
-
-				// Check for vscode.postMessage pattern
-				if (
-					callee.object &&
-					callee.object.type === "Identifier" &&
-					callee.object.name === "vscode" &&
-					callee.property &&
-					callee.property.name === "postMessage"
-				) {
-					const sourceCode = context.sourceCode
-					const callText = sourceCode.getText(node).trim()
-
-					context.report({
-						node,
-						messageId: "useGrpcClient",
-						data: {
-							code: callText,
-						},
-					})
-				}
-			},
-		}
-	},
-})

evals/cli/src/commands/runDiffEval.ts

@@ -6,6 +6,7 @@ interface RunDiffEvalOptions {
 	modelIds: string
 	systemPromptName: string
 	validAttemptsPerCase: number
+	maxAttemptsPerCase?: number
 	parsingFunction: string
 	diffEditFunction: string
 	thinkingBudget: number
@@ -16,6 +17,7 @@ interface RunDiffEvalOptions {
 	replay: boolean
 	replayRunId?: string
 	diffApplyFile?: string
+	saveLocally: boolean
 	maxCases?: number
 }
 
@@ -70,10 +72,18 @@ export async function runDiffEvalHandler(options: RunDiffEvalOptions) {
 		args.push("--verbose")
 	}
 
+	if (options.maxAttemptsPerCase) {
+		args.push("--max-attempts-per-case", String(options.maxAttemptsPerCase))
+	}
+
 	if (options.maxCases) {
 		args.push("--max-cases", String(options.maxCases))
 	}
 
+	if (options.saveLocally) {
+		args.push("--save-locally")
+	}
+
 	try {
 		console.log(chalk.gray(`Executing: npx tsx ${scriptPath} ${args.join(" ")}`))
 

evals/cli/src/index.ts

@@ -87,6 +87,7 @@ program
 	.option("--model-ids <model_ids>", "Comma-separated list of model IDs to test")
 	.option("--system-prompt-name <name>", "The name of the system prompt to use", "basicSystemPrompt")
 	.option("-n, --valid-attempts-per-case <number>", "Number of valid attempts per test case per model (will retry until this many valid attempts are collected)", "1")
+	.option("--max-attempts-per-case <number>", "Maximum total attempts per test case (default: 10x valid attempts)")
 	.option("--max-cases <number>", "Maximum number of test cases to run (limits total cases loaded)")
 	.option("--parsing-function <name>", "The parsing function to use", "parseAssistantMessageV2")
 	.option("--diff-edit-function <name>", "The diff editing function to use", "constructNewFileContentV2")
@@ -95,12 +96,14 @@ program
 	.option("--replay", "Run evaluation from a pre-recorded LLM output, skipping the API call", false)
 	.option("--replay-run-id <run_id>", "The ID of the run to replay from the database")
 	.option("--diff-apply-file <filename>", "The name of the diff apply file to use for the replay")
+	.option("--save-locally", "Save results to local JSON files in addition to database", false)
 	.option("-v, --verbose", "Enable verbose logging", false)
 	.action(async (options) => {
 		try {
 			const fullOptions = {
 				...options,
 				validAttemptsPerCase: parseInt(options.validAttemptsPerCase, 10),
+				maxAttemptsPerCase: options.maxAttemptsPerCase ? parseInt(options.maxAttemptsPerCase, 10) : undefined,
 				thinkingBudget: parseInt(options.thinkingBudget, 10),
 				maxCases: options.maxCases ? parseInt(options.maxCases, 10) : undefined,
 			}

evals/diff-edits/ClineWrapper.ts

@@ -11,9 +11,10 @@ import {
 import { constructNewFileContent as constructNewFileContent_06_06_25 } from "./diff-apply/diff-06-06-25"
 import { constructNewFileContent as constructNewFileContent_06_23_25 } from "./diff-apply/diff-06-23-25"
 import { constructNewFileContent as constructNewFileContent_06_25_25 } from "./diff-apply/diff-06-25-25"
+import { constructNewFileContent as constructNewFileContent_06_26_25 } from "./diff-apply/diff-06-26-25"
 
 type ParseAssistantMessageFn = (message: string) => AssistantMessageContent[]
-type ConstructNewFileContentFn = (diff: string, original: string, strict: boolean) => Promise<string>
+type ConstructNewFileContentFn = (diff: string, original: string, strict: boolean) => Promise<string | any>
 
 const parsingFunctions: Record<string, ParseAssistantMessageFn> = {
 	parseAssistantMessageV1: parseAssistantMessageV1,
@@ -25,9 +26,11 @@ const diffEditingFunctions: Record<string, ConstructNewFileContentFn> = {
 	"diff-06-06-25": constructNewFileContent_06_06_25,
 	"diff-06-23-25": constructNewFileContent_06_23_25,
 	"diff-06-25-25": constructNewFileContent_06_25_25,
+	"diff-06-26-25": constructNewFileContent_06_26_25,
 }
 
 import { TestInput, TestResult, ExtractedToolCall } from "./types"
+import { log } from "./helpers"
 export { TestInput, TestResult, ExtractedToolCall }
 
 interface StreamResult {
@@ -282,21 +285,21 @@ export async function runSingleEvaluation(input: TestInput): Promise<TestResult>
 		}
 
 		// check that we are editing the correct file path
-		console.log(`Expected file path: "${originalFilePath}"`);
-		console.log(`Actual file path used: "${diffToolPath}"`);
+		log(input.isVerbose, `Expected file path: "${originalFilePath}"`)
+		log(input.isVerbose, `Actual file path used: "${diffToolPath}"`)
 		if (diffToolPath !== originalFilePath) {
-			console.log(`❌ File path mismatch detected!`);
+			log(input.isVerbose, `❌ File path mismatch detected!`)
 			// Enhanced logging:
 			if (streamResult?.assistantMessage) {
-				console.log(`   Full model output (assistantMessage):`);
-				console.log(`   -----------------------------------------`);
-				console.log(`   ${streamResult.assistantMessage}`);
-				console.log(`   -----------------------------------------`);
+				log(input.isVerbose, `   Full model output (assistantMessage):`)
+				log(input.isVerbose, `   -----------------------------------------`)
+				log(input.isVerbose, `   ${streamResult.assistantMessage}`)
+				log(input.isVerbose, `   -----------------------------------------`)
 			}
 			if (toolCall) {
-				console.log(`   Parsed tool call that caused mismatch:`);
-				console.log(`   ${JSON.stringify(toolCall, null, 2)}`);
-				console.log(`   -----------------------------------------`);
+				log(input.isVerbose, `   Parsed tool call that caused mismatch:`)
+				log(input.isVerbose, `   ${JSON.stringify(toolCall, null, 2)}`)
+				log(input.isVerbose, `   -----------------------------------------`)
 			}
 			return {
 				success: false,
@@ -308,10 +311,18 @@ export async function runSingleEvaluation(input: TestInput): Promise<TestResult>
 
 		// checking if the diff edit succeeds, if it failed it will throw an error
 		let diffSuccess = true
+		let replacementData: any = undefined
 		try {
-			await constructNewFileContent(diffToolContent, originalFile, true)
+			const result = await constructNewFileContent(diffToolContent, originalFile, true)
+			
+			// Check if result is an object with replacements (new format)
+			if (typeof result === 'object' && result !== null && 'replacements' in result) {
+				replacementData = result.replacements
+			}
+			// If it's just a string, diffSuccess stays true and replacementData stays undefined
 		} catch (error: any) {
 			diffSuccess = false
+			log(input.isVerbose, `ERROR: ${error}`)
 		}
 
 		return {
@@ -320,6 +331,7 @@ export async function runSingleEvaluation(input: TestInput): Promise<TestResult>
 			toolCalls: detectedToolCalls,
 			diffEdit: diffToolContent,
 			diffEditSuccess: diffSuccess,
+			replacementData: replacementData,
 		}
 	} catch (error: any) {
 		return {

evals/diff-edits/TestRunner.ts

@@ -3,10 +3,11 @@ import { parseAssistantMessageV2, AssistantMessageContent } from "./parsing/pars
 import { constructNewFileContent as constructNewFileContent_06_06_25 } from "./diff-apply/diff-06-06-25"
 import { constructNewFileContent as constructNewFileContent_06_23_25 } from "./diff-apply/diff-06-23-25"
 import { constructNewFileContent as constructNewFileContent_06_25_25 } from "./diff-apply/diff-06-25-25"
+import { constructNewFileContent as constructNewFileContent_06_26_25 } from "./diff-apply/diff-06-26-25"
 import { constructNewFileContent as constructNewFileContentV3 } from "../../src/core/assistant-message/diff"
 import { basicSystemPrompt } from "./prompts/basicSystemPrompt-06-06-25"
 import { claude4SystemPrompt } from "./prompts/claude4SystemPrompt-06-06-25"
-import { formatResponse } from "./helpers"
+import { formatResponse, log } from "./helpers"
 import { Anthropic } from "@anthropic-ai/sdk"
 import * as fs from "fs"
 import * as path from "path"
@@ -39,12 +40,6 @@ const encoding = get_encoding("cl100k_base");
 
 let openRouterModelDataGlobal: Record<string, EvalOpenRouterModelInfo> = {}; // Global to store fetched data
 
-function log(isVerbose: boolean, message: string) {
-	if (isVerbose) {
-		console.log(message)
-	}
-}
-
 const systemPromptGeneratorLookup: Record<string, ConstructSystemPromptFn> = {
 	basicSystemPrompt: basicSystemPrompt,
 	claude4SystemPrompt: claude4SystemPrompt,
@@ -484,6 +479,7 @@ class NodeTestRunner {
 			"diff-06-06-25": constructNewFileContent_06_06_25,
 			"diff-06-23-25": constructNewFileContent_06_23_25,
 			"diff-06-25-25": constructNewFileContent_06_25_25,
+			"diff-06-26-25": constructNewFileContent_06_26_25,
 			constructNewFileContentV3: constructNewFileContentV3,
 		}
 		const constructNewFileContent = diffEditingFunctions[diffApplyFile]
@@ -639,6 +635,7 @@ class NodeTestRunner {
 			thinkingBudgetTokens: testConfig.thinking_tokens_budget,
 			originalDiffEditToolCallMessage: testConfig.replay ? testCase.original_diff_edit_tool_call_message : undefined,
 			diffApplyFile: testConfig.diff_apply_file,
+			isVerbose: isVerbose,
 		}
 
 		if (isVerbose) {
@@ -805,8 +802,8 @@ class NodeTestRunner {
 					log(isVerbose, `Warning: Failed to store result in database: ${error}`);
 				}
 				
-				// Safety check to prevent infinite loops - limit to 10 attempts per valid attempt requested
-				if (totalAttempts >= testConfig.number_of_runs * 10) {
+				// Safety check to prevent infinite loops - use configurable max attempts limit
+				if (totalAttempts >= testConfig.max_attempts_per_case) {
 					log(isVerbose, `  ⚠️ Reached maximum attempts (${totalAttempts}) for test case ${testCase.test_id}. Only got ${validAttempts}/${testConfig.number_of_runs} valid attempts.`);
 					break;
 				}
@@ -925,14 +922,16 @@ async function main() {
 		.option("--model-ids <model_ids>", "Comma-separated list of model IDs to test")
 		.option("--system-prompt-name <name>", "The name of the system prompt to use", "basicSystemPrompt")
 		.option("-n, --valid-attempts-per-case <number>", "Number of valid attempts per test case per model (will retry until this many valid attempts are collected)", "1")
+		.option("--max-attempts-per-case <number>", "Maximum total attempts per test case (default: 10x valid attempts)")
 		.option("--max-cases <number>", "Maximum number of test cases to run (limits total cases loaded)")
 		.option("--parsing-function <name>", "The parsing function to use", "parseAssistantMessageV2")
-		.option("--diff-edit-function <name>", "The diff editing function to use", "constructNewFileContentV2")
+		.option("--diff-edit-function <name>", "The diff editing function to use", "diff-06-25-25")
 		.option("--thinking-budget <tokens>", "Set the thinking tokens budget", "0")
 		.option("--parallel", "Run tests in parallel", false)
 		.option("--replay", "Run evaluation from a pre-recorded LLM output, skipping the API call", false)
 		.option("--replay-run-id <run_id>", "The ID of the run to replay from the database")
 		.option("--diff-apply-file <filename>", "The name of the diff apply file to use for the replay")
+		.option("--save-locally", "Save results to local JSON files in addition to database", false)
 		.option("-v, --verbose", "Enable verbose logging", false)
 		.option("--max-concurrency <number>", "Maximum number of parallel requests", "80")
 
@@ -943,6 +942,7 @@ async function main() {
 	const isVerbose = options.verbose
 	const testPath = options.testPath
 	const outputPath = options.outputPath
+	const saveLocally = options.saveLocally
 	const maxConcurrency = parseInt(options.maxConcurrency, 10);
 
 	// Parse model IDs from comma-separated string
@@ -953,6 +953,11 @@ async function main() {
 	}
 
 	const validAttemptsPerCase = parseInt(options.validAttemptsPerCase, 10);
+	
+	// Compute dynamic default for max attempts: 10x valid attempts if not specified
+	const maxAttemptsPerCase = options.maxAttemptsPerCase 
+		? parseInt(options.maxAttemptsPerCase, 10)
+		: validAttemptsPerCase * 10;
 
 	const runner = new NodeTestRunner(options.replay || !!options.replayRunId)
 
@@ -1058,6 +1063,7 @@ async function main() {
 					model_id: modelId,
 					system_prompt_name: options.systemPromptName,
 					number_of_runs: validAttemptsPerCase,
+					max_attempts_per_case: maxAttemptsPerCase,
 					parsing_function: options.parsingFunction,
 					diff_edit_function: options.diffEditFunction,
 					thinking_tokens_budget: parseInt(options.thinkingBudget, 10),
@@ -1125,7 +1131,7 @@ async function main() {
 
 			remainingTasks = remainingTasks.filter(task => {
 				const taskId = `${task.modelId}-${task.testCase.test_id}`;
-				if (taskStates[taskId].total >= validAttemptsPerCase * 10) {
+				if (taskStates[taskId].total >= task.testConfig.max_attempts_per_case) {
 					log(isVerbose, `  ⚠️ Reached maximum attempts for ${task.testCase.test_id} with ${task.modelId}.`);
 					return false;
 				}
@@ -1150,6 +1156,12 @@ async function main() {
 		const durationSeconds = ((endTime - startTime) / 1000).toFixed(2)
 		log(isVerbose, `\n-Total execution time: ${durationSeconds} seconds`)
 
+		// Save results locally if requested
+		if (saveLocally) {
+			runner.saveTestResults(results, outputPath);
+			log(isVerbose, `✓ Results also saved to JSON files in ${outputPath}`);
+		}
+
 		log(isVerbose, `\n✓ All results stored in database. Use the dashboard to view results.`)
 	} catch (error) {
 		console.error("\nError running tests:", error)

