update the current task's consecutiveAutoApprovedRequestsCount on max request change

-   Add Groq as a new API provider with support for all Groq models including Kimi-K2
-   Add user role display in organization UI for Cline account users
-   Fix message dialogs not showing option buttons properly
-   Fix authentication issues when using multiple VSCode windows

.changeset/calm-ads-glow.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-Add support for Gemini 2.5 Pro and Flash to SAP AI Core Provider

.changeset/real-ravens-nail.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Fix logging in with cline not getting past welcome screen

.clinerules/workflows/git-branch-analysis.md

@@ -0,0 +1,75 @@
+# Git Diff Analysis Workflow
+
+## Objective
+Analyze the current branch's changes against main to provide informed insights and context for development decisions.
+
+## Step 1: Gather Git Information
+<important>Do not return any text or conversation other than what is necessary to run these commands</important>
+
+**First, check the expected output size:**
+   ```shell
+   (git branch --show-current && echo "=== STATUS ===" && git status --porcelain | cat && echo "=== COMMIT MESSAGES ===" && git log main..HEAD --oneline | cat && echo "=== CHANGED FILES ===" && git diff main --name-only | cat && echo "=== FULL DIFF ===" && git diff main | cat) | wc -l
+   ```
+
+**If the expected line count is greater than 500 lines, use the file-based approach:**
+   ```shell
+   git branch --show-current > cline-git-analysis.temp && echo "=== STATUS ===" >> cline-git-analysis.temp && git status --porcelain >> cline-git-analysis.temp && echo "=== COMMIT MESSAGES ===" >> cline-git-analysis.temp && git log main..HEAD --oneline >> cline-git-analysis.temp && echo "=== CHANGED FILES ===" >> cline-git-analysis.temp && git diff main --name-only >> cline-git-analysis.temp && echo "=== FULL DIFF ===" >> cline-git-analysis.temp && git diff main >> cline-git-analysis.temp
+   ```
+
+   Then, read the file using the read_file tool. After you have read the file but before you proceed with subsequent steps, delete it:
+   ```shell
+   rm cline-git-analysis.temp
+   ```
+
+**If the expected line count is 500 lines or fewer, use the direct approach:**
+   ```shell
+   git branch --show-current && echo "=== STATUS ===" && git status --porcelain | cat && echo "=== COMMIT MESSAGES ===" && git log main..HEAD --oneline | cat && echo "=== CHANGED FILES ===" && git diff main --name-only | cat && echo "=== FULL DIFF ===" && git diff main | cat
+   ```
+
+<important>If using the direct approach, pipe outputs through `cat` to avoid interactive terminals. If the user's shell is not bash/zsh, adjust the command and chaining
+ syntax accordingly.</important>
+
+## Step 2: Silent, Structured Analysis Phase
+- Analyze all git output without providing commentary or narration
+- Read the full diff to understand the scope and nature of changes
+- Identify patterns, architectural modifications, or potential impacts
+- Use `read_file` to examine any related files providing additional context on the changes you have observed
+
+## Step 3: Context Gathering
+- Analyze related code without providing commentary or narration
+- Read relevant related source files if needed for complete understanding
+- Check dependencies, imports, or cross-references spanning the changes
+- Understand the broader codebase context around modifications
+- This additional context gathering should include related backend code, as well as related ui/frontend code
+- You will typically need to analyze at least several files, potentially many, in order to fully complete this step
+- You should not continue reading additional context if you have exhausted more than 60% of your available context window
+- If you have exhausted less than 40% of your context window, you should continue reviewing additional context
+
+## Step 4: Ready for User Interaction
+**Only after completing the full analysis:**
+- Engage with the user based on comprehensive understanding
+- Provide insights about specific modifications and their impacts
+- If you are certain they exist, note potential breaking changes or compatibility issues
+- Answer questions with informed context from the complete change set and context gathering
+- If the user has not provided a question, or the question is insufficient to provide a quality response, ask brief (one sentence) clarifying questions.
+- Only offer recommendations if they are applicable to the user's request and relevant to the changes that you have observed 
+
+## Key Rules
+- **No prose or conversation during git research phase**
+- **No prose or conversation during context gathering phase**
+- **Complete all analysis before any user interaction**
+- **Use gathered information for all subsequent questions and insights**
+- **Focus on understanding the complete picture before discussing**
+
+## Optional: Additional Analysis Commands
+For deeper investigation when needed:
+
+```shell
+# Detailed commit history with author info
+git log main..HEAD --format="%h %s (%an)" | cat
+
+# Change statistics
+git diff main --stat | cat
+
+# Specific file type changes
+git diff main --name-only | grep -E '\.(ts|js|tsx|jsx|py|md)$' | cat

.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",
 			{

.github/workflows/e2e.yml

@@ -0,0 +1,88 @@
+name: E2E Tests
+
+on:
+    push:
+        branches:
+            - main
+    pull_request:
+        types: [opened, reopened, synchronize, ready_for_review]
+    workflow_dispatch:
+
+concurrency:
+    group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+    cancel-in-progress: true
+
+jobs:
+    matrix_prep:
+        runs-on: ubuntu-latest
+        outputs:
+            matrix: ${{ steps.set-matrix.outputs.matrix }}
+        steps:
+            - id: set-matrix
+              run: |
+                  echo 'matrix=[{"runner":"ubuntu"},{"runner":"windows"},{"runner":"macos"}]' >> $GITHUB_OUTPUT
+
+    e2e:
+        needs: matrix_prep
+        strategy:
+            fail-fast: false
+            matrix:
+                include: ${{ fromJson(needs.matrix_prep.outputs.matrix) }}
+        runs-on: ${{ matrix.runner }}-latest
+        timeout-minutes: 20
+        permissions:
+            id-token: write
+            contents: read
+        steps:
+            - uses: actions/checkout@v4
+            - name: Setup Node.js environment
+              uses: actions/setup-node@v4
+              with:
+                  node-version: 22
+
+            # Cache root dependencies - only reuse if package-lock.json exactly matches
+            - name: Cache root dependencies
+              uses: actions/cache@v4
+              id: root-cache
+              with:
+                  path: node_modules
+                  key: ${{ runner.os }}-npm-${{ hashFiles('package-lock.json') }}
+
+            # Cache webview-ui dependencies - only reuse if package-lock.json exactly matches
+            - name: Cache webview-ui dependencies
+              uses: actions/cache@v4
+              id: webview-cache
+              with:
+                  path: webview-ui/node_modules
+                  key: ${{ runner.os }}-npm-webview-${{ hashFiles('webview-ui/package-lock.json') }}
+
+            - name: Install root dependencies
+              if: steps.root-cache.outputs.cache-hit != 'true'
+              run: npm ci
+
+            - name: Install webview-ui dependencies
+              if: steps.webview-cache.outputs.cache-hit != 'true'
+              run: cd webview-ui && npm ci
+
+            - name: Install xvfb on Linux
+              if: matrix.runner == 'ubuntu'
+              run: sudo apt-get update && sudo apt-get install -y xvfb
+
+            # Build the extension before running tests
+            - name: Build Tests and Extension
+              run: npm run pretest
+
+            - name: Run E2E tests - Linux
+              if: matrix.runner == 'ubuntu'
+              run: xvfb-run -a npm run test:e2e
+
+            - name: Run E2E tests - Non-Linux
+              if: matrix.runner != 'ubuntu'
+              run: npm run test:e2e
+
+            - uses: actions/upload-artifact@v4
+              if: ${{ failure() }}
+              with:
+                  name: playwright-recordings-${{ matrix.runner }}
+                  path: |
+                      test-results/playwright/

.github/workflows/test.yml

@@ -68,6 +68,10 @@ jobs:
               if: steps.webview-cache.outputs.cache-hit != 'true'
               run: cd webview-ui && npm ci
 
+            - name: Install xvfb on Linux
+              if: runner.os == 'Linux'
+              run: sudo apt-get update && sudo apt-get install -y xvfb
+
             - name: Install local modules on windows
               if: runner.os == 'Windows' && steps.root-cache.outputs.cache-hit == 'true'
               run: |

.gitignore

@@ -34,8 +34,8 @@ src/shared/proto/host/*.ts
 # Webview
 webview-ui/src/services/grpc-client.ts
 # Host bridge
-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
+
+# E2E Tests
+test-results

.vscode-test.mjs

@@ -2,7 +2,7 @@ import { defineConfig } from "@vscode/test-cli"
 import path from "path"
 
 export default defineConfig({
-	files: "{out/**/*.test.js,src/**/*.test.js}",
+	files: "{out/**/*.test.js,src/**/*.test.js,!src/test/e2e/**/*.test.js,!out/src/test/e2e/**/*.test.js}",
 	mocha: {
 		ui: "bdd",
 		timeout: 20000, // Maximum time (in ms) that a test can run before failing

.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

@@ -1,24 +1,40 @@
 # Default
 .vscode/**
 .vscode-test/**
-out/**
-node_modules/**
+out/
+dist-standalone/
+node_modules/
 src/**
+standalone/**
 .gitignore
 .yarnrc
 esbuild.js
 vsc-extension-quickstart.md
-**/tsconfig.json
+tsconfig*.json
 **/.eslintrc.json
 **/*.map
 **/*.ts
 **/.vscode-test.*
+eslint-rules/**
+.github/**
+.husky/**
 
 # Custom
-demo.gif
+**/demo.gif
 .nvmrc
 .gitattributes
 .prettierignore
+.husky/
+.github/
+eslint-rules/
+old_docs/
+evals/
+.changie.yaml
+.codespellrc
+.mocharc.json
+buf.yaml
+.changeset/
+.clinerules/
 
 # Ignore all webview-ui files except the build directory (https://github.com/microsoft/vscode-webview-ui-toolkit-samples/blob/main/frameworks/hello-world-react-cra/.vscodeignore)
 webview-ui/src/**
@@ -32,6 +48,7 @@ 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
@@ -42,3 +59,8 @@ docs/**
 
 # Include icons
 !assets/icons/**
+
+# Ignore E2E build files
+e2e-build.js
+e2e.vsix
+test-results/

CHANGELOG.md

@@ -1,5 +1,86 @@
 # Changelog
 
+## [3.19.5]
+
+-   Add Groq as a new API provider with support for all Groq models including Kimi-K2
+-   Add user role display in organization UI for Cline account users
+-   Fix message dialogs not showing option buttons properly
+-   Fix authentication issues when using multiple VSCode windows
+
+## [3.19.4]
+
+-   Add ability to choose Chinese endpoint for Moonshot provider
+
+## [3.19.3]
+
+-   Add Moonshot AI provider
+
+## [3.19.2]
+
+-   Show request ID in error messages returned by Cline Accounts API to help debug user reported issues
+
+## [3.19.1]
+
+-   Fix documentation
+
+## [3.19.0]
+
+-   Add Kimi-K2 as a recommended model in the Cline Provider, and route to Together/Groq for 131k context window and high throughput
+-   Added API Key support for Bedrock integration
+
+## [3.18.14]
+
+-   Fix bug where Cline account users logged in with invalid token would not be shown as logged out in webview presentation layer
+
+## [3.18.13]
+
+-   Fix authentication issue where Cline accounts users would keep getting logged out or seeing 'Unexpected API response' errors
+
+## [3.18.12]
+
+-   Fix flaky organization switching behavior in Cline provider that caused UI inconsistencies and double loading
+-   Fix insufficient credits error display to properly show error messages when account balance is too low
+-   Improve credit balance validation and error handling for Cline provider requests
+
+## [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 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!)

README.md

@@ -51,7 +51,7 @@ Thanks to [Claude 3.7 Sonnet's agentic coding capabilities](https://www.anthrop
 
 ### Use any API and Model
 
-Cline supports API providers like OpenRouter, Anthropic, OpenAI, Google Gemini, AWS Bedrock, Azure, GCP Vertex, and Cerebras. You can also configure any OpenAI compatible API, or use a local model through LM Studio/Ollama. If you're using OpenRouter, the extension fetches their latest model list, allowing you to use the newest models as soon as they're available.
+Cline supports API providers like OpenRouter, Anthropic, OpenAI, Google Gemini, AWS Bedrock, Azure, GCP Vertex, Cerebras and Groq. You can also configure any OpenAI compatible API, or use a local model through LM Studio/Ollama. If you're using OpenRouter, the extension fetches their latest model list, allowing you to use the newest models as soon as they're available.
 
 The extension also keeps track of total tokens and API usage cost for the entire task loop and individual requests, keeping you informed of spend every step of the way.
 

docs/docs.json

@@ -147,6 +147,7 @@
 				"pages": [
 					"provider-config/anthropic",
 					"provider-config/claude-code",
+					"provider-config/aws-bedrock-with-apikey-authentication",
 					"provider-config/aws-bedrock-with-credentials-authentication",
 					"provider-config/aws-bedrock-with-profile-authentication",
 					"provider-config/gcp-vertex-ai",

docs/enterprise-solutions/cloud-provider-integration.mdx

@@ -14,6 +14,8 @@ Certain scenarios may warrant using local models, including handling highly sens
 
 #### [IAM Security Best Practices](https://docs.aws.amazon.com/IAM/latest/UserGuide/best-practices.html) (For administrators)
 
+#### [AWS Bedrock setup for API Keys](/provider-config/aws-bedrock-with-apikey-authentication)
+
 #### [AWS Bedrock setup for Legacy IAM (AWS Credentials)](/provider-config/aws-bedrock-with-credentials-authentication)
 
 #### [AWS Bedrock setup for SSO token (AWS Profile)](/provider-config/aws-bedrock-with-profile-authentication)

docs/provider-config/aws-bedrock-with-apikey-authentication.mdx

@@ -0,0 +1,135 @@
+---
+title: "AWS Bedrock"
+description: "Learn how to set up AWS Bedrock with Cline using credentials authentication. This guide covers AWS environment setup, regional access verification, and secure integration with the Cline VS Code extension."
+---
+
+### Overview
+
+-   **AWS Bedrock:** A fully managed service that offers access to leading generative AI models (e.g., Anthropic Claude, Amazon Nova) through AWS.\
+    [Learn more about AWS Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html).
+-   **Cline:** A VS Code extension that acts as a coding assistant by integrating with AI models—empowering developers to generate code, debug, and analyze data.
+-   **Developer Focus:** This guide is tailored for individual developers that want to enable access to frontier models via AWS Bedrock with a simplified setup using API Keys.
+
+---
+
+### Step 1: Prepare Your AWS Environment
+
+#### 1.1 Individual user setup - Create a Bedrock API Key
+
+For more detailed instructions check the [documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/api-keys.html).
+
+1. **Sign in to the AWS Management Console:**\
+   [AWS Console](https://aws.amazon.com/console/)
+2. **Access Bedrock Console:**
+    - [Bedrock Console](https://console.aws.amazon.com/bedrock)
+    - Create a new Long Lived API Key. This API Key will have by default the `AmazonBedrockLimitedAccess` IAM policy
+      [View AmazonBedrockLimitedAccess Policy Details](https://docs.aws.amazon.com/bedrock/latest/userguide/security-iam.html)
+
+#### 1.2 Create or Modify the Policy
+
+To ensure Cline can interact with AWS Bedrock, your IAM user or role needs specific permissions. While the `AmazonBedrockLimitedAccess` managed policy provides comprehensive access, for a more restricted and secure setup adhering to the principle of least privilege, the following minimal permissions are sufficient for Cline's core model invocation functionality:
+
+-   `bedrock:InvokeModel`
+-   `bedrock:InvokeModelWithResponseStream`
+-   `bedrock:CallWithBearerToken`
+
+You can create a custom IAM policy with these permissions and attach it to your IAM user or role.
+
+1.  In the AWS IAM console, create a new policy.
+2.  Use the JSON editor to add the following policy document:
+    ```json
+    {
+    	"Version": "2012-10-17",
+    	"Statement": [
+    		{
+    			"Effect": "Allow",
+    			"Action": ["bedrock:InvokeModel", "bedrock:InvokeModelWithResponseStream", "bedrock:CallWithBearerToken"],
+    			"Resource": "*" // For enhanced security, scope this to specific model ARNs if possible.
+    		}
+    	]
+    }
+    ```
+3.  Name the policy (e.g., `ClineBedrockInvokeAccess`) and attach it to the IAM user associated with the key you created. The IAM user and the API key have the same prefix.
+
+**Important Considerations:**
+
+-   **Model Listing in Cline:** The minimal permissions (`bedrock:InvokeModel`, `bedrock:InvokeModelWithResponseStream`) are sufficient for Cline to _use_ a model if you specify the model ID directly in Cline's settings. If you rely on Cline to dynamically list available Bedrock models, you might need additional permissions like `bedrock:ListFoundationModels`.
+-   **AWS Marketplace Subscriptions:** For third-party models (e.g., Anthropic Claude), the **`AmazonBedrockLimitedAccess`** policy grants you the necessary permissions to subscribe via the AWS Marketplace. There is no explicit access to be enabled. For Anthropic models you are still required to submit a First Time Use (FTU) form via the Console. If you get the following message in the Cline chat `[ERROR] Failed to process response: Model use case details have not been submitted for this account. Fill out the Anthropic use case details form before using the model.` then open the [Playground in the AWS Bedrock Console](https://console.aws.amazon.com/bedrock/home?#/text-generation-playground), select any Anthropic model and fill in the form (you might need to send a prompt first)
+
+---
+
+### Step 2: Verify Regional and Model Access
+
+#### 2.1 Choose and Confirm a Region
+
+1. **Select a Region:**\
+   AWS Bedrock is available in multiple regions (e.g., US East, Europe, Asia Pacific). Choose the region that meets your latency and compliance needs.\
+   [AWS Global Infrastructure](https://aws.amazon.com/about-aws/global-infrastructure/regions_az/)
+2. **Verify Model Access:**
+    - **Note:** Some models are only accessible via an [Inference Profile](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html). In such case check the box "Cross Region Inference".
+
+---
+
+### Step 3: Configure the Cline VS Code Extension
+
+#### 3.1 Install and Open Cline
+
+1. **Install VS Code:**\
+   Download from the [VS Code website](https://code.visualstudio.com/).
+2. **Install the Cline Extension:**
+    - Open VS Code.
+    - Go to the Extensions Marketplace (`Ctrl+Shift+X` or `Cmd+Shift+X`).
+    - Search for **Cline** and install it.
+
+#### 3.2 Configure Cline Settings
+
+1. **Open Cline Settings:**
+    - Click on the settings ⚙️ to select your API Provider.
+2. **Select AWS Bedrock as the API Provider:**
+    - From the API Provider dropdown, choose **AWS Bedrock**.
+3. **Enter Your AWS API Key:**
+    - Input your **API Key**
+    - Specify the correct **AWS Region** (e.g., `us-east-1` or your enterprise-approved region).
+4. **Select a Model:**
+    - Choose an on-demand model (e.g., **anthropic.claude-3-5-sonnet-20241022-v2:0**).
+5. **Save and Test:**
+    - Click **Done/Save** to apply your settings.
+    - Test the integration by sending a simple prompt (e.g., "Generate a Python function to check if a number is prime.").
+
+---
+
+### Step 4: Security, Monitoring, and Best Practices
+
+1. **Secure Access:**
+    - Prefer AWS SSO/federated roles over long-lived API Key when possible.
+    - [AWS IAM Best Practices](https://docs.aws.amazon.com/IAM/latest/UserGuide/best-practices.html)
+2. **Enhance Network Security:**
+    - Consider setting up [AWS PrivateLink](https://docs.aws.amazon.com/vpc/latest/userguide/endpoint-services-overview.html) to securely connect to Bedrock.
+3. **Monitor and Log Activity:**
+    - Enable AWS CloudTrail to log Bedrock API calls.
+    - Use CloudWatch to monitor metrics like invocation count, latency, and token usage.
+    - Set up alerts for abnormal activity.
+4. **Handle Errors and Manage Costs:**
+    - Implement exponential backoff for throttling errors.
+    - Use AWS Cost Explorer and set billing alerts to track usage.\
+      [AWS Cost Management](https://docs.aws.amazon.com/cost-management/latest/userguide/what-is-aws-cost-management.html)
+5. **Regular Audits and Compliance:**
+    - Periodically review IAM roles and CloudTrail logs.
+    - Follow internal data privacy and governance policies.
+
+---
+
+### Conclusion
+
+By following these steps, your enterprise team can securely integrate AWS Bedrock with the Cline VS Code extension to accelerate development:
+
+1. **Prepare Your AWS Environment:** Create or use a secure IAM role/user, attach the `AmazonBedrockLimitedAccess` policy, and ensure necessary permissions.
+2. **Verify Region and Model Access:** Confirm that your selected region supports your required models.
+3. **Configure Cline in VS Code:** Install and set up Cline with your AWS credentials and choose an appropriate model.
+4. **Implement Security and Monitoring:** Use best practices for IAM, network security, monitoring, and cost management.
+
+For further details, consult the [AWS Bedrock Documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html) and coordinate with your internal cloud team. Happy coding!
+
+---
+
+_This guide will be updated as AWS Bedrock and Cline evolve. Always refer to the latest documentation and internal policies for up-to-date practices._

docs/provider-config/aws-bedrock-with-credentials-authentication.mdx

@@ -5,7 +5,7 @@ description: "Learn how to set up AWS Bedrock with Cline using credentials authe
 
 ### Overview
 
--   **AWS Bedrock:** A fully managed service that offers access to leading generative AI models (e.g., Anthropic Claude, Amazon Titan) through AWS.\
+-   **AWS Bedrock:** A fully managed service that offers access to leading generative AI models (e.g., Anthropic Claude, Amazon Nova) through AWS.\
     [Learn more about AWS Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html).
 -   **Cline:** A VS Code extension that acts as a coding assistant by integrating with AI models—empowering developers to generate code, debug, and analyze data.
 -   **Enterprise Focus:** This guide is tailored for organizations with established AWS environments (using IAM roles, AWS SSO, AWS Organizations, etc.) to ensure secure and compliant usage.
@@ -25,7 +25,7 @@ description: "Learn how to set up AWS Bedrock with Cline using credentials authe
 
 #### 1.2 Attach the Required Policies
 
-To ensure Cline can interact with AWS Bedrock, your IAM user or role needs specific permissions. While the `AmazonBedrockFullAccess` managed policy provides comprehensive access, for a more restricted and secure setup adhering to the principle of least privilege, the following minimal permissions are sufficient for Cline's core model invocation functionality:
+To ensure Cline can interact with AWS Bedrock, your IAM user or role needs specific permissions. While the `AmazonBedrockLimitedAccess` managed policy provides comprehensive access, for a more restricted and secure setup adhering to the principle of least privilege, the following minimal permissions are sufficient for Cline's core model invocation functionality:
 
 -   `bedrock:InvokeModel`
 -   `bedrock:InvokeModelWithResponseStream`
@@ -52,8 +52,8 @@ You can create a custom IAM policy with these permissions and attach it to your
 
 **Option 2: Using a Managed Policy (Simpler Initial Setup)**
 
--   Alternatively, you can attach the AWS managed policy **`AmazonBedrockFullAccess`**. This grants broader permissions, including the ability to list models, manage provisioning, and other Bedrock features. This might be simpler for initial setup or if you require these wider capabilities.
-    [View AmazonBedrockFullAccess Policy Details](https://docs.aws.amazon.com/bedrock/latest/userguide/security-iam.html)
+-   Alternatively, you can attach the AWS managed policy **`AmazonBedrockLimitedAccess`**. This grants broader permissions, including the ability to list models, manage provisioning, and other Bedrock features. This might be simpler for initial setup or if you require these wider capabilities.
+    [View AmazonBedrockLimitedAccess Policy Details](https://docs.aws.amazon.com/bedrock/latest/userguide/security-iam.html)
 
 **Important Considerations:**
 
@@ -71,8 +71,8 @@ You can create a custom IAM policy with these permissions and attach it to your
    AWS Bedrock is available in multiple regions (e.g., US East, Europe, Asia Pacific). Choose the region that meets your latency and compliance needs.\
    [AWS Global Infrastructure](https://aws.amazon.com/about-aws/global-infrastructure/regions_az/)
 2. **Verify Model Access:**
-    - In the AWS Bedrock console, confirm that the models your team requires (e.g., Anthropic Claude, Amazon Titan) are marked as "Access granted."
-    - **Note:** Some advanced models might require an [Inference Profile](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-prereq.html) if not available on-demand.
+    - In the AWS Bedrock console, confirm that the models your team requires (e.g., Anthropic Claude, Amazon Nova) are marked as "Access granted."
+    - **Note:** Some advanced models might require an [Inference Profile](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html) if not available on-demand.
 
 #### 2.2 Set Up AWS Marketplace Subscriptions (if needed)
 
@@ -138,7 +138,7 @@ You can create a custom IAM policy with these permissions and attach it to your
 
 By following these steps, your enterprise team can securely integrate AWS Bedrock with the Cline VS Code extension to accelerate development:
 
-1. **Prepare Your AWS Environment:** Create or use a secure IAM role/user, attach the `AmazonBedrockFullAccess` policy, and ensure necessary permissions.
+1. **Prepare Your AWS Environment:** Create or use a secure IAM role/user, attach the `AmazonBedrockLimitedAccess` policy, and ensure necessary permissions.
 2. **Verify Region and Model Access:** Confirm that your selected region supports your required models and subscribe via AWS Marketplace if needed.
 3. **Configure Cline in VS Code:** Install and set up Cline with your AWS credentials and choose an appropriate model.
 4. **Implement Security and Monitoring:** Use best practices for IAM, network security, monitoring, and cost management.

docs/provider-config/claude-code.mdx

@@ -1,11 +1,11 @@
 ---
 title: "Claude Code"
-description: "Use your Claude Max subscription with Cline instead of paying per token. Learn how to set up and configure the Claude Code provider."
+description: "Use your Claude Max or Pro subscription with Cline instead of paying per token. Learn how to set up and configure the Claude Code provider."
 ---
 
 **Website:** [https://docs.anthropic.com/en/docs/claude-code/setup](https://docs.anthropic.com/en/docs/claude-code/setup)
 
-The Claude Code provider lets you use your existing Claude subscription with Cline. If you have Claude Max, this means you can use Claude in Cline without paying extra API costs.
+The Claude Code provider lets you use your existing Claude subscription with Cline. If you have Claude Max or Pro, this means you can use Claude in Cline without paying extra API costs.
 
 <Frame>
 	<img

esbuild.js

@@ -5,6 +5,7 @@ const path = require("path")
 const production = process.argv.includes("--production")
 const watch = process.argv.includes("--watch")
 const standalone = process.argv.includes("--standalone")
+const e2eBuild = process.argv.includes("--e2e-build")
 const destDir = standalone ? "dist-standalone" : "dist"
 
 /**
@@ -153,15 +154,25 @@ const extensionConfig = {
 // Standalone-specific configuration
 const standaloneConfig = {
 	...baseConfig,
-	entryPoints: ["src/standalone/standalone.ts"],
-	outfile: `${destDir}/standalone.js`,
+	entryPoints: ["src/standalone/cline-core.ts"],
+	outfile: `${destDir}/cline-core.js`,
 	// These gRPC protos need to load files from the module directory at runtime,
 	// so they cannot be bundled.
 	external: ["vscode", "@grpc/reflection", "grpc-health-check"],
 }
 
+// E2E build script configuration
+const e2eBuildConfig = {
+	...baseConfig,
+	entryPoints: ["src/test/e2e/utils/build.ts"],
+	outfile: `${destDir}/e2e-build.js`,
+	external: ["@vscode/test-electron", "execa"],
+	sourcemap: false,
+	plugins: [aliasResolverPlugin, esbuildProblemMatcherPlugin],
+}
+
 async function main() {
-	const config = standalone ? standaloneConfig : extensionConfig
+	const config = standalone ? standaloneConfig : e2eBuild ? e2eBuildConfig : extensionConfig
 	const extensionCtx = await esbuild.context(config)
 	if (watch) {
 		await extensionCtx.watch()

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/diff-edits/README.md

@@ -36,7 +36,7 @@ It starts with our test cases. Each one is a JSON file in `./cases` that has the
 Then, for every test run, we set up a specific configuration. This includes which LLM we're testing, which system prompt it gets, which function we use to parse the model's raw output, and which function we use to actually apply the diff. Here's the command I've been using:
 
 ```bash
-npm run diff-eval -- --model-ids "anthropic/claude-3-5-sonnet-20241022,x-ai/grok-3-beta" --max-cases 4 --valid-attempts-per-case 2 --verbose --parallel
+npm run diff-eval -- --model-ids "anthropic/claude-3-5-sonnet,x-ai/grok-3-beta,anthropic/claude-3.7-sonnet,anthropic/claude-sonnet-4,google/gemini-2.5-pro-preview,google/gemini-2.5-flash" --max-cases 5 --valid-attempts-per-case 5 --parallel --diff-edit-function diff-06-26-25 --verbose 
 ```
 
 This will build the eval script, run it, and then open the streamlit dashboard to show the results.