evals/diff-edits/diff-apply/diff-06-26-25.ts

@@ -0,0 +1,960 @@
+const SEARCH_BLOCK_START = "------- SEARCH"
+const SEARCH_BLOCK_END = "======="
+const REPLACE_BLOCK_END = "+++++++ REPLACE"
+
+const SEARCH_BLOCK_CHAR = "-"
+const REPLACE_BLOCK_CHAR = "+"
+const LEGACY_SEARCH_BLOCK_CHAR = "<"
+const LEGACY_REPLACE_BLOCK_CHAR = ">"
+
+// Replace the exact string constants with flexible regex patterns
+const SEARCH_BLOCK_START_REGEX = /^[-]{3,} SEARCH>?$/
+const LEGACY_SEARCH_BLOCK_START_REGEX = /^[<]{3,} SEARCH>?$/
+
+const SEARCH_BLOCK_END_REGEX = /^[=]{3,}$/
+
+const REPLACE_BLOCK_END_REGEX = /^[+]{3,} REPLACE>?$/
+const LEGACY_REPLACE_BLOCK_END_REGEX = /^[>]{3,} REPLACE>?$/
+
+// Similarity thresholds for block anchor fallback matching
+const SINGLE_CANDIDATE_SIMILARITY_THRESHOLD = 0.0
+const MULTIPLE_CANDIDATES_SIMILARITY_THRESHOLD = 0.0
+
+/**
+ * Levenshtein distance algorithm implementation
+ */
+function levenshtein(a: string, b: string): number {
+	// Handle empty strings
+	if (a === "" || b === "") {
+		return Math.max(a.length, b.length)
+	}
+	const matrix = Array.from({ length: a.length + 1 }, (_, i) =>
+		Array.from({ length: b.length + 1 }, (_, j) => (i === 0 ? j : j === 0 ? i : 0)),
+	)
+
+	for (let i = 1; i <= a.length; i++) {
+		for (let j = 1; j <= b.length; j++) {
+			const cost = a[i - 1] === b[j - 1] ? 0 : 1
+			matrix[i][j] = Math.min(matrix[i - 1][j] + 1, matrix[i][j - 1] + 1, matrix[i - 1][j - 1] + cost)
+		}
+	}
+	return matrix[a.length][b.length]
+}
+
+// Helper functions to check if a line matches the flexible patterns
+function isSearchBlockStart(line: string): boolean {
+	return SEARCH_BLOCK_START_REGEX.test(line) || LEGACY_SEARCH_BLOCK_START_REGEX.test(line)
+}
+
+function isSearchBlockEnd(line: string): boolean {
+	return SEARCH_BLOCK_END_REGEX.test(line)
+}
+
+function isReplaceBlockEnd(line: string): boolean {
+	return REPLACE_BLOCK_END_REGEX.test(line) || LEGACY_REPLACE_BLOCK_END_REGEX.test(line)
+}
+
+/**
+ * Attempts a line-trimmed fallback match for the given search content in the original content.
+ * It tries to match `searchContent` lines against a block of lines in `originalContent` starting
+ * from `lastProcessedIndex`. Lines are matched by trimming leading/trailing whitespace and ensuring
+ * they are identical afterwards.
+ *
+ * Returns [matchIndexStart, matchIndexEnd] if found, or false if not found.
+ */
+function lineTrimmedFallbackMatch(originalContent: string, searchContent: string, startIndex: number): [number, number] | false {
+	// Split both contents into lines
+	const originalLines = originalContent.split("\n")
+	const searchLines = searchContent.split("\n")
+
+	// Trim trailing empty line if exists (from the trailing \n in searchContent)
+	if (searchLines[searchLines.length - 1] === "") {
+		searchLines.pop()
+	}
+
+	// Find the line number where startIndex falls
+	let startLineNum = 0
+	let currentIndex = 0
+	while (currentIndex < startIndex && startLineNum < originalLines.length) {
+		currentIndex += originalLines[startLineNum].length + 1 // +1 for \n
+		startLineNum++
+	}
+
+	// For each possible starting position in original content
+	for (let i = startLineNum; i <= originalLines.length - searchLines.length; i++) {
+		let matches = true
+
+		// Try to match all search lines from this position
+		for (let j = 0; j < searchLines.length; j++) {
+			const originalTrimmed = originalLines[i + j].trim()
+			const searchTrimmed = searchLines[j].trim()
+
+			if (originalTrimmed !== searchTrimmed) {
+				matches = false
+				break
+			}
+		}
+
+		// If we found a match, calculate the exact character positions
+		if (matches) {
+			// Find start character index
+			let matchStartIndex = 0
+			for (let k = 0; k < i; k++) {
+				matchStartIndex += originalLines[k].length + 1 // +1 for \n
+			}
+
+			// Find end character index
+			let matchEndIndex = matchStartIndex
+			for (let k = 0; k < searchLines.length; k++) {
+				matchEndIndex += originalLines[i + k].length + 1 // +1 for \n
+			}
+
+			return [matchStartIndex, matchEndIndex]
+		}
+	}
+
+	return false
+}
+
+/**
+ * Attempts to match blocks of code by using the first and last lines as anchors,
+ * with similarity checking to prevent false positives.
+ * This is a third-tier fallback strategy that helps match blocks where we can identify
+ * the correct location by matching the beginning and end, even if the exact content
+ * differs slightly.
+ *
+ * The matching strategy:
+ * 1. Only attempts to match blocks of 3 or more lines to avoid false positives
+ * 2. Extracts from the search content:
+ *    - First line as the "start anchor"
+ *    - Last line as the "end anchor"
+ * 3. Collects all candidate positions where both anchors match
+ * 4. Uses levenshtein distance to calculate similarity of middle lines
+ * 5. Returns match only if similarity meets threshold requirements
+ *
+ * This approach is particularly useful for matching blocks of code where:
+ * - The exact content might have minor differences
+ * - The beginning and end of the block are distinctive enough to serve as anchors
+ * - The overall structure (number of lines) remains the same
+ * - The middle content is reasonably similar (prevents false positives)
+ *
+ * @param originalContent - The full content of the original file
+ * @param searchContent - The content we're trying to find in the original file
+ * @param startIndex - The character index in originalContent where to start searching
+ * @returns A tuple of [startIndex, endIndex] if a match is found, false otherwise
+ */
+function blockAnchorFallbackMatch(originalContent: string, searchContent: string, startIndex: number): [number, number, number] | false {
+	const originalLines = originalContent.split("\n")
+	const searchLines = searchContent.split("\n")
+
+	// Only use this approach for blocks of 3+ lines
+	if (searchLines.length < 3) {
+		return false
+	}
+
+	// Trim trailing empty line if exists
+	if (searchLines[searchLines.length - 1] === "") {
+		searchLines.pop()
+	}
+
+	const firstLineSearch = searchLines[0].trim()
+	const lastLineSearch = searchLines[searchLines.length - 1].trim()
+	const searchBlockSize = searchLines.length
+
+	// Find the line number where startIndex falls
+	let startLineNum = 0
+	let currentIndex = 0
+	while (currentIndex < startIndex && startLineNum < originalLines.length) {
+		currentIndex += originalLines[startLineNum].length + 1
+		startLineNum++
+	}
+
+	// Collect all candidate positions
+	const candidates: number[] = []
+	for (let i = startLineNum; i <= originalLines.length - searchBlockSize; i++) {
+		if (originalLines[i].trim() === firstLineSearch && originalLines[i + searchBlockSize - 1].trim() === lastLineSearch) {
+			candidates.push(i)
+		}
+	}
+
+	// Return immediately if no candidates
+	if (candidates.length === 0) {
+		return false
+	}
+
+	// Handle single candidate scenario (using relaxed threshold)
+	if (candidates.length === 1) {
+		const i = candidates[0]
+		let similarity = 0
+		let linesToCheck = searchBlockSize - 2
+
+		for (let j = 1; j < searchBlockSize - 1; j++) {
+			const originalLine = originalLines[i + j].trim()
+			const searchLine = searchLines[j].trim()
+			const maxLen = Math.max(originalLine.length, searchLine.length)
+			if (maxLen === 0) {
+				continue
+			}
+			const distance = levenshtein(originalLine, searchLine)
+			similarity += (1 - distance / maxLen) / linesToCheck
+
+			// Exit early when threshold is reached
+			if (similarity >= SINGLE_CANDIDATE_SIMILARITY_THRESHOLD) {
+				break
+			}
+		}
+
+		if (similarity >= SINGLE_CANDIDATE_SIMILARITY_THRESHOLD) {
+			let matchStartIndex = 0
+			for (let k = 0; k < i; k++) {
+				matchStartIndex += originalLines[k].length + 1
+			}
+			let matchEndIndex = matchStartIndex
+			for (let k = 0; k < searchBlockSize; k++) {
+				matchEndIndex += originalLines[i + k].length + 1
+			}
+			return [matchStartIndex, matchEndIndex, similarity]
+		}
+		return false
+	}
+
+	// Calculate similarity for multiple candidates
+	let bestMatchIndex = -1
+	let maxSimilarity = -1
+
+	for (const i of candidates) {
+		let similarity = 0
+		for (let j = 1; j < searchBlockSize - 1; j++) {
+			const originalLine = originalLines[i + j].trim()
+			const searchLine = searchLines[j].trim()
+			const maxLen = Math.max(originalLine.length, searchLine.length)
+			if (maxLen === 0) {
+				continue
+			}
+			const distance = levenshtein(originalLine, searchLine)
+			similarity += 1 - distance / maxLen
+		}
+		similarity /= searchBlockSize - 2 // Average similarity
+
+		if (similarity > maxSimilarity) {
+			maxSimilarity = similarity
+			bestMatchIndex = i
+		}
+	}
+
+	// Threshold judgment
+	if (maxSimilarity >= MULTIPLE_CANDIDATES_SIMILARITY_THRESHOLD) {
+		const i = bestMatchIndex
+		let matchStartIndex = 0
+		for (let k = 0; k < i; k++) {
+			matchStartIndex += originalLines[k].length + 1
+		}
+		let matchEndIndex = matchStartIndex
+		for (let k = 0; k < searchBlockSize; k++) {
+			matchEndIndex += originalLines[i + k].length + 1
+		}
+		return [matchStartIndex, matchEndIndex, maxSimilarity]
+	}
+
+	return false
+}
+
+/**
+ * This function reconstructs the file content by applying a streamed diff (in a
+ * specialized SEARCH/REPLACE block format) to the original file content. It is designed
+ * to handle both incremental updates and the final resulting file after all chunks have
+ * been processed.
+ *
+ * The diff format is a custom structure that uses three markers to define changes:
+ *
+ *   ------- SEARCH
+ *   [Exact content to find in the original file]
+ *   =======
+ *   [Content to replace with]
+ *   +++++++ REPLACE
+ *
+ * Behavior and Assumptions:
+ * 1. The file is processed chunk-by-chunk. Each chunk of `diffContent` may contain
+ *    partial or complete SEARCH/REPLACE blocks. By calling this function with each
+ *    incremental chunk (with `isFinal` indicating the last chunk), the final reconstructed
+ *    file content is produced.
+ *
+ * 2. Matching Strategy (in order of attempt):
+ *    a. Exact Match: First attempts to find the exact SEARCH block text in the original file
+ *    b. Line-Trimmed Match: Falls back to line-by-line comparison ignoring leading/trailing whitespace
+ *    c. Block Anchor Match: For blocks of 3+ lines, tries to match using first/last lines as anchors
+ *    If all matching strategies fail, an error is thrown.
+ *
+ * 3. Empty SEARCH Section:
+ *    - If SEARCH is empty and the original file is empty, this indicates creating a new file
+ *      (pure insertion).
+ *    - If SEARCH is empty and the original file is not empty, this indicates a complete
+ *      file replacement (the entire original content is considered matched and replaced).
+ *
+ * 4. Applying Changes:
+ *    - Before encountering the "=======" marker, lines are accumulated as search content.
+ *    - After "=======" and before ">>>>>>> REPLACE", lines are accumulated as replacement content.
+ *    - Once the block is complete (">>>>>>> REPLACE"), the matched section in the original
+ *      file is replaced with the accumulated replacement lines, and the position in the original
+ *      file is advanced.
+ *
+ * 5. Incremental Output:
+ *    - As soon as the match location is found and we are in the REPLACE section, each new
+ *      replacement line is appended to the result so that partial updates can be viewed
+ *      incrementally.
+ *
+ * 6. Partial Markers:
+ *    - If the final line of the chunk looks like it might be part of a marker but is not one
+ *      of the known markers, it is removed. This prevents incomplete or partial markers
+ *      from corrupting the output.
+ *
+ * 7. Finalization:
+ *    - Once all chunks have been processed (when `isFinal` is true), any remaining original
+ *      content after the last replaced section is appended to the result.
+ *    - Trailing newlines are not forcibly added. The code tries to output exactly what is specified.
+ *
+ * Errors:
+ * - If the search block cannot be matched using any of the available matching strategies,
+ *   an error is thrown.
+ */
+export async function constructNewFileContent(
+	diffContent: string,
+	originalContent: string,
+	isFinal: boolean,
+	version: "v1" | "v2" = "v1",
+): Promise<any> {
+	const constructor = constructNewFileContentVersionMapping[version]
+	if (!constructor) {
+		throw new Error(`Invalid version '${version}' for file content constructor`)
+	}
+	return constructor(diffContent, originalContent, isFinal)
+}
+
+const constructNewFileContentVersionMapping: Record<
+	string,
+	(diffContent: string, originalContent: string, isFinal: boolean) => Promise<any>
+> = {
+	v1: constructNewFileContentV1,
+	v2: constructNewFileContentV2,
+} as const
+
+async function constructNewFileContentV1(diffContent: string, originalContent: string, isFinal: boolean): Promise<{
+	content: string;
+	replacements: Array<{ 
+		start: number; 
+		end: number; 
+		content: string;
+		method: string;
+		similarity: number;
+		searchContent: string;
+		matchedText: string;
+	}>;
+}> {
+	let result = ""
+	let lastProcessedIndex = 0
+
+	let currentSearchContent = ""
+	let currentReplaceContent = ""
+	let inSearch = false
+	let inReplace = false
+
+	let searchMatchIndex = -1
+	let searchEndIndex = -1
+	let matchMethod = ""
+	let similarityScore = -1.0
+
+	// Track all replacements to handle out-of-order edits
+	let replacements: Array<{ 
+		start: number; 
+		end: number; 
+		content: string;
+		method: string;
+		similarity: number;
+		searchContent: string;
+		matchedText: string;
+	}> = []
+	let pendingOutOfOrderReplacement = false
+
+	let lines = diffContent.split("\n")
+
+	// If the last line looks like a partial marker but isn't recognized,
+	// remove it because it might be incomplete.
+	const lastLine = lines[lines.length - 1]
+	if (
+		lines.length > 0 &&
+		(lastLine.startsWith(SEARCH_BLOCK_CHAR) ||
+			lastLine.startsWith(LEGACY_SEARCH_BLOCK_CHAR) ||
+			lastLine.startsWith("=") ||
+			lastLine.startsWith(REPLACE_BLOCK_CHAR) ||
+			lastLine.startsWith(LEGACY_REPLACE_BLOCK_CHAR)) &&
+		!isSearchBlockStart(lastLine) &&
+		!isSearchBlockEnd(lastLine) &&
+		!isReplaceBlockEnd(lastLine)
+	) {
+		lines.pop()
+	}
+
+	for (const line of lines) {
+		if (isSearchBlockStart(line)) {
+			inSearch = true
+			currentSearchContent = ""
+			currentReplaceContent = ""
+			continue
+		}
+
+		if (isSearchBlockEnd(line)) {
+			inSearch = false
+			inReplace = true
+
+			// Remove trailing linebreak for adding the === marker
+			// if (currentSearchContent.endsWith("\r\n")) {
+			// 	currentSearchContent = currentSearchContent.slice(0, -2)
+			// } else if (currentSearchContent.endsWith("\n")) {
+			// 	currentSearchContent = currentSearchContent.slice(0, -1)
+			// }
+
+			if (!currentSearchContent) {
+				// Empty search block
+				if (originalContent.length === 0) {
+					// New file scenario: nothing to match, just start inserting
+					searchMatchIndex = 0
+					searchEndIndex = 0
+					matchMethod = "empty_new_file"
+				} else {
+					// ERROR: Empty search block with non-empty file indicates malformed SEARCH marker
+					throw new Error(
+						"Empty SEARCH block detected with non-empty file. This usually indicates a malformed SEARCH marker.\n" +
+							"Please ensure your SEARCH marker follows the correct format:\n" +
+							"- Use '------- SEARCH' (7+ dashes + space + SEARCH)\n",
+					)
+				}
+			} else {
+				// Add check for inefficient full-file search
+				// if (currentSearchContent.trim() === originalContent.trim()) {
+				// 	throw new Error(
+				// 		"The SEARCH block contains the entire file content. Please either:\n" +
+				// 			"1. Use an empty SEARCH block to replace the entire file, or\n" +
+				// 			"2. Make focused changes to specific parts of the file that need modification.",
+				// 	)
+				// }
+
+				// Exact search match scenario
+				const exactIndex = originalContent.indexOf(currentSearchContent, lastProcessedIndex)
+				if (exactIndex !== -1) {
+					searchMatchIndex = exactIndex
+					searchEndIndex = exactIndex + currentSearchContent.length
+					matchMethod = "exact_match"
+				} else {
+					// Attempt fallback line-trimmed matching
+					const lineMatch = lineTrimmedFallbackMatch(originalContent, currentSearchContent, lastProcessedIndex)
+					if (lineMatch) {
+						;[searchMatchIndex, searchEndIndex] = lineMatch
+						matchMethod = "line_trimmed_fallback"
+					} else {
+						// Try block anchor fallback for larger blocks
+						const blockMatch = blockAnchorFallbackMatch(originalContent, currentSearchContent, lastProcessedIndex)
+						if (blockMatch) {
+							;[searchMatchIndex, searchEndIndex, similarityScore] = blockMatch
+							matchMethod = "block_anchor_fallback"
+						} else {
+							// Last resort: search the entire file from the beginning
+							const fullFileIndex = originalContent.indexOf(currentSearchContent, 0)
+							if (fullFileIndex !== -1) {
+								// Found in the file - could be out of order
+								searchMatchIndex = fullFileIndex
+								searchEndIndex = fullFileIndex + currentSearchContent.length
+								matchMethod = "full_file_search"
+								if (searchMatchIndex < lastProcessedIndex) {
+									pendingOutOfOrderReplacement = true
+								}
+							} else {
+								throw new Error(
+									`The SEARCH block:\n${currentSearchContent.trimEnd()}\n...does not match anything in the file.`,
+								)
+							}
+						}
+					}
+				}
+			}
+
+			// Check if this is an out-of-order replacement
+			if (searchMatchIndex < lastProcessedIndex) {
+				pendingOutOfOrderReplacement = true
+			}
+
+			// For in-order replacements, output everything up to the match location
+			if (!pendingOutOfOrderReplacement) {
+				result += originalContent.slice(lastProcessedIndex, searchMatchIndex)
+			}
+			continue
+		}
+
+		if (isReplaceBlockEnd(line)) {
+			// Finished one replace block
+
+			if (searchMatchIndex === -1) {
+				throw new Error(
+					`The SEARCH block:\n${currentSearchContent.trimEnd()}\n...is malformatted.`,
+				)
+			}
+
+			// Store this replacement
+			replacements.push({
+				start: searchMatchIndex,
+				end: searchEndIndex,
+				content: currentReplaceContent,
+				method: matchMethod,
+				similarity: similarityScore,
+				searchContent: currentSearchContent,
+				matchedText: originalContent.slice(searchMatchIndex, searchEndIndex),
+			})
+
+			// If this was an in-order replacement, advance lastProcessedIndex
+			if (!pendingOutOfOrderReplacement) {
+				lastProcessedIndex = searchEndIndex
+			}
+
+			// Reset for next block
+			inSearch = false
+			inReplace = false
+			currentSearchContent = ""
+			currentReplaceContent = ""
+			searchMatchIndex = -1
+			searchEndIndex = -1
+			similarityScore = -1.0
+			pendingOutOfOrderReplacement = false
+			continue
+		}
+
+		// Accumulate content for search or replace
+		// (currentReplaceContent is not being used for anything right now since we directly append to result.)
+		// (We artificially add a linebreak since we split on \n at the beginning. In order to not include a trailing linebreak in the final search/result blocks we need to remove it before using them. This allows for partial line matches to be correctly identified.)
+		// NOTE: search/replace blocks must be arranged in the order they appear in the file due to how we build the content using lastProcessedIndex. We also cannot strip the trailing newline since for non-partial lines it would remove the linebreak from the original content. (If we remove end linebreak from search, then we'd also have to remove it from replace but we can't know if it's a partial line or not since the model may be using the line break to indicate the end of the block rather than as part of the search content.) We require the model to output full lines in order for our fallbacks to work as well.
+		if (inSearch) {
+			currentSearchContent += line + "\n"
+		} else if (inReplace) {
+			currentReplaceContent += line + "\n"
+			// Only output replacement lines immediately for in-order replacements
+			if (searchMatchIndex !== -1 && !pendingOutOfOrderReplacement) {
+				result += line + "\n"
+			}
+		}
+	}
+
+	// If this is the final chunk, we need to apply all replacements and build the final result
+	if (isFinal) {
+		// Handle the case where we're still in replace mode when processing ends
+		// and this is the final chunk - treat it as if we encountered the REPLACE marker
+		if (inReplace && searchMatchIndex !== -1) {
+			// Store this replacement
+			replacements.push({
+				start: searchMatchIndex,
+				end: searchEndIndex,
+				content: currentReplaceContent,
+				method: matchMethod,
+				similarity: similarityScore,
+				searchContent: currentSearchContent,
+				matchedText: originalContent.slice(searchMatchIndex, searchEndIndex),
+			})
+
+			// If this was an in-order replacement, advance lastProcessedIndex
+			if (!pendingOutOfOrderReplacement) {
+				lastProcessedIndex = searchEndIndex
+			}
+
+			// Reset state
+			inSearch = false
+			inReplace = false
+			currentSearchContent = ""
+			currentReplaceContent = ""
+			searchMatchIndex = -1
+			searchEndIndex = -1
+			pendingOutOfOrderReplacement = false
+		}
+		// end of handling missing replace marker
+
+		// Sort replacements by start position
+		replacements.sort((a, b) => a.start - b.start)
+
+		// Rebuild the entire result by applying all replacements
+		result = ""
+		let currentPos = 0
+
+		for (const replacement of replacements) {
+			// Add original content up to this replacement
+			result += originalContent.slice(currentPos, replacement.start)
+			// Add the replacement content
+			result += replacement.content
+			// Move position to after the replaced section
+			currentPos = replacement.end
+		}
+
+		// Add any remaining original content
+		result += originalContent.slice(currentPos)
+	}
+
+	// For testing - return debug info
+	return {
+		content: result,
+		replacements: replacements
+	}
+}
+
+enum ProcessingState {
+	Idle = 0,
+	StateSearch = 1 << 0,
+	StateReplace = 1 << 1,
+}
+
+class NewFileContentConstructor {
+	private originalContent: string
+	private isFinal: boolean
+	private state: number
+	private pendingNonStandardLines: string[]
+	private result: string
+	private lastProcessedIndex: number
+	private currentSearchContent: string
+	private currentReplaceContent: string
+	private searchMatchIndex: number
+	private searchEndIndex: number
+
+	constructor(originalContent: string, isFinal: boolean) {
+		this.originalContent = originalContent
+		this.isFinal = isFinal
+		this.pendingNonStandardLines = []
+		this.result = ""
+		this.lastProcessedIndex = 0
+		this.state = ProcessingState.Idle
+		this.currentSearchContent = ""
+		this.currentReplaceContent = ""
+		this.searchMatchIndex = -1
+		this.searchEndIndex = -1
+	}
+
+	private resetForNextBlock() {
+		// Reset for next block
+		this.state = ProcessingState.Idle
+		this.currentSearchContent = ""
+		this.currentReplaceContent = ""
+		this.searchMatchIndex = -1
+		this.searchEndIndex = -1
+	}
+
+	private findLastMatchingLineIndex(regx: RegExp, lineLimit: number) {
+		for (let i = lineLimit; i > 0; ) {
+			i--
+			if (this.pendingNonStandardLines[i].match(regx)) {
+				return i
+			}
+		}
+		return -1
+	}
+
+	private updateProcessingState(newState: ProcessingState) {
+		const isValidTransition =
+			(this.state === ProcessingState.Idle && newState === ProcessingState.StateSearch) ||
+			(this.state === ProcessingState.StateSearch && newState === ProcessingState.StateReplace)
+
+		if (!isValidTransition) {
+			throw new Error(
+				`Invalid state transition.\n` +
+					"Valid transitions are:\n" +
+					"- Idle → StateSearch\n" +
+					"- StateSearch → StateReplace",
+			)
+		}
+
+		this.state |= newState
+	}
+
+	private isStateActive(state: ProcessingState): boolean {
+		return (this.state & state) === state
+	}
+
+	private activateReplaceState() {
+		this.updateProcessingState(ProcessingState.StateReplace)
+	}
+
+	private activateSearchState() {
+		this.updateProcessingState(ProcessingState.StateSearch)
+		this.currentSearchContent = ""
+		this.currentReplaceContent = ""
+	}
+
+	private isSearchingActive(): boolean {
+		return this.isStateActive(ProcessingState.StateSearch)
+	}
+
+	private isReplacingActive(): boolean {
+		return this.isStateActive(ProcessingState.StateReplace)
+	}
+
+	private hasPendingNonStandardLines(pendingNonStandardLineLimit: number): boolean {
+		return this.pendingNonStandardLines.length - pendingNonStandardLineLimit < this.pendingNonStandardLines.length
+	}
+
+	public processLine(line: string) {
+		this.internalProcessLine(line, true, this.pendingNonStandardLines.length)
+	}
+
+	public getResult() {
+		// If this is the final chunk, append any remaining original content
+		if (this.isFinal && this.lastProcessedIndex < this.originalContent.length) {
+			this.result += this.originalContent.slice(this.lastProcessedIndex)
+		}
+		if (this.isFinal && this.state !== ProcessingState.Idle) {
+			throw new Error("File processing incomplete - SEARCH/REPLACE operations still active during finalization")
+		}
+		return this.result
+	}
+
+	private internalProcessLine(
+		line: string,
+		canWritependingNonStandardLines: boolean,
+		pendingNonStandardLineLimit: number,
+	): number {
+		let removeLineCount = 0
+		if (isSearchBlockStart(line)) {
+			removeLineCount = this.trimPendingNonStandardTrailingEmptyLines(pendingNonStandardLineLimit)
+			if (removeLineCount > 0) {
+				pendingNonStandardLineLimit = pendingNonStandardLineLimit - removeLineCount
+			}
+			if (this.hasPendingNonStandardLines(pendingNonStandardLineLimit)) {
+				this.tryFixSearchReplaceBlock(pendingNonStandardLineLimit)
+				canWritependingNonStandardLines && (this.pendingNonStandardLines.length = 0)
+			}
+			this.activateSearchState()
+		} else if (isSearchBlockEnd(line)) {
+			// 校验非标内容
+			if (!this.isSearchingActive()) {
+				this.tryFixSearchBlock(pendingNonStandardLineLimit)
+				canWritependingNonStandardLines && (this.pendingNonStandardLines.length = 0)
+			}
+			this.activateReplaceState()
+			this.beforeReplace()
+		} else if (isReplaceBlockEnd(line)) {
+			if (!this.isReplacingActive()) {
+				this.tryFixReplaceBlock(pendingNonStandardLineLimit)
+				canWritependingNonStandardLines && (this.pendingNonStandardLines.length = 0)
+			}
+			this.lastProcessedIndex = this.searchEndIndex
+			this.resetForNextBlock()
+		} else {
+			// Accumulate content for search or replace
+			// (currentReplaceContent is not being used for anything right now since we directly append to result.)
+			// (We artificially add a linebreak since we split on \n at the beginning. In order to not include a trailing linebreak in the final search/result blocks we need to remove it before using them. This allows for partial line matches to be correctly identified.)
+			// NOTE: search/replace blocks must be arranged in the order they appear in the file due to how we build the content using lastProcessedIndex. We also cannot strip the trailing newline since for non-partial lines it would remove the linebreak from the original content. (If we remove end linebreak from search, then we'd also have to remove it from replace but we can't know if it's a partial line or not since the model may be using the line break to indicate the end of the block rather than as part of the search content.) We require the model to output full lines in order for our fallbacks to work as well.
+			if (this.isReplacingActive()) {
+				this.currentReplaceContent += line + "\n"
+				// Output replacement lines immediately if we know the insertion point
+				if (this.searchMatchIndex !== -1) {
+					this.result += line + "\n"
+				}
+			} else if (this.isSearchingActive()) {
+				this.currentSearchContent += line + "\n"
+			} else {
+				let appendToPendingNonStandardLines = canWritependingNonStandardLines
+				if (appendToPendingNonStandardLines) {
+					// 处理非标内容
+					this.pendingNonStandardLines.push(line)
+				}
+			}
+		}
+		return removeLineCount
+	}
+
+	private beforeReplace() {
+		// Remove trailing linebreak for adding the === marker
+		// if (currentSearchContent.endsWith("\r\n")) {
+		// 	currentSearchContent = currentSearchContent.slice(0, -2)
+		// } else if (currentSearchContent.endsWith("\n")) {
+		// 	currentSearchContent = currentSearchContent.slice(0, -1)
+		// }
+
+		if (!this.currentSearchContent) {
+			// Empty search block
+			if (this.originalContent.length === 0) {
+				// New file scenario: nothing to match, just start inserting
+				this.searchMatchIndex = 0
+				this.searchEndIndex = 0
+			} else {
+				// Complete file replacement scenario: treat the entire file as matched
+				this.searchMatchIndex = 0
+				this.searchEndIndex = this.originalContent.length
+			}
+		} else {
+			// Add check for inefficient full-file search
+			// if (currentSearchContent.trim() === originalContent.trim()) {
+			// 	throw new Error(
+			// 		"The SEARCH block contains the entire file content. Please either:\n" +
+			// 			"1. Use an empty SEARCH block to replace the entire file, or\n" +
+			// 			"2. Make focused changes to specific parts of the file that need modification.",
+			// 	)
+			// }
+			// Exact search match scenario
+			const exactIndex = this.originalContent.indexOf(this.currentSearchContent, this.lastProcessedIndex)
+			if (exactIndex !== -1) {
+				this.searchMatchIndex = exactIndex
+				this.searchEndIndex = exactIndex + this.currentSearchContent.length
+			} else {
+				// Attempt fallback line-trimmed matching
+				const lineMatch = lineTrimmedFallbackMatch(
+					this.originalContent,
+					this.currentSearchContent,
+					this.lastProcessedIndex,
+				)
+				if (lineMatch) {
+					;[this.searchMatchIndex, this.searchEndIndex] = lineMatch
+				} else {
+					// Try block anchor fallback for larger blocks
+					const blockMatch = blockAnchorFallbackMatch(
+						this.originalContent,
+						this.currentSearchContent,
+						this.lastProcessedIndex,
+					)
+					if (blockMatch) {
+						;[this.searchMatchIndex, this.searchEndIndex, /* ignore similarity */] = blockMatch
+					} else {
+						throw new Error(
+							`The SEARCH block:\n${this.currentSearchContent.trimEnd()}\n...does not match anything in the file.`,
+						)
+					}
+				}
+			}
+		}
+		if (this.searchMatchIndex < this.lastProcessedIndex) {
+			throw new Error(
+				`The SEARCH block:\n${this.currentSearchContent.trimEnd()}\n...matched an incorrect content in the file.`,
+			)
+		}
+		// Output everything up to the match location
+		this.result += this.originalContent.slice(this.lastProcessedIndex, this.searchMatchIndex)
+	}
+
+	private tryFixSearchBlock(lineLimit: number): number {
+		let removeLineCount = 0
+		if (lineLimit < 0) {
+			lineLimit = this.pendingNonStandardLines.length
+		}
+		if (!lineLimit) {
+			throw new Error("Invalid SEARCH/REPLACE block structure - no lines available to process")
+		}
+		let searchTagRegexp = /^([-]{3,}|[<]{3,}) SEARCH$/
+		const searchTagIndex = this.findLastMatchingLineIndex(searchTagRegexp, lineLimit)
+		if (searchTagIndex !== -1) {
+			let fixLines = this.pendingNonStandardLines.slice(searchTagIndex, lineLimit)
+			fixLines[0] = SEARCH_BLOCK_START
+			for (const line of fixLines) {
+				removeLineCount += this.internalProcessLine(line, false, searchTagIndex)
+			}
+		} else {
+			throw new Error(
+				`Invalid REPLACE marker detected - could not find matching SEARCH block starting from line ${searchTagIndex + 1}`,
+			)
+		}
+		return removeLineCount
+	}
+
+	private tryFixReplaceBlock(lineLimit: number): number {
+		let removeLineCount = 0
+		if (lineLimit < 0) {
+			lineLimit = this.pendingNonStandardLines.length
+		}
+		if (!lineLimit) {
+			throw new Error()
+		}
+		let replaceBeginTagRegexp = /^[=]{3,}$/
+		const replaceBeginTagIndex = this.findLastMatchingLineIndex(replaceBeginTagRegexp, lineLimit)
+		if (replaceBeginTagIndex !== -1) {
+			// // 校验非标内容
+			// if (!this.isSearchingActive()) {
+			// 	removeLineCount += this.tryFixSearchBlock(replaceBeginTagIndex)
+			// }
+			let fixLines = this.pendingNonStandardLines.slice(replaceBeginTagIndex - removeLineCount, lineLimit - removeLineCount)
+			fixLines[0] = SEARCH_BLOCK_END
+			for (const line of fixLines) {
+				removeLineCount += this.internalProcessLine(line, false, replaceBeginTagIndex - removeLineCount)
+			}
+		} else {
+			throw new Error(`Malformed REPLACE block - missing valid separator after line ${replaceBeginTagIndex + 1}`)
+		}
+		return removeLineCount
+	}
+
+	private tryFixSearchReplaceBlock(lineLimit: number): number {
+		let removeLineCount = 0
+		if (lineLimit < 0) {
+			lineLimit = this.pendingNonStandardLines.length
+		}
+		if (!lineLimit) {
+			throw new Error()
+		}
+
+		let replaceEndTagRegexp = /^([+]{3,}|[>]{3,}) REPLACE$/
+		const replaceEndTagIndex = this.findLastMatchingLineIndex(replaceEndTagRegexp, lineLimit)
+		const likeReplaceEndTag = replaceEndTagIndex === lineLimit - 1
+		if (likeReplaceEndTag) {
+			// // 校验非标内容
+			// if (!this.isReplacingActive()) {
+			// 	removeLineCount += this.tryFixReplaceBlock(replaceEndTagIndex)
+			// }
+			let fixLines = this.pendingNonStandardLines.slice(replaceEndTagIndex - removeLineCount, lineLimit - removeLineCount)
+			fixLines[fixLines.length - 1] = REPLACE_BLOCK_END
+			for (const line of fixLines) {
+				removeLineCount += this.internalProcessLine(line, false, replaceEndTagIndex - removeLineCount)
+			}
+		} else {
+			throw new Error("Malformed SEARCH/REPLACE block structure: Missing valid closing REPLACE marker")
+		}
+		return removeLineCount
+	}
+
+	/**
+	 * Removes trailing empty lines from the pendingNonStandardLines array
+	 * @param lineLimit - The index to start checking from (exclusive).
+	 *                    Removes empty lines from lineLimit-1 backwards.
+	 * @returns The number of empty lines removed
+	 */
+	private trimPendingNonStandardTrailingEmptyLines(lineLimit: number): number {
+		let removedCount = 0
+		let i = Math.min(lineLimit, this.pendingNonStandardLines.length) - 1
+
+		while (i >= 0 && this.pendingNonStandardLines[i].trim() === "") {
+			this.pendingNonStandardLines.pop()
+			removedCount++
+			i--
+		}
+
+		return removedCount
+	}
+}
+
+export async function constructNewFileContentV2(diffContent: string, originalContent: string, isFinal: boolean): Promise<string> {
+	let newFileContentConstructor = new NewFileContentConstructor(originalContent, isFinal)
+
+	let lines = diffContent.split("\n")
+
+	// If the last line looks like a partial marker but isn't recognized,
+	// remove it because it might be incomplete.
+	const lastLine = lines[lines.length - 1]
+	if (
+		lines.length > 0 &&
+		(lastLine.startsWith(SEARCH_BLOCK_CHAR) ||
+			lastLine.startsWith(LEGACY_SEARCH_BLOCK_CHAR) ||
+			lastLine.startsWith("=") ||
+			lastLine.startsWith(REPLACE_BLOCK_CHAR) ||
+			lastLine.startsWith(LEGACY_REPLACE_BLOCK_CHAR)) &&
+		lastLine !== SEARCH_BLOCK_START &&
+		lastLine !== SEARCH_BLOCK_END &&
+		lastLine !== REPLACE_BLOCK_END
+	) {
+		lines.pop()
+	}
+
+	for (const line of lines) {
+		newFileContentConstructor.processLine(line)
+	}
+
+	let result = newFileContentConstructor.getResult()
+	return result
+}

evals/diff-edits/helpers.ts

@@ -23,3 +23,9 @@ export const formatResponse = {
 		return formatImagesIntoBlocks(images)
 	},
 }
+
+export function log(isVerbose: boolean, message: string) {
+	if (isVerbose) {
+		console.log(message)
+	}
+}

evals/diff-edits/types.ts

@@ -29,6 +29,7 @@ export interface TestConfig {
 	model_id: string
 	system_prompt_name: string
 	number_of_runs: number
+	max_attempts_per_case: number
 	parsing_function: string
 	diff_edit_function: string
 	thinking_tokens_budget: number
@@ -81,6 +82,7 @@ export interface TestResult {
 	diffEdit?: string
 	toolCalls?: ExtractedToolCall[]
 	diffEditSuccess?: boolean
+	replacementData?: any
 	error?: string
 	errorString?: string
 }
@@ -102,4 +104,5 @@ export interface TestInput {
 	thinkingBudgetTokens: number
 	originalDiffEditToolCallMessage?: string
 	diffApplyFile?: string
+	isVerbose: boolean
 }

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "claude-dev",
-	"version": "3.18.1",
+	"version": "3.18.11",
 	"lockfileVersion": 2,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "claude-dev",
-			"version": "3.18.1",
+			"version": "3.18.11",
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@anthropic-ai/sdk": "^0.37.0",

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": "3.18.1",
+	"version": "3.18.11",
 	"icon": "assets/icons/icon.png",
 	"engines": {
 		"vscode": "^1.84.0"

proto/account.proto

@@ -1,76 +1,129 @@
 syntax = "proto3";
 
 package cline;
+import "common.proto";
 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);
+  // 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);
     
-    // Handles the user clicking the logout button in the UI.
-    // Clears API keys and user state.
-    rpc accountLogoutClicked(EmptyRequest) returns (Empty);
+  // Handles the user clicking the logout button in the UI.
+  // Clears API keys and user state.
+  rpc accountLogoutClicked(EmptyRequest) returns (Empty);
 
-    // Subscribe to auth callback events (when authentication tokens are received)
-    rpc subscribeToAuthCallback(EmptyRequest) returns (stream String);
+  // Subscribe to auth status update events (when authentication state changes)
+  rpc subscribeToAuthStatusUpdate(EmptyRequest) 
+      returns (stream AuthState);
     
-    // Handles authentication state changes from the Firebase context.
-    // Updates the user info in global state and returns the updated value.
-    rpc authStateChanged(AuthStateChangedRequest) returns (AuthStateChanged);
+  // Handles authentication state changes from the Firebase context.
+  // Updates the user info in global state and returns the updated value.
+  rpc authStateChanged(AuthStateChangedRequest) 
+      returns (AuthState);
     
-    // Fetches all user credits data (balance, usage transactions, payment transactions)
-    rpc fetchUserCreditsData(EmptyRequest) returns (UserCreditsData);
+  // Fetches all user credits data
+  // (balance, usage transactions, payment transactions)
+  rpc getUserCredits(EmptyRequest) returns (UserCreditsData);
+
+  rpc getOrganizationCredits(GetOrganizationCreditsRequest) returns (OrganizationCreditsData);
+
+  // Fetches all user organizations data
+  // Returns a list of UserOrganization objects
+  rpc getUserOrganizations(EmptyRequest) returns (UserOrganizationsResponse);
+
+  rpc setUserOrganization(UserOrganizationUpdateRequest) returns (Empty);
 }
 
 message AuthStateChangedRequest {
-    Metadata metadata = 1;
-    UserInfo user = 2;
+  Metadata metadata = 1;
+  UserInfo user = 2;
 }
 
-message AuthStateChanged {
-    optional UserInfo user = 1;
+message AuthState {
+  optional UserInfo user = 1;
 }
 
+// User's information
 message UserInfo {
-    optional string display_name = 1;
-    optional string email = 2;
-    optional string photo_url = 3;
+  string uid = 1;
+  optional string display_name = 2;
+  optional string email = 3;
+  optional string photo_url = 4;
+}
+
+message UserOrganization {
+  bool active = 1;
+  string member_id = 2;
+  string name = 3;
+  string organization_id = 4;
+  repeated string roles = 5; // ["admin", "member", "owner"]
+}
+
+message UserOrganizationsResponse {
+  repeated UserOrganization organizations = 1;
+}
+
+message UserOrganizationUpdateRequest {
+  optional string organization_id = 1;
 }
 
-// Response containing all user credits data
 message UserCreditsData {
-    UserCreditsBalance balance = 1;
-    repeated UsageTransaction usage_transactions = 2;
-    repeated PaymentTransaction payment_transactions = 3;
+  UserCreditsBalance balance = 1;
+  repeated UsageTransaction usage_transactions = 2;
+  repeated PaymentTransaction payment_transactions = 3;
+}
+
+message GetOrganizationCreditsRequest {
+  string organization_id = 1;
+}
+
+message OrganizationCreditsData {
+  UserCreditsBalance balance = 1;
+  string organization_id = 2;
+  repeated OrganizationUsageTransaction usage_transactions = 3;
 }
 
-// User's current credit balance
 message UserCreditsBalance {
-    double current_balance = 1;
+  double current_balance = 1;
 }
 
-// Usage transaction record
 message UsageTransaction {
-    string spent_at = 1;
-    string creator_id = 2;
-    double credits = 3;
-    string model_provider = 4;
-    string model = 5;
-    int32 prompt_tokens = 6;
-    int32 completion_tokens = 7;
-    int32 total_tokens = 8;
+  string ai_inference_provider_name = 1;
+  string ai_model_name = 2;
+  string ai_model_type_name = 3;
+  int32 completion_tokens = 4;
+  double cost_usd = 5;
+  string created_at = 6;
+  double credits_used = 7;
+  string generation_id = 8;
+  string organization_id = 9;
+  int32 prompt_tokens = 10;
+  int32 total_tokens = 11;
+  string user_id = 12;
 }
 
-// Payment transaction record
 message PaymentTransaction {
-    string paid_at = 1;
-    string creator_id = 2;
-    int32 amount_cents = 3;
-    double credits = 4;
+  string paid_at = 1;
+  string creator_id = 2;
+  int32 amount_cents = 3;
+  double credits = 4;
 }
+
+message OrganizationUsageTransaction {
+  string ai_inference_provider_name = 1;
+  string ai_model_name = 2;
+  string ai_model_type_name = 3;
+  int32 completion_tokens = 4;
+  double cost_usd = 5;
+  string created_at = 6;
+  double credits_used = 7;
+  string generation_id = 8;
+  string organization_id = 9;
+  int32 prompt_tokens = 10;
+  int32 total_tokens = 11;
+  string user_id = 12;
+}

proto/browser.proto

@@ -1,11 +1,10 @@
 syntax = "proto3";
 
 package cline;
+import "common.proto";
 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);

proto/build-proto-config.js

@@ -26,5 +26,6 @@ export const hostServiceNameMap = {
 	watch: "host.WatchService",
 	workspace: "host.WorkspaceService",
 	env: "host.EnvService",
+	window: "host.WindowService",
 	// Add new host services here
 }

proto/checkpoints.proto

@@ -1,11 +1,10 @@
 syntax = "proto3";
 
 package cline;
+import "common.proto";
 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);

proto/file.proto

@@ -1,11 +1,10 @@
 syntax = "proto3";
 
 package cline;
+import "common.proto";
 option java_package = "bot.cline.proto";
 option java_multiple_files = true;
 
-import "common.proto";
-
 // Service for file-related operations
 service FileService {
   // Copies text to clipboard

proto/host/env.proto

@@ -13,4 +13,7 @@ service EnvService {
 
   // Reads text from the system clipboard.
   rpc clipboardReadText(cline.EmptyRequest) returns (cline.String);
+
+  // Opens a URL in the user's default browser or application.
+  rpc openExternal(cline.StringRequest) returns (cline.Empty);
 }

proto/host/uri.proto

@@ -1,36 +0,0 @@
-syntax = "proto3";
-
-package host;
-option java_package = "bot.cline.host.proto";
-option java_multiple_files = true;
-
-import "common.proto";
-
-// UriService provides methods for working with URIs in the IDE
-service UriService {
-  // Create a new file URI from a file path
-  rpc file(cline.StringRequest) returns (Uri);
-  
-  // Join a URI with additional path segments
-  rpc joinPath(JoinPathRequest) returns (Uri);
-  
-  // Parse a string URI into a Uri object
-  rpc parse(cline.StringRequest) returns (Uri);
-}
-
-// Uri represents a URI in the IDE
-message Uri {
-  string scheme = 1;
-  string authority = 2;
-  string path = 3;
-  string query = 4;
-  string fragment = 5;
-  string fs_path = 6;
-}
-
-// Request for joining path segments to a URI
-message JoinPathRequest {
-  cline.Metadata metadata = 1;
-  Uri base = 2;
-  repeated string path_segments = 3;
-}

proto/host/window.proto

@@ -0,0 +1,48 @@
+syntax = "proto3";
+
+package host;
+option java_package = "bot.cline.host.proto";
+option java_multiple_files = true;
+
+import "common.proto";
+
+// Provides methods for working with IDE windows and editors.
+service WindowService {
+  // Opens a text document in the editor and returns editor information.
+  rpc showTextDocument(ShowTextDocumentRequest) returns (TextEditorInfo);
+  rpc showOpenDialogue(ShowOpenDialogueRequest) returns (SelectedResources);
+}
+
+message ShowTextDocumentRequest {
+  cline.Metadata metadata = 1;
+  string path = 2;
+  optional ShowTextDocumentOptions options = 3;
+}
+
+// See https://code.visualstudio.com/api/references/vscode-api#TextDocumentShowOptions
+message ShowTextDocumentOptions {
+  optional bool preview = 1;
+  optional bool preserve_focus = 2;
+  optional int32 view_column = 3;
+}
+
+message TextEditorInfo {
+  string document_path = 1;
+  optional int32 view_column = 2;
+  bool is_active = 3;
+}
+
+message ShowOpenDialogueRequest {
+  cline.Metadata metadata = 1;
+  optional bool can_select_many = 2;
+  optional string open_label = 3;
+  optional ShowOpenDialogueFilterOption filters = 4;
+}
+
+message ShowOpenDialogueFilterOption {
+  repeated string files = 1;
+}
+
+message SelectedResources {
+  repeated string paths = 1;
+}

proto/mcp.proto

@@ -1,16 +1,15 @@
 syntax = "proto3";
 
 package cline;
+import "common.proto";
 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);
-  rpc downloadMcp(StringRequest) returns (Empty);
+  rpc downloadMcp(StringRequest) returns (McpDownloadResponse);
   rpc restartMcpServer(StringRequest) returns (McpServers);
   rpc deleteMcpServer(StringRequest) returns (McpServers);
   rpc toggleToolAutoApprove(ToggleToolAutoApproveRequest) returns (McpServers);
@@ -119,3 +118,15 @@ message McpMarketplaceItem {
 message McpMarketplaceCatalog {
   repeated McpMarketplaceItem items = 1;
 }
+
+message McpDownloadResponse {
+  string mcp_id = 1;
+  string github_url = 2;
+  string name = 3;
+  string author = 4;
+  string description = 5;
+  string readme_content = 6;
+  string llms_installation_content = 7;
+  bool requires_api_key = 8;
+  optional string error = 9;
+}

proto/models.proto

@@ -1,11 +1,10 @@
 syntax = "proto3";
 
 package cline;
+import "common.proto";
 option java_package = "bot.cline.proto";
 option java_multiple_files = true;
 
-import "common.proto";
-
 // Service for model-related operations
 service ModelsService {
   // Fetches available models from Ollama
@@ -165,7 +164,7 @@ message ModelsApiConfiguration {
   // From ApiHandlerOptions (excluding onRetryAttempt function)
   optional string api_model_id = 1;
   optional string api_key = 2;
-  optional string cline_api_key = 3;
+  optional string cline_account_id = 3;
   optional string task_id = 4;
   optional string lite_llm_base_url = 5;
   optional string lite_llm_model_id = 6;

proto/slash.proto

@@ -1,11 +1,10 @@
 syntax = "proto3";
 
 package cline;
+import "common.proto";
 option java_package = "bot.cline.proto";
 option java_multiple_files = true;
 
-import "common.proto";
-
 // SlashService provides methods for managing slash
 service SlashService {
   // Sends button click message

proto/state.proto

@@ -1,10 +1,9 @@
 syntax = "proto3";
 package cline;
+import "common.proto";
 option java_package = "bot.cline.proto";
 option java_multiple_files = true;
 
-import "common.proto";
-
 service StateService {
   rpc getLatestState(EmptyRequest) returns (State);
   rpc updateTerminalConnectionTimeout(Int64Request) returns (Int64);
@@ -18,6 +17,7 @@ service StateService {
   rpc updateAutoApprovalSettings(AutoApprovalSettingsRequest) returns (Empty);
   rpc updateSettings(UpdateSettingsRequest) returns (Empty);
   rpc updateTelemetrySetting(TelemetrySettingRequest) returns (Empty);
+  rpc setWelcomeViewCompleted(BooleanRequest) returns (Empty);
 }
 
 message State {
@@ -125,7 +125,7 @@ message ApiConfiguration {
   optional string api_base_url = 4;
   
   // Provider-specific API keys
-  optional string cline_api_key = 5;
+  optional string cline_account_id = 5;
   optional string openrouter_api_key = 6;
   optional string anthropic_base_url = 7;
   optional string openai_api_key = 8;

proto/task.proto

@@ -1,11 +1,10 @@
 syntax = "proto3";
 
 package cline;
+import "common.proto";
 option java_package = "bot.cline.proto";
 option java_multiple_files = true;
 
-import "common.proto";
-
 service TaskService {
   // Cancels the currently running task
   rpc cancelTask(EmptyRequest) returns (Empty);

proto/ui.proto

@@ -1,11 +1,10 @@
 syntax = "proto3";
 
 package cline;
+import "common.proto";
 option java_package = "bot.cline.proto";
 option java_multiple_files = true;
 
-import "common.proto";
-
 // Enum for webview provider types
 enum WebviewProviderType {
   SIDEBAR = 0;

proto/web.proto

@@ -1,11 +1,10 @@
 syntax = "proto3";
 
 package cline;
+import "common.proto";
 option java_package = "bot.cline.proto";
 option java_multiple_files = true;
 
-import "common.proto";
-
 service WebService {
   rpc checkIsImageUrl(StringRequest) returns (IsImageUrl);
   rpc fetchOpenGraphData(StringRequest) returns (OpenGraphData);

scripts/package-standalone.mjs

@@ -1,83 +1,100 @@
-import fs from "fs"
-import path from "path"
-import { glob } from "glob"
 import archiver from "archiver"
-import { cp } from "fs/promises"
 import { execSync } from "child_process"
-
+import fs from "fs"
+import { cp } from "fs/promises"
+import { glob } from "glob"
+import ignore from "ignore"
+import path from "path"
 const BUILD_DIR = "dist-standalone"
-const SOURCE_DIR = "standalone/runtime-files"
+const RUNTIME_DEPS_DIR = "standalone/runtime-files"
 
-await cp(SOURCE_DIR, BUILD_DIR, { recursive: true })
-
-// Run npm install in the distribution directory
-console.log("Running npm install in distribution directory...")
-const cwd = process.cwd()
-process.chdir(BUILD_DIR)
-try {
-	execSync("npm install", { stdio: "inherit" })
-	// Move the vscode directory into node_modules.
-	// It can't be installed using npm because it will create a symlink which is not portable.
-	fs.renameSync("vscode", path.join("node_modules", "vscode"))
-} catch (error) {
-	console.error("Error during setup:", error)
-	process.exit(1)
-} finally {
-	process.chdir(cwd)
+async function main() {
+	await installNodeDependencies()
+	await zipDistribution()
 }
 
-// Check for native .node modules.
-const nativeModules = await glob("**/*.node", { cwd: BUILD_DIR, nodir: true })
-if (nativeModules.length > 0) {
-	console.error("Native node modules cannot be included in the standalone distribution:\n", nativeModules.join("\n"))
-	process.exit(1)
+async function installNodeDependencies() {
+	await cpr(RUNTIME_DEPS_DIR, BUILD_DIR)
+
+	console.log("Running npm install in distribution directory...")
+	const cwd = process.cwd()
+	process.chdir(BUILD_DIR)
+
+	try {
+		execSync("npm install", { stdio: "inherit" })
+		// Move the vscode directory into node_modules.
+		// It can't be installed using npm because it will create a symlink which cannot be unzipped correctly on windows.
+		fs.renameSync("vscode", path.join("node_modules", "vscode"))
+	} catch (error) {
+		console.error("Error during setup:", error)
+		process.exit(1)
+	} finally {
+		process.chdir(cwd)
+	}
+
+	// Check for native .node modules.
+	const nativeModules = await glob("**/*.node", { cwd: BUILD_DIR, nodir: true })
+	if (nativeModules.length > 0) {
+		console.error("Native node modules cannot be included in the standalone distribution:\n", nativeModules.join("\n"))
+		process.exit(1)
+	}
 }
 
-// Zip the build directory (excluding any pre-existing output zip).
-const zipPath = path.join(BUILD_DIR, "standalone.zip")
-const output = fs.createWriteStream(zipPath)
-const archive = archiver("zip", { zlib: { level: 3 } })
+async function zipDistribution() {
+	// Zip the build directory (excluding any pre-existing output zip).
+	const zipPath = path.join(BUILD_DIR, "standalone.zip")
+	const output = fs.createWriteStream(zipPath)
+	const archive = archiver("zip", { zlib: { level: 3 } })
+	// Use the same ignore file that vscode uses when packaging the extension.
+	const vscodeignore = ignore().add(fs.readFileSync(".vscodeignore", "utf8"))
 
-output.on("close", () => {
-	console.log(`Created ${zipPath} (${(archive.pointer() / 1024 / 1024).toFixed(1)} MB)`)
-})
-archive.on("warning", (err) => {
-	console.warn(`Warning: ${err}`)
-})
-archive.on("error", (err) => {
-	throw err
-})
+	output.on("close", () => {
+		console.log(`Created ${zipPath} (${(archive.pointer() / 1024 / 1024).toFixed(1)} MB)`)
+	})
+	archive.on("warning", (err) => {
+		console.warn(`Warning: ${err}`)
+	})
+	archive.on("error", (err) => {
+		throw err
+	})
 
-archive.pipe(output)
-archive.glob("**/*", {
-	cwd: BUILD_DIR,
-	ignore: ["standalone.zip"],
-})
+	archive.pipe(output)
+	// Add all the files from the standalone build dir.
+	archive.glob("**/*", {
+		cwd: BUILD_DIR,
+		ignore: ["standalone.zip"],
+	})
 
-// Add the whole cline directory under "extension"
-archive.directory(process.cwd(), "extension", (entry) => {
-	// Skip certain directories.
-	const exclude = [
-		BUILD_DIR + "/",
-		"node_modules/", // node_modules nearly 1GB.
-		"webview-ui/node_modules/", // node_modules nearly 1GB.
-	]
-	// These node modules are used at runtime as assets, they need to be included.
-	const include = ["node_modules/@vscode/", "webview-ui/node_modules/katex"]
-	const name = entry.name
-
-	if (include.some((prefix) => name.startsWith(prefix))) {
+	// Add the whole cline directory under "extension"
+	archive.directory(process.cwd(), "extension", (entry) => {
+		if (entry.name.startsWith(".git")) {
+			return false
+		}
+		if (entry.name.endsWith(".DS_Store")) {
+			return false
+		}
+		if (entry.name === "dist" || entry.name.startsWith("dist" + path.sep)) {
+			// Don't include the vscode extension build dir.
+			return false
+		}
+		if (vscodeignore.ignores(entry.name)) {
+			// Exclude entries also ignored by the vscode packager.
+			return false
+		}
 		return entry
-	}
-	if (exclude.some((prefix) => name.startsWith(prefix))) {
-		return false
-	}
-	if (name.match(/(^|\/)\./)) {
-		// exclude dot directories
-		return false
-	}
-	return entry
-})
+	})
 
-console.log("Zipping package...")
-await archive.finalize()
+	console.log("Zipping package...")
+	await archive.finalize()
+}
+
+/* cp -r */
+async function cpr(source, dest) {
+	await cp(source, dest, {
+		recursive: true,
+		preserveTimestamps: true,
+		dereference: false, // preserve symlinks instead of following them
+	})
+}
+
+await main()

src/api/index.ts

@@ -38,62 +38,202 @@ export interface SingleCompletionHandler {
 	completePrompt(prompt: string): Promise<string>
 }
 
-function createHandlerForProvider(apiProvider: string | undefined, options: any): ApiHandler {
+function createHandlerForProvider(apiProvider: string | undefined, options: Omit<ApiConfiguration, "apiProvider">): ApiHandler {
 	switch (apiProvider) {
 		case "anthropic":
-			return new AnthropicHandler(options)
+			return new AnthropicHandler({
+				apiKey: options.apiKey,
+				anthropicBaseUrl: options.anthropicBaseUrl,
+				apiModelId: options.apiModelId,
+				thinkingBudgetTokens: options.thinkingBudgetTokens,
+			})
 		case "openrouter":
-			return new OpenRouterHandler(options)
+			return new OpenRouterHandler({
+				openRouterApiKey: options.openRouterApiKey,
+				openRouterModelId: options.openRouterModelId,
+				openRouterModelInfo: options.openRouterModelInfo,
+				openRouterProviderSorting: options.openRouterProviderSorting,
+				reasoningEffort: options.reasoningEffort,
+				thinkingBudgetTokens: options.thinkingBudgetTokens,
+			})
 		case "bedrock":
-			return new AwsBedrockHandler(options)
+			return new AwsBedrockHandler({
+				apiModelId: options.apiModelId,
+				awsAccessKey: options.awsAccessKey,
+				awsSecretKey: options.awsSecretKey,
+				awsSessionToken: options.awsSessionToken,
+				awsRegion: options.awsRegion,
+				awsUseCrossRegionInference: options.awsUseCrossRegionInference,
+				awsBedrockUsePromptCache: options.awsBedrockUsePromptCache,
+				awsUseProfile: options.awsUseProfile,
+				awsProfile: options.awsProfile,
+				awsBedrockEndpoint: options.awsBedrockEndpoint,
+				awsBedrockCustomSelected: options.awsBedrockCustomSelected,
+				awsBedrockCustomModelBaseId: options.awsBedrockCustomModelBaseId,
+				thinkingBudgetTokens: options.thinkingBudgetTokens,
+			})
 		case "vertex":
-			return new VertexHandler(options)
+			return new VertexHandler({
+				vertexProjectId: options.vertexProjectId,
+				vertexRegion: options.vertexRegion,
+				apiModelId: options.apiModelId,
+				thinkingBudgetTokens: options.thinkingBudgetTokens,
+				geminiApiKey: options.geminiApiKey,
+				geminiBaseUrl: options.geminiBaseUrl,
+				taskId: options.taskId,
+			})
 		case "openai":
-			return new OpenAiHandler(options)
+			return new OpenAiHandler({
+				openAiApiKey: options.openAiApiKey,
+				openAiBaseUrl: options.openAiBaseUrl,
+				azureApiVersion: options.azureApiVersion,
+				openAiHeaders: options.openAiHeaders,
+				openAiModelId: options.openAiModelId,
+				openAiModelInfo: options.openAiModelInfo,
+				reasoningEffort: options.reasoningEffort,
+			})
 		case "ollama":
-			return new OllamaHandler(options)
+			return new OllamaHandler({
+				ollamaBaseUrl: options.ollamaBaseUrl,
+				ollamaModelId: options.ollamaModelId,
+				ollamaApiOptionsCtxNum: options.ollamaApiOptionsCtxNum,
+				requestTimeoutMs: options.requestTimeoutMs,
+			})
 		case "lmstudio":
-			return new LmStudioHandler(options)
+			return new LmStudioHandler({
+				lmStudioBaseUrl: options.lmStudioBaseUrl,
+				lmStudioModelId: options.lmStudioModelId,
+			})
 		case "gemini":
-			return new GeminiHandler(options)
+			return new GeminiHandler({
+				vertexProjectId: options.vertexProjectId,
+				vertexRegion: options.vertexRegion,
+				geminiApiKey: options.geminiApiKey,
+				geminiBaseUrl: options.geminiBaseUrl,
+				thinkingBudgetTokens: options.thinkingBudgetTokens,
+				apiModelId: options.apiModelId,
+				taskId: options.taskId,
+			})
 		case "openai-native":
-			return new OpenAiNativeHandler(options)
+			return new OpenAiNativeHandler({
+				openAiNativeApiKey: options.openAiNativeApiKey,
+				reasoningEffort: options.reasoningEffort,
+				apiModelId: options.apiModelId,
+			})
 		case "deepseek":
-			return new DeepSeekHandler(options)
+			return new DeepSeekHandler({
+				deepSeekApiKey: options.deepSeekApiKey,
+				apiModelId: options.apiModelId,
+			})
 		case "requesty":
-			return new RequestyHandler(options)
+			return new RequestyHandler({
+				requestyApiKey: options.requestyApiKey,
+				reasoningEffort: options.reasoningEffort,
+				thinkingBudgetTokens: options.thinkingBudgetTokens,
+				requestyModelId: options.requestyModelId,
+				requestyModelInfo: options.requestyModelInfo,
+			})
 		case "fireworks":
-			return new FireworksHandler(options)
+			return new FireworksHandler({
+				fireworksApiKey: options.fireworksApiKey,
+				fireworksModelId: options.fireworksModelId,
+				fireworksModelMaxCompletionTokens: options.fireworksModelMaxCompletionTokens,
+				fireworksModelMaxTokens: options.fireworksModelMaxTokens,
+			})
 		case "together":
-			return new TogetherHandler(options)
+			return new TogetherHandler({
+				togetherApiKey: options.togetherApiKey,
+				togetherModelId: options.togetherModelId,
+			})
 		case "qwen":
-			return new QwenHandler(options)
+			return new QwenHandler({
+				qwenApiKey: options.qwenApiKey,
+				qwenApiLine: options.qwenApiLine,
+				apiModelId: options.apiModelId,
+				thinkingBudgetTokens: options.thinkingBudgetTokens,
+			})
 		case "doubao":
-			return new DoubaoHandler(options)
+			return new DoubaoHandler({
+				doubaoApiKey: options.doubaoApiKey,
+				apiModelId: options.apiModelId,
+			})
 		case "mistral":
-			return new MistralHandler(options)
+			return new MistralHandler({
+				mistralApiKey: options.mistralApiKey,
+				apiModelId: options.apiModelId,
+			})
 		case "vscode-lm":
-			return new VsCodeLmHandler(options)
+			return new VsCodeLmHandler({
+				vsCodeLmModelSelector: options.vsCodeLmModelSelector,
+			})
 		case "cline":
-			return new ClineHandler(options)
+			return new ClineHandler({
+				taskId: options.taskId,
+				reasoningEffort: options.reasoningEffort,
+				thinkingBudgetTokens: options.thinkingBudgetTokens,
+				openRouterProviderSorting: options.openRouterProviderSorting,
+				openRouterModelId: options.openRouterModelId,
+				openRouterModelInfo: options.openRouterModelInfo,
+			})
 		case "litellm":
-			return new LiteLlmHandler(options)
+			return new LiteLlmHandler({
+				liteLlmApiKey: options.liteLlmApiKey,
+				liteLlmBaseUrl: options.liteLlmBaseUrl,
+				liteLlmModelId: options.liteLlmModelId,
+				liteLlmModelInfo: options.liteLlmModelInfo,
+				thinkingBudgetTokens: options.thinkingBudgetTokens,
+				liteLlmUsePromptCache: options.liteLlmUsePromptCache,
+				taskId: options.taskId,
+			})
 		case "nebius":
-			return new NebiusHandler(options)
+			return new NebiusHandler({
+				nebiusApiKey: options.nebiusApiKey,
+				apiModelId: options.apiModelId,
+			})
 		case "asksage":
-			return new AskSageHandler(options)
+			return new AskSageHandler({
+				asksageApiKey: options.asksageApiKey,
+				asksageApiUrl: options.asksageApiUrl,
+				apiModelId: options.apiModelId,
+			})
 		case "xai":
-			return new XAIHandler(options)
+			return new XAIHandler({
+				xaiApiKey: options.xaiApiKey,
+				reasoningEffort: options.reasoningEffort,
+				apiModelId: options.apiModelId,
+			})
 		case "sambanova":
-			return new SambanovaHandler(options)
+			return new SambanovaHandler({
+				sambanovaApiKey: options.sambanovaApiKey,
+				apiModelId: options.apiModelId,
+			})
 		case "cerebras":
-			return new CerebrasHandler(options)
+			return new CerebrasHandler({
+				cerebrasApiKey: options.cerebrasApiKey,
+				apiModelId: options.apiModelId,
+			})
 		case "sapaicore":
-			return new SapAiCoreHandler(options)
+			return new SapAiCoreHandler({
+				sapAiCoreClientId: options.sapAiCoreClientId,
+				sapAiCoreClientSecret: options.sapAiCoreClientSecret,
+				sapAiCoreTokenUrl: options.sapAiCoreTokenUrl,
+				sapAiResourceGroup: options.sapAiResourceGroup,
+				sapAiCoreBaseUrl: options.sapAiCoreBaseUrl,
+				apiModelId: options.apiModelId,
+			})
 		case "claude-code":
-			return new ClaudeCodeHandler(options)
+			return new ClaudeCodeHandler({
+				claudeCodePath: options.claudeCodePath,
+				apiModelId: options.apiModelId,
+				thinkingBudgetTokens: options.thinkingBudgetTokens,
+			})
 		default:
-			return new AnthropicHandler(options)
+			return new AnthropicHandler({
+				apiKey: options.apiKey,
+				anthropicBaseUrl: options.anthropicBaseUrl,
+				apiModelId: options.apiModelId,
+				thinkingBudgetTokens: options.thinkingBudgetTokens,
+			})
 	}
 }
 

src/api/providers/__tests__/ollama.test.ts

@@ -45,8 +45,10 @@ describe("OllamaHandler", () => {
 				this.skip()
 			}
 			this.timeout(5000)
+			// Ensure client is initialized
+			const client = (handler as any).ensureClient()
 			// Mock the Ollama client's chat method
-			const chatStub = sinon.stub(handler["client"], "chat").resolves({
+			const chatStub = sinon.stub(client, "chat").resolves({
 				[Symbol.asyncIterator]: async function* () {
 					yield {
 						message: { content: "Hello, world!" },
@@ -139,8 +141,9 @@ describe("OllamaHandler", () => {
 			// Restore real timers for this test
 			clock.restore()
 
-			// Mock the Ollama client's chat method to fail on first call and succeed on second
-			const chatStub = sinon.stub(handler["client"], "chat")
+			// Ensure client is initialized and mock the Ollama client's chat method to fail on first call and succeed on second
+			const client = (handler as any).ensureClient()
+			const chatStub = sinon.stub(client, "chat")
 
 			// First call throws an error
 			chatStub.onFirstCall().rejects(new Error("API Error"))

src/api/providers/anthropic.ts

@@ -5,20 +5,42 @@ import { anthropicDefaultModelId, AnthropicModelId, anthropicModels, ApiHandlerO
 import { ApiHandler } from "../index"
 import { ApiStream } from "../transform/stream"
 