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": "3.18.3",
+	"version": "3.19.5",
 	"icon": "assets/icons/icon.png",
 	"engines": {
 		"vscode": "^1.84.0"
@@ -330,12 +330,12 @@
 		"watch:esbuild": "node esbuild.js --watch",
 		"watch:tsc": "tsc --noEmit --watch --project tsconfig.json",
 		"package": "npm run check-types && npm run build:webview && npm run lint && node esbuild.js --production",
-		"protos": "node proto/build-proto.js && node scripts/generate-server-setup.mjs && node scripts/generate-host-bridge-client.mjs",
+		"protos": "node scripts/build-proto.mjs && node scripts/generate-server-setup.mjs && node scripts/generate-host-bridge-client.mjs",
 		"postprotos": "prettier src/shared/proto src/core/controller src/hosts/ webview-ui/src/services src/generated --write --log-level warn",
 		"clean": "rimraf dist dist-standalone webview-ui/build src/generated out/",
 		"compile-tests": "node ./scripts/build-tests.js",
 		"watch-tests": "tsc -p . -w --outDir out",
-		"check-types": "npm run protos && tsc --noEmit",
+		"check-types": "npm run protos && npx tsc --noEmit && cd webview-ui && npx tsc -b --noEmit",
 		"lint": "eslint src --ext ts && eslint webview-ui/src --ext ts && buf lint && cd webview-ui && npm run lint",
 		"format": "prettier . --check",
 		"format:fix": "prettier . --write",
@@ -345,6 +345,8 @@
 		"test:integration": "vscode-test",
 		"test:unit": "TS_NODE_PROJECT='./tsconfig.unit-test.json' mocha",
 		"test:coverage": "vscode-test --coverage",
+		"e2e": "playwright test -c playwright.config.ts",
+		"test:e2e": "playwright install && vsce package --no-dependencies --out dist/e2e.vsix && node src/test/e2e/utils/build.js && playwright test",
 		"install:all": "npm install && cd webview-ui && npm install",
 		"dev:webview": "cd webview-ui && npm run dev",
 		"build:webview": "cd webview-ui && npm run build",
@@ -383,7 +385,8 @@
 		"@typescript-eslint/parser": "^7.18.0",
 		"@typescript-eslint/utils": "^8.33.0",
 		"@vscode/test-cli": "^0.0.10",
-		"@vscode/test-electron": "^2.4.1",
+		"@vscode/test-electron": "^2.5.2",
+		"@vscode/vsce": "^3.6.0",
 		"chai": "^4.3.10",
 		"chalk": "^5.3.0",
 		"esbuild": "^0.25.0",
@@ -392,6 +395,7 @@
 		"grpc-tools": "^1.13.0",
 		"husky": "^9.1.7",
 		"lint-staged": "^16.1.0",
+		"minimatch": "^3.0.3",
 		"mintlify": "^4.0.515",
 		"npm-run-all": "^4.1.5",
 		"prettier": "^3.3.3",
@@ -408,8 +412,8 @@
 	"dependencies": {
 		"@anthropic-ai/sdk": "^0.37.0",
 		"@anthropic-ai/vertex-sdk": "^0.6.4",
-		"@aws-sdk/client-bedrock-runtime": "^3.826.0",
-		"@aws-sdk/credential-providers": "^3.826.0",
+		"@aws-sdk/client-bedrock-runtime": "^3.840.0",
+		"@aws-sdk/credential-providers": "^3.840.0",
 		"@bufbuild/protobuf": "^2.2.5",
 		"@cerebras/cerebras_cloud_sdk": "^1.35.0",
 		"@google-cloud/vertexai": "^1.9.3",
@@ -424,6 +428,7 @@
 		"@opentelemetry/sdk-node": "^0.39.1",
 		"@opentelemetry/sdk-trace-node": "^1.30.1",
 		"@opentelemetry/semantic-conventions": "^1.30.0",
+		"@playwright/test": "^1.53.2",
 		"@sentry/browser": "^9.12.0",
 		"@streamparser/json": "^0.0.22",
 		"@vscode/codicons": "^0.0.36",
@@ -448,6 +453,7 @@
 		"image-size": "^2.0.2",
 		"isbinaryfile": "^5.0.2",
 		"jschardet": "^3.1.4",
+		"jwt-decode": "^4.0.0",
 		"mammoth": "^1.8.0",
 		"monaco-vscode-textmate-theme-converter": "^0.1.7",
 		"nice-grpc": "^2.1.12",

playwright.config.ts

@@ -0,0 +1,17 @@
+import { defineConfig } from "@playwright/test"
+
+const isGitHubAction = !!process.env.CI
+
+export default defineConfig({
+	workers: 1,
+	retries: 1,
+	testDir: "src/test/e2e",
+	timeout: 20000,
+	expect: {
+		timeout: 20000,
+	},
+	fullyParallel: true,
+	reporter: isGitHubAction ? [["github"], ["list"]] : [["list"]],
+	globalSetup: require.resolve("./src/test/e2e/utils/setup"),
+	globalTeardown: require.resolve("./src/test/e2e/utils/teardown"),
+})

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/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/diff.proto

@@ -0,0 +1,39 @@
+syntax = "proto3";
+
+package host;
+option java_package = "bot.cline.host.proto";
+option java_multiple_files = true;
+
+import "common.proto";
+
+// Provides methods for diff views.
+service DiffService {
+  // Open the diff view/editor.
+  rpc openDiff(OpenDiffRequest) returns (OpenDiffResponse);
+  rpc replaceText(ReplaceTextRequest) returns (ReplaceTextResponse);
+}
+
+message OpenDiffRequest {
+  optional cline.Metadata metadata = 1;
+  // The absolute path of the document being edited.
+  optional string path = 2;
+  // The new content for the file.
+  optional string content = 3;
+}
+
+message OpenDiffResponse {
+  // A unique identifier for the diff view that was opened.
+  optional string diff_id = 1;
+}
+
+message ReplaceTextRequest {
+  optional cline.Metadata metadata = 1;
+  optional string diff_id = 2;
+  optional string content = 3;
+  optional int32 start_line = 4;
+  optional int32 end_line = 5;
+}
+
+message ReplaceTextResponse {
+  // TBD
+}

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

@@ -11,6 +11,7 @@ service WindowService {
   // Opens a text document in the editor and returns editor information.
   rpc showTextDocument(ShowTextDocumentRequest) returns (TextEditorInfo);
   rpc showOpenDialogue(ShowOpenDialogueRequest) returns (SelectedResources);
+  rpc showMessage(ShowMessageRequest) returns (SelectedResponse);
 }
 
 message ShowTextDocumentRequest {
@@ -46,3 +47,27 @@ message ShowOpenDialogueFilterOption {
 message SelectedResources {
   repeated string paths = 1;
 }
+
+enum ShowMessageType {
+  ERROR = 0;
+  INFORMATION = 1;
+  WARNING = 2;
+}
+
+message ShowMessageRequest {
+  cline.Metadata metadata = 1;
+  ShowMessageType type = 2;
+  string message = 3;
+  optional ShowMessageRequestOptions options = 4;
+}
+
+message ShowMessageRequestOptions {
+  repeated string items = 1;
+  optional bool modal = 2;
+  optional string detail = 3;
+
+}
+
+message SelectedResponse {
+  optional string selected_option = 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
@@ -24,6 +23,8 @@ service ModelsService {
   rpc subscribeToOpenRouterModels(EmptyRequest) returns (stream OpenRouterCompatibleModelInfo);
   // Updates API configuration
   rpc updateApiConfigurationProto(UpdateApiConfigurationRequest) returns (Empty);
+   // Refreshes and returns Groq models
+  rpc refreshGroqModels(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
 }
 
 // List of VS Code LM models
@@ -121,8 +122,10 @@ enum ApiProvider {
   XAI = 21;
   SAMBANOVA = 22;
   CEREBRAS = 23;
-  SAPAICORE = 24;
-  CLAUDE_CODE = 25;
+  GROQ = 24;
+  SAPAICORE = 25;
+  CLAUDE_CODE = 26;
+  MOONSHOT = 27;
 }
 
 // Model info for OpenAI-compatible models
@@ -165,7 +168,7 @@ 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;
@@ -236,4 +239,11 @@ message ModelsApiConfiguration {
   optional string sap_ai_core_token_url = 71;
   optional string sap_ai_core_base_url = 72;
   optional string claude_code_path = 73;
-}
+  optional string aws_authentication = 74;
+  optional string aws_bedrock_api_key = 75;
+  optional string moonshot_api_key = 76;
+  optional string moonshot_api_line = 77;
+  optional string groq_api_key = 78;
+  optional string groq_model_id = 79;
+  optional OpenRouterModelInfo groq_model_info = 80;
+}

proto/package.json

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

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);
@@ -113,7 +112,7 @@ message UpdateSettingsRequest {
   optional int64 shell_integration_timeout = 8;
   optional bool terminal_reuse_enabled = 9;
   optional bool mcp_responses_collapsed = 10;
-  optional bool mcp_rich_display_enabled = 11;
+  optional string mcp_display_mode = 11;
   optional int64 terminal_output_line_limit = 12;
 }
 
@@ -126,7 +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;
@@ -233,4 +232,12 @@ message ApiConfiguration {
 
   // Claude Code specific
   optional string claude_code_path = 77;
+
+  // Extension fields for Bedrock Api Keys
+  optional string aws_authentication = 78;
+  optional string aws_bedrock_api_key = 79;
+
+  // Moonshot
+  optional string moonshot_api_key = 80;
+  optional string moonshot_api_line = 81;
 }

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/build-proto-config.mjs

@@ -27,5 +27,6 @@ export const hostServiceNameMap = {
 	workspace: "host.WorkspaceService",
 	env: "host.EnvService",
 	window: "host.WindowService",
+	diff: "host.DiffService",
 	// Add new host services here
 }

scripts/build-proto.mjs

@@ -9,22 +9,22 @@ import chalk from "chalk"
 import os from "os"
 
 import { createRequire } from "module"
-import { serviceNameMap, hostServiceNameMap } from "./build-proto-config.js"
+import { serviceNameMap, hostServiceNameMap } from "./build-proto-config.mjs"
 
 const require = createRequire(import.meta.url)
 const PROTOC = path.join(require.resolve("grpc-tools"), "../bin/protoc")
 
-const SCRIPT_DIR = path.dirname(fileURLToPath(import.meta.url))
-const ROOT_DIR = path.resolve(SCRIPT_DIR, "..")
+const SCRIPT_NAME = path.relative(process.cwd(), fileURLToPath(import.meta.url))
 
-const TS_OUT_DIR = path.join(ROOT_DIR, "src", "shared", "proto")
-const GRPC_JS_OUT_DIR = path.join(ROOT_DIR, "src", "generated", "grpc-js")
-const NICE_JS_OUT_DIR = path.join(ROOT_DIR, "src", "generated", "nice-grpc")
-const DESCRIPTOR_OUT_DIR = path.join(ROOT_DIR, "dist-standalone", "proto")
+const PROTO_DIR = path.resolve("proto")
+const TS_OUT_DIR = path.resolve("src/shared/proto")
+const GRPC_JS_OUT_DIR = path.resolve("src/generated/grpc-js")
+const NICE_JS_OUT_DIR = path.resolve("src/generated/nice-grpc")
+const DESCRIPTOR_OUT_DIR = path.resolve("dist-standalone/proto")
 
 const isWindows = process.platform === "win32"
 const TS_PROTO_PLUGIN = isWindows
-	? path.join(ROOT_DIR, "node_modules", ".bin", "protoc-gen-ts_proto.cmd") // Use the .bin directory path for Windows
+	? path.resolve("node_modules/.bin/protoc-gen-ts_proto.cmd") // Use the .bin directory path for Windows
 	: require.resolve("ts-proto/protoc-gen-ts_proto")
 
 const TS_PROTO_OPTIONS = [
@@ -37,12 +37,7 @@ const TS_PROTO_OPTIONS = [
 ]
 
 // Service directories derived from imported serviceNameMap
-const serviceDirs = Object.keys(serviceNameMap).map((serviceKey) => path.join(ROOT_DIR, "src", "core", "controller", serviceKey))
-
-// Host service directories derived from imported hostServiceNameMap
-const hostServiceDirs = Object.keys(hostServiceNameMap).map((serviceKey) =>
-	path.join(ROOT_DIR, "src", "hosts", "vscode", serviceKey),
-)
+const serviceDirs = Object.keys(serviceNameMap).map((serviceKey) => path.join("src/core/controller", serviceKey))
 
 async function main() {
 	console.log(chalk.bold.blue("Starting Protocol Buffer code generation..."))
@@ -61,8 +56,8 @@ async function main() {
 	await ensureProtoFilesExist()
 
 	// Process all proto files
-	const protoFiles = await globby("**/*.proto", { cwd: SCRIPT_DIR, realpath: true })
-	console.log(chalk.cyan(`Processing ${protoFiles.length} proto files from`), SCRIPT_DIR)
+	const protoFiles = await globby("**/*.proto", { cwd: PROTO_DIR, realpath: true })
+	console.log(chalk.cyan(`Processing ${protoFiles.length} proto files from`), PROTO_DIR)
 
 	tsProtoc(TS_OUT_DIR, protoFiles, TS_PROTO_OPTIONS)
 	// grpc-js is used to generate service impls for the ProtoBus service.
@@ -73,7 +68,7 @@ async function main() {
 	const descriptorFile = path.join(DESCRIPTOR_OUT_DIR, "descriptor_set.pb")
 	const descriptorProtocCommand = [
 		PROTOC,
-		`--proto_path="${SCRIPT_DIR}"`,
+		`--proto_path="${PROTO_DIR}"`,
 		`--descriptor_set_out="${descriptorFile}"`,
 		"--include_imports",
 		...protoFiles,
@@ -89,11 +84,12 @@ async function main() {
 	log_verbose(chalk.green("Protocol Buffer code generation completed successfully."))
 	log_verbose(chalk.green(`TypeScript files generated in: ${TS_OUT_DIR}`))
 
-	await generateMethodRegistrations()
-	await generateHostMethodRegistrations()
-	await generateServiceConfig()
-	await generateHostServiceConfig()
-	await generateGrpcClientConfig()
+	await generateProtoBusServiceConfig()
+	await generateProtoBusMethodRegistrations()
+	await generateProtoBusGrpcClientConfig()
+
+	await generateHostBridgeServiceConfig()
+	await generateHostBridgeMethodRegistrations()
 
 	console.log(chalk.bold.blue("Finished Protocol Buffer code generation."))
 }
@@ -102,7 +98,7 @@ async function tsProtoc(outDir, protoFiles, protoOptions) {
 	// Build the protoc command with proper path handling for cross-platform
 	const command = [
 		PROTOC,
-		`--proto_path="${SCRIPT_DIR}"`,
+		`--proto_path="${PROTO_DIR}"`,
 		`--plugin=protoc-gen-ts_proto="${TS_PROTO_PLUGIN}"`,
 		`--ts_proto_out="${outDir}"`,
 		`--ts_proto_opt=${protoOptions.join(",")} `,
@@ -122,7 +118,7 @@ async function tsProtoc(outDir, protoFiles, protoOptions) {
  * Generate a gRPC client configuration file for the webview
  * This eliminates the need for manual imports and client creation in grpc-client.ts
  */
-async function generateGrpcClientConfig() {
+async function generateProtoBusGrpcClientConfig() {
 	log_verbose(chalk.cyan("Generating gRPC client configuration..."))
 
 	const serviceImports = []
@@ -147,7 +143,7 @@ async function generateGrpcClientConfig() {
 
 	// Generate the file content
 	const content = `// AUTO-GENERATED FILE - DO NOT MODIFY DIRECTLY
-// Generated by proto/build-proto.js
+// Generated by ${SCRIPT_NAME}
 
 import { createGrpcClient } from "./grpc-client-base"
 ${serviceImports.join("\n")}
@@ -158,7 +154,7 @@ export {
 	${serviceExports.join(",\n\t")}
 }`
 
-	const filePath = path.join(ROOT_DIR, "webview-ui", "src", "services", "grpc-client.ts")
+	const filePath = path.resolve("webview-ui/src/services/grpc-client.ts")
 	await writeFileWithMkdirs(filePath, content)
 	log_verbose(chalk.green(`Generated gRPC client at ${filePath}`))
 }
@@ -221,12 +217,12 @@ async function parseProtoForStreamingMethods(protoFiles, scriptDir) {
 	return streamingMethodsMap
 }
 
-async function generateMethodRegistrations() {
+async function generateProtoBusMethodRegistrations() {
 	log_verbose(chalk.cyan("Generating method registration files..."))
 