+interface AnthropicHandlerOptions {
+	apiKey?: string
+	anthropicBaseUrl?: string
+	apiModelId?: string
+	thinkingBudgetTokens?: number
+}
+
 export class AnthropicHandler implements ApiHandler {
 	private options: ApiHandlerOptions
-	private client: Anthropic
+	private client: Anthropic | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: AnthropicHandlerOptions) {
 		this.options = options
-		this.client = new Anthropic({
-			apiKey: this.options.apiKey,
-			baseURL: this.options.anthropicBaseUrl || undefined,
-		})
+	}
+
+	private ensureClient(): Anthropic {
+		if (!this.client) {
+			if (!this.options.apiKey) {
+				throw new Error("Anthropic API key is required")
+			}
+			try {
+				this.client = new Anthropic({
+					apiKey: this.options.apiKey,
+					baseURL: this.options.anthropicBaseUrl || undefined,
+				})
+			} catch (error) {
+				throw new Error(`Error creating Anthropic client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
+
 		const model = this.getModel()
 		let stream: AnthropicStream<Anthropic.RawMessageStreamEvent>
 		const modelId = model.id
@@ -44,7 +66,7 @@ export class AnthropicHandler implements ApiHandler {
 				)
 				const lastUserMsgIndex = userMsgIndices[userMsgIndices.length - 1] ?? -1
 				const secondLastMsgUserIndex = userMsgIndices[userMsgIndices.length - 2] ?? -1
-				stream = await this.client.messages.create(
+				stream = await client.messages.create(
 					{
 						model: modelId,
 						thinking: reasoningOn ? { type: "enabled", budget_tokens: budget_tokens } : undefined,
@@ -118,7 +140,7 @@ export class AnthropicHandler implements ApiHandler {
 				break
 			}
 			default: {
-				stream = await this.client.messages.create({
+				stream = await client.messages.create({
 					model: modelId,
 					max_tokens: model.info.maxTokens || 8192,
 					temperature: 0,

src/api/providers/asksage.ts

@@ -1,16 +1,15 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { ApiHandler } from ".."
-import {
-	ApiHandlerOptions,
-	ModelInfo,
-	AskSageModelId,
-	askSageModels,
-	askSageDefaultModelId,
-	askSageDefaultURL,
-} from "@shared/api"
+import { ModelInfo, AskSageModelId, askSageModels, askSageDefaultModelId, askSageDefaultURL } from "@shared/api"
 import { ApiStream } from "../transform/stream"
 import { withRetry } from "../retry"
 
+interface AskSageHandlerOptions {
+	asksageApiKey?: string
+	asksageApiUrl?: string
+	apiModelId?: string
+}
+
 type AskSageRequest = {
 	system_prompt: string
 	message: {
@@ -31,11 +30,11 @@ type AskSageResponse = {
 }
 
 export class AskSageHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: AskSageHandlerOptions
 	private apiUrl: string
 	private apiKey: string
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: AskSageHandlerOptions) {
 		console.log("init api url", options.asksageApiUrl, askSageDefaultURL)
 		this.options = options
 		this.apiKey = options.asksageApiKey || ""

src/api/providers/bedrock.ts

@@ -2,7 +2,7 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { withRetry } from "../retry"
 import { ApiHandler } from "../"
 import { convertToR1Format } from "../transform/r1-format"
-import { ApiHandlerOptions, bedrockDefaultModelId, BedrockModelId, bedrockModels, ModelInfo } from "@shared/api"
+import { bedrockDefaultModelId, BedrockModelId, bedrockModels, ModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "../../utils/cost"
 import { ApiStream } from "../transform/stream"
 import { fromNodeProviderChain } from "@aws-sdk/credential-providers"
@@ -16,6 +16,22 @@ import {
 // Import proper AWS SDK types
 import type { Message, ContentBlock } from "@aws-sdk/client-bedrock-runtime"
 
+interface AwsBedrockHandlerOptions {
+	apiModelId?: string
+	awsAccessKey?: string
+	awsSecretKey?: string
+	awsSessionToken?: string
+	awsRegion?: string
+	awsUseCrossRegionInference?: boolean
+	awsBedrockUsePromptCache?: boolean
+	awsUseProfile?: boolean
+	awsProfile?: string
+	awsBedrockEndpoint?: string
+	awsBedrockCustomSelected?: boolean
+	awsBedrockCustomModelBaseId?: BedrockModelId
+	thinkingBudgetTokens?: number
+}
+
 // Extend AWS SDK types to include additionalModelResponseFields
 interface ExtendedMetadata {
 	usage?: {
@@ -90,9 +106,9 @@ interface ProviderChainOptions {
 
 // https://docs.anthropic.com/en/api/claude-on-amazon-bedrock
 export class AwsBedrockHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: AwsBedrockHandlerOptions
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: AwsBedrockHandlerOptions) {
 		this.options = options
 	}
 

src/api/providers/cerebras.ts

@@ -1,38 +1,63 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import Cerebras from "@cerebras/cerebras_cloud_sdk"
 import { withRetry } from "../retry"
-import { ApiHandlerOptions, ModelInfo, CerebrasModelId, cerebrasDefaultModelId, cerebrasModels } from "@shared/api"
+import { ModelInfo, CerebrasModelId, cerebrasDefaultModelId, cerebrasModels } from "@shared/api"
 import { ApiHandler } from "../index"
 import { ApiStream } from "@api/transform/stream"
 
+interface CerebrasHandlerOptions {
+	cerebrasApiKey?: string
+	apiModelId?: string
+}
+
 export class CerebrasHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: Cerebras
+	private options: CerebrasHandlerOptions
+	private client: Cerebras | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: CerebrasHandlerOptions) {
 		this.options = options
+	}
 
-		// Clean and validate the API key
-		const cleanApiKey = this.options.cerebrasApiKey?.trim()
+	private ensureClient(): Cerebras {
+		if (!this.client) {
+			// Clean and validate the API key
+			const cleanApiKey = this.options.cerebrasApiKey?.trim()
 
-		if (!cleanApiKey) {
-			throw new Error("Cerebras API key is required")
+			if (!cleanApiKey) {
+				throw new Error("Cerebras API key is required")
+			}
+
+			try {
+				this.client = new Cerebras({
+					apiKey: cleanApiKey,
+					timeout: 30000, // 30 second timeout
+				})
+			} catch (error) {
+				throw new Error(`Error creating Cerebras client: ${error.message}`)
+			}
 		}
-
-		this.client = new Cerebras({
-			apiKey: cleanApiKey,
-			timeout: 30000, // 30 second timeout
-		})
+		return this.client
 	}
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
+
 		// Convert Anthropic messages to Cerebras format
 		const cerebrasMessages: Array<{
 			role: "system" | "user" | "assistant"
 			content: string
 		}> = [{ role: "system", content: systemPrompt }]
 
+		// Helper function to strip thinking tags from content
+		const stripThinkingTags = (content: string): string => {
+			return content.replace(/<think>[\s\S]*?<\/think>/g, "").trim()
+		}
+
+		// Check if this is a reasoning model that uses thinking tags
+		const modelId = this.getModel().id
+		const isReasoningModel = modelId.includes("qwen") || modelId.includes("deepseek-r1-distill")
+
 		// Convert Anthropic messages to Cerebras format
 		for (const message of messages) {
 			if (message.role === "user") {
@@ -50,7 +75,7 @@ export class CerebrasHandler implements ApiHandler {
 					: message.content
 				cerebrasMessages.push({ role: "user", content })
 			} else if (message.role === "assistant") {
-				const content = Array.isArray(message.content)
+				let content = Array.isArray(message.content)
 					? message.content
 							.map((block) => {
 								if (block.type === "text") {
@@ -60,12 +85,19 @@ export class CerebrasHandler implements ApiHandler {
 							})
 							.join("\n")
 					: message.content || ""
+
+				// Strip thinking tags from assistant messages for reasoning models
+				// so the model doesn't see its own thinking in the conversation history
+				if (isReasoningModel) {
+					content = stripThinkingTags(content)
+				}
+
 				cerebrasMessages.push({ role: "assistant", content })
 			}
 		}
 
 		try {
-			const stream = await this.client.chat.completions.create({
+			const stream = await client.chat.completions.create({
 				model: this.getModel().id,
 				messages: cerebrasMessages,
 				temperature: 0,
@@ -74,8 +106,6 @@ export class CerebrasHandler implements ApiHandler {
 
 			// Handle streaming response
 			let reasoning: string | null = null // Track reasoning content for models that support thinking
-			const modelId = this.getModel().id
-			const isReasoningModel = modelId.includes("qwen") || modelId.includes("deepseek-r1-distill")
 
 			for await (const chunk of stream as any) {
 				// Type assertion for the streaming chunk

src/api/providers/claude-code.ts

@@ -1,15 +1,21 @@
 import type { Anthropic } from "@anthropic-ai/sdk"
-import { claudeCodeDefaultModelId, ClaudeCodeModelId, claudeCodeModels, type ApiHandlerOptions } from "@/shared/api"
+import { claudeCodeDefaultModelId, ClaudeCodeModelId, claudeCodeModels } from "@/shared/api"
 import { type ApiHandler } from ".."
 import { ApiStreamUsageChunk, type ApiStream } from "../transform/stream"
 import { withRetry } from "../retry"
 import { runClaudeCode } from "@/integrations/claude-code/run"
 import { filterMessagesForClaudeCode } from "@/integrations/claude-code/message-filter"
 
-export class ClaudeCodeHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+interface ClaudeCodeHandlerOptions {
+	claudeCodePath?: string
+	apiModelId?: string
+	thinkingBudgetTokens?: number
+}
 
-	constructor(options: ApiHandlerOptions) {
+export class ClaudeCodeHandler implements ApiHandler {
+	private options: ClaudeCodeHandlerOptions
+
+	constructor(options: ClaudeCodeHandlerOptions) {
 		this.options = options
 	}
 
@@ -27,6 +33,7 @@ export class ClaudeCodeHandler implements ApiHandler {
 			messages: filteredMessages,
 			path: this.options.claudeCodePath,
 			modelId: this.getModel().id,
+			thinkingBudgetTokens: this.options.thinkingBudgetTokens,
 		})
 
 		// Usage is included with assistant messages,

src/api/providers/cline.ts

@@ -1,143 +1,200 @@
 import { Anthropic } from "@anthropic-ai/sdk"
-import OpenAI from "openai"
 import { ApiHandler } from "../"
-import { ApiHandlerOptions, ModelInfo, openRouterDefaultModelId, openRouterDefaultModelInfo } from "@shared/api"
+import { ClineAccountService } from "@/services/account/ClineAccountService"
+import { ModelInfo, openRouterDefaultModelId, openRouterDefaultModelInfo } from "@shared/api"
 import { createOpenRouterStream } from "../transform/openrouter-stream"
 import { ApiStream, ApiStreamUsageChunk } from "../transform/stream"
 import axios from "axios"
 import { OpenRouterErrorResponse } from "./types"
 import { withRetry } from "../retry"
+import { AuthService } from "@/services/auth/AuthService"
+import OpenAI from "openai"
+
+interface ClineHandlerOptions {
+	taskId?: string
+	reasoningEffort?: string
+	thinkingBudgetTokens?: number
+	openRouterProviderSorting?: string
+	openRouterModelId?: string
+	openRouterModelInfo?: ModelInfo
+	clineAccountId?: string
+}
 
 export class ClineHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
+	private options: ClineHandlerOptions
+	private clineAccountService = ClineAccountService.getInstance()
+	private _authService: AuthService
+	private client: OpenAI | undefined
+	// TODO: replace this with a global API Host
+	private readonly _baseUrl = "https://api.cline.bot"
+	// private readonly _baseUrl = "https://core-api.staging.int.cline.bot"
+	// private readonly _baseUrl = "http://localhost:7777"
 	lastGenerationId?: string
+	private counter = 0
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: ClineHandlerOptions) {
 		this.options = options
-		this.client = new OpenAI({
-			baseURL: "https://api.cline.bot/v1",
-			apiKey: this.options.clineApiKey || "",
-			defaultHeaders: {
-				"HTTP-Referer": "https://cline.bot", // Optional, for including your app on cline.bot rankings.
-				"X-Title": "Cline", // Optional. Shows in rankings on cline.bot.
-				"X-Task-ID": this.options.taskId || "", // Include the task ID in the request headers
-			},
-		})
+		this._authService = AuthService.getInstance()
+	}
+
+	private async ensureClient(): Promise<OpenAI> {
+		const clineAccountAuthToken = await this._authService.getAuthToken()
+		if (!clineAccountAuthToken) {
+			throw new Error("Cline account authentication token is required")
+		}
+		if (!this.client) {
+			try {
+				this.client = new OpenAI({
+					baseURL: `${this._baseUrl}/api/v1`,
+					apiKey: clineAccountAuthToken,
+					defaultHeaders: {
+						"HTTP-Referer": "https://cline.bot",
+						"X-Title": "Cline",
+						"X-Task-ID": this.options.taskId || "",
+					},
+				})
+			} catch (error: any) {
+				throw new Error(`Error creating Cline client: ${error.message}`)
+			}
+		}
+		// Ensure the client is always using the latest auth token
+		this.client.apiKey = clineAccountAuthToken
+		return this.client
 	}
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = await this.ensureClient()
+
 		this.lastGenerationId = undefined
 
-		const stream = await createOpenRouterStream(
-			this.client,
-			systemPrompt,
-			messages,
-			this.getModel(),
-			this.options.reasoningEffort,
-			this.options.thinkingBudgetTokens,
-			this.options.openRouterProviderSorting,
+		const me = await this.clineAccountService.fetchMe()
+		console.log(
+			"SwitchAuthToken: Active Organization",
+			me?.organizations.filter((org) => org.active)[0]?.name || "No active organization",
 		)
 
 		let didOutputUsage: boolean = false
 
-		for await (const chunk of stream) {
-			// openrouter returns an error object instead of the openai sdk throwing an error
-			if ("error" in chunk) {
-				const error = chunk.error as OpenRouterErrorResponse["error"]
-				console.error(`Cline API Error: ${error?.code} - ${error?.message}`)
-				// Include metadata in the error message if available
-				const metadataStr = error.metadata ? `\nMetadata: ${JSON.stringify(error.metadata, null, 2)}` : ""
-				throw new Error(`Cline API Error ${error.code}: ${error.message}${metadataStr}`)
-			}
+		try {
+			const stream = await createOpenRouterStream(
+				client,
+				systemPrompt,
+				messages,
+				this.getModel(),
+				this.options.reasoningEffort,
+				this.options.thinkingBudgetTokens,
+				this.options.openRouterProviderSorting,
+			)
 
-			if (!this.lastGenerationId && chunk.id) {
-				this.lastGenerationId = chunk.id
-			}
-
-			// Check for mid-stream error via finish_reason
-			const choice = chunk.choices?.[0]
-			// OpenRouter may return finish_reason = "error" with error details
-			if ((choice?.finish_reason as string) === "error") {
-				const choiceWithError = choice as any
-				if (choiceWithError.error) {
-					const error = choiceWithError.error
-					console.error(`Cline Mid-Stream Error: ${error.code || error.type || "Unknown"} - ${error.message}`)
-					throw new Error(`Cline Mid-Stream Error: ${error.code || error.type || "Unknown"} - ${error.message}`)
-				} else {
-					throw new Error("Cline Mid-Stream Error: Stream terminated with error status but no error details provided")
+			for await (const chunk of stream) {
+				// openrouter returns an error object instead of the openai sdk throwing an error
+				if ("error" in chunk) {
+					const error = chunk.error as OpenRouterErrorResponse["error"]
+					console.error(`Cline API Error: ${error?.code} - ${error?.message}`)
+					// Include metadata in the error message if available
+					const metadataStr = error.metadata ? `\nMetadata: ${JSON.stringify(error.metadata, null, 2)}` : ""
+					throw new Error(`Cline API Error ${error.code}: ${error.message}${metadataStr}`)
 				}
-			}
-
-			const delta = choice?.delta
-			if (delta?.content) {
-				yield {
-					type: "text",
-					text: delta.content,
+				if (!this.lastGenerationId && chunk.id) {
+					this.lastGenerationId = chunk.id
 				}
-			}
 
-			// Reasoning tokens are returned separately from the content
-			if ("reasoning" in delta && delta.reasoning) {
-				yield {
-					type: "reasoning",
+				// Check for mid-stream error via finish_reason
+				const choice = chunk.choices?.[0]
+				// OpenRouter may return finish_reason = "error" with error details
+				if ((choice?.finish_reason as string) === "error") {
+					const choiceWithError = choice as any
+					if (choiceWithError.error) {
+						const error = choiceWithError.error
+						console.error(`Cline Mid-Stream Error: ${error.code || error.type || "Unknown"} - ${error.message}`)
+						throw new Error(`Cline Mid-Stream Error: ${error.code || error.type || "Unknown"} - ${error.message}`)
+					} else {
+						throw new Error(
+							"Cline Mid-Stream Error: Stream terminated with error status but no error details provided",
+						)
+					}
+				}
+
+				const delta = choice?.delta
+				if (delta?.content) {
+					yield {
+						type: "text",
+						text: delta.content,
+					}
+				}
+
+				// Reasoning tokens are returned separately from the content
+				if ("reasoning" in delta && delta.reasoning) {
+					yield {
+						type: "reasoning",
+						// @ts-ignore-next-line
+						reasoning: delta.reasoning,
+					}
+				}
+
+				if (!didOutputUsage && chunk.usage) {
 					// @ts-ignore-next-line
-					reasoning: delta.reasoning,
-				}
-			}
+					let totalCost = (chunk.usage.cost || 0) + (chunk.usage.cost_details?.upstream_inference_cost || 0)
+					const modelId = this.getModel().id
 
-			if (!didOutputUsage && chunk.usage) {
-				// @ts-ignore-next-line
-				let totalCost = (chunk.usage.cost || 0) + (chunk.usage.cost_details?.upstream_inference_cost || 0)
-				const modelId = this.getModel().id
-				const provider = modelId.split("/")[0]
+					// const provider = modelId.split("/")[0]
+					// // If provider is x-ai, set totalCost to 0 (we're doing a promo)
+					// if (provider === "x-ai") {
+					// 	totalCost = 0
+					// }
 
-				// If provider is x-ai, set totalCost to 0 (we're doing a promo)
-				if (provider === "x-ai") {
-					totalCost = 0
-				}
-
-				if (modelId.includes("gemini")) {
-					yield {
-						type: "usage",
-						cacheWriteTokens: 0,
-						cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens || 0,
-						inputTokens: (chunk.usage.prompt_tokens || 0) - (chunk.usage.prompt_tokens_details?.cached_tokens || 0),
-						outputTokens: chunk.usage.completion_tokens || 0,
-						// @ts-ignore-next-line
-						totalCost,
-					}
-				} else {
-					yield {
-						type: "usage",
-						cacheWriteTokens: 0,
-						cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens || 0,
-						inputTokens: chunk.usage.prompt_tokens || 0,
-						outputTokens: chunk.usage.completion_tokens || 0,
-						// @ts-ignore-next-line
-						totalCost,
+					if (modelId.includes("gemini")) {
+						yield {
+							type: "usage",
+							cacheWriteTokens: 0,
+							cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens || 0,
+							inputTokens:
+								(chunk.usage.prompt_tokens || 0) - (chunk.usage.prompt_tokens_details?.cached_tokens || 0),
+							outputTokens: chunk.usage.completion_tokens || 0,
+							// @ts-ignore-next-line
+							totalCost,
+						}
+					} else {
+						yield {
+							type: "usage",
+							cacheWriteTokens: 0,
+							cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens || 0,
+							inputTokens: chunk.usage.prompt_tokens || 0,
+							outputTokens: chunk.usage.completion_tokens || 0,
+							// @ts-ignore-next-line
+							totalCost,
+						}
 					}
+					didOutputUsage = true
 				}
-				didOutputUsage = true
 			}
-		}
 
-		// Fallback to generation endpoint if usage chunk not returned
-		if (!didOutputUsage) {
-			const apiStreamUsage = await this.getApiStreamUsage()
-			if (apiStreamUsage) {
-				yield apiStreamUsage
+			// Fallback to generation endpoint if usage chunk not returned
+			if (!didOutputUsage) {
+				console.warn("Cline API did not return usage chunk, fetching from generation endpoint")
+				const apiStreamUsage = await this.getApiStreamUsage()
+				if (apiStreamUsage) {
+					yield apiStreamUsage
+				}
 			}
+		} catch (error) {
+			if (error.code === "ERR_BAD_REQUEST" || error.status === 401) {
+				throw new Error("Unauthorized: Please sign in to Cline before trying again.")
+			}
+			console.error("Cline API Error:", error)
 		}
 	}
 
 	async getApiStreamUsage(): Promise<ApiStreamUsageChunk | undefined> {
 		if (this.lastGenerationId) {
 			try {
-				const response = await axios.get(`https://api.cline.bot/v1/generation?id=${this.lastGenerationId}`, {
+				// TODO: replace this with firebase auth
+				// TODO: use global API Host
+
+				const response = await axios.get(`${this.clineAccountService.baseUrl}/generation?id=${this.lastGenerationId}`, {
 					headers: {
-						Authorization: `Bearer ${this.options.clineApiKey}`,
+						Authorization: `Bearer ${this.options.clineAccountId}`,
 					},
 					timeout: 15_000, // this request hangs sometimes
 				})
@@ -175,9 +232,6 @@ export class ClineHandler implements ApiHandler {
 
 	getModel(): { id: string; info: ModelInfo } {
 		let modelId = this.options.openRouterModelId
-		if (modelId === "x-ai/grok-3") {
-			modelId = "x-ai/grok-3-beta"
-		}
 		const modelInfo = this.options.openRouterModelInfo
 		if (modelId && modelInfo) {
 			return { id: modelId, info: modelInfo }

src/api/providers/deepseek.ts

@@ -8,16 +8,34 @@ import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 import { convertToR1Format } from "../transform/r1-format"
 
-export class DeepSeekHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
+interface DeepSeekHandlerOptions {
+	deepSeekApiKey?: string
+	apiModelId?: string
+}
 
-	constructor(options: ApiHandlerOptions) {
+export class DeepSeekHandler implements ApiHandler {
+	private options: DeepSeekHandlerOptions
+	private client: OpenAI | undefined
+
+	constructor(options: DeepSeekHandlerOptions) {
 		this.options = options
-		this.client = new OpenAI({
-			baseURL: "https://api.deepseek.com/v1",
-			apiKey: this.options.deepSeekApiKey,
-		})
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.deepSeekApiKey) {
+				throw new Error("DeepSeek API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					baseURL: "https://api.deepseek.com/v1",
+					apiKey: this.options.deepSeekApiKey,
+				})
+			} catch (error) {
+				throw new Error(`Error creating DeepSeek client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	private async *yieldUsage(info: ModelInfo, usage: OpenAI.Completions.CompletionUsage | undefined): ApiStream {
@@ -54,6 +72,7 @@ export class DeepSeekHandler implements ApiHandler {
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const model = this.getModel()
 
 		const isDeepseekReasoner = model.id.includes("deepseek-reasoner")
@@ -67,7 +86,7 @@ export class DeepSeekHandler implements ApiHandler {
 			openAiMessages = convertToR1Format([{ role: "user", content: systemPrompt }, ...messages])
 		}
 
-		const stream = await this.client.chat.completions.create({
+		const stream = await client.chat.completions.create({
 			model: model.id,
 			max_completion_tokens: model.info.maxTokens,
 			messages: openAiMessages,

src/api/providers/doubao.ts

@@ -1,20 +1,38 @@
 import { ApiHandler } from ".."
-import { ApiHandlerOptions, doubaoDefaultModelId, DoubaoModelId, doubaoModels, ModelInfo } from "@shared/api"
+import { doubaoDefaultModelId, DoubaoModelId, doubaoModels, ModelInfo } from "@shared/api"
 import { Anthropic } from "@anthropic-ai/sdk"
 import OpenAI from "openai"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 import { withRetry } from "../retry"
 
+interface DoubaoHandlerOptions {
+	doubaoApiKey?: string
+	apiModelId?: string
+}
+
 export class DoubaoHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
-	constructor(options: ApiHandlerOptions) {
+	private options: DoubaoHandlerOptions
+	private client: OpenAI | undefined
+	constructor(options: DoubaoHandlerOptions) {
 		this.options = options
-		this.client = new OpenAI({
-			baseURL: "https://ark.cn-beijing.volces.com/api/v3/",
-			apiKey: this.options.doubaoApiKey,
-		})
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.doubaoApiKey) {
+				throw new Error("Doubao API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					baseURL: "https://ark.cn-beijing.volces.com/api/v3/",
+					apiKey: this.options.doubaoApiKey,
+				})
+			} catch (error) {
+				throw new Error(`Error creating Doubao client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	getModel(): { id: DoubaoModelId; info: ModelInfo } {
@@ -31,12 +49,13 @@ export class DoubaoHandler implements ApiHandler {
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const model = this.getModel()
 		let openAiMessages: OpenAI.Chat.ChatCompletionMessageParam[] = [
 			{ role: "system", content: systemPrompt },
 			...convertToOpenAiMessages(messages),
 		]
-		const stream = await this.client.chat.completions.create({
+		const stream = await client.chat.completions.create({
 			model: model.id,
 			max_completion_tokens: model.info.maxTokens,
 			messages: openAiMessages,

src/api/providers/fireworks.ts

@@ -2,31 +2,45 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import OpenAI from "openai"
 import { withRetry } from "../retry"
 import { ApiHandler } from ".."
-import {
-	ApiHandlerOptions,
-	DeepSeekModelId,
-	ModelInfo,
-	deepSeekDefaultModelId,
-	deepSeekModels,
-	openAiModelInfoSaneDefaults,
-} from "../../shared/api"
+import { ModelInfo, openAiModelInfoSaneDefaults } from "../../shared/api"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 
-export class FireworksHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
+interface FireworksHandlerOptions {
+	fireworksApiKey?: string
+	fireworksModelId?: string
+	fireworksModelMaxCompletionTokens?: number
+	fireworksModelMaxTokens?: number
+}
 
-	constructor(options: ApiHandlerOptions) {
+export class FireworksHandler implements ApiHandler {
+	private options: FireworksHandlerOptions
+	private client: OpenAI | undefined
+
+	constructor(options: FireworksHandlerOptions) {
 		this.options = options
-		this.client = new OpenAI({
-			baseURL: "https://api.fireworks.ai/inference/v1",
-			apiKey: this.options.fireworksApiKey,
-		})
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.fireworksApiKey) {
+				throw new Error("Fireworks API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					baseURL: "https://api.fireworks.ai/inference/v1",
+					apiKey: this.options.fireworksApiKey,
+				})
+			} catch (error) {
+				throw new Error(`Error creating Fireworks client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const modelId = this.options.fireworksModelId ?? ""
 
 		const openAiMessages: OpenAI.Chat.ChatCompletionMessageParam[] = [
@@ -34,7 +48,7 @@ export class FireworksHandler implements ApiHandler {
 			...convertToOpenAiMessages(messages),
 		]
 
-		const stream = await this.client.chat.completions.create({
+		const stream = await client.chat.completions.create({
 			model: modelId,
 			...(this.options.fireworksModelMaxCompletionTokens
 				? { max_completion_tokens: this.options.fireworksModelMaxCompletionTokens }

src/api/providers/gemini.ts

@@ -12,8 +12,15 @@ import { telemetryService } from "@services/posthog/telemetry/TelemetryService"
 // Define a default TTL for the cache (e.g., 15 minutes in seconds)
 const DEFAULT_CACHE_TTL_SECONDS = 900
 
-interface GeminiHandlerOptions extends ApiHandlerOptions {
+interface GeminiHandlerOptions {
 	isVertex?: boolean
+	vertexProjectId?: string
+	vertexRegion?: string
+	geminiApiKey?: string
+	geminiBaseUrl?: string
+	thinkingBudgetTokens?: number
+	apiModelId?: string
+	taskId?: string
 }
 
 /**
@@ -38,30 +45,45 @@ interface GeminiHandlerOptions extends ApiHandlerOptions {
  */
 export class GeminiHandler implements ApiHandler {
 	private options: ApiHandlerOptions
-	private client: GoogleGenAI
+	private client: GoogleGenAI | undefined
 
 	constructor(options: GeminiHandlerOptions) {
 		// Store the options
 		this.options = options
+	}
 
-		if (options.isVertex) {
-			// Initialize with Vertex AI configuration
-			const project = this.options.vertexProjectId ?? "not-provided"
-			const location = this.options.vertexRegion ?? "not-provided"
+	private ensureClient(): GoogleGenAI {
+		if (!this.client) {
+			const options = this.options as GeminiHandlerOptions
 