 	// Parse proto files for streaming methods
-	const protoFiles = await globby("*.proto", { cwd: SCRIPT_DIR })
-	const streamingMethodsMap = await parseProtoForStreamingMethods(protoFiles, SCRIPT_DIR)
+	const protoFiles = await globby("*.proto", { cwd: PROTO_DIR })
+	const streamingMethodsMap = await parseProtoForStreamingMethods(protoFiles, PROTO_DIR)
 
 	for (const serviceDir of serviceDirs) {
 		const serviceName = path.basename(serviceDir)
@@ -243,7 +239,7 @@ async function generateMethodRegistrations() {
 
 		// Create the methods.ts file with header
 		let methodsContent = `// AUTO-GENERATED FILE - DO NOT MODIFY DIRECTLY
-// Generated by proto/build-proto.js
+// Generated by ${SCRIPT_NAME}
 
 // Import all method implementations
 import { registerMethod } from "./index"\n`
@@ -292,7 +288,7 @@ export function registerAllMethods(): void {
 		// Generate index.ts file
 		const capitalizedServiceName = serviceName.charAt(0).toUpperCase() + serviceName.slice(1)
 		const indexContent = `// AUTO-GENERATED FILE - DO NOT MODIFY DIRECTLY
-// Generated by proto/build-proto.js
+// Generated by ${SCRIPT_NAME}
 
 import { createServiceRegistry, ServiceMethodHandler, StreamingMethodHandler } from "../grpc-service"
 import { StreamingResponseHandler } from "../grpc-handler"
@@ -327,7 +323,7 @@ registerAllMethods()`
  * Generate a service configuration file that maps service names to their handlers
  * This eliminates the need for manual switch/case statements in grpc-handler.ts
  */
-async function generateServiceConfig() {
+async function generateProtoBusServiceConfig() {
 	log_verbose(chalk.cyan("Generating service configuration file..."))
 
 	const serviceImports = []
@@ -347,7 +343,7 @@ async function generateServiceConfig() {
 	}
 
 	const content = `// AUTO-GENERATED FILE - DO NOT MODIFY DIRECTLY
-// Generated by proto/build-proto.js
+// Generated by ${SCRIPT_NAME}
 
 import { Controller } from "./index"
 import { StreamingResponseHandler } from "./grpc-handler"
@@ -367,7 +363,7 @@ export interface ServiceHandlerConfig {
 export const serviceHandlers: Record<string, ServiceHandlerConfig> = {${serviceConfigs.join(",")}
 };`
 
-	const configPath = path.join(ROOT_DIR, "src", "core", "controller", "grpc-service-config.ts")
+	const configPath = path.resolve("src/core/controller/grpc-service-config.ts")
 	await writeFileWithMkdirs(configPath, content)
 	log_verbose(chalk.green(`Generated service configuration at ${configPath}`))
 }
@@ -380,7 +376,7 @@ async function ensureProtoFilesExist() {
 	log_verbose(chalk.cyan("Checking for missing proto files..."))
 
 	// Get existing proto files
-	const existingProtoFiles = await globby("*.proto", { cwd: SCRIPT_DIR })
+	const existingProtoFiles = await globby("*.proto", { cwd: PROTO_DIR })
 	const existingProtoServices = existingProtoFiles.map((file) => path.basename(file, ".proto"))
 
 	// Check each service in serviceNameMap
@@ -417,7 +413,7 @@ service ${serviceClassName} {
 `
 
 			// Write the template proto file
-			const protoFilePath = path.join(SCRIPT_DIR, `${serviceName}.proto`)
+			const protoFilePath = path.join(PROTO_DIR, `${serviceName}.proto`)
 			await fs.writeFile(protoFilePath, protoContent)
 			log_verbose(chalk.green(`Created template proto file at ${protoFilePath}`))
 		}
@@ -427,17 +423,22 @@ service ${serviceClassName} {
 /**
  * Generate method registration files for host services
  */
-async function generateHostMethodRegistrations() {
+async function generateHostBridgeMethodRegistrations() {
 	log_verbose(chalk.cyan("Generating host method registration files..."))
+	// Host service directories derived from imported hostServiceNameMap
+	const hostServiceDirs = Object.keys(hostServiceNameMap).map((serviceKey) =>
+		path.join("src/hosts/vscode/hostbridge", serviceKey),
+	)
 
 	// Parse proto files for streaming methods
-	const hostProtoFiles = await globby("*.proto", { cwd: path.join(SCRIPT_DIR, "host") })
-	const streamingMethodsMap = await parseProtoForStreamingMethods(hostProtoFiles, path.join(SCRIPT_DIR, "host"))
+	const hostProtoFiles = await globby("*.proto", { cwd: path.join(PROTO_DIR, "host") })
+	const streamingMethodsMap = await parseProtoForStreamingMethods(hostProtoFiles, path.join(PROTO_DIR, "host"))
 
 	for (const serviceDir of hostServiceDirs) {
 		const serviceName = path.basename(serviceDir)
 		const fullServiceName = hostServiceNameMap[serviceName]
 		const streamingMethods = streamingMethodsMap.get(fullServiceName) || []
+		const outputDir = path.join("src/generated/hosts/vscode/hostbridge", serviceName)
 
 		log_verbose(chalk.cyan(`Generating method registrations for host ${serviceName}...`))
 
@@ -449,7 +450,7 @@ async function generateHostMethodRegistrations() {
 
 		// Create the methods.ts file with header
 		let methodsContent = `// AUTO-GENERATED FILE - DO NOT MODIFY DIRECTLY
-// Generated by proto/build-proto.js
+// Generated ${SCRIPT_NAME}
 
 // Import all method implementations
 import { registerMethod } from "./index"\n`
@@ -457,7 +458,7 @@ import { registerMethod } from "./index"\n`
 		// Import implementations directly
 		for (const file of implementationFiles) {
 			const baseName = path.basename(file, ".ts")
-			methodsContent += `import { ${baseName} } from "./${baseName}"\n`
+			methodsContent += `import { ${baseName} } from "@hosts/vscode/hostbridge/${serviceName}/${baseName}"\n`
 		}
 
 		// Add streaming methods information
@@ -491,17 +492,17 @@ export function registerAllMethods(): void {
 		methodsContent += `}`
 
 		// Write the methods.ts file
-		const registryFile = path.join(serviceDir, "methods.ts")
+		const registryFile = path.join(outputDir, "methods.ts")
 		await writeFileWithMkdirs(registryFile, methodsContent)
 		log_verbose(chalk.green(`Generated ${registryFile}`))
 
 		// Generate index.ts file
 		const capitalizedServiceName = serviceName.charAt(0).toUpperCase() + serviceName.slice(1)
 		const indexContent = `// AUTO-GENERATED FILE - DO NOT MODIFY DIRECTLY
-// Generated by proto/build-proto.js
+// Generated by ${SCRIPT_NAME}
 
-import { createServiceRegistry, ServiceMethodHandler, StreamingMethodHandler } from "../host-grpc-service"
-import { StreamingResponseHandler } from "../host-grpc-handler"
+import { createServiceRegistry, ServiceMethodHandler, StreamingMethodHandler } from "@hosts/vscode/hostbridge-grpc-service"
+import { StreamingResponseHandler } from "@hosts/vscode/hostbridge-grpc-handler"
 import { registerAllMethods } from "./methods"
 
 // Create ${serviceName} service registry
@@ -521,7 +522,7 @@ export const isStreamingMethod = ${serviceName}Service.isStreamingMethod
 registerAllMethods()`
 
 		// Write the index.ts file
-		const indexFile = path.join(serviceDir, "index.ts")
+		const indexFile = path.join(outputDir, "index.ts")
 		await writeFileWithMkdirs(indexFile, indexContent)
 		log_verbose(chalk.green(`Generated ${indexFile}`))
 	}
@@ -532,7 +533,7 @@ registerAllMethods()`
 /**
  * Generate a service configuration file for host services
  */
-async function generateHostServiceConfig() {
+async function generateHostBridgeServiceConfig() {
 	log_verbose(chalk.cyan("Generating host service configuration file..."))
 
 	const serviceImports = []
@@ -542,7 +543,7 @@ async function generateHostServiceConfig() {
 	for (const [dirName, fullServiceName] of Object.entries(hostServiceNameMap)) {
 		const capitalizedName = dirName.charAt(0).toUpperCase() + dirName.slice(1)
 		serviceImports.push(
-			`import { handle${capitalizedName}ServiceRequest, handle${capitalizedName}ServiceStreamingRequest } from "./${dirName}/index"`,
+			`import { handle${capitalizedName}ServiceRequest, handle${capitalizedName}ServiceStreamingRequest } from "@generated/hosts/vscode/hostbridge/${dirName}/index"`,
 		)
 		serviceConfigs.push(`
   "${fullServiceName}": {
@@ -552,9 +553,9 @@ async function generateHostServiceConfig() {
 	}
 
 	const content = `// AUTO-GENERATED FILE - DO NOT MODIFY DIRECTLY
-// Generated by proto/build-proto.js
+// Generated by ${SCRIPT_NAME}
 
-import { StreamingResponseHandler } from "./host-grpc-handler"
+import { StreamingResponseHandler } from "@/hosts/vscode/hostbridge-grpc-handler"
 ${serviceImports.join("\n")}
 
 /**
@@ -571,7 +572,7 @@ export interface HostServiceHandlerConfig {
 export const hostServiceHandlers: Record<string, HostServiceHandlerConfig> = {${serviceConfigs.join(",")}
 };`
 
-	const filePath = path.join(ROOT_DIR, "src/hosts/vscode/host-grpc-service-config.ts")
+	const filePath = "src/generated/hosts/vscode/hostbridge-grpc-service-config.ts"
 	await writeFileWithMkdirs(filePath, content)
 	log_verbose(chalk.green(`Generated host service configuration at ${filePath}`))
 }
@@ -583,15 +584,33 @@ async function cleanup() {
 	for (const file of existingFiles) {
 		await fs.unlink(path.join(TS_OUT_DIR, file))
 	}
-	await rmdir(path.join(ROOT_DIR, "src", "generated"))
+	await rmdir("src/generated")
 
 	// Clean up generated files that were moved.
-	await fs.rm(path.join(ROOT_DIR, "src", "standalone", "services", "host-grpc-client.ts"), { force: true })
-	await rmdir(path.join(ROOT_DIR, "src", "standalone", "services"))
-	await fs.rm(path.join(ROOT_DIR, "hosts", "vscode"), { force: true, recursive: true })
-	await rmdir(path.join(ROOT_DIR, "hosts"))
+	await fs.rm("src/standalone/services/host-grpc-client.ts", { force: true })
+	await rmdir("src/standalone/services")
+	await fs.rm("hosts/vscode", { force: true, recursive: true })
+	await rmdir("hosts")
 
-	await fs.rm(path.join(ROOT_DIR, "src/standalone/server-setup.ts"), { force: true })
+	await fs.rm("src/standalone/server-setup.ts", { force: true })
+	await fs.rm("src/hosts/vscode/host-grpc-service-config.ts", { force: true })
+	const oldhostbridgefiles = [
+		"src/hosts/vscode/workspace/methods.ts",
+		"src/hosts/vscode/workspace/index.ts",
+		"src/hosts/vscode/diff/methods.ts",
+		"src/hosts/vscode/diff/index.ts",
+		"src/hosts/vscode/env/methods.ts",
+		"src/hosts/vscode/env/index.ts",
+		"src/hosts/vscode/window/methods.ts",
+		"src/hosts/vscode/window/index.ts",
+		"src/hosts/vscode/watch/methods.ts",
+		"src/hosts/vscode/watch/index.ts",
+		"src/hosts/vscode/uri/methods.ts",
+		"src/hosts/vscode/uri/index.ts",
+	]
+	for (const file of oldhostbridgefiles) {
+		await fs.rm(file, { force: true })
+	}
 }
 
 /**

scripts/get-vscode-usages.sh

@@ -5,17 +5,31 @@ DIR=${1:-src/}
 DEST_DIR=dist-standalone
 SDK_DEST=$DEST_DIR/vscode-sdk-uses.txt
 CSS_DEST=$DEST_DIR/vscode-css-uses.txt
+TMP=/tmp/vscode-sdk-uses.txt.tmp
 mkdir -p $DEST_DIR
 
 {
 git grep -h 'vscode\.' $DIR |
 grep -Ev '//.*vscode' | # remove commented out code
+grep -v vscode.commands.executeCommand | # executeCommand is handled separately
+grep -Ev '"vscode' | # remove command strings that get included because they start with vscode
 sed 's|.*vscode\.|vscode.|'| # remove everything before vscode.
 sed 's/[^a-zA-Z0-9_.].*$//' | # remove everything after last identifier
 grep -E '\.[a-z][^.]+$' | # remove types (last part of identifier should be lowercase)
-sort | uniq -c | sort -n | # Count occurrences
-cat > $SDK_DEST
+cat > $TMP
 }
+{
+  grep -rh vscode.commands.executeCommand $DIR |
+  perl -ne 'print if /["\x27"]/'  | # Remove occurrences where the command is not on the same line (line doesnt contain quote chars) :(
+  sed -n 's|.*\(vscode.commands.executeCommand[^,]*\).*|\1|p'| # Remove all params after the first one
+  sed 's|\(".*"\).*|\1)|'| # Close the parantheses
+  cat >> $TMP
+}
+
+# Count occurrences
+cat $TMP | sort | uniq -c | sort -n > $SDK_DEST
+rm $TMP
+
 echo Wrote uses of the vscode SDK to $(realpath $SDK_DEST)
 
 {

scripts/package-standalone.mjs

@@ -1,83 +1,175 @@
-import fs from "fs"
-import path from "path"
-import { glob } from "glob"
+#!/usr/bin/env node
+
 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 minimatch from "minimatch"
+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 } })
 
-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
+	// Exclude the same files as the VCE vscode extension packager.
+	// Also ignore the dist directory, the build directory for the extension.
+	const isIgnored = createIsIgnored(["dist/**"])
 
-	if (include.some((prefix) => name.startsWith(prefix))) {
+	// Add the whole cline directory under "extension", except the for the ignored files.
+	archive.directory(process.cwd(), "extension", (entry) => {
+		if (isIgnored(entry.name)) {
+			log_verbose("Ignoring", entry.name)
+			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()
+}
+
+/**
+ * This is based on https://github.com/microsoft/vscode-vsce/blob/fafad8a63e9cf31179f918eb7a4eeb376834c904/src/package.ts#L1695
+ * because the .vscodeignore format is not compatible with the `ignore` npm module.
+ */
+function createIsIgnored(standaloneIgnores) {
+	const MinimatchOptions = { dot: true }
+	const defaultIgnore = [
+		".vscodeignore",
+		"package-lock.json",
+		"npm-debug.log",
+		"yarn.lock",
+		"yarn-error.log",
+		"npm-shrinkwrap.json",
+		".editorconfig",
+		".npmrc",
+		".yarnrc",
+		".gitattributes",
+		"*.todo",
+		"tslint.yaml",
+		".eslintrc*",
+		".babelrc*",
+		".prettierrc*",
+		".cz-config.js",
+		".commitlintrc*",
+		"webpack.config.js",
+		"ISSUE_TEMPLATE.md",
+		"CONTRIBUTING.md",
+		"PULL_REQUEST_TEMPLATE.md",
+		"CODE_OF_CONDUCT.md",
+		".github",
+		".travis.yml",
+		"appveyor.yml",
+		"**/.git",
+		"**/.git/**",
+		"**/*.vsix",
+		"**/.DS_Store",
+		"**/*.vsixmanifest",
+		"**/.vscode-test/**",
+		"**/.vscode-test-web/**",
+	]
+
+	const rawIgnore = fs.readFileSync(".vscodeignore", "utf8")
+
+	// Parse raw ignore by splitting output into lines and filtering out empty lines and comments
+	const parsedIgnore = rawIgnore
+		.split(/[\n\r]/)
+		.map((s) => s.trim())
+		.filter((s) => !!s)
+		.filter((i) => !/^\s*#/.test(i))
+
+	// Add '/**' to possible folder names
+	const expandedIgnore = [
+		...parsedIgnore,
+		...parsedIgnore.filter((i) => !/(^|\/)[^/]*\*[^/]*$/.test(i)).map((i) => (/\/$/.test(i) ? `${i}**` : `${i}/**`)),
+	]
+
+	// Combine with default ignore list
+	// Also ignore the dist directory- the build directory for the extension.
+	const allIgnore = [...defaultIgnore, ...expandedIgnore, ...standaloneIgnores]
+
+	// Split into ignore and negate list
+	const [ignore, negate] = allIgnore.reduce(
+		(r, e) => (!/^\s*!/.test(e) ? [[...r[0], e], r[1]] : [r[0], [...r[1], e]]),
+		[[], []],
+	)
+
+	function isIgnored(f) {
+		return (
+			ignore.some((i) => minimatch(f, i, MinimatchOptions)) &&
+			!negate.some((i) => minimatch(f, i.substr(1), MinimatchOptions))
+		)
+	}
+	return isIgnored
+}
+
+/* cp -r */
+async function cpr(source, dest) {
+	await cp(source, dest, {
+		recursive: true,
+		preserveTimestamps: true,
+		dereference: false, // preserve symlinks instead of following them
+	})
+}
+
+function log_verbose(...args) {
+	if (process.argv.includes("-v") || process.argv.includes("--verbose")) {
+		console.log(...args)
+	}
+}
+
+await main()

src/api/index.ts

@@ -27,6 +27,8 @@ import { SambanovaHandler } from "./providers/sambanova"
 import { CerebrasHandler } from "./providers/cerebras"
 import { SapAiCoreHandler } from "./providers/sapaicore"
 import { ClaudeCodeHandler } from "./providers/claude-code"
+import { MoonshotHandler } from "./providers/moonshot"
+import { GroqHandler } from "./providers/groq"
 
 export interface ApiHandler {
 	createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream
@@ -38,62 +40,217 @@ 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,
+				awsAuthentication: options.awsAuthentication,
+				awsBedrockApiKey: options.awsBedrockApiKey,
+				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 "moonshot":
+			return new MoonshotHandler({
+				moonshotApiKey: options.moonshotApiKey,
+				moonshotApiLine: options.moonshotApiLine,
+				apiModelId: options.apiModelId,
+			})
 		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 "groq":
+			return new GroqHandler({
+				groqApiKey: options.groqApiKey,
+				groqModelId: options.groqModelId,
+				groqModelInfo: options.groqModelInfo,
+				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__/bedrock.test.ts

@@ -182,6 +182,24 @@ describe("AwsBedrockHandler", () => {
 
 			process.env["AWS_PROFILE"]!.should.equal(preAWSProfile)
 		})
+
+		it("should work with AWS_BEARER_TOKEN_BEDROCK", async () => {
+			process.env["AWS_BEARER_TOKEN_BEDROCK"] = "test-key"
+
+			const preAWSProfile = process.env["AWS_BEARER_TOKEN_BEDROCK"]
+
+			await AwsBedrockHandler["withTempEnv"](
+				() => {
+					delete process.env["AWS_BEARER_TOKEN_BEDROCK"]
+				},
+				async () => {
+					should.not.exist(process.env["AWS_BEARER_TOKEN_BEDROCK"])
+					return "test"
+				},
+			)
+
+			process.env["AWS_BEARER_TOKEN_BEDROCK"]!.should.equal(preAWSProfile)
+		})
 	})
 
 	const mockOptions: ApiHandlerOptions = {
@@ -192,6 +210,7 @@ describe("AwsBedrockHandler", () => {
 		awsSessionToken: "",
 		awsUseProfile: false,
 		awsProfile: "",
+		awsBedrockApiKey: "",
 		awsBedrockUsePromptCache: false,
 		awsUseCrossRegionInference: false,
 		awsBedrockEndpoint: "",

src/api/providers/anthropic.ts

@@ -5,11 +5,18 @@ 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 | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: AnthropicHandlerOptions) {
 		this.options = options
 	}
 

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 +16,24 @@ 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
+	awsAuthentication?: string
+	awsBedrockApiKey?: 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 +108,9 @@ 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
 	}
 
@@ -170,7 +188,10 @@ export class AwsBedrockHandler implements ApiHandler {
 	}> {
 		// Configure provider options
 		const providerOptions: ProviderChainOptions = {}
-		if (this.options.awsUseProfile) {
+		const useProfile =
+			(this.options.awsAuthentication === undefined && this.options.awsUseProfile) ||
+			this.options.awsAuthentication === "profile"
+		if (useProfile) {
 			// For profile-based auth, always use ignoreCache to detect credential file changes
 			// This solves the AWS Identity Manager issue where credential files change externally
 			providerOptions.ignoreCache = true
@@ -184,7 +205,7 @@ export class AwsBedrockHandler implements ApiHandler {
 		return await AwsBedrockHandler.withTempEnv(
 			() => {
 				AwsBedrockHandler.setEnv("AWS_REGION", this.options.awsRegion)
-				if (this.options.awsUseProfile) {
+				if (useProfile) {
 					AwsBedrockHandler.setEnv("AWS_PROFILE", this.options.awsProfile)
 				} else {
 					delete process.env["AWS_PROFILE"]
@@ -208,15 +229,26 @@ export class AwsBedrockHandler implements ApiHandler {
 	 * Creates a BedrockRuntimeClient with the appropriate credentials
 	 */
 	private async getBedrockClient(): Promise<BedrockRuntimeClient> {
-		const credentials = await this.getAwsCredentials()
+		let auth: any
 
+		if (this.options.awsAuthentication === "apikey") {
+			auth = {
+				token: { token: this.options.awsBedrockApiKey },
+				authSchemePreference: ["httpBearerAuth"],
+			}
+		} else {
+			const credentials = await this.getAwsCredentials()
+			auth = {
+				credentials: {
+					accessKeyId: credentials.accessKeyId,
+					secretAccessKey: credentials.secretAccessKey,
+					sessionToken: credentials.sessionToken,
+				},
+			}
+		}
 		return new BedrockRuntimeClient({
 			region: this.getRegion(),
-			credentials: {
-				accessKeyId: credentials.accessKeyId,
-				secretAccessKey: credentials.secretAccessKey,
-				sessionToken: credentials.sessionToken,
-			},
+			...auth,
 			...(this.options.awsBedrockEndpoint && { endpoint: this.options.awsBedrockEndpoint }),
 		})
 	}

src/api/providers/cerebras.ts

@@ -1,15 +1,20 @@
 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 options: CerebrasHandlerOptions
 	private client: Cerebras | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: CerebrasHandlerOptions) {
 		this.options = options
 	}
 

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
 	}
 

src/api/providers/cline.ts

@@ -1,157 +1,207 @@
 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"
+import { version as extensionVersion } from "../../../package.json"
+import { shouldSkipReasoningForModel } from "@utils/model-utils"
+import { CLINE_ACCOUNT_AUTH_ERROR_MESSAGE } from "@/shared/ClineAccount"
+
+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 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._authService = AuthService.getInstance()
 	}
 
-	private ensureClient(): OpenAI {
+	private async ensureClient(): Promise<OpenAI> {
+		const clineAccountAuthToken = await this._authService.getAuthToken()
+		if (!clineAccountAuthToken) {
+			throw new Error(CLINE_ACCOUNT_AUTH_ERROR_MESSAGE)
+		}
 		if (!this.client) {
-			if (!this.options.clineApiKey) {
-				throw new Error("You don't seem to be logged in to a Cline account.")
-			}
 			try {
 				this.client = new OpenAI({
-					baseURL: "https://api.cline.bot/v1",
-					apiKey: this.options.clineApiKey || "",
+					baseURL: `${this._baseUrl}/api/v1`,
+					apiKey: clineAccountAuthToken,
 					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
+						"HTTP-Referer": "https://cline.bot",
+						"X-Title": "Cline",
+						"X-Task-ID": this.options.taskId || "",
+						"X-Cline-Version": extensionVersion,
 					},
 				})
-			} catch (error) {
+			} 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 = this.ensureClient()
-		this.lastGenerationId = undefined
+		try {
+			const client = await this.ensureClient()
 
-		const stream = await createOpenRouterStream(
-			client,
-			systemPrompt,
-			messages,
-			this.getModel(),
-			this.options.reasoningEffort,
-			this.options.thinkingBudgetTokens,
-			this.options.openRouterProviderSorting,
-		)
+			this.lastGenerationId = undefined
 
-		let didOutputUsage: boolean = false
+			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}`)
-			}
+			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
+				// Skip reasoning content for Grok 4 models since it only displays "thinking" without providing useful information
+				if ("reasoning" in delta && delta.reasoning && !shouldSkipReasoningForModel(this.options.openRouterModelId)) {
+					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) {
+			console.error("Cline API Error:", error)
+			const requestId = error?.request_id ? `\n | Request ID: ${error.request_id}` : ""
+			if (error.code === "ERR_BAD_REQUEST" || error.status === 401) {
+				throw new Error(CLINE_ACCOUNT_AUTH_ERROR_MESSAGE + requestId)
+			} else if (error.code === "insufficient_credits" || error.status === 402) {
+				if (error.error) {
+					throw new Error(JSON.stringify(error.error))
+				}
+			}
+			const _error = error instanceof Error ? error : new Error(String(error))
+			_error.message = _error.message + requestId
+			throw _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
 				})
@@ -189,9 +239,6 @@ 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

@@ -8,11 +8,16 @@ import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 import { convertToR1Format } from "../transform/r1-format"
 
+interface DeepSeekHandlerOptions {
+	deepSeekApiKey?: string
+	apiModelId?: string
+}
+
 export class DeepSeekHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: DeepSeekHandlerOptions
 	private client: OpenAI | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: DeepSeekHandlerOptions) {
 		this.options = options
 	}
 

src/api/providers/doubao.ts

@@ -1,15 +1,20 @@
 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 options: DoubaoHandlerOptions
 	private client: OpenAI | undefined
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: DoubaoHandlerOptions) {
 		this.options = options
 	}
 

src/api/providers/fireworks.ts

@@ -2,22 +2,22 @@ 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"
 
+interface FireworksHandlerOptions {
+	fireworksApiKey?: string
+	fireworksModelId?: string
+	fireworksModelMaxCompletionTokens?: number
+	fireworksModelMaxTokens?: number
+}
+
 export class FireworksHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: FireworksHandlerOptions
 	private client: OpenAI | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: FireworksHandlerOptions) {
 		this.options = options
 	}
 

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
 }
 
 /**

src/api/providers/groq.ts

@@ -0,0 +1,290 @@
+import { Anthropic } from "@anthropic-ai/sdk"
+import OpenAI from "openai"
+import { withRetry } from "../retry"
+import { ApiHandler } from "../"
+import { GroqModelId, ModelInfo, groqDefaultModelId, groqModels } from "@shared/api"
+import { calculateApiCostOpenAI } from "../../utils/cost"
+import { convertToOpenAiMessages } from "../transform/openai-format"
+import { ApiStream } from "../transform/stream"
+
+interface GroqHandlerOptions {
+	groqApiKey?: string
+	groqModelId?: string
+	groqModelInfo?: ModelInfo
+	apiModelId?: string // For backward compatibility
+}
+
+// Model family definitions for enhanced behavior
+interface GroqModelFamily {
+	name: string
+	supportedFeatures: {
+		streaming: boolean
+		temperature: boolean
+		vision: boolean
+		tools: boolean
+	}
+	maxTokensOverride?: number
+	specialParams?: Record<string, any>
+}
+
+const MODEL_FAMILIES: Record<string, GroqModelFamily> = {
+	// Moonshort 4 Family - Latest generation with vision support
+	"kimi-k2": {
+		name: "kimi-k2",
+		supportedFeatures: { streaming: true, temperature: true, vision: true, tools: true },
+		maxTokensOverride: 8192,
+	},
+	// Llama 4 Family - Latest generation with vision support
+	llama4: {
+		name: "Llama 4",
+		supportedFeatures: { streaming: true, temperature: true, vision: true, tools: true },
+		maxTokensOverride: 8192,
+	},
+	// Llama 3.3 Family - Balanced performance
+	"llama3.3": {
+		name: "Llama 3.3",
+		supportedFeatures: { streaming: true, temperature: true, vision: false, tools: true },
+		maxTokensOverride: 32768,
+	},
+	// Llama 3.1 Family - Fast inference
+	"llama3.1": {
+		name: "Llama 3.1",
+		supportedFeatures: { streaming: true, temperature: true, vision: false, tools: true },
+		maxTokensOverride: 131072,
+	},
+	// DeepSeek Family - Reasoning-optimized
+	deepseek: {
+		name: "DeepSeek",
+		supportedFeatures: { streaming: true, temperature: true, vision: false, tools: true },
+		maxTokensOverride: 8192,
+		specialParams: {
+			top_p: 0.95,
+			reasoning_format: "parsed",
+		},
+	},
+	// Qwen Family - Enhanced for Q&A
+	qwen: {
+		name: "Qwen",
+		supportedFeatures: { streaming: true, temperature: true, vision: false, tools: true },
+		maxTokensOverride: 32768,
+	},
+	// Compound Models - Hybrid architectures
+	compound: {
+		name: "Compound",
+		supportedFeatures: { streaming: true, temperature: true, vision: false, tools: true },
+		maxTokensOverride: 8192,
+	},
+}
+
+export class GroqHandler implements ApiHandler {
+	private options: GroqHandlerOptions
+	private client: OpenAI | undefined
+
+	constructor(options: GroqHandlerOptions) {
+		this.options = options
+	}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.groqApiKey) {
+				throw new Error("Groq API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					baseURL: "https://api.groq.com/openai/v1",
+					apiKey: this.options.groqApiKey,
+				})
+			} catch (error) {
+				throw new Error(`Error creating Groq client: ${error.message}`)
+			}
+		}
+		return this.client
+	}
+
+	private async *yieldUsage(info: ModelInfo, usage: OpenAI.Completions.CompletionUsage | undefined): ApiStream {
+		const inputTokens = usage?.prompt_tokens || 0
+		const outputTokens = usage?.completion_tokens || 0
+		const totalCost = calculateApiCostOpenAI(info, inputTokens, outputTokens)
+		yield {
+			type: "usage",
+			inputTokens,
+			outputTokens,
+			cacheWriteTokens: 0,
+			cacheReadTokens: 0,
+			totalCost,
+		}
+	}
+
+	/**
+	 * Detects the model family based on the model ID
+	 */
+	private detectModelFamily(modelId: string): GroqModelFamily {
+		if (modelId.includes("kimi-k2")) {
+			return MODEL_FAMILIES["kimi-k2"]
+		}
+		// Llama 4 variants
+		if (modelId.includes("llama-4") || modelId.includes("llama/llama-4")) {
+			return MODEL_FAMILIES.llama4
+		}
+		// Llama 3.3 variants
+		if (modelId.includes("llama-3.3")) {
+			return MODEL_FAMILIES["llama3.3"]
+		}
+		// Llama 3.1 variants
+		if (modelId.includes("llama-3.1")) {
+			return MODEL_FAMILIES["llama3.1"]
+		}
+		// DeepSeek variants
+		if (modelId.includes("deepseek")) {
+			return MODEL_FAMILIES.deepseek
+		}
+		// Qwen variants
+		if (modelId.includes("qwen")) {
+			return MODEL_FAMILIES.qwen
+		}
+		// Compound variants
+		if (modelId.includes("compound")) {
+			return MODEL_FAMILIES.compound
+		}
+
+		// Default fallback to Llama 3.3 behavior
+		return MODEL_FAMILIES["kimi-k2"]
+	}
+
+	/**
+	 * Gets the optimal max_tokens based on model family and capabilities
+	 */
+	private getOptimalMaxTokens(model: { id: string; info: ModelInfo }, modelFamily: GroqModelFamily): number {
+		// Use model-specific max tokens if available
+		if (model.info.maxTokens && model.info.maxTokens > 0) {
+			return model.info.maxTokens
+		}
+
+		// Use family override if available
+		if (modelFamily.maxTokensOverride) {
+			return modelFamily.maxTokensOverride
+		}
+
+		// Default fallback
+		return 8192
+	}
+
+	@withRetry()
+	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
+		const model = this.getModel()
+		const modelFamily = this.detectModelFamily(model.id)
+
+		// Optimize parameters based on model family
+		const temperature = 0
+		const maxTokens = this.getOptimalMaxTokens(model, modelFamily)
+
+		const openAiMessages: OpenAI.Chat.ChatCompletionMessageParam[] = [
+			{ role: "system", content: systemPrompt },
+			...convertToOpenAiMessages(messages),
+		]
+
+		// Build request parameters with model-specific optimizations
+		const requestParams: OpenAI.Chat.ChatCompletionCreateParamsStreaming & {
+			reasoning_format?: "parsed" | "raw" | "hidden"
+			top_p?: number
+		} = {
+			model: model.id,
+			max_tokens: maxTokens,
+			messages: openAiMessages,
+			stream: true,
+			stream_options: { include_usage: true },
+			temperature,
+		}
+
+		// Add any special parameters for specific model families
+		if (modelFamily.specialParams) {
+			Object.assign(requestParams, modelFamily.specialParams)
+		}
+
+		const stream = await client.chat.completions.create(requestParams)
+
+		for await (const chunk of stream) {
+			const delta = chunk.choices[0]?.delta
+
+			// Handle reasoning field if present (for reasoning models with parsed output)
+			if ((delta as any)?.reasoning) {
+				const reasoningContent = (delta as any).reasoning as string
+				yield {
+					type: "reasoning",
+					reasoning: reasoningContent,
+				}
+				continue
+			}
+
+			// Handle content field - trust the parsed output from Groq
+			if (delta?.content) {
+				yield {
+					type: "text",
+					text: delta.content,
+				}
+			}
+
+			// Handle usage information
+			if (chunk.usage) {
+				yield* this.yieldUsage(model.info, chunk.usage)
+			}
+		}
+	}
+
+	/**
+	 * Checks if the current model supports vision/images
+	 */
+	supportsImages(): boolean {
+		const model = this.getModel()
+		return model.info.supportsImages === true
+	}
+
+	/**
+	 * Checks if the current model supports tools
+	 */
+	supportsTools(): boolean {
+		const model = this.getModel()
+		const modelFamily = this.detectModelFamily(model.id)
+		return modelFamily.supportedFeatures.tools
+	}
+
+	/**
+	 * Gets model information with enhanced family detection
+	 */
+	getModel(): { id: string; info: ModelInfo } {
+		// First priority: groqModelId and groqModelInfo (like Requesty does)
+		const groqModelId = this.options.groqModelId
+		const groqModelInfo = this.options.groqModelInfo
+		if (groqModelId && groqModelInfo) {
+			return { id: groqModelId, info: groqModelInfo }
+		}
+
+		// Second priority: groqModelId with static model info
+		if (groqModelId && groqModelId in groqModels) {
+			const id = groqModelId as GroqModelId
+			return { id, info: groqModels[id] }
+		}
+
+		// Third priority: apiModelId (for backward compatibility)
+		const apiModelId = this.options.apiModelId
+		if (apiModelId && apiModelId in groqModels) {
+			const id = apiModelId as GroqModelId
+			return { id, info: groqModels[id] }
+		}
+
+		// Default fallback
+		return {
+			id: groqDefaultModelId,
+			info: groqModels[groqDefaultModelId],
+		}
+	}
+
+	/**
+	 * Gets model family information for debugging/introspection
+	 */
+	getModelFamily(): GroqModelFamily {
+		const model = this.getModel()
+		return this.detectModelFamily(model.id)
+	}
+}