-			this.client = new GoogleGenAI({
-				vertexai: true,
-				project,
-				location,
-			})
-		} else {
-			// Initialize with standard API key
-			if (!options.geminiApiKey) {
-				throw new Error("API key is required for Google Gemini when not using Vertex AI")
+			if (options.isVertex) {
+				// Initialize with Vertex AI configuration
+				const project = this.options.vertexProjectId ?? "not-provided"
+				const location = this.options.vertexRegion ?? "not-provided"
+
+				try {
+					this.client = new GoogleGenAI({
+						vertexai: true,
+						project,
+						location,
+					})
+				} catch (error) {
+					throw new Error(`Error creating Gemini Vertex AI client: ${error.message}`)
+				}
+			} else {
+				// Initialize with standard API key
+				if (!options.geminiApiKey) {
+					throw new Error("API key is required for Google Gemini when not using Vertex AI")
+				}
+
+				try {
+					this.client = new GoogleGenAI({ apiKey: options.geminiApiKey })
+				} catch (error) {
+					throw new Error(`Error creating Gemini client: ${error.message}`)
+				}
 			}
-
-			this.client = new GoogleGenAI({ apiKey: options.geminiApiKey })
 		}
+		return this.client
 	}
 
 	/**
@@ -80,6 +102,7 @@ export class GeminiHandler implements ApiHandler {
 		maxDelay: 15000,
 	})
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const { id: modelId, info } = this.getModel()
 		const contents = messages.map(convertAnthropicMessageToGemini)
 
@@ -117,7 +140,7 @@ export class GeminiHandler implements ApiHandler {
 		let lastUsageMetadata: GenerateContentResponseUsageMetadata | undefined
 
 		try {
-			const result = await this.client.models.generateContentStream({
+			const result = await client.models.generateContentStream({
 				model: modelId,
 				contents: contents,
 				config: {
@@ -351,6 +374,7 @@ export class GeminiHandler implements ApiHandler {
 	 */
 	async countTokens(content: Array<any>): Promise<number> {
 		try {
+			const client = this.ensureClient()
 			const { id: model } = this.getModel()
 
 			// Convert content to Gemini format
@@ -362,7 +386,7 @@ export class GeminiHandler implements ApiHandler {
 			})
 
 			// Use Gemini's token counting API
-			const response = await this.client.models.countTokens({
+			const response = await client.models.countTokens({
 				model,
 				contents: [{ parts: geminiContent }],
 			})

src/api/providers/litellm.ts

@@ -1,28 +1,52 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import OpenAI from "openai"
-import { ApiHandlerOptions, liteLlmDefaultModelId, liteLlmModelInfoSaneDefaults } from "@shared/api"
+import { liteLlmDefaultModelId, liteLlmModelInfoSaneDefaults, LiteLLMModelInfo } from "@shared/api"
 import { ApiHandler } from ".."
 import { ApiStream } from "../transform/stream"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { withRetry } from "../retry"
 
-export class LiteLlmHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
+interface LiteLlmHandlerOptions {
+	liteLlmApiKey?: string
+	liteLlmBaseUrl?: string
+	liteLlmModelId?: string
+	liteLlmModelInfo?: LiteLLMModelInfo
+	thinkingBudgetTokens?: number
+	liteLlmUsePromptCache?: boolean
+	taskId?: string
+}
 
-	constructor(options: ApiHandlerOptions) {
+export class LiteLlmHandler implements ApiHandler {
+	private options: LiteLlmHandlerOptions
+	private client: OpenAI | undefined
+
+	constructor(options: LiteLlmHandlerOptions) {
 		this.options = options
-		this.client = new OpenAI({
-			baseURL: this.options.liteLlmBaseUrl || "http://localhost:4000",
-			apiKey: this.options.liteLlmApiKey || "noop",
-		})
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.liteLlmApiKey) {
+				throw new Error("LiteLLM API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					baseURL: this.options.liteLlmBaseUrl || "http://localhost:4000",
+					apiKey: this.options.liteLlmApiKey || "noop",
+				})
+			} catch (error) {
+				throw new Error(`Error creating LiteLLM client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	async calculateCost(prompt_tokens: number, completion_tokens: number): Promise<number | undefined> {
 		// Reference: https://github.com/BerriAI/litellm/blob/122ee634f434014267af104814022af1d9a0882f/litellm/proxy/spend_tracking/spend_management_endpoints.py#L1473
+		const client = this.ensureClient()
 		const modelId = this.options.liteLlmModelId || liteLlmDefaultModelId
 		try {
-			const response = await fetch(`${this.client.baseURL}/spend/calculate`, {
+			const response = await fetch(`${client.baseURL}/spend/calculate`, {
 				method: "POST",
 				headers: {
 					"Content-Type": "application/json",
@@ -54,6 +78,7 @@ export class LiteLlmHandler implements ApiHandler {
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const formattedMessages = convertToOpenAiMessages(messages)
 		const systemMessage: OpenAI.Chat.ChatCompletionSystemMessageParam = {
 			role: "system",
@@ -101,21 +126,15 @@ export class LiteLlmHandler implements ApiHandler {
 			return message
 		})
 
-		const requestPayload: OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming & {
-			metadata?: { cline_task_id: string }
-		} = {
+		const stream = await client.chat.completions.create({
 			model: this.options.liteLlmModelId || liteLlmDefaultModelId,
 			messages: [enhancedSystemMessage, ...enhancedMessages],
 			temperature,
 			stream: true,
 			stream_options: { include_usage: true },
 			...(thinkingConfig && { thinking: thinkingConfig }), // Add thinking configuration when applicable
-			...(this.options.taskId && {
-				metadata: { cline_task_id: this.options.taskId },
-			}),
-		}
-
-		const stream = await this.client.chat.completions.create(requestPayload)
+			...(this.options.taskId && { litellm_session_id: `cline-${this.options.taskId}` }), // Add session ID for LiteLLM tracking
+		})
 
 		const inputCost = (await this.calculateCost(1e6, 0)) || 0
 		const outputCost = (await this.calculateCost(0, 1e6)) || 0

src/api/providers/lmstudio.ts

@@ -6,27 +6,43 @@ import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 import { withRetry } from "../retry"
 
-export class LmStudioHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
+interface LmStudioHandlerOptions {
+	lmStudioBaseUrl?: string
+	lmStudioModelId?: string
+}
 
-	constructor(options: ApiHandlerOptions) {
+export class LmStudioHandler implements ApiHandler {
+	private options: LmStudioHandlerOptions
+	private client: OpenAI | undefined
+
+	constructor(options: LmStudioHandlerOptions) {
 		this.options = options
-		this.client = new OpenAI({
-			baseURL: (this.options.lmStudioBaseUrl || "http://localhost:1234") + "/v1",
-			apiKey: "noop",
-		})
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			try {
+				this.client = new OpenAI({
+					baseURL: (this.options.lmStudioBaseUrl || "http://localhost:1234") + "/v1",
+					apiKey: "noop",
+				})
+			} catch (error) {
+				throw new Error(`Error creating LM Studio client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	@withRetry({ retryAllErrors: true })
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const openAiMessages: OpenAI.Chat.ChatCompletionMessageParam[] = [
 			{ role: "system", content: systemPrompt },
 			...convertToOpenAiMessages(messages),
 		]
 
 		try {
-			const stream = await this.client.chat.completions.create({
+			const stream = await client.chat.completions.create({
 				model: this.getModel().id,
 				messages: openAiMessages,
 				stream: true,

src/api/providers/mistral.ts

@@ -2,24 +2,43 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { Mistral } from "@mistralai/mistralai"
 import { withRetry } from "../retry"
 import { ApiHandler } from "../"
-import { ApiHandlerOptions, mistralDefaultModelId, MistralModelId, mistralModels, ModelInfo } from "@shared/api"
+import { mistralDefaultModelId, MistralModelId, mistralModels, ModelInfo } from "@shared/api"
 import { convertToMistralMessages } from "../transform/mistral-format"
 import { ApiStream } from "../transform/stream"
 
-export class MistralHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: Mistral
+interface MistralHandlerOptions {
+	mistralApiKey?: string
+	apiModelId?: string
+}
 
-	constructor(options: ApiHandlerOptions) {
+export class MistralHandler implements ApiHandler {
+	private options: MistralHandlerOptions
+	private client: Mistral | undefined
+
+	constructor(options: MistralHandlerOptions) {
 		this.options = options
-		this.client = new Mistral({
-			apiKey: this.options.mistralApiKey,
-		})
+	}
+
+	private ensureClient(): Mistral {
+		if (!this.client) {
+			if (!this.options.mistralApiKey) {
+				throw new Error("Mistral API key is required")
+			}
+			try {
+				this.client = new Mistral({
+					apiKey: this.options.mistralApiKey,
+				})
+			} catch (error) {
+				throw new Error(`Error creating Mistral client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
-		const stream = await this.client.chat
+		const client = this.ensureClient()
+		const stream = await client.chat
 			.stream({
 				model: this.getModel().id,
 				// max_completion_tokens: this.getModel().info.maxTokens,

src/api/providers/nebius.ts

@@ -5,27 +5,45 @@ import { ApiHandler } from "../index"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 import { convertToR1Format } from "../transform/r1-format"
-import { nebiusDefaultModelId, nebiusModels, type ModelInfo, type ApiHandlerOptions, type NebiusModelId } from "../../shared/api"
+import { nebiusDefaultModelId, nebiusModels, type ModelInfo, type NebiusModelId } from "../../shared/api"
+
+interface NebiusHandlerOptions {
+	nebiusApiKey?: string
+	apiModelId?: string
+}
 
 export class NebiusHandler implements ApiHandler {
-	private client: OpenAI
+	private client: OpenAI | undefined
 
-	constructor(private readonly options: ApiHandlerOptions) {
-		this.client = new OpenAI({
-			baseURL: "https://api.studio.nebius.ai/v1",
-			apiKey: this.options.nebiusApiKey,
-		})
+	constructor(private readonly options: NebiusHandlerOptions) {}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.nebiusApiKey) {
+				throw new Error("Nebius API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					baseURL: "https://api.studio.nebius.ai/v1",
+					apiKey: this.options.nebiusApiKey,
+				})
+			} catch (error) {
+				throw new Error(`Error creating Nebius client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const model = this.getModel()
 
 		const openAiMessages: OpenAI.Chat.ChatCompletionMessageParam[] = model.id.includes("DeepSeek-R1")
 			? convertToR1Format([{ role: "user", content: systemPrompt }, ...messages])
 			: [{ role: "system", content: systemPrompt }, ...convertToOpenAiMessages(messages)]
 
-		const stream = await this.client.chat.completions.create({
+		const stream = await client.chat.completions.create({
 			model: model.id,
 			messages: openAiMessages,
 			temperature: 0,

src/api/providers/ollama.ts

@@ -6,17 +6,35 @@ import { convertToOllamaMessages } from "../transform/ollama-format"
 import { ApiStream } from "../transform/stream"
 import { withRetry } from "../retry"
 
-export class OllamaHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: Ollama
+interface OllamaHandlerOptions {
+	ollamaBaseUrl?: string
+	ollamaModelId?: string
+	ollamaApiOptionsCtxNum?: string
+	requestTimeoutMs?: number
+}
 
-	constructor(options: ApiHandlerOptions) {
+export class OllamaHandler implements ApiHandler {
+	private options: OllamaHandlerOptions
+	private client: Ollama | undefined
+
+	constructor(options: OllamaHandlerOptions) {
 		this.options = options
-		this.client = new Ollama({ host: this.options.ollamaBaseUrl || "http://localhost:11434" })
+	}
+
+	private ensureClient(): Ollama {
+		if (!this.client) {
+			try {
+				this.client = new Ollama({ host: this.options.ollamaBaseUrl || "http://localhost:11434" })
+			} catch (error) {
+				throw new Error(`Error creating Ollama client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	@withRetry({ retryAllErrors: true })
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const ollamaMessages: Message[] = [{ role: "system", content: systemPrompt }, ...convertToOllamaMessages(messages)]
 
 		try {
@@ -27,7 +45,7 @@ export class OllamaHandler implements ApiHandler {
 			})
 
 			// Create the actual API request promise
-			const apiPromise = this.client.chat({
+			const apiPromise = client.chat({
 				model: this.getModel().id,
 				messages: ollamaMessages,
 				stream: true,

src/api/providers/openai-native.ts

@@ -8,15 +8,34 @@ import { calculateApiCostOpenAI } from "../../utils/cost"
 import { ApiStream } from "../transform/stream"
 import type { ChatCompletionReasoningEffort } from "openai/resources/chat/completions"
 
-export class OpenAiNativeHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
+interface OpenAiNativeHandlerOptions {
+	openAiNativeApiKey?: string
+	reasoningEffort?: string
+	apiModelId?: string
+}
 
-	constructor(options: ApiHandlerOptions) {
+export class OpenAiNativeHandler implements ApiHandler {
+	private options: OpenAiNativeHandlerOptions
+	private client: OpenAI | undefined
+
+	constructor(options: OpenAiNativeHandlerOptions) {
 		this.options = options
-		this.client = new OpenAI({
-			apiKey: this.options.openAiNativeApiKey,
-		})
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.openAiNativeApiKey) {
+				throw new Error("OpenAI API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					apiKey: this.options.openAiNativeApiKey,
+				})
+			} catch (error: any) {
+				throw new Error(`Error creating OpenAI client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	private async *yieldUsage(info: ModelInfo, usage: OpenAI.Completions.CompletionUsage | undefined): ApiStream {
@@ -38,6 +57,7 @@ export class OpenAiNativeHandler implements ApiHandler {
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const model = this.getModel()
 
 		switch (model.id) {
@@ -45,7 +65,7 @@ export class OpenAiNativeHandler implements ApiHandler {
 			case "o1-preview":
 			case "o1-mini": {
 				// o1 doesn't support streaming, non-1 temp, or system prompt
-				const response = await this.client.chat.completions.create({
+				const response = await client.chat.completions.create({
 					model: model.id,
 					messages: [{ role: "user", content: systemPrompt }, ...convertToOpenAiMessages(messages)],
 				})
@@ -61,7 +81,7 @@ export class OpenAiNativeHandler implements ApiHandler {
 			case "o4-mini":
 			case "o3":
 			case "o3-mini": {
-				const stream = await this.client.chat.completions.create({
+				const stream = await client.chat.completions.create({
 					model: model.id,
 					messages: [{ role: "developer", content: systemPrompt }, ...convertToOpenAiMessages(messages)],
 					stream: true,
@@ -85,7 +105,7 @@ export class OpenAiNativeHandler implements ApiHandler {
 				break
 			}
 			default: {
-				const stream = await this.client.chat.completions.create({
+				const stream = await client.chat.completions.create({
 					model: model.id,
 					// max_completion_tokens: this.getModel().info.maxTokens,
 					temperature: 0,

src/api/providers/openai.ts

@@ -1,44 +1,68 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import OpenAI, { AzureOpenAI } from "openai"
 import { withRetry } from "../retry"
-import { ApiHandlerOptions, azureOpenAiDefaultApiVersion, ModelInfo, openAiModelInfoSaneDefaults } from "@shared/api"
+import { azureOpenAiDefaultApiVersion, ModelInfo, openAiModelInfoSaneDefaults, OpenAiCompatibleModelInfo } from "@shared/api"
 import { ApiHandler } from "../index"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 import { convertToR1Format } from "../transform/r1-format"
 import type { ChatCompletionReasoningEffort } from "openai/resources/chat/completions"
 
-export class OpenAiHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
+interface OpenAiHandlerOptions {
+	openAiApiKey?: string
+	openAiBaseUrl?: string
+	azureApiVersion?: string
+	openAiHeaders?: Record<string, string>
+	openAiModelId?: string
+	openAiModelInfo?: OpenAiCompatibleModelInfo
+	reasoningEffort?: string
+}
 
-	constructor(options: ApiHandlerOptions) {
+export class OpenAiHandler implements ApiHandler {
+	private options: OpenAiHandlerOptions
+	private client: OpenAI | undefined
+
+	constructor(options: OpenAiHandlerOptions) {
 		this.options = options
-		// Azure API shape slightly differs from the core API shape: https://github.com/openai/openai-node?tab=readme-ov-file#microsoft-azure-openai
-		// Use azureApiVersion to determine if this is an Azure endpoint, since the URL may not always contain 'azure.com'
-		if (
-			this.options.azureApiVersion ||
-			((this.options.openAiBaseUrl?.toLowerCase().includes("azure.com") ||
-				this.options.openAiBaseUrl?.toLowerCase().includes("azure.us")) &&
-				!this.options.openAiModelId?.toLowerCase().includes("deepseek"))
-		) {
-			this.client = new AzureOpenAI({
-				baseURL: this.options.openAiBaseUrl,
-				apiKey: this.options.openAiApiKey,
-				apiVersion: this.options.azureApiVersion || azureOpenAiDefaultApiVersion,
-				defaultHeaders: this.options.openAiHeaders,
-			})
-		} else {
-			this.client = new OpenAI({
-				baseURL: this.options.openAiBaseUrl,
-				apiKey: this.options.openAiApiKey,
-				defaultHeaders: this.options.openAiHeaders,
-			})
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.openAiApiKey) {
+				throw new Error("OpenAI API key is required")
+			}
+			try {
+				// Azure API shape slightly differs from the core API shape: https://github.com/openai/openai-node?tab=readme-ov-file#microsoft-azure-openai
+				// Use azureApiVersion to determine if this is an Azure endpoint, since the URL may not always contain 'azure.com'
+				if (
+					this.options.azureApiVersion ||
+					((this.options.openAiBaseUrl?.toLowerCase().includes("azure.com") ||
+						this.options.openAiBaseUrl?.toLowerCase().includes("azure.us")) &&
+						!this.options.openAiModelId?.toLowerCase().includes("deepseek"))
+				) {
+					this.client = new AzureOpenAI({
+						baseURL: this.options.openAiBaseUrl,
+						apiKey: this.options.openAiApiKey,
+						apiVersion: this.options.azureApiVersion || azureOpenAiDefaultApiVersion,
+						defaultHeaders: this.options.openAiHeaders,
+					})
+				} else {
+					this.client = new OpenAI({
+						baseURL: this.options.openAiBaseUrl,
+						apiKey: this.options.openAiApiKey,
+						defaultHeaders: this.options.openAiHeaders,
+					})
+				}
+			} catch (error: any) {
+				throw new Error(`Error creating OpenAI client: ${error.message}`)
+			}
 		}
+		return this.client
 	}
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const modelId = this.options.openAiModelId ?? ""
 		const isDeepseekReasoner = modelId.includes("deepseek-reasoner")
 		const isR1FormatRequired = this.options.openAiModelInfo?.isR1FormatRequired ?? false
@@ -68,7 +92,7 @@ export class OpenAiHandler implements ApiHandler {
 			reasoningEffort = (this.options.reasoningEffort as ChatCompletionReasoningEffort) || "medium"
 		}
 
-		const stream = await this.client.chat.completions.create({
+		const stream = await client.chat.completions.create({
 			model: modelId,
 			messages: openAiMessages,
 			temperature,

src/api/providers/openrouter.ts

@@ -3,35 +3,58 @@ import axios from "axios"
 import { setTimeout as setTimeoutPromise } from "node:timers/promises"
 import OpenAI from "openai"
 import { ApiHandler } from "../"
-import { ApiHandlerOptions, ModelInfo, openRouterDefaultModelId, openRouterDefaultModelInfo } from "@shared/api"
+import { ModelInfo, openRouterDefaultModelId, openRouterDefaultModelInfo } from "@shared/api"
 import { withRetry } from "../retry"
 import { createOpenRouterStream } from "../transform/openrouter-stream"
 import { ApiStream, ApiStreamUsageChunk } from "../transform/stream"
 import { OpenRouterErrorResponse } from "./types"
 
+interface OpenRouterHandlerOptions {
+	openRouterApiKey?: string
+	openRouterModelId?: string
+	openRouterModelInfo?: ModelInfo
+	openRouterProviderSorting?: string
+	reasoningEffort?: string
+	thinkingBudgetTokens?: number
+}
+
 export class OpenRouterHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
+	private options: OpenRouterHandlerOptions
+	private client: OpenAI | undefined
 	lastGenerationId?: string
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: OpenRouterHandlerOptions) {
 		this.options = options
-		this.client = new OpenAI({
-			baseURL: "https://openrouter.ai/api/v1",
-			apiKey: this.options.openRouterApiKey,
-			defaultHeaders: {
-				"HTTP-Referer": "https://cline.bot", // Optional, for including your app on openrouter.ai rankings.
-				"X-Title": "Cline", // Optional. Shows in rankings on openrouter.ai.
-			},
-		})
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.openRouterApiKey) {
+				throw new Error("OpenRouter API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					baseURL: "https://openrouter.ai/api/v1",
+					apiKey: this.options.openRouterApiKey,
+					defaultHeaders: {
+						"HTTP-Referer": "https://cline.bot", // Optional, for including your app on openrouter.ai rankings.
+						"X-Title": "Cline", // Optional. Shows in rankings on openrouter.ai.
+					},
+				})
+			} catch (error: any) {
+				throw new Error(`Error creating OpenRouter client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		this.lastGenerationId = undefined
 
 		const stream = await createOpenRouterStream(
-			this.client,
+			client,
 			systemPrompt,
 			messages,
 			this.getModel(),
@@ -190,9 +213,6 @@ export class OpenRouterHandler implements ApiHandler {
 
 	getModel(): { id: string; info: ModelInfo } {
 		let modelId = this.options.openRouterModelId
-		if (modelId === "x-ai/grok-3") {
-			modelId = "x-ai/grok-3-beta"
-		}
 		const modelInfo = this.options.openRouterModelInfo
 		if (modelId && modelInfo) {
 			return { id: modelId, info: modelInfo }

src/api/providers/qwen.ts

@@ -2,7 +2,6 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import OpenAI from "openai"
 import { ApiHandler } from "../"
 import {
-	ApiHandlerOptions,
 	ModelInfo,
 	mainlandQwenModels,
 	internationalQwenModels,
@@ -16,19 +15,39 @@ import { ApiStream } from "../transform/stream"
 import { convertToR1Format } from "../transform/r1-format"
 import { withRetry } from "../retry"
 
-export class QwenHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
+interface QwenHandlerOptions {
+	qwenApiKey?: string
+	qwenApiLine?: string
+	apiModelId?: string
+	thinkingBudgetTokens?: number
+}
 
-	constructor(options: ApiHandlerOptions) {
+export class QwenHandler implements ApiHandler {
+	private options: QwenHandlerOptions
+	private client: OpenAI | undefined
+
+	constructor(options: QwenHandlerOptions) {
 		this.options = options
-		this.client = new OpenAI({
-			baseURL:
-				this.options.qwenApiLine === "china"
-					? "https://dashscope.aliyuncs.com/compatible-mode/v1"
-					: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
-			apiKey: this.options.qwenApiKey,
-		})
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.qwenApiKey) {
+				throw new Error("Alibaba API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					baseURL:
+						this.options.qwenApiLine === "china"
+							? "https://dashscope.aliyuncs.com/compatible-mode/v1"
+							: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
+					apiKey: this.options.qwenApiKey,
+				})
+			} catch (error: any) {
+				throw new Error(`Error creating Alibaba client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	getModel(): { id: MainlandQwenModelId | InternationalQwenModelId; info: ModelInfo } {
@@ -51,6 +70,7 @@ export class QwenHandler implements ApiHandler {
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const model = this.getModel()
 		const isDeepseekReasoner = model.id.includes("deepseek-r1")
 		const isReasoningModelFamily = model.id.includes("qwen3") || ["qwen-plus-latest", "qwen-turbo-latest"].includes(model.id)
@@ -76,7 +96,7 @@ export class QwenHandler implements ApiHandler {
 			temperature = undefined
 		}
 
-		const stream = await this.client.chat.completions.create({
+		const stream = await client.chat.completions.create({
 			model: model.id,
 			max_completion_tokens: model.info.maxTokens,
 			messages: openAiMessages,

src/api/providers/requesty.ts

@@ -7,6 +7,14 @@ import { convertToOpenAiMessages } from "@api/transform/openai-format"
 import { calculateApiCostOpenAI } from "@utils/cost"
 import { ApiStream } from "@api/transform/stream"
 
+interface RequestyHandlerOptions {
+	requestyApiKey?: string
+	reasoningEffort?: string
+	thinkingBudgetTokens?: number
+	requestyModelId?: string
+	requestyModelInfo?: ModelInfo
+}
+
 // Requesty usage includes an extra field for Anthropic use cases.
 // Safely cast the prompt token details section to the appropriate structure.
 interface RequestyUsage extends OpenAI.CompletionUsage {
@@ -18,23 +26,37 @@ interface RequestyUsage extends OpenAI.CompletionUsage {
 }
 
 export class RequestyHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
+	private options: RequestyHandlerOptions
+	private client: OpenAI | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: RequestyHandlerOptions) {
 		this.options = options
-		this.client = new OpenAI({
-			baseURL: "https://router.requesty.ai/v1",
-			apiKey: this.options.requestyApiKey,
-			defaultHeaders: {
-				"HTTP-Referer": "https://cline.bot",
-				"X-Title": "Cline",
-			},
-		})
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.requestyApiKey) {
+				throw new Error("Requesty API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					baseURL: "https://router.requesty.ai/v1",
+					apiKey: this.options.requestyApiKey,
+					defaultHeaders: {
+						"HTTP-Referer": "https://cline.bot",
+						"X-Title": "Cline",
+					},
+				})
+			} catch (error: any) {
+				throw new Error(`Error creating Requesty client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const model = this.getModel()
 
 		const openAiMessages: OpenAI.Chat.ChatCompletionMessageParam[] = [
@@ -57,7 +79,7 @@ export class RequestyHandler implements ApiHandler {
 				: {}
 
 		// @ts-ignore-next-line
-		const stream = await this.client.chat.completions.create({
+		const stream = await client.chat.completions.create({
 			model: model.id,
 			max_tokens: model.info.maxTokens || undefined,
 			messages: openAiMessages,

src/api/providers/sambanova.ts

@@ -1,26 +1,45 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import OpenAI from "openai"
 import { withRetry } from "../retry"
-import { ApiHandlerOptions, ModelInfo, SambanovaModelId, sambanovaDefaultModelId, sambanovaModels } from "@shared/api"
+import { ModelInfo, SambanovaModelId, sambanovaDefaultModelId, sambanovaModels } from "@shared/api"
 import { ApiHandler } from "../index"
 import { convertToOpenAiMessages } from "@/api/transform/openai-format"
 import { ApiStream } from "@api/transform/stream"
 import { convertToR1Format } from "@api/transform/r1-format"
 
-export class SambanovaHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
+interface SambanovaHandlerOptions {
+	sambanovaApiKey?: string
+	apiModelId?: string
+}
 
-	constructor(options: ApiHandlerOptions) {
+export class SambanovaHandler implements ApiHandler {
+	private options: SambanovaHandlerOptions
+	private client: OpenAI | undefined
+
+	constructor(options: SambanovaHandlerOptions) {
 		this.options = options
-		this.client = new OpenAI({
-			baseURL: "https://api.sambanova.ai/v1",
-			apiKey: this.options.sambanovaApiKey,
-		})
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.sambanovaApiKey) {
+				throw new Error("SambaNova API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					baseURL: "https://api.sambanova.ai/v1",
+					apiKey: this.options.sambanovaApiKey,
+				})
+			} catch (error: any) {
+				throw new Error(`Error creating SambaNova client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const model = this.getModel()
 
 		let openAiMessages: OpenAI.Chat.ChatCompletionMessageParam[] = [
@@ -34,7 +53,7 @@ export class SambanovaHandler implements ApiHandler {
 			openAiMessages = convertToR1Format([{ role: "user", content: systemPrompt }, ...messages])
 		}
 