src/api/providers/litellm.ts

@@ -1,16 +1,26 @@
 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"
 
+interface LiteLlmHandlerOptions {
+	liteLlmApiKey?: string
+	liteLlmBaseUrl?: string
+	liteLlmModelId?: string
+	liteLlmModelInfo?: LiteLLMModelInfo
+	thinkingBudgetTokens?: number
+	liteLlmUsePromptCache?: boolean
+	taskId?: string
+}
+
 export class LiteLlmHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: LiteLlmHandlerOptions
 	private client: OpenAI | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: LiteLlmHandlerOptions) {
 		this.options = options
 	}
 

src/api/providers/lmstudio.ts

@@ -6,11 +6,16 @@ import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 import { withRetry } from "../retry"
 
+interface LmStudioHandlerOptions {
+	lmStudioBaseUrl?: string
+	lmStudioModelId?: string
+}
+
 export class LmStudioHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: LmStudioHandlerOptions
 	private client: OpenAI | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: LmStudioHandlerOptions) {
 		this.options = options
 	}
 

src/api/providers/mistral.ts

@@ -2,15 +2,20 @@ 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"
 
+interface MistralHandlerOptions {
+	mistralApiKey?: string
+	apiModelId?: string
+}
+
 export class MistralHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: MistralHandlerOptions
 	private client: Mistral | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: MistralHandlerOptions) {
 		this.options = options
 	}
 

src/api/providers/moonshot.ts

@@ -0,0 +1,90 @@
+import { Anthropic } from "@anthropic-ai/sdk"
+import OpenAI from "openai"
+import { withRetry } from "../retry"
+import { ApiHandler } from "../index"
+import { convertToOpenAiMessages } from "../transform/openai-format"
+import { ApiStream } from "../transform/stream"
+import { ModelInfo, MoonshotModelId, moonshotModels, moonshotDefaultModelId } from "@/shared/api"
+
+interface MoonshotHandlerOptions {
+	moonshotApiKey?: string
+	moonshotApiLine?: string
+	apiModelId?: string
+}
+
+export class MoonshotHandler implements ApiHandler {
+	private client: OpenAI | undefined
+
+	constructor(private readonly options: MoonshotHandlerOptions) {}
+
+	private ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.moonshotApiKey) {
+				throw new Error("Moonshot API key is required")
+			}
+			try {
+				this.client = new OpenAI({
+					baseURL:
+						this.options.moonshotApiLine === "china" ? "https://api.moonshot.cn/v1" : "https://api.moonshot.ai/v1",
+					apiKey: this.options.moonshotApiKey,
+				})
+			} catch (error) {
+				throw new Error(`Error creating Moonshot 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[] = [
+			{ role: "system", content: systemPrompt },
+			...convertToOpenAiMessages(messages),
+		]
+
+		const stream = await client.chat.completions.create({
+			model: model.id,
+			messages: openAiMessages,
+			temperature: 0,
+			stream: true,
+			stream_options: { include_usage: true },
+		})
+		for await (const chunk of stream) {
+			const delta = chunk.choices[0]?.delta
+			if (delta?.content) {
+				yield {
+					type: "text",
+					text: delta.content,
+				}
+			}
+
+			if (delta && "reasoning_content" in delta && delta.reasoning_content) {
+				yield {
+					type: "reasoning",
+					reasoning: (delta.reasoning_content as string | undefined) || "",
+				}
+			}
+
+			if (chunk.usage) {
+				yield {
+					type: "usage",
+					inputTokens: chunk.usage.prompt_tokens || 0,
+					outputTokens: chunk.usage.completion_tokens || 0,
+				}
+			}
+		}
+	}
+
+	getModel(): { id: MoonshotModelId; info: ModelInfo } {
+		const modelId = this.options.apiModelId
+
+		if (modelId && modelId in moonshotModels) {
+			const id = modelId as MoonshotModelId
+			return { id, info: moonshotModels[id] }
+		}
+		return { id: moonshotDefaultModelId, info: moonshotModels[moonshotDefaultModelId] }
+	}
+}

src/api/providers/nebius.ts

@@ -5,12 +5,17 @@ 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 | undefined
 
-	constructor(private readonly options: ApiHandlerOptions) {}
+	constructor(private readonly options: NebiusHandlerOptions) {}
 
 	private ensureClient(): OpenAI {
 		if (!this.client) {

src/api/providers/ollama.ts

@@ -6,11 +6,18 @@ import { convertToOllamaMessages } from "../transform/ollama-format"
 import { ApiStream } from "../transform/stream"
 import { withRetry } from "../retry"
 
+interface OllamaHandlerOptions {
+	ollamaBaseUrl?: string
+	ollamaModelId?: string
+	ollamaApiOptionsCtxNum?: string
+	requestTimeoutMs?: number
+}
+
 export class OllamaHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: OllamaHandlerOptions
 	private client: Ollama | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: OllamaHandlerOptions) {
 		this.options = options
 	}
 

src/api/providers/openai-native.ts

@@ -8,11 +8,17 @@ import { calculateApiCostOpenAI } from "../../utils/cost"
 import { ApiStream } from "../transform/stream"
 import type { ChatCompletionReasoningEffort } from "openai/resources/chat/completions"
 
+interface OpenAiNativeHandlerOptions {
+	openAiNativeApiKey?: string
+	reasoningEffort?: string
+	apiModelId?: string
+}
+
 export class OpenAiNativeHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: OpenAiNativeHandlerOptions
 	private client: OpenAI | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: OpenAiNativeHandlerOptions) {
 		this.options = options
 	}
 

src/api/providers/openai.ts

@@ -1,18 +1,28 @@
 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"
 
+interface OpenAiHandlerOptions {
+	openAiApiKey?: string
+	openAiBaseUrl?: string
+	azureApiVersion?: string
+	openAiHeaders?: Record<string, string>
+	openAiModelId?: string
+	openAiModelInfo?: OpenAiCompatibleModelInfo
+	reasoningEffort?: string
+}
+
 export class OpenAiHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: OpenAiHandlerOptions
 	private client: OpenAI | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: OpenAiHandlerOptions) {
 		this.options = options
 	}
 

src/api/providers/openrouter.ts

@@ -3,18 +3,28 @@ 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"
+import { shouldSkipReasoningForModel } from "@utils/model-utils"
+
+interface OpenRouterHandlerOptions {
+	openRouterApiKey?: string
+	openRouterModelId?: string
+	openRouterModelInfo?: ModelInfo
+	openRouterProviderSorting?: string
+	reasoningEffort?: string
+	thinkingBudgetTokens?: number
+}
 
 export class OpenRouterHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: OpenRouterHandlerOptions
 	private client: OpenAI | undefined
 	lastGenerationId?: string
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: OpenRouterHandlerOptions) {
 		this.options = options
 	}
 
@@ -103,7 +113,8 @@ export class OpenRouterHandler implements ApiHandler {
 			}
 
 			// Reasoning tokens are returned separately from the content
-			if ("reasoning" in delta && delta.reasoning) {
+			// Skip reasoning content for Grok 4 models since it only displays "thinking" without providing useful information
+			if ("reasoning" in delta && delta.reasoning && !shouldSkipReasoningForModel(this.options.openRouterModelId)) {
 				yield {
 					type: "reasoning",
 					// @ts-ignore-next-line
@@ -204,9 +215,6 @@ 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,
@@ -16,11 +15,18 @@ import { ApiStream } from "../transform/stream"
 import { convertToR1Format } from "../transform/r1-format"
 import { withRetry } from "../retry"
 
+interface QwenHandlerOptions {
+	qwenApiKey?: string
+	qwenApiLine?: string
+	apiModelId?: string
+	thinkingBudgetTokens?: number
+}
+
 export class QwenHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: QwenHandlerOptions
 	private client: OpenAI | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: QwenHandlerOptions) {
 		this.options = options
 	}
 

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 {
@@ -18,10 +26,10 @@ interface RequestyUsage extends OpenAI.CompletionUsage {
 }
 
 export class RequestyHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: RequestyHandlerOptions
 	private client: OpenAI | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: RequestyHandlerOptions) {
 		this.options = options
 	}
 

src/api/providers/sambanova.ts

@@ -1,17 +1,22 @@
 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"
 
+interface SambanovaHandlerOptions {
+	sambanovaApiKey?: string
+	apiModelId?: string
+}
+
 export class SambanovaHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: SambanovaHandlerOptions
 	private client: OpenAI | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: SambanovaHandlerOptions) {
 		this.options = options
 	}
 

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()
@@ -283,7 +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 {
@@ -346,7 +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) {
@@ -422,7 +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]
@@ -446,7 +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 {

src/api/providers/together.ts

@@ -1,17 +1,22 @@
 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"
 
+interface TogetherHandlerOptions {
+	togetherApiKey?: string
+	togetherModelId?: string
+}
+
 export class TogetherHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: TogetherHandlerOptions
 	private client: OpenAI | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: TogetherHandlerOptions) {
 		this.options = options
 	}
 

src/api/providers/vertex.ts

@@ -6,12 +6,22 @@ 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 | undefined
 	private clientAnthropic: AnthropicVertex | undefined
-	private options: ApiHandlerOptions
+	private options: VertexHandlerOptions
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: VertexHandlerOptions) {
 		this.options = options
 	}
 

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

@@ -1,17 +1,24 @@
 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"
+import { shouldSkipReasoningForModel } from "@utils/model-utils"
+
+interface XAIHandlerOptions {
+	xaiApiKey?: string
+	reasoningEffort?: string
+	apiModelId?: string
+}
 
 export class XAIHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: XAIHandlerOptions
 	private client: OpenAI | undefined
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: XAIHandlerOptions) {
 		this.options = options
 	}
 
@@ -64,10 +71,13 @@ export class XAIHandler implements ApiHandler {
 			}
 
 			if (delta && "reasoning_content" in delta && delta.reasoning_content) {
-				yield {
-					type: "reasoning",
-					// @ts-ignore-next-line
-					reasoning: delta.reasoning_content,
+				// Skip reasoning content for Grok 4 models since it only displays "thinking" without providing useful information
+				if (!shouldSkipReasoningForModel(modelId)) {
+					yield {
+						type: "reasoning",
+						// @ts-ignore-next-line
+						reasoning: delta.reasoning_content,
+					}
 				}
 			}
 

src/api/transform/openrouter-stream.ts

@@ -139,6 +139,10 @@ export async function createOpenRouterStream(
 		shouldApplyMiddleOutTransform = true
 	}
 
+	// hardcoded provider sorting for kimi-k2
+	const isKimiK2 = model.id.startsWith("moonshotai/kimi-k2")
+	openRouterProviderSorting = isKimiK2 ? undefined : openRouterProviderSorting
+
 	// @ts-ignore-next-line
 	const stream = await client.chat.completions.create({
 		model: model.id,
@@ -153,6 +157,8 @@ export async function createOpenRouterStream(
 		...(model.id.startsWith("openai/o") ? { reasoning_effort: reasoningEffort || "medium" } : {}),
 		...(reasoning ? { reasoning } : {}),
 		...(openRouterProviderSorting ? { provider: { sort: openRouterProviderSorting } } : {}),
+		// limit providers to only those that support the 131k context window
+		...(isKimiK2 ? { provider: { order: ["groq", "together"], allow_fallbacks: false } } : {}),
 	})
 
 	return stream

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

@@ -6,9 +6,9 @@ import * as path from "path"
 import { FileContextTracker } from "./FileContextTracker"
 import * as diskModule from "@core/storage/disk"
 import type { TaskMetadata, FileMetadataEntry } from "./ContextTrackerTypes"
-import type { WebviewProviderCreator } from "@/hosts/host-providers"
+import type { DiffViewProviderCreator, WebviewProviderCreator } from "@/hosts/host-providers"
 import * as hostProviders from "@hosts/host-providers"
-import { vscodeHostBridgeClient } from "@/hosts/vscode/client/host-grpc-client"
+import { vscodeHostBridgeClient } from "@/hosts/vscode/hostbridge/client/host-grpc-client"
 
 describe("FileContextTracker", () => {
 	let sandbox: sinon.SinonSandbox
@@ -53,7 +53,11 @@ describe("FileContextTracker", () => {
 		mockTaskMetadata = { files_in_context: [], model_usage: [] }
 		getTaskMetadataStub = sandbox.stub(diskModule, "getTaskMetadata").resolves(mockTaskMetadata)
 		saveTaskMetadataStub = sandbox.stub(diskModule, "saveTaskMetadata").resolves()
-		hostProviders.initializeHostProviders(((_) => {}) as WebviewProviderCreator, vscodeHostBridgeClient)
+		hostProviders.initializeHostProviders(
+			((_) => {}) as WebviewProviderCreator,
+			(() => {}) as DiffViewProviderCreator,
+			vscodeHostBridgeClient,
+		)
 
 		// Create tracker instance
 		taskId = "test-task-id"