-		const stream = await this.client.chat.completions.create({
+		const stream = await client.chat.completions.create({
 			model: this.getModel().id,
 			messages: openAiMessages,
 			temperature: 0,

src/api/providers/sapaicore.ts

@@ -2,10 +2,19 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import axios from "axios"
 import OpenAI from "openai"
 import { ApiHandler } from "../"
-import { ApiHandlerOptions, ModelInfo, sapAiCoreDefaultModelId, SapAiCoreModelId, sapAiCoreModels } from "../../shared/api"
+import { ModelInfo, sapAiCoreDefaultModelId, SapAiCoreModelId, sapAiCoreModels } from "../../shared/api"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 
+interface SapAiCoreHandlerOptions {
+	sapAiCoreClientId?: string
+	sapAiCoreClientSecret?: string
+	sapAiCoreTokenUrl?: string
+	sapAiResourceGroup?: string
+	sapAiCoreBaseUrl?: string
+	apiModelId?: string
+}
+
 interface Deployment {
 	id: string
 	name: string
@@ -19,11 +28,11 @@ interface Token {
 	expires_at: number
 }
 export class SapAiCoreHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: SapAiCoreHandlerOptions
 	private token?: Token
 	private deployments?: Deployment[]
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: SapAiCoreHandlerOptions) {
 		this.options = options
 	}
 
@@ -60,6 +69,7 @@ export class SapAiCoreHandler implements ApiHandler {
 			Authorization: `Bearer ${token}`,
 			"AI-Resource-Group": this.options.sapAiResourceGroup || "default",
 			"Content-Type": "application/json",
+			"AI-Client-Type": "Cline",
 		}
 
 		const url = `${this.options.sapAiCoreBaseUrl}/v2/lm/deployments?$top=10000&$skip=0`
@@ -116,6 +126,7 @@ export class SapAiCoreHandler implements ApiHandler {
 			Authorization: `Bearer ${token}`,
 			"AI-Resource-Group": this.options.sapAiResourceGroup || "default",
 			"Content-Type": "application/json",
+			"AI-Client-Type": "Cline",
 		}
 
 		const model = this.getModel()
@@ -123,6 +134,7 @@ export class SapAiCoreHandler implements ApiHandler {
 
 		const anthropicModels = [
 			"anthropic--claude-4-sonnet",
+			"anthropic--claude-4-opus",
 			"anthropic--claude-3.7-sonnet",
 			"anthropic--claude-3.5-sonnet",
 			"anthropic--claude-3-sonnet",
@@ -132,12 +144,18 @@ export class SapAiCoreHandler implements ApiHandler {
 
 		const openAIModels = ["gpt-4o", "gpt-4", "gpt-4o-mini", "o1", "gpt-4.1", "gpt-4.1-nano", "o3-mini", "o3", "o4-mini"]
 
+		const geminiModels = ["gemini-2.5-flash", "gemini-2.5-pro"]
+
 		let url: string
 		let payload: any
 		if (anthropicModels.includes(model.id)) {
 			url = `${this.options.sapAiCoreBaseUrl}/v2/inference/deployments/${deploymentId}/invoke-with-response-stream`
 
-			if (model.id === "anthropic--claude-3.7-sonnet" || model.id === "anthropic--claude-4-sonnet") {
+			if (
+				model.id === "anthropic--claude-4-sonnet" ||
+				model.id === "anthropic--claude-4-opus" ||
+				model.id === "anthropic--claude-3.7-sonnet"
+			) {
 				url = `${this.options.sapAiCoreBaseUrl}/v2/inference/deployments/${deploymentId}/converse-stream`
 				payload = {
 					inferenceConfig: {
@@ -182,6 +200,9 @@ export class SapAiCoreHandler implements ApiHandler {
 				delete payload.stream
 				delete payload.stream_options
 			}
+		} else if (geminiModels.includes(model.id)) {
+			url = `${this.options.sapAiCoreBaseUrl}/v2/inference/deployments/${deploymentId}/models/${model.id}:streamGenerateContent`
+			payload = this.convertToGeminiFormat(systemPrompt, messages)
 		} else {
 			throw new Error(`Unsupported model: ${model.id}`)
 		}
@@ -222,8 +243,14 @@ export class SapAiCoreHandler implements ApiHandler {
 				}
 			} else if (openAIModels.includes(model.id)) {
 				yield* this.streamCompletionGPT(response.data, model)
-			} else if (model.id === "anthropic--claude-3.7-sonnet" || model.id === "anthropic--claude-4-sonnet") {
+			} else if (
+				model.id === "anthropic--claude-4-sonnet" ||
+				model.id === "anthropic--claude-4-opus" ||
+				model.id === "anthropic--claude-3.7-sonnet"
+			) {
 				yield* this.streamCompletionSonnet37(response.data, model)
+			} else if (geminiModels.includes(model.id)) {
+				yield* this.streamCompletionGemini(response.data, model)
 			} else {
 				yield* this.streamCompletion(response.data, model)
 			}
@@ -267,7 +294,6 @@ export class SapAiCoreHandler implements ApiHandler {
 						const jsonData = line.slice(6)
 						try {
 							const data = JSON.parse(jsonData)
-							console.log("Received data:", data)
 							if (data.type === "message_start") {
 								usage.input_tokens = data.message.usage.input_tokens
 								yield {
@@ -330,7 +356,6 @@ export class SapAiCoreHandler implements ApiHandler {
 						try {
 							// Parse the incoming JSON data from the stream
 							const data = JSON.parse(toStrictJson(jsonData))
-							console.log("Received data:", data)
 
 							// Handle metadata (token usage)
 							if (data.metadata?.usage) {
@@ -406,7 +431,6 @@ export class SapAiCoreHandler implements ApiHandler {
 						const jsonData = line.slice(6)
 						try {
 							const data = JSON.parse(jsonData)
-							console.log("Received GPT data:", data)
 
 							if (data.choices && data.choices.length > 0) {
 								const choice = data.choices[0]
@@ -430,7 +454,7 @@ export class SapAiCoreHandler implements ApiHandler {
 								}
 							}
 
-							if (data.choices && data.choices[0].finish_reason === "stop") {
+							if (data.choices?.[0]?.finish_reason === "stop") {
 								// Final usage yield, if not already provided
 								if (!data.usage) {
 									yield {
@@ -452,6 +476,88 @@ export class SapAiCoreHandler implements ApiHandler {
 		}
 	}
 
+	private async *streamCompletionGemini(
+		stream: any,
+		model: { id: SapAiCoreModelId; info: ModelInfo },
+	): AsyncGenerator<any, void, unknown> {
+		let promptTokens = 0
+		let outputTokens = 0
+		let cacheReadTokens = 0
+		let thoughtsTokenCount = 0
+
+		try {
+			for await (const chunk of stream) {
+				const lines = chunk.toString().split("\n").filter(Boolean)
+				for (const line of lines) {
+					if (line.startsWith("data: ")) {
+						const jsonData = line.slice(6)
+						try {
+							const data = JSON.parse(jsonData)
+							const candidateForThoughts = data?.candidates?.[0]
+							const partsForThoughts = candidateForThoughts?.content?.parts
+							let thoughts = ""
+
+							if (partsForThoughts) {
+								for (const part of partsForThoughts) {
+									const { thought, text } = part
+									if (thought && text) {
+										thoughts += text + "\n"
+									}
+								}
+							}
+
+							if (thoughts.trim() !== "") {
+								yield {
+									type: "reasoning",
+									reasoning: thoughts.trim(),
+								}
+							}
+
+							if (data.text) {
+								yield {
+									type: "text",
+									text: data.text,
+								}
+							}
+
+							if (data.candidates && data.candidates[0]?.content?.parts) {
+								for (const part of data.candidates[0].content.parts) {
+									if (part.text && !part.thought) {
+										// Only non-thought text
+										yield {
+											type: "text",
+											text: part.text,
+										}
+									}
+								}
+							}
+
+							if (data.usageMetadata) {
+								promptTokens = data.usageMetadata.promptTokenCount ?? promptTokens
+								outputTokens = data.usageMetadata.candidatesTokenCount ?? outputTokens
+								thoughtsTokenCount = data.usageMetadata.thoughtsTokenCount ?? thoughtsTokenCount
+								cacheReadTokens = data.usageMetadata.cachedContentTokenCount ?? cacheReadTokens
+
+								yield {
+									type: "usage",
+									inputTokens: promptTokens - cacheReadTokens,
+									outputTokens,
+									thoughtsTokenCount,
+									cacheReadTokens,
+								}
+							}
+						} catch (error) {
+							console.error("Failed to parse Gemini JSON data:", error)
+						}
+					}
+				}
+			}
+		} catch (error) {
+			console.error("Error streaming Gemini completion:", error)
+			throw error
+		}
+	}
+
 	createUserReadableRequest(
 		userContent: Array<
 			Anthropic.TextBlockParam | Anthropic.ImageBlockParam | Anthropic.ToolUseBlockParam | Anthropic.ToolResultBlockParam
@@ -486,6 +592,50 @@ export class SapAiCoreHandler implements ApiHandler {
 		throw new Error(`Unsupported image format: ${format}`)
 	}
 
+	private convertToGeminiFormat(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]) {
+		const contents = messages.map(this.convertAnthropicMessageToGemini)
+
+		const payload = {
+			contents,
+			systemInstruction: {
+				parts: [
+					{
+						text: systemPrompt,
+					},
+				],
+			},
+			generationConfig: {
+				maxOutputTokens: this.getModel().info.maxTokens,
+				temperature: 0.0,
+			},
+		}
+
+		return payload
+	}
+
+	private convertAnthropicMessageToGemini(message: Anthropic.Messages.MessageParam) {
+		const role = message.role === "assistant" ? "model" : "user"
+		const parts = []
+
+		if (typeof message.content === "string") {
+			parts.push({ text: message.content })
+		} else if (Array.isArray(message.content)) {
+			for (const block of message.content) {
+				if (block.type === "text") {
+					parts.push({ text: block.text })
+				} else if (block.type === "image") {
+					parts.push({
+						inlineData: {
+							mimeType: block.source.media_type,
+							data: block.source.data,
+						},
+					})
+				}
+			}
+		}
+
+		return { role, parts }
+	}
 	private formatAnthropicMessages(messages: Anthropic.Messages.MessageParam[]): any[] {
 		return messages.map((m) => {
 			const contentBlocks: any[] = []

src/api/providers/together.ts

@@ -1,26 +1,45 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import OpenAI from "openai"
 import { withRetry } from "../retry"
-import { ApiHandlerOptions, ModelInfo, openAiModelInfoSaneDefaults } from "@shared/api"
+import { ModelInfo, openAiModelInfoSaneDefaults } from "@shared/api"
 import { ApiHandler } from "../index"
 import { convertToOpenAiMessages } from "@api/transform/openai-format"
 import { ApiStream } from "@api/transform/stream"
 import { convertToR1Format } from "@api/transform/r1-format"
 
-export class TogetherHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
+interface TogetherHandlerOptions {
+	togetherApiKey?: string
+	togetherModelId?: string
+}
 
-	constructor(options: ApiHandlerOptions) {
+export class TogetherHandler implements ApiHandler {
+	private options: TogetherHandlerOptions
+	private client: OpenAI | undefined
+
+	constructor(options: TogetherHandlerOptions) {
 		this.options = options
-		this.client = new OpenAI({
-			baseURL: "https://api.together.xyz/v1",
-			apiKey: this.options.togetherApiKey,
-		})
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.togetherApiKey) {
+				throw new Error("Together API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					baseURL: "https://api.together.xyz/v1",
+					apiKey: this.options.togetherApiKey,
+				})
+			} catch (error: any) {
+				throw new Error(`Error creating Together client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const modelId = this.options.togetherModelId ?? ""
 		const isDeepseekReasoner = modelId.includes("deepseek-reasoner")
 
@@ -33,7 +52,7 @@ export class TogetherHandler implements ApiHandler {
 			openAiMessages = convertToR1Format([{ role: "user", content: systemPrompt }, ...messages])
 		}
 
-		const stream = await this.client.chat.completions.create({
+		const stream = await client.chat.completions.create({
 			model: modelId,
 			messages: openAiMessages,
 			temperature: 0,

src/api/providers/vertex.ts

@@ -6,26 +6,60 @@ import { ApiHandlerOptions, ModelInfo, vertexDefaultModelId, VertexModelId, vert
 import { ApiStream } from "@api/transform/stream"
 import { GeminiHandler } from "./gemini"
 
+interface VertexHandlerOptions {
+	vertexProjectId?: string
+	vertexRegion?: string
+	apiModelId?: string
+	thinkingBudgetTokens?: number
+	geminiApiKey?: string
+	geminiBaseUrl?: string
+	taskId?: string
+}
+
 export class VertexHandler implements ApiHandler {
-	private geminiHandler: GeminiHandler
-	private clientAnthropic: AnthropicVertex
-	private options: ApiHandlerOptions
+	private geminiHandler: GeminiHandler | undefined
+	private clientAnthropic: AnthropicVertex | undefined
+	private options: VertexHandlerOptions
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: VertexHandlerOptions) {
 		this.options = options
+	}
 
-		// Create a GeminiHandler with isVertex flag for Gemini models
-		this.geminiHandler = new GeminiHandler({
-			...options,
-			isVertex: true,
-		})
+	private ensureGeminiHandler(): GeminiHandler {
+		if (!this.geminiHandler) {
+			try {
+				// Create a GeminiHandler with isVertex flag for Gemini models
+				this.geminiHandler = new GeminiHandler({
+					...this.options,
+					isVertex: true,
+				})
+			} catch (error: any) {
+				throw new Error(`Error creating Vertex AI Gemini handler: ${error.message}`)
+			}
+		}
+		return this.geminiHandler
+	}
 
-		// Initialize Anthropic client for Claude models
-		this.clientAnthropic = new AnthropicVertex({
-			projectId: this.options.vertexProjectId,
-			// https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/use-claude#regions
-			region: this.options.vertexRegion,
-		})
+	private ensureAnthropicClient(): AnthropicVertex {
+		if (!this.clientAnthropic) {
+			if (!this.options.vertexProjectId) {
+				throw new Error("Vertex AI project ID is required")
+			}
+			if (!this.options.vertexRegion) {
+				throw new Error("Vertex AI region is required")
+			}
+			try {
+				// Initialize Anthropic client for Claude models
+				this.clientAnthropic = new AnthropicVertex({
+					projectId: this.options.vertexProjectId,
+					// https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/use-claude#regions
+					region: this.options.vertexRegion,
+				})
+			} catch (error: any) {
+				throw new Error(`Error creating Vertex AI Anthropic client: ${error.message}`)
+			}
+		}
+		return this.clientAnthropic
 	}
 
 	@withRetry()
@@ -35,10 +69,13 @@ export class VertexHandler implements ApiHandler {
 
 		// For Gemini models, use the GeminiHandler
 		if (!modelId.includes("claude")) {
-			yield* this.geminiHandler.createMessage(systemPrompt, messages)
+			const geminiHandler = this.ensureGeminiHandler()
+			yield* geminiHandler.createMessage(systemPrompt, messages)
 			return
 		}
 
+		const clientAnthropic = this.ensureAnthropicClient()
+
 		// Claude implementation
 		let budget_tokens = this.options.thinkingBudgetTokens || 0
 		const reasoningOn =
@@ -63,7 +100,7 @@ export class VertexHandler implements ApiHandler {
 				)
 				const lastUserMsgIndex = userMsgIndices[userMsgIndices.length - 1] ?? -1
 				const secondLastMsgUserIndex = userMsgIndices[userMsgIndices.length - 2] ?? -1
-				stream = await this.clientAnthropic.beta.messages.create(
+				stream = await clientAnthropic.beta.messages.create(
 					{
 						model: modelId,
 						max_tokens: model.info.maxTokens || 8192,
@@ -125,7 +162,7 @@ export class VertexHandler implements ApiHandler {
 				break
 			}
 			default: {
-				stream = await this.clientAnthropic.beta.messages.create({
+				stream = await clientAnthropic.beta.messages.create({
 					model: modelId,
 					max_tokens: model.info.maxTokens || 8192,
 					temperature: 0,

src/api/providers/vscode-lm.ts

@@ -5,10 +5,14 @@ import { calculateApiCostAnthropic } from "@utils/cost"
 import { ApiStream } from "@api/transform/stream"
 import { convertToVsCodeLmMessages } from "@api/transform/vscode-lm-format"
 import { SELECTOR_SEPARATOR, stringifyVsCodeLmModelSelector } from "@shared/vsCodeSelectorUtils"
-import { ApiHandlerOptions, ModelInfo, openAiModelInfoSaneDefaults } from "@shared/api"
+import { ModelInfo, openAiModelInfoSaneDefaults } from "@shared/api"
 import type { LanguageModelChatSelector as LanguageModelChatSelectorFromTypes } from "./types"
 import { withRetry } from "../retry"
 