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

@@ -3,11 +3,12 @@ import { RuleFileRequest, RuleFile } from "@shared/proto/file"
 import { FileMethodHandler } from "./index"
 import { refreshClineRulesToggles } from "@core/context/instructions/user-instructions/cline-rules"
 import { createRuleFile as createRuleFileImpl } from "@core/context/instructions/user-instructions/rule-helpers"
-import * as vscode from "vscode"
 import * as path from "path"
 import { handleFileServiceRequest } from "./index"
 import { refreshWorkflowToggles } from "@/core/context/instructions/user-instructions/workflows"
 import { getCwd, getDesktopDir } from "@/utils/path"
+import { getHostBridgeProvider } from "@/hosts/host-providers"
+import { ShowMessageRequest, ShowMessageType } from "@/shared/proto/host/window"
 
 /**
  * Creates a rule file in either global or workspace rules directory
@@ -42,7 +43,13 @@ export const createRuleFile: FileMethodHandler = async (controller: Controller,
 	const fileTypeName = request.type === "workflow" ? "workflow" : "rule"
 
 	if (fileExists) {
-		vscode.window.showWarningMessage(`${fileTypeName} file "${request.filename}" already exists.`)
+		const message = `${fileTypeName} file "${request.filename}" already exists.`
+		getHostBridgeProvider().windowClient.showMessage(
+			ShowMessageRequest.create({
+				type: ShowMessageType.WARNING,
+				message,
+			}),
+		)
 		// Still open it for editing
 		await handleFileServiceRequest(controller, "openFile", { value: filePath })
 	} else {
@@ -55,8 +62,12 @@ export const createRuleFile: FileMethodHandler = async (controller: Controller,
 
 		await handleFileServiceRequest(controller, "openFile", { value: filePath })
 
-		vscode.window.showInformationMessage(
-			`Created new ${request.isGlobal ? "global" : "workspace"} ${fileTypeName} file: ${request.filename}`,
+		const message = `Created new ${request.isGlobal ? "global" : "workspace"} ${fileTypeName} file: ${request.filename}`
+		getHostBridgeProvider().windowClient.showMessage(
+			ShowMessageRequest.create({
+				type: ShowMessageType.INFORMATION,
+				message,
+			}),
 		)
 	}
 

src/core/controller/file/deleteRuleFile.ts

@@ -1,9 +1,10 @@
 import { deleteRuleFile as deleteRuleFileImpl } from "@core/context/instructions/user-instructions/rule-helpers"
 import { RuleFile, RuleFileRequest } from "@shared/proto/file"
 import * as path from "path"
-import * as vscode from "vscode"
 import { Controller } from ".."
 import { FileMethodHandler } from "./index"
+import { getHostBridgeProvider } from "@/hosts/host-providers"
+import { ShowMessageRequest, ShowMessageType } from "@/shared/proto/host/window"
 
 /**
  * Deletes a rule file from either global or workspace rules directory
@@ -44,7 +45,13 @@ export const deleteRuleFile: FileMethodHandler = async (controller: Controller,
 
 	const fileTypeName = request.type === "workflow" ? "workflow" : "rule"
 
-	vscode.window.showInformationMessage(`${fileTypeName} file "${fileName}" deleted successfully`)
+	const message = `${fileTypeName} file "${fileName}" deleted successfully`
+	getHostBridgeProvider().windowClient.showMessage(
+		ShowMessageRequest.create({
+			type: ShowMessageType.INFORMATION,
+			message,
+		}),
+	)
 
 	return RuleFile.create({
 		filePath: request.rulePath,

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 { 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
@@ -13,47 +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({
-						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/index.ts

@@ -27,21 +27,15 @@ import pWaitFor from "p-wait-for"
 import * as path from "path"
 import * as vscode from "vscode"
 import { ensureMcpServersDirectoryExists, ensureSettingsDirectoryExists, GlobalFileNames } from "../storage/disk"
-import {
-	getAllExtensionState,
-	getGlobalState,
-	getSecret,
-	getWorkspaceState,
-	storeSecret,
-	updateGlobalState,
-	updateWorkspaceState,
-} from "../storage/state"
+import { getAllExtensionState, getGlobalState, getWorkspaceState, storeSecret, updateGlobalState } from "../storage/state"
 import { Task } from "../task"
-import { sendAuthCallbackEvent } from "./account/subscribeToAuthCallback"
 import { handleGrpcRequest, handleGrpcRequestCancel } from "./grpc-handler"
-import { sendMcpMarketplaceCatalogEvent } from "./mcp/subscribeToMcpMarketplaceCatalog"
 import { sendStateUpdate } from "./state/subscribeToState"
 import { sendAddToInputEvent } from "./ui/subscribeToAddToInput"
+import { sendMcpMarketplaceCatalogEvent } from "./mcp/subscribeToMcpMarketplaceCatalog"
+import { AuthService } from "@/services/auth/AuthService"
+import { ShowMessageRequest, ShowMessageType } from "@/shared/proto/host/window"
+import { getHostBridgeProvider } from "@/hosts/host-providers"
 
 /*
 https://github.com/microsoft/vscode-webview-ui-toolkit-samples/blob/main/default/weather-webview/src/providers/WeatherViewProvider.ts
@@ -54,11 +48,11 @@ 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(
@@ -78,10 +72,9 @@ export class Controller {
 			(msg) => this.postMessageToWebview(msg),
 			this.context.extension?.packageJSON?.version ?? "1.0.0",
 		)
-		this.accountService = new ClineAccountService(async () => {
-			const { apiConfiguration } = await this.getStateToPostToWebview()
-			return apiConfiguration?.clineApiKey
-		})
+		this.accountService = ClineAccountService.getInstance()
+		this.authService = AuthService.getInstance(context)
+		this.authService.restoreRefreshTokenAndRetrieveAuthInfo()
 
 		// Clean up legacy checkpoints
 		cleanupLegacyCheckpoints(this.context.globalStorageUri.fsPath, this.outputChannel).catch((error) => {
@@ -89,6 +82,10 @@ 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/
@@ -111,13 +108,24 @@ 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 updateGlobalState(this.context, "apiProvider", "openrouter")
 			await this.postStateToWebview()
-			vscode.window.showInformationMessage("Successfully logged out of Cline")
+			getHostBridgeProvider().windowClient.showMessage(
+				ShowMessageRequest.create({
+					type: ShowMessageType.INFORMATION,
+					message: "Successfully logged out of Cline",
+				}),
+			)
 		} catch (error) {
-			vscode.window.showErrorMessage("Logout failed")
+			getHostBridgeProvider().windowClient.showMessage(
+				ShowMessageRequest.create({
+					type: ShowMessageType.INFORMATION,
+					message: "Logout failed",
+				}),
+			)
 		}
 	}
 
@@ -141,10 +149,13 @@ 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
@@ -239,8 +250,8 @@ export class Controller {
 	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)
@@ -394,7 +405,7 @@ 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 updateGlobalState(this.context, "chatSettings", persistentChatSettings)
 		await this.postStateToWebview()
@@ -450,24 +461,9 @@ 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
-	}
-
-	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 updateGlobalState(this.context, "apiProvider", clineProvider)
@@ -475,12 +471,10 @@ export class Controller {
 			// 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) {
@@ -488,17 +482,20 @@ 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")
+			getHostBridgeProvider().windowClient.showMessage(
+				ShowMessageRequest.create({
+					type: ShowMessageType.ERROR,
+					message: "Failed to log in to Cline",
+				}),
+			)
 			// Even on login failure, we preserve any existing tokens
 			// Only clear tokens on explicit logout
 		}
 	}
 
 	// MCP Marketplace
-
 	private async fetchMcpMarketplaceFromApi(silent: boolean = false): Promise<McpMarketplaceCatalog | undefined> {
 		try {
 			const response = await axios.get("https://api.cline.bot/v1/mcp/marketplace", {
@@ -527,7 +524,12 @@ export class Controller {
 			console.error("Failed to fetch MCP marketplace:", error)
 			if (!silent) {
 				const errorMessage = error instanceof Error ? error.message : "Failed to fetch MCP marketplace"
-				vscode.window.showErrorMessage(errorMessage)
+				getHostBridgeProvider().windowClient.showMessage(
+					ShowMessageRequest.create({
+						type: ShowMessageType.ERROR,
+						message: errorMessage,
+					}),
+				)
 			}
 			return undefined
 		}
@@ -611,7 +613,12 @@ export class Controller {
 		} catch (error) {
 			console.error("Failed to handle cached MCP marketplace:", error)
 			const errorMessage = error instanceof Error ? error.message : "Failed to handle cached MCP marketplace"
-			vscode.window.showErrorMessage(errorMessage)
+			getHostBridgeProvider().windowClient.showMessage(
+				ShowMessageRequest.create({
+					type: ShowMessageType.ERROR,
+					message: errorMessage,
+				}),
+			)
 		}
 	}
 
@@ -822,7 +829,7 @@ export class Controller {
 			chatSettings: storedChatSettings,
 			userInfo,
 			mcpMarketplaceEnabled,
-			mcpRichDisplayEnabled,
+			mcpDisplayMode,
 			telemetrySetting,
 			planActSeparateModelsSetting,
 			enableCheckpointsSetting,
@@ -837,10 +844,13 @@ export class Controller {
 			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 =
@@ -872,7 +882,7 @@ export class Controller {
 			chatSettings,
 			userInfo,
 			mcpMarketplaceEnabled,
-			mcpRichDisplayEnabled,
+			mcpDisplayMode,
 			telemetrySetting,
 			planActSeparateModelsSetting,
 			enableCheckpointsSetting: enableCheckpointsSetting ?? true,
@@ -972,14 +982,24 @@ export class Controller {
 			// Check if there's a workspace folder open
 			const cwd = await getCwd()
 			if (!cwd) {
-				vscode.window.showErrorMessage("No workspace folder open")
+				getHostBridgeProvider().windowClient.showMessage(
+					ShowMessageRequest.create({
+						type: ShowMessageType.ERROR,
+						message: "No workspace folder open",
+					}),
+				)
 				return
 			}
 
 			// Get the git diff
 			const gitDiff = await getWorkingState(cwd)
 			if (gitDiff === "No changes in working directory") {
-				vscode.window.showInformationMessage("No changes in workspace for commit message")
+				getHostBridgeProvider().windowClient.showMessage(
+					ShowMessageRequest.create({
+						type: ShowMessageType.INFORMATION,
+						message: "No changes in workspace for commit message",
+					}),
+				)
 				return
 			}
 
@@ -1046,27 +1066,59 @@ Commit message:`
 								if (api && api.repositories.length > 0) {
 									const repo = api.repositories[0]
 									repo.inputBox.value = commitMessage
-									vscode.window.showInformationMessage("Commit message generated and applied")
+									const message = "Commit message generated and applied"
+									getHostBridgeProvider().windowClient.showMessage(
+										ShowMessageRequest.create({
+											type: ShowMessageType.INFORMATION,
+											message,
+										}),
+									)
 								} else {
-									vscode.window.showErrorMessage("No Git repositories found")
+									const message = "No Git repositories found"
+									getHostBridgeProvider().windowClient.showMessage(
+										ShowMessageRequest.create({
+											type: ShowMessageType.ERROR,
+											message,
+										}),
+									)
 								}
 							} else {
-								vscode.window.showErrorMessage("Git extension not found")
+								const message = "Git extension not found"
+								getHostBridgeProvider().windowClient.showMessage(
+									ShowMessageRequest.create({
+										type: ShowMessageType.ERROR,
+										message,
+									}),
+								)
 							}
 						} else {
-							vscode.window.showErrorMessage("Failed to generate commit message")
+							const message = "Failed to generate commit message"
+							getHostBridgeProvider().windowClient.showMessage(
+								ShowMessageRequest.create({
+									type: ShowMessageType.ERROR,
+									message,
+								}),
+							)
 						}
 					} catch (innerError) {
 						const innerErrorMessage = innerError instanceof Error ? innerError.message : String(innerError)
-						vscode.window.showErrorMessage(`Failed to generate commit message: ${innerErrorMessage}`)
+						getHostBridgeProvider().windowClient.showMessage(
+							ShowMessageRequest.create({
+								type: ShowMessageType.ERROR,
+								message: `Failed to generate commit message: ${innerErrorMessage}`,
+							}),
+						)
 					}
 				},
 			)
 		} catch (error) {
 			const errorMessage = error instanceof Error ? error.message : String(error)
-			vscode.window.showErrorMessage(`Failed to generate commit message: ${errorMessage}`)
+			getHostBridgeProvider().windowClient.showMessage(
+				ShowMessageRequest.create({
+					type: ShowMessageType.ERROR,
+					message: `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/refreshGroqModels.ts