+interface VsCodeLmHandlerOptions {
+	vsCodeLmModelSelector?: any
+}
+
 // Cline does not update VSCode type definitions or engine requirements to maintain compatibility.
 // This declaration (as seen in src/integrations/TerminalManager.ts) provides types for the Language Model API in newer versions of VSCode.
 // Extracted from https://github.com/microsoft/vscode/blob/131ee0ef660d600cd0a7e6058375b281553abe20/src/vscode-dts/vscode.d.ts
@@ -124,12 +128,12 @@ declare module "vscode" {
  * ```
  */
 export class VsCodeLmHandler implements ApiHandler, SingleCompletionHandler {
-	private options: ApiHandlerOptions
+	private options: VsCodeLmHandlerOptions
 	private client: vscode.LanguageModelChat | null
 	private disposable: vscode.Disposable | null
 	private currentRequestCancellation: vscode.CancellationTokenSource | null
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: VsCodeLmHandlerOptions) {
 		this.options = options
 		this.client = null
 		this.disposable = null

src/api/providers/xai.ts

@@ -1,26 +1,46 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import OpenAI from "openai"
 import { ApiHandler } from "../"
-import { ApiHandlerOptions, XAIModelId, ModelInfo, xaiDefaultModelId, xaiModels } from "@shared/api"
+import { XAIModelId, ModelInfo, xaiDefaultModelId, xaiModels } from "@shared/api"
 import { convertToOpenAiMessages } from "@api/transform/openai-format"
 import { ApiStream } from "@api/transform/stream"
 import { ChatCompletionReasoningEffort } from "openai/resources/chat/completions"
 import { withRetry } from "../retry"
 
-export class XAIHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private client: OpenAI
+interface XAIHandlerOptions {
+	xaiApiKey?: string
+	reasoningEffort?: string
+	apiModelId?: string
+}
 
-	constructor(options: ApiHandlerOptions) {
+export class XAIHandler implements ApiHandler {
+	private options: XAIHandlerOptions
+	private client: OpenAI | undefined
+
+	constructor(options: XAIHandlerOptions) {
 		this.options = options
-		this.client = new OpenAI({
-			baseURL: "https://api.x.ai/v1",
-			apiKey: this.options.xaiApiKey,
-		})
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.xaiApiKey) {
+				throw new Error("xAI API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					baseURL: "https://api.x.ai/v1",
+					apiKey: this.options.xaiApiKey,
+				})
+			} catch (error: any) {
+				throw new Error(`Error creating xAI client: ${error.message}`)
+			}
+		}
+		return this.client
 	}
 
 	@withRetry()
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
 		const modelId = this.getModel().id
 		// ensure reasoning effort is either "low" or "high" for grok-3-mini
 		let reasoningEffort: ChatCompletionReasoningEffort | undefined
@@ -30,7 +50,7 @@ export class XAIHandler implements ApiHandler {
 				reasoningEffort = undefined
 			}
 		}
-		const stream = await this.client.chat.completions.create({
+		const stream = await client.chat.completions.create({
 			model: modelId,
 			max_completion_tokens: this.getModel().info.maxTokens,
 			temperature: 0,

src/core/assistant-message/diff.test.ts

@@ -156,6 +156,45 @@ replaced
 			expected: "line2\nreplaced\nline4",
 			isFinal: true,
 		},
+		{
+			name: "malformed diff - missing separator",
+			original: "line1\nline2\nline3",
+			diff: `------- SEARCH
+line2
++++++++ REPLACE
+replaced`,
+			shouldThrow: true,
+		},
+		{
+			name: "malformed diff - trailing space on separator",
+			original: "line1\nline2\nline3",
+			diff: `------- SEARCH
+line2
+======= 
+replaced
++++++++ REPLACE`,
+			shouldThrow: true,
+		},
+		{
+			name: "malformed diff - double replace markers",
+			original: "line1\nline2\nline3",
+			diff: `------- SEARCH
+line2
++++++++ REPLACE
+first replacement
++++++++ REPLACE`,
+			shouldThrow: true,
+		},
+		{
+			name: "malformed diff - malformed separator with dashes",
+			original: "line1\nline2\nline3",
+			diff: `------- SEARCH
+line2
+------- =======
+replaced
++++++++ REPLACE`,
+			shouldThrow: true,
+		},
 	]
 	//.filter(({name}) => name === "multiple ordered replacements")
 	//.filter(({name}) => name === "delete then replace")

src/core/assistant-message/diff.ts

@@ -380,6 +380,10 @@ async function constructNewFileContentV1(diffContent: string, originalContent: s
 		if (isReplaceBlockEnd(line)) {
 			// Finished one replace block
 
+			if (searchMatchIndex === -1) {
+				throw new Error(`The SEARCH block:\n${currentSearchContent.trimEnd()}\n...is malformatted.`)
+			}
+
 			// Store this replacement
 			replacements.push({
 				start: searchMatchIndex,

src/core/context/context-tracking/FileContextTracker.ts

@@ -36,17 +36,6 @@ export class FileContextTracker {
 		this.taskId = taskId
 	}
 
-	/**
-	 * Gets the current working directory or returns undefined if it cannot be determined
-	 */
-	private async getCwd(): Promise<string | undefined> {
-		const cwd = await getCwd(undefined)
-		if (!cwd) {
-			console.info("No workspace folder available - cannot determine current working directory")
-		}
-		return cwd
-	}
-
 	/**
 	 * File watchers are set up for each file that is tracked in the task metadata.
 	 */
@@ -56,8 +45,9 @@ export class FileContextTracker {
 			return
 		}
 
-		const cwd = await this.getCwd()
+		const cwd = await getCwd()
 		if (!cwd) {
+			console.info("No workspace folder available - cannot determine current working directory")
 			return
 		}
 
@@ -87,8 +77,9 @@ export class FileContextTracker {
 	 */
 	async trackFileContext(filePath: string, operation: "read_tool" | "user_edited" | "cline_edited" | "file_mentioned") {
 		try {
-			const cwd = await this.getCwd()
+			const cwd = await getCwd()
 			if (!cwd) {
+				console.info("No workspace folder available - cannot determine current working directory")
 				return
 			}
 
@@ -244,7 +235,9 @@ export class FileContextTracker {
 	async storePendingFileContextWarning(files: string[]): Promise<void> {
 		try {
 			const key = `pendingFileContextWarning_${this.taskId}`
-			await updateWorkspaceState(this.context, key, files)
+			// NOTE: Using 'as any' because dynamic keys like pendingFileContextWarning_${taskId}
+			// are legitimate workspace state keys but don't fit the strict LocalStateKey type system
+			await updateWorkspaceState(this.context, key as any, files)
 		} catch (error) {
 			console.error("Error storing pending file context warning:", error)
 		}
@@ -256,7 +249,7 @@ export class FileContextTracker {
 	async retrievePendingFileContextWarning(): Promise<string[] | undefined> {
 		try {
 			const key = `pendingFileContextWarning_${this.taskId}`
-			const files = (await getWorkspaceState(this.context, key)) as string[]
+			const files = (await getWorkspaceState(this.context, key as any)) as string[]
 			return files
 		} catch (error) {
 			console.error("Error retrieving pending file context warning:", error)
@@ -271,7 +264,7 @@ export class FileContextTracker {
 		try {
 			const files = await this.retrievePendingFileContextWarning()
 			if (files) {
-				await updateWorkspaceState(this.context, `pendingFileContextWarning_${this.taskId}`, undefined)
+				await updateWorkspaceState(this.context, `pendingFileContextWarning_${this.taskId}` as any, undefined)
 				return files
 			}
 		} catch (error) {
@@ -302,7 +295,7 @@ export class FileContextTracker {
 
 			if (orphanedPendingContextTasks.length > 0) {
 				for (const key of orphanedPendingContextTasks) {
-					await updateWorkspaceState(context, key, undefined)
+					await updateWorkspaceState(context, key as any, undefined)
 				}
 			}
 

src/core/controller/account/accountLoginClicked.ts

@@ -1,8 +1,9 @@
-import * as vscode from "vscode"
-import crypto from "crypto"
 import { Controller } from "../index"
-import { storeSecret } from "../../storage/state"
+import { AuthService } from "@/services/auth/AuthService"
 import { EmptyRequest, String } from "../../../shared/proto/common"
+import { openExternal } from "@utils/env"
+
+const authService = AuthService.getInstance()
 
 /**
  * Handles the user clicking the login link in the UI.
@@ -13,21 +14,5 @@ import { EmptyRequest, String } from "../../../shared/proto/common"
  * @returns The login URL as a string.
  */
 export async function accountLoginClicked(controller: Controller, _: EmptyRequest): Promise<String> {
-	// Generate nonce for state validation
-	const nonce = crypto.randomBytes(32).toString("hex")
-	await storeSecret(controller.context, "authNonce", nonce)
-
-	// Open browser for authentication with state param
-	console.log("Login button clicked in account page")
-	console.log("Opening auth page with state param")
-
-	const uriScheme = vscode.env.uriScheme
-
-	const authUrl = vscode.Uri.parse(
-		`https://app.cline.bot/auth?state=${encodeURIComponent(nonce)}&callback_url=${encodeURIComponent(`${uriScheme || "vscode"}://saoudrizwan.claude-dev/auth`)}`,
-	)
-	await vscode.env.openExternal(authUrl)
-	return String.create({
-		value: authUrl.toString(),
-	})
+	return await authService.createAuthRequest()
 }

src/core/controller/account/accountLogoutClicked.ts

@@ -1,7 +1,9 @@
+import { AuthService } from "@/services/auth/AuthService"
 import { Empty } from "../../../shared/proto/common"
 import type { EmptyRequest } from "../../../shared/proto/common"
 import type { Controller } from "../index"
 
+const authService = AuthService.getInstance()
 /**
  * Handles the account logout action
  * @param controller The controller instance
@@ -10,5 +12,6 @@ import type { Controller } from "../index"
  */
 export async function accountLogoutClicked(controller: Controller, _request: EmptyRequest): Promise<Empty> {
 	await controller.handleSignOut()
+	await authService.handleDeauth()
 	return Empty.create({})
 }

src/core/controller/account/authStateChanged.ts

@@ -1,4 +1,4 @@
-import { AuthStateChangedRequest, AuthStateChanged } from "@shared/proto/account"
+import { AuthStateChangedRequest, AuthState } from "@shared/proto/account"
 import type { Controller } from "../index"
 import { updateGlobalState } from "../../storage/state"
 
@@ -9,13 +9,13 @@ import { updateGlobalState } from "../../storage/state"
  * @param request The auth state change request
  * @returns The updated user info
  */
-export async function authStateChanged(controller: Controller, request: AuthStateChangedRequest): Promise<AuthStateChanged> {
+export async function authStateChanged(controller: Controller, request: AuthStateChangedRequest): Promise<AuthState> {
 	try {
 		// Store the user info directly in global state
 		await updateGlobalState(controller.context, "userInfo", request.user)
 
 		// Return the same user info
-		return AuthStateChanged.create({ user: request.user })
+		return AuthState.create({ user: request.user })
 	} catch (error) {
 		console.error(`Failed to update auth state: ${error}`)
 		throw error

src/core/controller/account/getOrganizationCredits.ts

@@ -0,0 +1,50 @@
+import type { Controller } from "../index"
+import { GetOrganizationCreditsRequest, OrganizationCreditsData, OrganizationUsageTransaction } from "@shared/proto/account"
+
+/**
+ * Handles fetching all organization credits data (balance, usage, payments)
+ * @param controller The controller instance
+ * @param request Organization credits request
+ * @returns Organization credits data response
+ */
+export async function getOrganizationCredits(
+	controller: Controller,
+	request: GetOrganizationCreditsRequest,
+): Promise<OrganizationCreditsData> {
+	try {
+		if (!controller.accountService) {
+			throw new Error("Account service not available")
+		}
+
+		// Call the individual RPC variants in parallel
+		const [balanceData, usageTransactions] = await Promise.all([
+			controller.accountService.fetchOrganizationCreditsRPC(request.organizationId),
+			controller.accountService.fetchOrganizationUsageTransactionsRPC(request.organizationId),
+		])
+
+		return OrganizationCreditsData.create({
+			balance: balanceData ? { currentBalance: balanceData.balance / 100 } : { currentBalance: 0 },
+			organizationId: balanceData?.organizationId || "",
+			usageTransactions:
+				usageTransactions?.map((tx) =>
+					OrganizationUsageTransaction.create({
+						aiInferenceProviderName: tx.aiInferenceProviderName,
+						aiModelName: tx.aiModelName,
+						aiModelTypeName: tx.aiModelTypeName,
+						completionTokens: tx.completionTokens,
+						costUsd: tx.costUsd,
+						createdAt: tx.createdAt,
+						creditsUsed: tx.creditsUsed,
+						generationId: tx.generationId,
+						organizationId: tx.organizationId,
+						promptTokens: tx.promptTokens,
+						totalTokens: tx.totalTokens,
+						userId: tx.userId,
+					}),
+				) || [],
+		})
+	} catch (error) {
+		console.error(`Failed to fetch organization credits data: ${error}`)
+		throw error
+	}
+}

src/core/controller/account/getUserCredits.ts

@@ -8,7 +8,7 @@ import { UserCreditsData } from "@shared/proto/account"
  * @param request Empty request
  * @returns User credits data response
  */
-export async function fetchUserCreditsData(controller: Controller, request: EmptyRequest): Promise<UserCreditsData> {
+export async function getUserCredits(controller: Controller, request: EmptyRequest): Promise<UserCreditsData> {
 	try {
 		if (!controller.accountService) {
 			throw new Error("Account service not available")
@@ -21,11 +21,10 @@ export async function fetchUserCreditsData(controller: Controller, request: Empt
 			controller.accountService.fetchPaymentTransactionsRPC(),
 		])
 
-		// Since generated types match exactly, no conversion needed!
 		return UserCreditsData.create({
-			balance: balance ? { currentBalance: balance.currentBalance } : { currentBalance: 0 },
-			usageTransactions: usageTransactions || [],
-			paymentTransactions: paymentTransactions || [],
+			balance: balance ? { currentBalance: balance.balance / 100 } : { currentBalance: 0 },
+			usageTransactions: usageTransactions,
+			paymentTransactions: paymentTransactions,
 		})
 	} catch (error) {
 		console.error(`Failed to fetch user credits data: ${error}`)

src/core/controller/account/getUserOrganizations.ts

@@ -0,0 +1,35 @@
+import type { Controller } from "../index"
+import type { EmptyRequest } from "@shared/proto/common"
+import { UserOrganization, UserOrganizationsResponse } from "@shared/proto/account"
+
+/**
+ * Handles fetching all user credits data (balance, usage, payments)
+ * @param controller The controller instance
+ * @param request Empty request
+ * @returns User credits data response
+ */
+export async function getUserOrganizations(controller: Controller, request: EmptyRequest): Promise<UserOrganizationsResponse> {
+	try {
+		if (!controller.accountService) {
+			throw new Error("Account service not available")
+		}
+
+		// Fetch user organizations from the account service
+		const organizations = await controller.accountService.fetchUserOrganizationsRPC()
+
+		return UserOrganizationsResponse.create({
+			organizations:
+				organizations?.map((org) =>
+					UserOrganization.create({
+						active: org.active,
+						memberId: org.memberId,
+						name: org.name,
+						organizationId: org.organizationId,
+						roles: org.roles ? [...org.roles] : [],
+					}),
+				) || [],
+		})
+	} catch (error) {
+		throw error
+	}
+}

src/core/controller/account/setUserOrganization.ts

@@ -0,0 +1,24 @@
+import type { Controller } from "../index"
+import { Empty } from "@shared/proto/common"
+import { UserOrganizationUpdateRequest } from "@shared/proto/account"
+
+/**
+ * Handles setting the user's active organization
+ * @param controller The controller instance
+ * @param request UserOrganization to set as active
+ * @returns Empty response
+ */
+export async function setUserOrganization(controller: Controller, request: UserOrganizationUpdateRequest): Promise<Empty> {
+	try {
+		if (!controller.accountService) {
+			throw new Error("Account service not available")
+		}
+
+		// Switch to the specified organization using the account service
+		await controller.accountService.switchAccount(request.organizationId)
+
+		return Empty.create({})
+	} catch (error) {
+		throw error
+	}
+}

src/core/controller/account/subscribeToAuthCallback.ts

@@ -1,59 +0,0 @@
-import { Controller } from "../index"
-import { EmptyRequest } from "../../../shared/proto/common"
-import { String as ProtoString } from "../../../shared/proto/common"
-import { StreamingResponseHandler, getRequestRegistry } from "../grpc-handler"
-
-// Keep track of active authCallback subscriptions
-const activeAuthCallbackSubscriptions = new Set<StreamingResponseHandler>()
-
-/**
- * Subscribe to authCallback events
- * @param controller The controller instance
- * @param request The empty request
- * @param responseStream The streaming response handler
- * @param requestId The ID of the request (passed by the gRPC handler)
- */
-export async function subscribeToAuthCallback(
-	controller: Controller,
-	request: EmptyRequest,
-	responseStream: StreamingResponseHandler,
-	requestId?: string,
-): Promise<void> {
-	// Add this subscription to the active subscriptions
-	activeAuthCallbackSubscriptions.add(responseStream)
-
-	// Register cleanup when the connection is closed
-	const cleanup = () => {
-		activeAuthCallbackSubscriptions.delete(responseStream)
-	}
-
-	// Register the cleanup function with the request registry if we have a requestId
-	if (requestId) {
-		getRequestRegistry().registerRequest(requestId, cleanup, { type: "authCallback_subscription" }, responseStream)
-	}
-}
-
-/**
- * Send an authCallback event to all active subscribers
- * @param customToken The custom token for authentication
- */
-export async function sendAuthCallbackEvent(customToken: string): Promise<void> {
-	// Send the event to all active subscribers
-	const promises = Array.from(activeAuthCallbackSubscriptions).map(async (responseStream) => {
-		try {
-			const event: ProtoString = {
-				value: customToken,
-			}
-			await responseStream(
-				event,
-				false, // Not the last message
-			)
-		} catch (error) {
-			console.error("Error sending authCallback event:", error)
-			// Remove the subscription if there was an error
-			activeAuthCallbackSubscriptions.delete(responseStream)
-		}
-	})
-
-	await Promise.all(promises)
-}

src/core/controller/account/subscribeToAuthStatusUpdate.ts

@@ -0,0 +1,5 @@
+import { AuthService } from "../../../services/auth/AuthService"
+
+const authService = AuthService.getInstance()
+export const subscribeToAuthStatusUpdate = authService.subscribeToAuthStatusUpdate.bind(authService)
+export const sendAuthStatusUpdateEvent = authService.sendAuthStatusUpdate.bind(authService)

src/core/controller/file/createRuleFile.ts

@@ -6,8 +6,8 @@ import { createRuleFile as createRuleFileImpl } from "@core/context/instructions
 import * as vscode from "vscode"
 import * as path from "path"
 import { handleFileServiceRequest } from "./index"
-import { cwd } from "@core/task"
 import { refreshWorkflowToggles } from "@/core/context/instructions/user-instructions/workflows"
+import { getCwd, getDesktopDir } from "@/utils/path"
 
 /**
  * Creates a rule file in either global or workspace rules directory
@@ -32,6 +32,7 @@ export const createRuleFile: FileMethodHandler = async (controller: Controller,
 		throw new Error("Missing or invalid parameters")
 	}
 
+	const cwd = await getCwd(getDesktopDir())
 	const { filePath, fileExists } = await createRuleFileImpl(request.isGlobal, request.filename, cwd, request.type)
 
 	if (!filePath) {

src/core/controller/file/deleteRuleFile.ts

@@ -1,13 +1,9 @@
-import { Controller } from ".."
-import { RuleFileRequest, RuleFile } from "@shared/proto/file"
-import { FileMethodHandler } from "./index"
-import { refreshClineRulesToggles } from "@core/context/instructions/user-instructions/cline-rules"
 import { deleteRuleFile as deleteRuleFileImpl } from "@core/context/instructions/user-instructions/rule-helpers"
-import { refreshExternalRulesToggles } from "@core/context/instructions/user-instructions/external-rules"
-import { refreshWorkflowToggles } from "@core/context/instructions/user-instructions/workflows"
-import * as vscode from "vscode"
+import { RuleFile, RuleFileRequest } from "@shared/proto/file"
 import * as path from "path"
-import { cwd } from "@core/task"
+import * as vscode from "vscode"
+import { Controller } from ".."
+import { FileMethodHandler } from "./index"
 
 /**
  * Deletes a rule file from either global or workspace rules directory

src/core/controller/file/getRelativePaths.ts

@@ -1,10 +1,10 @@
-import { Controller } from ".."
-import { RelativePathsRequest, RelativePaths } from "@shared/proto/file"
-import { FileMethodHandler } from "./index"
-import * as vscode from "vscode"
+import { asRelativePath } from "@/utils/path"
+import { RelativePaths, RelativePathsRequest } from "@shared/proto/file"
 import * as path from "path"
-import { Metadata, StringRequest } from "@shared/proto/common"
-import { getHostBridgeProvider } from "@hosts/host-providers"
+import { URI } from "vscode-uri"
+import { Controller } from ".."
+import { FileMethodHandler } from "./index"
+import { isDirectory } from "@/utils/fs"
 
 /**
  * Converts a list of URIs to workspace-relative paths
@@ -13,48 +13,32 @@ import { getHostBridgeProvider } from "@hosts/host-providers"
  * @returns Response with resolved relative paths
  */
 export const getRelativePaths: FileMethodHandler = async (
-	controller: Controller,
+	_controller: Controller,
 	request: RelativePathsRequest,
 ): Promise<RelativePaths> => {
-	const resolvedPaths = await Promise.all(
-		request.uris.map(async (uriString) => {
-			try {
-				// Use the host URI service client instead of directly using vscode.Uri.parse
-				const parseResponse = await getHostBridgeProvider().uriServiceClient.parse(
-					StringRequest.create({
-						metadata: Metadata.create({}),
-						value: uriString,
-					}),
-				)
-				const fileUri = vscode.Uri.parse(`${parseResponse.scheme}://${parseResponse.authority}${parseResponse.path}`)
-				console.log("[DEBUG] UriServiceClient.parse:", fileUri)
-				const relativePathToGet = vscode.workspace.asRelativePath(fileUri, false)
+	const result = []
+	for (const uriString of request.uris) {
+		try {
+			result.push(await getRelativePath(uriString))
+		} catch (error) {
+			console.error(`Error calculating relative path for ${uriString}:`, error)
+		}
+	}
+	return RelativePaths.create({ paths: result })
+}
 
-				// If the path is still absolute, it's outside the workspace
-				if (path.isAbsolute(relativePathToGet)) {
-					console.warn(`Dropped file ${relativePathToGet} is outside the workspace. Sending original path.`)
-					return fileUri.fsPath.replace(/\\/g, "/")
-				} else {
-					let finalPath = "/" + relativePathToGet.replace(/\\/g, "/")
-					try {
-						const stat = await vscode.workspace.fs.stat(fileUri)
-						if (stat.type === vscode.FileType.Directory) {
-							finalPath += "/"
-						}
-					} catch (statError) {
-						console.error(`Error stating file ${fileUri.fsPath}:`, statError)
-					}
-					return finalPath
-				}
-			} catch (error) {
-				console.error(`Error calculating relative path for ${uriString}:`, error)
-				return null
-			}
-		}),
-	)
+async function getRelativePath(uriString: string): Promise<string> {
+	const filePath = URI.parse(uriString, true).fsPath
+	const relativePath = await asRelativePath(filePath)
 
-	// Filter out any null values from errors
-	const validPaths = resolvedPaths.filter((path): path is string => path !== null)
+	// If the path is still absolute, it's outside the workspace
+	if (path.isAbsolute(relativePath)) {
+		throw new Error(`Dropped file ${relativePath} is outside the workspace.`)
+	}
 
-	return RelativePaths.create({ paths: validPaths })
+	let result = "/" + relativePath.replace(/\\/g, "/")
+	if (await isDirectory(filePath)) {
+		result += "/"
+	}
+	return result
 }

src/core/controller/file/openMention.ts

@@ -8,7 +8,7 @@ import { openMention as coreOpenMention } from "../../mentions"
  * @param request The string request containing the mention text
  * @returns Empty response
  */
-export async function openMention(controller: Controller, request: StringRequest): Promise<Empty> {
+export async function openMention(_controller: Controller, request: StringRequest): Promise<Empty> {
 	coreOpenMention(request.value)
 	return Empty.create()
 }

src/core/controller/file/refreshRules.ts

@@ -4,7 +4,7 @@ import type { Controller } from "../index"
 import { refreshClineRulesToggles } from "@core/context/instructions/user-instructions/cline-rules"
 import { refreshExternalRulesToggles } from "@core/context/instructions/user-instructions/external-rules"
 import { refreshWorkflowToggles } from "@core/context/instructions/user-instructions/workflows"
-import { cwd } from "@core/task"
+import { getCwd, getDesktopDir } from "@/utils/path"
 
 /**
  * Refreshes all rule toggles (Cline, External, and Workflows)
@@ -14,6 +14,7 @@ import { cwd } from "@core/task"
  */
 export async function refreshRules(controller: Controller, _request: EmptyRequest): Promise<RefreshedRules> {
 	try {
+		const cwd = await getCwd(getDesktopDir())
 		const { globalToggles, localToggles } = await refreshClineRulesToggles(controller.context, cwd)
 		const { cursorLocalToggles, windsurfLocalToggles } = await refreshExternalRulesToggles(controller.context, cwd)
 		const { localWorkflowToggles, globalWorkflowToggles } = await refreshWorkflowToggles(controller.context, cwd)

src/core/controller/index.ts

@@ -1,54 +1,46 @@
+import { telemetryService } from "@/services/posthog/telemetry/TelemetryService"
+import { getCwd, getDesktopDir } from "@/utils/path"
 import { Anthropic } from "@anthropic-ai/sdk"
+import { buildApiHandler } from "@api/index"
+import { cleanupLegacyCheckpoints } from "@integrations/checkpoints/CheckpointMigration"
+import { extractCommitMessage } from "@integrations/git/commit-message-generator"
+import { downloadTask } from "@integrations/misc/export-markdown"
+import WorkspaceTracker from "@integrations/workspace/WorkspaceTracker"
+import { ClineAccountService } from "@services/account/ClineAccountService"
+import { McpHub } from "@services/mcp/McpHub"
+import { ApiProvider, ModelInfo } from "@shared/api"
+import { ChatContent } from "@shared/ChatContent"
+import { ChatSettings, StoredChatSettings } from "@shared/ChatSettings"
+import { ClineRulesToggles } from "@shared/cline-rules"
+import { ExtensionMessage, ExtensionState, Platform } from "@shared/ExtensionMessage"
+import { HistoryItem } from "@shared/HistoryItem"
+import { McpMarketplaceCatalog } from "@shared/mcp"
+import { TelemetrySetting } from "@shared/TelemetrySetting"
+import { UserInfo } from "@shared/UserInfo"
+import { WebviewMessage } from "@shared/WebviewMessage"
+import { fileExistsAtPath } from "@utils/fs"
+import { getWorkingState } from "@utils/git"
 import axios from "axios"
-import { v4 as uuidv4 } from "uuid"
 import fs from "fs/promises"
 import { setTimeout as setTimeoutPromise } from "node:timers/promises"
 import pWaitFor from "p-wait-for"
 import * as path from "path"
 import * as vscode from "vscode"
-import { handleGrpcRequest, handleGrpcRequestCancel } from "./grpc-handler"
-import { buildApiHandler } from "@api/index"
-import { cleanupLegacyCheckpoints } from "@integrations/checkpoints/CheckpointMigration"
-import { downloadTask } from "@integrations/misc/export-markdown"
-import WorkspaceTracker from "@integrations/workspace/WorkspaceTracker"
-import { ClineAccountService } from "@services/account/ClineAccountService"
-import { McpHub } from "@services/mcp/McpHub"
-import { telemetryService } from "@/services/posthog/telemetry/TelemetryService"
-import { ApiProvider, ModelInfo } from "@shared/api"
-import { ChatContent } from "@shared/ChatContent"
-import { ChatSettings, StoredChatSettings } from "@shared/ChatSettings"
-import { ExtensionMessage, ExtensionState, Platform } from "@shared/ExtensionMessage"
-import { HistoryItem } from "@shared/HistoryItem"
-import { McpMarketplaceCatalog } from "@shared/mcp"
-import { UserInfo } from "@shared/UserInfo"
-import { TelemetrySetting } from "@shared/TelemetrySetting"
-import { WebviewMessage } from "@shared/WebviewMessage"
-import { fileExistsAtPath } from "@utils/fs"
-import { getWorkingState } from "@utils/git"
-import { extractCommitMessage } from "@integrations/git/commit-message-generator"
 import { ensureMcpServersDirectoryExists, ensureSettingsDirectoryExists, GlobalFileNames } from "../storage/disk"
 import {
 	getAllExtensionState,
 	getGlobalState,
-	getSecret,
 	getWorkspaceState,
 	storeSecret,
-	updateApiConfiguration,
 	updateGlobalState,
 	updateWorkspaceState,
 } from "../storage/state"
 import { Task } from "../task"
-import { ClineRulesToggles } from "@shared/cline-rules"
+import { handleGrpcRequest, handleGrpcRequestCancel } from "./grpc-handler"
 import { sendStateUpdate } from "./state/subscribeToState"
 import { sendAddToInputEvent } from "./ui/subscribeToAddToInput"
-import { sendAuthCallbackEvent } from "./account/subscribeToAuthCallback"
 import { sendMcpMarketplaceCatalogEvent } from "./mcp/subscribeToMcpMarketplaceCatalog"
-import { sendRelinquishControlEvent } from "./ui/subscribeToRelinquishControl"
-import { handleTaskServiceRequest } from "./task"
-import { BooleanRequest } from "@shared/proto/common"
-import { getHostBridgeProvider } from "@/hosts/host-providers"
-import { GetWorkspacePathsRequest } from "@/shared/proto/index.host"
-import { getCwd } from "@/utils/path"
+import { AuthService } from "@/services/auth/AuthService"
 
 /*
 https://github.com/microsoft/vscode-webview-ui-toolkit-samples/blob/main/default/weather-webview/src/providers/WeatherViewProvider.ts
@@ -61,11 +53,11 @@ export class Controller {
 	private postMessage: (message: ExtensionMessage) => Thenable<boolean> | undefined
 
 	private disposables: vscode.Disposable[] = []
-	private mode: "plan" | "act" = "plan" // In-memory plan/act mode state
 	task?: Task
 	workspaceTracker: WorkspaceTracker
 	mcpHub: McpHub
 	accountService: ClineAccountService
+	authService: AuthService
 	latestAnnouncementId = "june-25-2025_16:11:00" // update to some unique identifier when we add a new announcement
 
 	constructor(
@@ -85,13 +77,9 @@ export class Controller {
 			(msg) => this.postMessageToWebview(msg),
 			this.context.extension?.packageJSON?.version ?? "1.0.0",
 		)
-		this.accountService = new ClineAccountService(
-			(msg) => this.postMessageToWebview(msg),
-			async () => {
-				const { apiConfiguration } = await this.getStateToPostToWebview()
-				return apiConfiguration?.clineApiKey
-			},
-		)
+		this.accountService = ClineAccountService.getInstance()
+		this.authService = AuthService.getInstance(context)
+		this.authService.restoreAuthToken()
 
 		// Clean up legacy checkpoints
 		cleanupLegacyCheckpoints(this.context.globalStorageUri.fsPath, this.outputChannel).catch((error) => {
@@ -99,6 +87,10 @@ export class Controller {
 		})
 	}
 
+	private async getCurrentMode(): Promise<"plan" | "act"> {
+		return ((await getGlobalState(this.context, "mode")) as "plan" | "act" | undefined) || "act"
+	}
+
 	/*
 	VSCode extensions use the disposable pattern to clean up resources when the sidebar/editor tab is closed by the user or system. This applies to event listening, commands, interacting with the UI, etc.
 	- https://vscode-docs.readthedocs.io/en/stable/extensions/patterns-and-principles/
@@ -121,9 +113,10 @@ export class Controller {
 	// Auth methods
 	async handleSignOut() {
 		try {
-			await storeSecret(this.context, "clineApiKey", undefined)
+			// TODO: update to clineAccountId and then move clineApiKey to a clear function.
+			await storeSecret(this.context, "clineAccountId", undefined)
 			await updateGlobalState(this.context, "userInfo", undefined)
-			await updateWorkspaceState(this.context, "apiProvider", "openrouter")
+			await updateGlobalState(this.context, "apiProvider", "openrouter")
 			await this.postStateToWebview()
 			vscode.window.showInformationMessage("Successfully logged out of Cline")
 		} catch (error) {
@@ -151,10 +144,13 @@ export class Controller {
 			taskHistory,
 		} = await getAllExtensionState(this.context)
 
-		// Reconstruct ChatSettings with in-memory mode and stored preferences
+		// Get current mode using helper function
+		const currentMode = await this.getCurrentMode()
+
+		// Reconstruct ChatSettings with mode from global state and stored preferences
 		const chatSettings: ChatSettings = {
 			...storedChatSettings, // Spread stored preferences (preferredLanguage, openAIReasoningEffort)
-			mode: this.mode, // Use in-memory mode (override any stored mode)
+			mode: currentMode, // Use mode from global state
 		}
 
 		const NEW_USER_TASK_COUNT_THRESHOLD = 10
@@ -178,7 +174,6 @@ export class Controller {
 			this.workspaceTracker,
 			(historyItem) => this.updateTaskHistory(historyItem),
 			() => this.postStateToWebview(),
-			(message) => this.postMessageToWebview(message),
 			(taskId) => this.reinitExistingTaskFromId(taskId),
 			() => this.cancelTask(),
 			apiConfiguration,
@@ -190,6 +185,7 @@ export class Controller {
 			terminalOutputLineLimit ?? 500,
 			defaultTerminalProfile ?? "default",
 			enableCheckpointsSetting ?? true,
+			await getCwd(getDesktopDir()),
 			task,
 			images,
 			files,
@@ -243,13 +239,14 @@ export class Controller {
 		await updateGlobalState(this.context, "telemetrySetting", telemetrySetting)
 		const isOptedIn = telemetrySetting !== "disabled"
 		telemetryService.updateTelemetryState(isOptedIn)
+		await this.postStateToWebview()
 	}
 