@@ -0,0 +1,254 @@
+import { Controller } from ".."
+import { EmptyRequest } from "../../../shared/proto/common"
+import { OpenRouterCompatibleModelInfo, OpenRouterModelInfo } from "../../../shared/proto/models"
+import { getAllExtensionState } from "../../storage/state"
+import { groqModels } from "../../../shared/api"
+import axios from "axios"
+import path from "path"
+import fs from "fs/promises"
+import { fileExistsAtPath } from "@utils/fs"
+import { GlobalFileNames } from "@core/storage/disk"
+
+/**
+ * Refreshes the Groq models and returns the updated model list
+ * @param controller The controller instance
+ * @param request Empty request object
+ * @returns Response containing the Groq models
+ */
+export async function refreshGroqModels(controller: Controller, request: EmptyRequest): Promise<OpenRouterCompatibleModelInfo> {
+	const groqModelsFilePath = path.join(await ensureCacheDirectoryExists(controller), GlobalFileNames.groqModels)
+
+	// Get the Groq API key from the controller's state
+	const { apiConfiguration } = await getAllExtensionState(controller.context)
+	const groqApiKey = apiConfiguration?.groqApiKey
+
+	let models: Record<string, Partial<OpenRouterModelInfo>> = {}
+	try {
+		if (!groqApiKey) {
+			console.log("No Groq API key found, using static models as fallback")
+			// Don't throw an error, just use static models
+			for (const [modelId, modelInfo] of Object.entries(groqModels)) {
+				models[modelId] = {
+					maxTokens: modelInfo.maxTokens,
+					contextWindow: modelInfo.contextWindow,
+					supportsImages: modelInfo.supportsImages,
+					supportsPromptCache: modelInfo.supportsPromptCache,
+					inputPrice: modelInfo.inputPrice,
+					outputPrice: modelInfo.outputPrice,
+					cacheWritesPrice: (modelInfo as any).cacheWritesPrice || 0,
+					cacheReadsPrice: (modelInfo as any).cacheReadsPrice || 0,
+					description: modelInfo.description || `${modelId} model`,
+				}
+			}
+		} else {
+			// Ensure the API key is properly formatted
+			const cleanApiKey = groqApiKey.trim()
+			if (!cleanApiKey.startsWith("gsk_")) {
+				throw new Error("Invalid Groq API key format. Groq API keys should start with 'gsk_'")
+			}
+
+			console.log("Fetching Groq models with API key:", cleanApiKey.substring(0, 10) + "...")
+
+			const response = await axios.get("https://api.groq.com/openai/v1/models", {
+				headers: {
+					Authorization: `Bearer ${cleanApiKey}`,
+					"Content-Type": "application/json",
+					"User-Agent": "Cline-VSCode-Extension",
+				},
+				timeout: 10000, // 10 second timeout
+			})
+
+			if (response.data?.data) {
+				const rawModels = response.data.data
+
+				for (const rawModel of rawModels) {
+					// Filter out non-chat models and validate model capabilities
+					if (!isValidChatModel(rawModel)) {
+						continue
+					}
+
+					// Check if we have static pricing information for this model
+					const staticModelInfo = groqModels[rawModel.id as keyof typeof groqModels]
+
+					const modelInfo: Partial<OpenRouterModelInfo> = {
+						maxTokens: rawModel.max_completion_tokens || staticModelInfo?.maxTokens || 8192,
+						contextWindow: rawModel.context_window || staticModelInfo?.contextWindow || 8192,
+						supportsImages: detectImageSupport(rawModel, staticModelInfo),
+						supportsPromptCache: staticModelInfo?.supportsPromptCache || false,
+						inputPrice: staticModelInfo?.inputPrice || 0,
+						outputPrice: staticModelInfo?.outputPrice || 0,
+						cacheWritesPrice: (staticModelInfo as any)?.cacheWritesPrice || 0,
+						cacheReadsPrice: (staticModelInfo as any).cacheReadsPrice || 0,
+						description: generateModelDescription(rawModel, staticModelInfo),
+					}
+
+					models[rawModel.id] = modelInfo
+				}
+			} else {
+				console.error("Invalid response from Groq API")
+			}
+			await fs.writeFile(groqModelsFilePath, JSON.stringify(models))
+			console.log("Groq models fetched and saved", models)
+		}
+	} catch (error) {
+		console.error("Error fetching Groq models:", error)
+
+		// Provide more specific error messages
+		let errorMessage = "Unknown error occurred"
+		if (axios.isAxiosError(error)) {
+			if (error.response?.status === 401) {
+				errorMessage = "Invalid Groq API key. Please check your API key in settings."
+			} else if (error.response?.status === 403) {
+				errorMessage = "Access forbidden. Please verify your Groq API key has the correct permissions."
+			} else if (error.response?.status === 429) {
+				errorMessage = "Rate limit exceeded. Please try again later."
+			} else if (error.code === "ECONNABORTED") {
+				errorMessage = "Request timeout. Please check your internet connection."
+			} else {
+				errorMessage = `API request failed: ${error.response?.status || error.code || "Unknown error"}`
+			}
+		} else if (error instanceof Error) {
+			errorMessage = error.message
+		}
+
+		console.error("Groq API Error:", errorMessage)
+
+		// If we failed to fetch models, try to read cached models first
+		const cachedModels = await readGroqModels(controller)
+		if (cachedModels && Object.keys(cachedModels).length > 0) {
+			console.log("Using cached Groq models")
+			models = cachedModels
+		} else {
+			// Fall back to static models from shared/api.ts
+			console.log("Using static Groq models as fallback")
+			for (const [modelId, modelInfo] of Object.entries(groqModels)) {
+				models[modelId] = {
+					maxTokens: modelInfo.maxTokens,
+					contextWindow: modelInfo.contextWindow,
+					supportsImages: modelInfo.supportsImages,
+					supportsPromptCache: modelInfo.supportsPromptCache,
+					inputPrice: modelInfo.inputPrice,
+					outputPrice: modelInfo.outputPrice,
+					cacheWritesPrice: (modelInfo as any).cacheWritesPrice || 0,
+					cacheReadsPrice: (modelInfo as any).cacheReadsPrice || 0,
+					description: modelInfo.description || `${modelId} model`,
+				}
+			}
+		}
+	}
+
+	// Convert the Record<string, Partial<OpenRouterModelInfo>> to Record<string, OpenRouterModelInfo>
+	// by filling in any missing required fields with defaults
+	const typedModels: Record<string, OpenRouterModelInfo> = {}
+	for (const [key, model] of Object.entries(models)) {
+		typedModels[key] = {
+			maxTokens: model.maxTokens ?? 8192,
+			contextWindow: model.contextWindow ?? 8192,
+			supportsImages: model.supportsImages ?? false,
+			supportsPromptCache: model.supportsPromptCache ?? false,
+			inputPrice: model.inputPrice ?? 0,
+			outputPrice: model.outputPrice ?? 0,
+			cacheWritesPrice: model.cacheWritesPrice ?? 0,
+			cacheReadsPrice: model.cacheReadsPrice ?? 0,
+			description: model.description ?? "",
+			tiers: model.tiers ?? [],
+		}
+	}
+
+	return OpenRouterCompatibleModelInfo.create({ models: typedModels })
+}
+
+/**
+ * Reads cached Groq models from disk
+ */
+async function readGroqModels(controller: Controller): Promise<Record<string, Partial<OpenRouterModelInfo>> | undefined> {
+	const groqModelsFilePath = path.join(await ensureCacheDirectoryExists(controller), GlobalFileNames.groqModels)
+	const fileExists = await fileExistsAtPath(groqModelsFilePath)
+	if (fileExists) {
+		try {
+			const fileContents = await fs.readFile(groqModelsFilePath, "utf8")
+			return JSON.parse(fileContents)
+		} catch (error) {
+			console.error("Error reading cached Groq models:", error)
+			return undefined
+		}
+	}
+	return undefined
+}
+
+/**
+ * Validates if a model is suitable for chat completions
+ */
+function isValidChatModel(rawModel: any): boolean {
+	// Check if model is active (if the property exists)
+	if (rawModel.hasOwnProperty("active") && !rawModel.active) {
+		return false
+	}
+	// Filter out non-chat models (whisper, TTS, guard models, etc.)
+	if (
+		rawModel.id.includes("whisper") ||
+		rawModel.id.includes("tts") ||
+		rawModel.id.includes("guard") ||
+		rawModel.id.includes("embedding") ||
+		rawModel.id.includes("moderation") ||
+		rawModel.id.includes("allam")
+	) {
+		return false
+	}
+
+	// Check if model supports chat completions
+	if (rawModel.object === "model" && rawModel.id) {
+		return true
+	}
+
+	return false
+}
+
+/**
+ * Detects if a model supports image input
+ */
+function detectImageSupport(rawModel: any, staticModelInfo?: any): boolean {
+	// Use static info if available
+	if (staticModelInfo?.supportsImages !== undefined) {
+		return staticModelInfo.supportsImages
+	}
+
+	// Detect based on model name patterns
+	const modelId = rawModel.id.toLowerCase()
+	if (modelId.includes("vision") || modelId.includes("maverick") || modelId.includes("scout")) {
+		return true
+	}
+
+	return false
+}
+
+/**
+ * Generates a descriptive name for the model
+ */
+function generateModelDescription(rawModel: any, staticModelInfo?: any): string {
+	// Use static description if available
+	if (staticModelInfo?.description) {
+		return staticModelInfo.description
+	}
+
+	// Generate description based on model characteristics
+	const modelId = rawModel.id
+	const contextWindow = rawModel.context_window || 8192
+	const ownedBy = rawModel.owned_by || "Unknown"
+
+	// Special handling for new models
+	if (modelId.includes("compound")) {
+		return `${ownedBy}'s ${modelId} model with ${contextWindow.toLocaleString()} token context window - Advanced compound architecture`
+	}
+
+	return `${ownedBy} model with ${contextWindow.toLocaleString()} token context window`
+}
+
+/**
+ * Ensures the cache directory exists and returns its path
+ */
+async function ensureCacheDirectoryExists(controller: Controller): Promise<string> {
+	const cacheDir = path.join(controller.context.globalStorageUri.fsPath, "cache")
+	await fs.mkdir(cacheDir, { recursive: true })
+	return cacheDir
+}

src/core/controller/models/refreshOpenRouterModels.ts

@@ -101,9 +101,15 @@ 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
+					case "moonshotai/kimi-k2":
+						// forcing kimi-k2 to use the together provider for full context and best throughput
+						modelInfo.inputPrice = 1
+						modelInfo.outputPrice = 3
+						modelInfo.contextWindow = 131_000
+						break
 					default:
 						if (rawModel.id.startsWith("openai/")) {
 							modelInfo.cacheReadsPrice = parsePrice(rawModel.pricing?.input_cache_read)
@@ -122,11 +128,6 @@ 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/resetState.ts

@@ -2,8 +2,9 @@ import { Controller } from ".."
 import { Empty } from "../../../shared/proto/common"
 import { ResetStateRequest } from "../../../shared/proto/state"
 import { resetGlobalState, resetWorkspaceState } from "../../../core/storage/state"
-import * as vscode from "vscode"
 import { sendChatButtonClickedEvent } from "../ui/subscribeToChatButtonClicked"
+import { ShowMessageRequest, ShowMessageType } from "@/shared/proto/host/window"
+import { getHostBridgeProvider } from "@/hosts/host-providers"
 
 /**
  * Resets the extension state to its defaults
@@ -14,10 +15,20 @@ import { sendChatButtonClickedEvent } from "../ui/subscribeToChatButtonClicked"
 export async function resetState(controller: Controller, request: ResetStateRequest): Promise<Empty> {
 	try {
 		if (request.global) {
-			vscode.window.showInformationMessage("Resetting global state...")
+			getHostBridgeProvider().windowClient.showMessage(
+				ShowMessageRequest.create({
+					type: ShowMessageType.INFORMATION,
+					message: "Resetting global state...",
+				}),
+			)
 			await resetGlobalState(controller.context)
 		} else {
-			vscode.window.showInformationMessage("Resetting workspace state...")
+			getHostBridgeProvider().windowClient.showMessage(
+				ShowMessageRequest.create({
+					type: ShowMessageType.INFORMATION,
+					message: "Resetting workspace state...",
+				}),
+			)
 			await resetWorkspaceState(controller.context)
 		}
 
@@ -26,7 +37,12 @@ export async function resetState(controller: Controller, request: ResetStateRequ
 			controller.task = undefined
 		}
 
-		vscode.window.showInformationMessage("State reset")
+		getHostBridgeProvider().windowClient.showMessage(
+			ShowMessageRequest.create({
+				type: ShowMessageType.INFORMATION,
+				message: "State reset",
+			}),
+		)
 		await controller.postStateToWebview()
 
 		await sendChatButtonClickedEvent(controller.id)
@@ -34,7 +50,12 @@ export async function resetState(controller: Controller, request: ResetStateRequ
 		return Empty.create()
 	} catch (error) {
 		console.error("Error resetting state:", error)
-		vscode.window.showErrorMessage(`Failed to reset state: ${error instanceof Error ? error.message : String(error)}`)
+		getHostBridgeProvider().windowClient.showMessage(
+			ShowMessageRequest.create({
+				type: ShowMessageType.ERROR,
+				message: `Failed to reset state: ${error instanceof Error ? error.message : String(error)}`,
+			}),
+		)
 		throw error
 	}
 }

src/core/controller/state/updateDefaultTerminalProfile.ts

@@ -1,8 +1,9 @@
-import * as vscode from "vscode"
 import { Controller } from "../index"
 import * as proto from "@/shared/proto"
 import { updateGlobalState } from "../../storage/state"
 import { TerminalInfo } from "@/integrations/terminal/TerminalRegistry"
+import { getHostBridgeProvider } from "@/hosts/host-providers"
+import { ShowMessageRequest, ShowMessageType } from "@/shared/proto/host/window"
 
 export async function updateDefaultTerminalProfile(
 	controller: Controller,
@@ -25,16 +26,25 @@ export async function updateDefaultTerminalProfile(
 
 		// Show information message if terminals were closed
 		if (closedCount > 0) {
-			vscode.window.showInformationMessage(
-				`Closed ${closedCount} ${closedCount === 1 ? "terminal" : "terminals"} with different profile.`,
+			const message = `Closed ${closedCount} ${closedCount === 1 ? "terminal" : "terminals"} with different profile.`
+			getHostBridgeProvider().windowClient.showMessage(
+				ShowMessageRequest.create({
+					type: ShowMessageType.INFORMATION,
+					message,
+				}),
 			)
 		}
 
 		// Show warning if there are busy terminals that couldn't be closed
 		if (busyTerminals.length > 0) {
-			vscode.window.showWarningMessage(
+			const message =
 				`${busyTerminals.length} busy ${busyTerminals.length === 1 ? "terminal has" : "terminals have"} a different profile. ` +
-					`Close ${busyTerminals.length === 1 ? "it" : "them"} to use the new profile for all commands.`,
+				`Close ${busyTerminals.length === 1 ? "it" : "them"} to use the new profile for all commands.`
+			getHostBridgeProvider().windowClient.showMessage(
+				ShowMessageRequest.create({
+					type: ShowMessageType.WARNING,
+					message,
+				}),
 			)
 		}
 	}

src/core/controller/state/updateSettings.ts

@@ -50,15 +50,24 @@ export async function updateSettings(controller: Controller, request: UpdateSett
 			await controller.context.globalState.update("mcpResponsesCollapsed", request.mcpResponsesCollapsed)
 		}
 
-		// Update MCP responses collapsed setting
-		if (request.mcpRichDisplayEnabled !== undefined) {
-			await controller.context.globalState.update("mcpRichDisplayEnabled", request.mcpRichDisplayEnabled)
+		// Update MCP display mode setting
+		if (request.mcpDisplayMode !== undefined) {
+			await controller.context.globalState.update("mcpDisplayMode", request.mcpDisplayMode)
 		}
 
 		// 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/deleteAllTaskHistory.ts

@@ -4,7 +4,8 @@ import { Controller } from ".."
 import { DeleteAllTaskHistoryCount } from "../../../shared/proto/task"
 import { getGlobalState, updateGlobalState } from "../../storage/state"
 import { fileExistsAtPath } from "../../../utils/fs"
-import vscode from "vscode"
+import { ShowMessageRequest, ShowMessageType } from "@/shared/proto/host/window"
+import { getHostBridgeProvider } from "@/hosts/host-providers"
 
 /**
  * Deletes all task history, with an option to preserve favorites
@@ -21,12 +22,18 @@ export async function deleteAllTaskHistory(controller: Controller): Promise<Dele
 		const taskHistory = ((await getGlobalState(controller.context, "taskHistory")) as any[]) || []
 		const totalTasks = taskHistory.length
 
-		const userChoice = await vscode.window.showWarningMessage(
-			"What would you like to delete?",
-			{ modal: true },
-			"Delete All Except Favorites",
-			"Delete Everything",
-		)
+		const userChoice = (
+			await getHostBridgeProvider().windowClient.showMessage(
+				ShowMessageRequest.create({
+					type: ShowMessageType.WARNING,
+					message: "What would you like to delete?",
+					options: {
+						modal: true,
+						items: ["Delete All Except Favorites", "Delete Everything"],
+					},
+				}),
+			)
+		)?.selectedOption
 
 		// Default VS Code Cancel button returns `undefined` - don't delete anything
 		if (userChoice === undefined) {
@@ -59,11 +66,18 @@ export async function deleteAllTaskHistory(controller: Controller): Promise<Dele
 				})
 			} else {
 				// No favorited tasks found - show warning and ask user what to do
-				const answer = await vscode.window.showWarningMessage(
-					"No favorited tasks found. Would you like to delete all tasks anyway?",
-					{ modal: true },
-					"Delete All Tasks",
-				)
+				const answer = (
+					await getHostBridgeProvider().windowClient.showMessage(
+						ShowMessageRequest.create({
+							type: ShowMessageType.WARNING,
+							message: "No favorited tasks found. Would you like to delete all tasks anyway?",
+							options: {
+								modal: true,
+								items: ["Delete All Tasks"],
+							},
+						}),
+					)
+				)?.selectedOption
 
 				// User cancelled - don't delete anything
 				if (answer === undefined) {
@@ -91,8 +105,11 @@ export async function deleteAllTaskHistory(controller: Controller): Promise<Dele
 				await fs.rm(checkpointsDirPath, { recursive: true, force: true })
 			}
 		} catch (error) {
-			vscode.window.showErrorMessage(
-				`Encountered error while deleting task history, there may be some files left behind. Error: ${error instanceof Error ? error.message : String(error)}`,
+			getHostBridgeProvider().windowClient.showMessage(
+				ShowMessageRequest.create({
+					type: ShowMessageType.ERROR,
+					message: `Encountered error while deleting task history, there may be some files left behind. Error: ${error instanceof Error ? error.message : String(error)}`,
+				}),
 			)
 		}