 	async togglePlanActModeWithChatSettings(chatSettings: ChatSettings, chatContent?: ChatContent): Promise<boolean> {
 		const didSwitchToActMode = chatSettings.mode === "act"
 
-		// Store mode in-memory only
-		this.mode = chatSettings.mode
+		// Store mode to global state
+		await updateGlobalState(this.context, "mode", chatSettings.mode)
 
 		// Capture mode switch telemetry | Capture regardless of if we know the taskId
 		telemetryService.captureModeSwitch(this.task?.taskId ?? "0", chatSettings.mode)
@@ -265,11 +262,6 @@ export class Controller {
 			previousModeReasoningEffort: newReasoningEffort,
 			previousModeAwsBedrockCustomSelected: newAwsBedrockCustomSelected,
 			previousModeAwsBedrockCustomModelBaseId: newAwsBedrockCustomModelBaseId,
-			previousModeSapAiCoreClientId: newSapAiCoreClientId,
-			previousModeSapAiCoreClientSecret: newSapAiCoreClientSecret,
-			previousModeSapAiCoreBaseUrl: newSapAiCoreBaseUrl,
-			previousModeSapAiCoreTokenUrl: newSapAiCoreTokenUrl,
-			previousModeSapAiCoreResourceGroup: newSapAiResourceGroup,
 			previousModeSapAiCoreModelId: newSapAiCoreModelId,
 			planActSeparateModelsSetting,
 		} = await getAllExtensionState(this.context)
@@ -278,9 +270,9 @@ export class Controller {
 
 		if (shouldSwitchModel) {
 			// Save the last model used in this mode
-			await updateWorkspaceState(this.context, "previousModeApiProvider", apiConfiguration.apiProvider)
-			await updateWorkspaceState(this.context, "previousModeThinkingBudgetTokens", apiConfiguration.thinkingBudgetTokens)
-			await updateWorkspaceState(this.context, "previousModeReasoningEffort", apiConfiguration.reasoningEffort)
+			await updateGlobalState(this.context, "previousModeApiProvider", apiConfiguration.apiProvider)
+			await updateGlobalState(this.context, "previousModeThinkingBudgetTokens", apiConfiguration.thinkingBudgetTokens)
+			await updateGlobalState(this.context, "previousModeReasoningEffort", apiConfiguration.reasoningEffort)
 			switch (apiConfiguration.apiProvider) {
 				case "anthropic":
 				case "vertex":
@@ -290,16 +282,16 @@ export class Controller {
 				case "qwen":
 				case "deepseek":
 				case "xai":
-					await updateWorkspaceState(this.context, "previousModeModelId", apiConfiguration.apiModelId)
+					await updateGlobalState(this.context, "previousModeModelId", apiConfiguration.apiModelId)
 					break
 				case "bedrock":
-					await updateWorkspaceState(this.context, "previousModeModelId", apiConfiguration.apiModelId)
-					await updateWorkspaceState(
+					await updateGlobalState(this.context, "previousModeModelId", apiConfiguration.apiModelId)
+					await updateGlobalState(
 						this.context,
 						"previousModeAwsBedrockCustomSelected",
 						apiConfiguration.awsBedrockCustomSelected,
 					)
-					await updateWorkspaceState(
+					await updateGlobalState(
 						this.context,
 						"previousModeAwsBedrockCustomModelBaseId",
 						apiConfiguration.awsBedrockCustomModelBaseId,
@@ -307,51 +299,38 @@ export class Controller {
 					break
 				case "openrouter":
 				case "cline":
-					await updateWorkspaceState(this.context, "previousModeModelId", apiConfiguration.openRouterModelId)
-					await updateWorkspaceState(this.context, "previousModeModelInfo", apiConfiguration.openRouterModelInfo)
+					await updateGlobalState(this.context, "previousModeModelId", apiConfiguration.openRouterModelId)
+					await updateGlobalState(this.context, "previousModeModelInfo", apiConfiguration.openRouterModelInfo)
 					break
 				case "vscode-lm":
 					// Important we don't set modelId to this, as it's an object not string (webview expects model id to be a string)
-					await updateWorkspaceState(
+					await updateGlobalState(
 						this.context,
 						"previousModeVsCodeLmModelSelector",
 						apiConfiguration.vsCodeLmModelSelector,
 					)
 					break
 				case "openai":
-					await updateWorkspaceState(this.context, "previousModeModelId", apiConfiguration.openAiModelId)
-					await updateWorkspaceState(this.context, "previousModeModelInfo", apiConfiguration.openAiModelInfo)
+					await updateGlobalState(this.context, "previousModeModelId", apiConfiguration.openAiModelId)
+					await updateGlobalState(this.context, "previousModeModelInfo", apiConfiguration.openAiModelInfo)
 					break
 				case "ollama":
-					await updateWorkspaceState(this.context, "previousModeModelId", apiConfiguration.ollamaModelId)
+					await updateGlobalState(this.context, "previousModeModelId", apiConfiguration.ollamaModelId)
 					break
 				case "lmstudio":
-					await updateWorkspaceState(this.context, "previousModeModelId", apiConfiguration.lmStudioModelId)
+					await updateGlobalState(this.context, "previousModeModelId", apiConfiguration.lmStudioModelId)
 					break
 				case "litellm":
-					await updateWorkspaceState(this.context, "previousModeModelId", apiConfiguration.liteLlmModelId)
-					await updateWorkspaceState(this.context, "previousModeModelInfo", apiConfiguration.liteLlmModelInfo)
+					await updateGlobalState(this.context, "previousModeModelId", apiConfiguration.liteLlmModelId)
+					await updateGlobalState(this.context, "previousModeModelInfo", apiConfiguration.liteLlmModelInfo)
 					break
 				case "requesty":
-					await updateWorkspaceState(this.context, "previousModeModelId", apiConfiguration.requestyModelId)
-					await updateWorkspaceState(this.context, "previousModeModelInfo", apiConfiguration.requestyModelInfo)
+					await updateGlobalState(this.context, "previousModeModelId", apiConfiguration.requestyModelId)
+					await updateGlobalState(this.context, "previousModeModelInfo", apiConfiguration.requestyModelInfo)
 					break
 				case "sapaicore":
-					await updateWorkspaceState(this.context, "previousModeModelId", apiConfiguration.apiModelId)
-					await updateWorkspaceState(this.context, "previousModeSapAiCoreClientId", apiConfiguration.sapAiCoreClientId)
-					await updateWorkspaceState(
-						this.context,
-						"previousModeSapAiCoreClientSecret",
-						apiConfiguration.sapAiCoreClientSecret,
-					)
-					await updateWorkspaceState(this.context, "previousModeSapAiCoreBaseUrl", apiConfiguration.sapAiCoreBaseUrl)
-					await updateWorkspaceState(this.context, "previousModeSapAiCoreTokenUrl", apiConfiguration.sapAiCoreTokenUrl)
-					await updateWorkspaceState(
-						this.context,
-						"previousModeSapAiCoreResourceGroup",
-						apiConfiguration.sapAiResourceGroup,
-					)
-					await updateWorkspaceState(this.context, "previousModeSapAiCoreModelId", apiConfiguration.sapAiCoreModelId)
+					await updateGlobalState(this.context, "previousModeModelId", apiConfiguration.apiModelId)
+					await updateGlobalState(this.context, "previousModeSapAiCoreModelId", apiConfiguration.sapAiCoreModelId)
 					break
 			}
 
@@ -363,9 +342,9 @@ export class Controller {
 				newReasoningEffort ||
 				newVsCodeLmModelSelector
 			) {
-				await updateWorkspaceState(this.context, "apiProvider", newApiProvider)
-				await updateWorkspaceState(this.context, "thinkingBudgetTokens", newThinkingBudgetTokens)
-				await updateWorkspaceState(this.context, "reasoningEffort", newReasoningEffort)
+				await updateGlobalState(this.context, "apiProvider", newApiProvider)
+				await updateGlobalState(this.context, "thinkingBudgetTokens", newThinkingBudgetTokens)
+				await updateGlobalState(this.context, "reasoningEffort", newReasoningEffort)
 				switch (newApiProvider) {
 					case "anthropic":
 					case "vertex":
@@ -375,41 +354,42 @@ export class Controller {
 					case "qwen":
 					case "deepseek":
 					case "xai":
-						await updateWorkspaceState(this.context, "apiModelId", newModelId)
+						await updateGlobalState(this.context, "apiModelId", newModelId)
 						break
 					case "bedrock":
-						await updateWorkspaceState(this.context, "apiModelId", newModelId)
-						await updateWorkspaceState(this.context, "awsBedrockCustomSelected", newAwsBedrockCustomSelected)
-						await updateWorkspaceState(this.context, "awsBedrockCustomModelBaseId", newAwsBedrockCustomModelBaseId)
+						await updateGlobalState(this.context, "apiModelId", newModelId)
+						await updateGlobalState(this.context, "awsBedrockCustomSelected", newAwsBedrockCustomSelected)
+						await updateGlobalState(this.context, "awsBedrockCustomModelBaseId", newAwsBedrockCustomModelBaseId)
 						break
 					case "openrouter":
 					case "cline":
-						await updateWorkspaceState(this.context, "openRouterModelId", newModelId)
-						await updateWorkspaceState(this.context, "openRouterModelInfo", newModelInfo)
+						await updateGlobalState(this.context, "openRouterModelId", newModelId)
+						await updateGlobalState(this.context, "openRouterModelInfo", newModelInfo)
 						break
 					case "vscode-lm":
-						await updateWorkspaceState(this.context, "vsCodeLmModelSelector", newVsCodeLmModelSelector)
+						await updateGlobalState(this.context, "vsCodeLmModelSelector", newVsCodeLmModelSelector)
 						break
 					case "openai":
-						await updateWorkspaceState(this.context, "openAiModelId", newModelId)
-						await updateWorkspaceState(this.context, "openAiModelInfo", newModelInfo)
+						await updateGlobalState(this.context, "openAiModelId", newModelId)
+						await updateGlobalState(this.context, "openAiModelInfo", newModelInfo)
 						break
 					case "ollama":
-						await updateWorkspaceState(this.context, "ollamaModelId", newModelId)
+						await updateGlobalState(this.context, "ollamaModelId", newModelId)
 						break
 					case "lmstudio":
-						await updateWorkspaceState(this.context, "lmStudioModelId", newModelId)
+						await updateGlobalState(this.context, "lmStudioModelId", newModelId)
 						break
 					case "litellm":
-						await updateWorkspaceState(this.context, "liteLlmModelId", newModelId)
-						await updateWorkspaceState(this.context, "liteLlmModelInfo", newModelInfo)
+						await updateGlobalState(this.context, "liteLlmModelId", newModelId)
+						await updateGlobalState(this.context, "liteLlmModelInfo", newModelInfo)
 						break
 					case "requesty":
-						await updateWorkspaceState(this.context, "requestyModelId", newModelId)
-						await updateWorkspaceState(this.context, "requestyModelInfo", newModelInfo)
+						await updateGlobalState(this.context, "requestyModelId", newModelId)
+						await updateGlobalState(this.context, "requestyModelInfo", newModelInfo)
 						break
 					case "sapaicore":
-						await updateWorkspaceState(this.context, "apiModelId", newModelId)
+						await updateGlobalState(this.context, "apiModelId", newModelId)
+						await updateGlobalState(this.context, "sapAiCoreModelId", newSapAiCoreModelId)
 						break
 				}
 
@@ -420,9 +400,9 @@ export class Controller {
 			}
 		}
 
-		// Save only non-mode properties to workspace storage
+		// Save only non-mode properties to global storage
 		const { mode, ...persistentChatSettings }: { mode: string } & StoredChatSettings = chatSettings
-		await updateWorkspaceState(this.context, "chatSettings", persistentChatSettings)
+		await updateGlobalState(this.context, "chatSettings", persistentChatSettings)
 		await this.postStateToWebview()
 
 		if (this.task) {
@@ -477,33 +457,24 @@ export class Controller {
 	}
 
 	// Auth
-
 	public async validateAuthState(state: string | null): Promise<boolean> {
-		const storedNonce = await getSecret(this.context, "authNonce")
-		if (!state || state !== storedNonce) {
-			return false
-		}
-		await storeSecret(this.context, "authNonce", undefined) // Clear after use
-		return true
+		return state === this.authService.authNonce
 	}
 
-	async handleAuthCallback(customToken: string, apiKey: string) {
+	async handleAuthCallback(customToken: string, provider: string | null = null) {
 		try {
-			// Store API key for API calls
-			await storeSecret(this.context, "clineApiKey", apiKey)
-
-			// Send custom token to webview for Firebase auth
-			await sendAuthCallbackEvent(customToken)
+			await this.authService.handleAuthCallback(customToken, provider ? provider : "google")
 
 			const clineProvider: ApiProvider = "cline"
-			await updateWorkspaceState(this.context, "apiProvider", clineProvider)
+			await updateGlobalState(this.context, "apiProvider", clineProvider)
+
+			// Mark welcome view as completed since user has successfully logged in
+			await updateGlobalState(this.context, "welcomeViewCompleted", true)
 
-			// Update API configuration with the new provider and API key
 			const { apiConfiguration } = await getAllExtensionState(this.context)
 			const updatedConfig = {
 				...apiConfiguration,
 				apiProvider: clineProvider,
-				clineApiKey: apiKey,
 			}
 
 			if (this.task) {
@@ -511,7 +482,6 @@ export class Controller {
 			}
 
 			await this.postStateToWebview()
-			// vscode.window.showInformationMessage("Successfully logged in to Cline")
 		} catch (error) {
 			console.error("Failed to handle auth callback:", error)
 			vscode.window.showErrorMessage("Failed to log in to Cline")
@@ -521,7 +491,6 @@ export class Controller {
 	}
 
 	// MCP Marketplace
-
 	private async fetchMcpMarketplaceFromApi(silent: boolean = false): Promise<McpMarketplaceCatalog | undefined> {
 		try {
 			const response = await axios.get("https://api.cline.bot/v1/mcp/marketplace", {
@@ -655,7 +624,7 @@ export class Controller {
 		}
 
 		const openrouter: ApiProvider = "openrouter"
-		await updateWorkspaceState(this.context, "apiProvider", openrouter)
+		await updateGlobalState(this.context, "apiProvider", openrouter)
 		await storeSecret(this.context, "openRouterApiKey", apiKey)
 		await this.postStateToWebview()
 		if (this.task) {
@@ -702,7 +671,7 @@ export class Controller {
 		await setTimeoutPromise(100)
 
 		// Post message to webview with the selected code
-		const fileMention = this.getFileMentionFromPath(filePath)
+		const fileMention = await this.getFileMentionFromPath(filePath)
 
 		let input = `${fileMention}\n\`\`\`\n${code}\n\`\`\``
 		if (diagnostics) {
@@ -739,7 +708,7 @@ export class Controller {
 		await vscode.commands.executeCommand("claude-dev.SidebarProvider.focus")
 		await setTimeoutPromise(100)
 
-		const fileMention = this.getFileMentionFromPath(filePath)
+		const fileMention = await this.getFileMentionFromPath(filePath)
 		const problemsString = this.convertDiagnosticsToProblemsString(diagnostics)
 		await this.initTask(`Fix the following code in ${fileMention}\n\`\`\`\n${code}\n\`\`\`\n\nProblems:\n${problemsString}`)
 
@@ -855,14 +824,18 @@ export class Controller {
 			terminalReuseEnabled,
 			defaultTerminalProfile,
 			isNewUser,
+			welcomeViewCompleted,
 			mcpResponsesCollapsed,
 			terminalOutputLineLimit,
 		} = await getAllExtensionState(this.context)
 
-		// Reconstruct ChatSettings with in-memory mode and stored preferences
+		// Get current mode using helper function
+		const currentMode = await this.getCurrentMode()
+
+		// Reconstruct ChatSettings with mode from global state and stored preferences
 		const chatSettings: ChatSettings = {
 			...storedChatSettings, // Spread stored preferences (preferredLanguage, openAIReasoningEffort)
-			mode: this.mode, // Use in-memory mode (override any stored mode)
+			mode: currentMode, // Use mode from global state
 		}
 
 		const localClineRulesToggles =
@@ -909,6 +882,7 @@ export class Controller {
 			terminalReuseEnabled,
 			defaultTerminalProfile,
 			isNewUser,
+			welcomeViewCompleted: welcomeViewCompleted as boolean, // Can be undefined but is set to either true or false by the migration that runs on extension launch in extension.ts
 			mcpResponsesCollapsed,
 			terminalOutputLineLimit,
 		}
@@ -918,7 +892,7 @@ export class Controller {
 		if (this.task) {
 			await telemetryService.sendCollectedEvents(this.task.taskId)
 		}
-		this.task?.abortTask()
+		await this.task?.abortTask()
 		this.task = undefined // removes reference to it, so once promises end it will be garbage collected
 	}
 
@@ -1088,6 +1062,4 @@ Commit message:`
 			vscode.window.showErrorMessage(`Failed to generate commit message: ${errorMessage}`)
 		}
 	}
-
-	// dev
 }

src/core/controller/mcp/downloadMcp.ts

@@ -1,6 +1,7 @@
 import { Controller } from ".."
-import { Empty, StringRequest } from "../../../shared/proto/common"
-import { McpServer, McpDownloadResponse } from "@shared/mcp"
+import { StringRequest } from "../../../shared/proto/common"
+import { McpDownloadResponse } from "../../../shared/proto/mcp"
+import { McpServer } from "@shared/mcp"
 import axios from "axios"
 import * as vscode from "vscode"
 import { sendChatButtonClickedEvent } from "../ui/subscribeToChatButtonClicked"
@@ -9,9 +10,9 @@ import { sendChatButtonClickedEvent } from "../ui/subscribeToChatButtonClicked"
  * Download an MCP server from the marketplace
  * @param controller The controller instance
  * @param request The request containing the MCP ID
- * @returns Empty response
+ * @returns MCP download response with details or error
  */
-export async function downloadMcp(controller: Controller, request: StringRequest): Promise<Empty> {
+export async function downloadMcp(controller: Controller, request: StringRequest): Promise<McpDownloadResponse> {
 	try {
 		// Check if mcpId is provided
 		if (!request.value) {
@@ -54,12 +55,6 @@ export async function downloadMcp(controller: Controller, request: StringRequest
 			throw new Error("Missing README content in MCP download response")
 		}
 
-		// Send details to webview
-		await controller.postMessageToWebview({
-			type: "mcpDownloadDetails",
-			mcpDownloadDetails: mcpDetails,
-		})
-
 		// Create task with context from README and added guidelines for MCP server installation
 		const task = `Set up the MCP server from ${mcpDetails.githubUrl} while adhering to these MCP server installation rules:
 - Start by loading the MCP documentation.
@@ -80,8 +75,17 @@ Here is the project's README to help you get started:\n\n${mcpDetails.readmeCont
 		await controller.initTask(task)
 		await sendChatButtonClickedEvent(controller.id)
 
-		// Return an empty response - the client only cares if the call succeeded
-		return Empty.create()
+		// Return the download details directly
+		return McpDownloadResponse.create({
+			mcpId: mcpDetails.mcpId,
+			githubUrl: mcpDetails.githubUrl,
+			name: mcpDetails.name,
+			author: mcpDetails.author,
+			description: mcpDetails.description,
+			readmeContent: mcpDetails.readmeContent,
+			llmsInstallationContent: mcpDetails.llmsInstallationContent,
+			requiresApiKey: mcpDetails.requiresApiKey,
+		})
 	} catch (error) {
 		console.error("Failed to download MCP:", error)
 		let errorMessage = "Failed to download MCP"
@@ -100,13 +104,17 @@ Here is the project's README to help you get started:\n\n${mcpDetails.readmeCont
 			errorMessage = error.message
 		}
 
-		// Show error in both notification and marketplace UI
-		vscode.window.showErrorMessage(errorMessage)
-		await controller.postMessageToWebview({
-			type: "mcpDownloadDetails",
+		// Return error in the response instead of throwing
+		return McpDownloadResponse.create({
+			mcpId: "",
+			githubUrl: "",
+			name: "",
+			author: "",
+			description: "",
+			readmeContent: "",
+			llmsInstallationContent: "",
+			requiresApiKey: false,
 			error: errorMessage,
 		})
-
-		throw error
 	}
 }

src/core/controller/models/refreshOpenRouterModels.ts

@@ -101,7 +101,7 @@ export async function refreshOpenRouterModels(
 						break
 					case "x-ai/grok-3-beta":
 						modelInfo.supportsPromptCache = true
-						modelInfo.cacheWritesPrice = 0
+						modelInfo.cacheWritesPrice = 0.75
 						modelInfo.cacheReadsPrice = 0
 						break
 					default:
@@ -122,11 +122,6 @@ export async function refreshOpenRouterModels(
 						break
 				}
 
-				// add new model id
-				if (rawModel.id === "x-ai/grok-3-beta") {
-					models["x-ai/grok-3"] = modelInfo
-				}
-
 				models[rawModel.id] = modelInfo
 			}
 		} else {

src/core/controller/state/setWelcomeViewCompleted.ts

@@ -0,0 +1,25 @@
+import type { BooleanRequest } from "../../../shared/proto/common"
+import { Empty } from "../../../shared/proto/common"
+import type { Controller } from "../index"
+import { updateGlobalState } from "../../storage/state"
+
+/**
+ * Sets the welcomeViewCompleted flag to the specified boolean value
+ * @param controller The controller instance
+ * @param request The boolean request containing the value to set
+ * @returns Empty response
+ */
+export async function setWelcomeViewCompleted(controller: Controller, request: BooleanRequest): Promise<Empty> {
+	try {
+		// Update the global state to set welcomeViewCompleted to the requested value
+		await updateGlobalState(controller.context, "welcomeViewCompleted", request.value)
+
+		await controller.postStateToWebview()
+
+		console.log(`Welcome view completed set to: ${request.value}`)
+		return Empty.create({})
+	} catch (error) {
+		console.error("Failed to set welcome view completed:", error)
+		throw error
+	}
+}

src/core/controller/state/updateSettings.ts

@@ -58,7 +58,16 @@ export async function updateSettings(controller: Controller, request: UpdateSett
 		// Update chat settings
 		if (request.chatSettings) {
 			const chatSettings = convertProtoChatSettingsToChatSettings(request.chatSettings)
-			await controller.context.workspaceState.update("chatSettings", chatSettings)
+
+			// Store mode to global state
+			if (chatSettings.mode !== undefined) {
+				await controller.context.globalState.update("mode", chatSettings.mode)
+			}
+
+			// Store chat settings (excluding mode) to global state
+			const { mode, ...globalChatSettings } = chatSettings
+			await controller.context.globalState.update("chatSettings", globalChatSettings)
+
 			if (controller.task) {
 				controller.task.chatSettings = chatSettings
 			}

src/core/controller/task/deleteTasksWithIds.ts

@@ -1,5 +1,6 @@
 import path from "path"
 import fs from "fs/promises"
+import vscode from "vscode"
 import { Controller } from ".."
 import { Empty, StringArrayRequest, BooleanRequest } from "../../../shared/proto/common"
 import { TaskMethodHandler } from "./index"
@@ -20,6 +21,18 @@ export const deleteTasksWithIds: TaskMethodHandler = async (
 		throw new Error("Missing task IDs")
 	}
 
+	const taskCount = request.value.length
+	const message =
+		taskCount === 1
+			? "Are you sure you want to delete this task? This action cannot be undone."
+			: `Are you sure you want to delete these ${taskCount} tasks? This action cannot be undone.`
+
+	const userChoice = await vscode.window.showWarningMessage(message, { modal: true }, "Delete")
+
+	if (userChoice === undefined) {
+		return Empty.create()
+	}
+
 	for (const id of request.value) {
 		await deleteTaskWithId(controller, id)
 	}

src/core/controller/task/newTask.ts

@@ -1,7 +1,6 @@
 import { Controller } from ".."
 import { Empty } from "../../../shared/proto/common"
 import { NewTaskRequest } from "../../../shared/proto/task"
-import { handleFileServiceRequest } from "../file"
 
 /**
  * Creates a new task with the given text and optional images

src/core/controller/ui/initializeWebview.ts

@@ -1,7 +1,7 @@
 import type { Controller } from "../index"
 import { EmptyRequest, Empty } from "@shared/proto/common"
 import { handleModelsServiceRequest } from "../models"
-import { getAllExtensionState, getGlobalState, updateWorkspaceState } from "../../storage/state"
+import { getAllExtensionState, getGlobalState, updateGlobalState } from "../../storage/state"
 import { sendOpenRouterModelsEvent } from "../models/subscribeToOpenRouterModels"
 import { sendMcpMarketplaceCatalogEvent } from "../mcp/subscribeToMcpMarketplaceCatalog"
 import { telemetryService } from "@/services/posthog/telemetry/TelemetryService"
@@ -32,7 +32,7 @@ export async function initializeWebview(controller: Controller, request: EmptyRe
 				// Update model info in state (this needs to be done here since we don't want to update state while settings is open, and we may refresh models there)
 				const { apiConfiguration } = await getAllExtensionState(controller.context)
 				if (apiConfiguration.openRouterModelId && response.models[apiConfiguration.openRouterModelId]) {
-					await updateWorkspaceState(
+					await updateGlobalState(
 						controller.context,
 						"openRouterModelInfo",
 						response.models[apiConfiguration.openRouterModelId],

src/core/controller/web/openInBrowser.ts

@@ -1,6 +1,6 @@
-import * as vscode from "vscode"
 import { Controller } from ".."
 import { Empty, StringRequest } from "../../../shared/proto/common"
+import { openExternal } from "@utils/env"
 
 /**
  * Opens a URL in the user's default browser
@@ -11,7 +11,7 @@ import { Empty, StringRequest } from "../../../shared/proto/common"
 export async function openInBrowser(controller: Controller, request: StringRequest): Promise<Empty> {
 	try {
 		if (request.value) {
-			await vscode.env.openExternal(vscode.Uri.parse(request.value))
+			await openExternal(request.value)
 		}
 		return Empty.create()
 	} catch (error) {

src/core/mentions/index.ts

@@ -11,13 +11,15 @@ import { getLatestTerminalOutput } from "@integrations/terminal/get-latest-outpu
 import { getCommitInfo } from "@utils/git"
 import { getWorkingState } from "@utils/git"
 import { FileContextTracker } from "../context/context-tracking/FileContextTracker"
+import { getCwd } from "@/utils/path"
+import { openExternal } from "@utils/env"
 
-export function openMention(mention?: string): void {
+export async function openMention(mention?: string): Promise<void> {
 	if (!mention) {
 		return
 	}
 
-	const cwd = vscode.workspace.workspaceFolders?.map((folder) => folder.uri.fsPath).at(0)
+	const cwd = await getCwd()
 	if (!cwd) {
 		return
 	}
@@ -35,7 +37,7 @@ export function openMention(mention?: string): void {
 	} else if (mention === "terminal") {
 		vscode.commands.executeCommand("workbench.action.terminal.focus")
 	} else if (mention.startsWith("http")) {
-		vscode.env.openExternal(vscode.Uri.parse(mention))
+		await openExternal(mention)
 	}
 }
 

src/core/prompts/model_prompts/claude4-experimental.ts

@@ -234,10 +234,9 @@ In each user message, the environment_details will specify the current mode. The
 ## What is PLAN MODE?
 
 - While you are usually in ACT MODE, the user may switch to PLAN MODE in order to have a back and forth with you to plan how to best accomplish the task. 
-- When starting in PLAN MODE, depending on the user's request, you may need to do some information gathering e.g. using ${readTool.name} or ${grepToolDefinition.name} to get more context about the task. You may also ask the user clarifying questions to get a better understanding of the task. You may return mermaid diagrams to visually display your understanding.
-- Once you've gained more context about the user's request, you should architect a detailed plan for how you will accomplish the task. Returning mermaid diagrams may be helpful here as well.
+- When starting in PLAN MODE, depending on the user's request, you may need to do some information gathering e.g. using ${readTool.name} or ${grepToolDefinition.name} to get more context about the task. You may also ask the user clarifying questions to get a better understanding of the task.
+- Once you've gained more context about the user's request, you should architect a detailed plan for how you will accomplish the task.
 - Then you might ask the user if they are pleased with this plan, or if they would like to make any changes. Think of this as a brainstorming session where you can discuss the task and plan the best way to accomplish it.
-- If at any point a mermaid diagram would make your plan clearer to help the user quickly see the structure, you are encouraged to include a Mermaid code block in the response. (Note: if you use colors in your mermaid diagrams, be sure to use high contrast colors so the text is readable.)
 - Finally once it seems like you've reached a good plan, ask the user to switch you back to ACT MODE to implement the solution.
 
 ====
@@ -257,7 +256,6 @@ CAPABILITIES
 			: ""
 	}
 - You have access to MCP servers that may provide additional tools and resources. Each server may provide different capabilities that you can use to accomplish tasks more effectively.
-- You can use LaTeX syntax in your responses to render mathematical expressions
 
 ====
 

src/core/prompts/model_prompts/claude4.ts

@@ -574,10 +574,9 @@ In each user message, the environment_details will specify the current mode. The
 ## What is PLAN MODE?
 
 - While you are usually in ACT MODE, the user may switch to PLAN MODE in order to have a back and forth with you to plan how to best accomplish the task. 
-- When starting in PLAN MODE, depending on the user's request, you may need to do some information gathering e.g. using read_file or search_files to get more context about the task. You may also ask the user clarifying questions with ask_followup_question to get a better understanding of the task. You may return mermaid diagrams to visually display your understanding.
-- Once you've gained more context about the user's request, you should architect a detailed plan for how you will accomplish the task. Returning mermaid diagrams may be helpful here as well. Present the plan to the user using the plan_mode_respond tool.
+- When starting in PLAN MODE, depending on the user's request, you may need to do some information gathering e.g. using read_file or search_files to get more context about the task. You may also ask the user clarifying questions with ask_followup_question to get a better understanding of the task.
+- Once you've gained more context about the user's request, you should architect a detailed plan for how you will accomplish the task. Present the plan to the user using the plan_mode_respond tool.
 - Then you might ask the user if they are pleased with this plan, or if they would like to make any changes. Think of this as a brainstorming session where you can discuss the task and plan the best way to accomplish it.
-- If at any point a mermaid diagram would make your plan clearer to help the user quickly see the structure, you are encouraged to include a Mermaid code block in the response. (Note: if you use colors in your mermaid diagrams, be sure to use high contrast colors so the text is readable.)
 - Finally once it seems like you've reached a good plan, ask the user to switch you back to ACT MODE to implement the solution.
 
 ====
@@ -597,7 +596,6 @@ CAPABILITIES
         : ""
 }
 - You have access to MCP servers that may provide additional tools and resources. Each server may provide different capabilities that you can use to accomplish tasks more effectively.
-- You can use LaTeX syntax in your responses to render mathematical expressions
 
 ====
 

src/core/prompts/responses.ts

@@ -35,6 +35,9 @@ Otherwise, if you have not completed the task and do not need additional informa
 	tooManyMistakes: (feedback?: string) =>
 		`You seem to be having trouble proceeding. The user has provided the following feedback to help guide you:\n<feedback>\n${feedback}\n</feedback>`,
 
+	autoApprovalMaxReached: (feedback?: string) =>
+		`Auto-approval limit reached. The user has provided the following feedback to help guide you:\n<feedback>\n${feedback}\n</feedback>`,
+
 	missingToolParameterError: (paramName: string) =>
 		`Missing value for required parameter '${paramName}'. Please retry with complete response.\n\n${toolUseInstructionsReminder}`,
 

src/core/prompts/system.ts

@@ -568,10 +568,9 @@ In each user message, the environment_details will specify the current mode. The
 ## What is PLAN MODE?
 
 - While you are usually in ACT MODE, the user may switch to PLAN MODE in order to have a back and forth with you to plan how to best accomplish the task. 
-- When starting in PLAN MODE, depending on the user's request, you may need to do some information gathering e.g. using read_file or search_files to get more context about the task. You may also ask the user clarifying questions to get a better understanding of the task. You may return mermaid diagrams to visually display your understanding.
-- Once you've gained more context about the user's request, you should architect a detailed plan for how you will accomplish the task. Returning mermaid diagrams may be helpful here as well.
+- When starting in PLAN MODE, depending on the user's request, you may need to do some information gathering e.g. using read_file or search_files to get more context about the task. You may also ask the user clarifying questions to get a better understanding of the task. 
+- Once you've gained more context about the user's request, you should architect a detailed plan for how you will accomplish the task. 
 - Then you might ask the user if they are pleased with this plan, or if they would like to make any changes. Think of this as a brainstorming session where you can discuss the task and plan the best way to accomplish it.
-- If at any point a mermaid diagram would make your plan clearer to help the user quickly see the structure, you are encouraged to include a Mermaid code block in the response. (Note: if you use colors in your mermaid diagrams, be sure to use high contrast colors so the text is readable.)
 - Finally once it seems like you've reached a good plan, ask the user to switch you back to ACT MODE to implement the solution.
 
 ====
@@ -591,7 +590,6 @@ CAPABILITIES
 		: ""
 }
 - You have access to MCP servers that may provide additional tools and resources. Each server may provide different capabilities that you can use to accomplish tasks more effectively.
-- You can use LaTeX syntax in your responses to render mathematical expressions
 
 ====