cache for evals

* Refactor constructNewFileContent and add tests for out-of-order replacements

- Renamed function `constructNewFileContent` to `cnfc` for clarity.
- Updated the versioning logic to default to "v1" in `constructNewFileContent`.
- Enhanced the implementation to handle out-of-order search/replace blocks.
- Added comprehensive test cases to validate the new functionality, including scenarios with overlapping content and deletions.

* Create quick-rocks-guess.md

* Add flexibility for search/replace markers matching

* Refactor tests for edge cases in diff handling

* Handle case where model doesnt include ending replace marker

* Fix search/replace counter

.changeset/blue-cobras-allow.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Migrated updateSettings to protos, removed didUpdateSettings, altered Plan/Act toggling in settings menu

.changeset/blue-moons-mate.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-Put all the navigation state and message handling and navigation functions in the extension state context instead of the app.tsx

.changeset/eight-otters-grow.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Fixed issue where telemetry warning popup was created for every new Cline window

.changeset/eleven-monkeys-watch.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+Prioritize active files in file context menu

.changeset/giant-cycles-divide.md

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

.changeset/heavy-bananas-shave.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Added promise to task init to prevent race condition with checkpoints

.changeset/honest-boats-fix.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Spring cleaning

.changeset/hot-dodos-rhyme.md

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

.changeset/little-gifts-invite.md

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

.changeset/long-zebras-yawn.md

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

.changeset/pink-deers-burn.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-migrate accountLogoutClicked to protobus

.changeset/quick-rocks-guess.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Fix bug where replace_in_file would not be able to handle for out-of-order SEARCH/REPLACE blocks

.changeset/rare-ducks-give.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+Context menu is default to File option on start up

.changeset/six-candles-check.md

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

.changeset/six-rice-end.md

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

.changeset/smart-ladybugs-give.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+the response of the mcps is displayed with a collapsible which allows to focus on the model responses.

.changeset/wild-gifts-switch.md

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

.clinerules/cline-overview.md

@@ -164,6 +164,7 @@ Key providers include:
 - **OpenRouter**: Meta-provider supporting multiple model providers
 - **AWS Bedrock**: Integration with Amazon's AI services
 - **Gemini**: Google's AI models
+- **Cerebras**: High-performance inference with Llama, Qwen, and DeepSeek models
 - **Ollama**: Local model hosting
 - **LM Studio**: Local model hosting
 - **VSCode LM**: VSCode's built-in language models

.clinerules/workflows/pr-review.md

@@ -0,0 +1,351 @@
+You have access to the `gh` terminal command. I already authenticated it for you. Please review it to use the PR that I asked you to review. You're already in the `cline` repo.
+
+<detailed_sequence_of_steps>
+# GitHub PR Review Process - Detailed Sequence of Steps
+
+## 1. Gather PR Information
+1. Get the PR title, description, and comments:
+   ```bash
+   gh pr view <PR-number> --json title,body,comments
+   ```
+
+2. Get the full diff of the PR:
+   ```bash
+   gh pr diff <PR-number>
+   ```
+
+## 2. Understand the Context
+1. Identify which files were modified in the PR:
+   ```bash
+   gh pr view <PR-number> --json files
+   ```
+
+2. Examine the original files in the main branch to understand the context:
+   ```xml
+   <read_file>
+   <path>path/to/file</path>
+   </read_file>
+   ```
+
+3. For specific sections of a file, you can use search_files:
+   ```xml
+   <search_files>
+   <path>path/to/directory</path>
+   <regex>search term</regex>
+   <file_pattern>*.ts</file_pattern>
+   </search_files>
+   ```
+
+## 3. Analyze the Changes
+1. For each modified file, understand:
+   - What was changed
+   - Why it was changed (based on PR description)
+   - How it affects the codebase
+   - Potential side effects
+
+2. Look for:
+   - Code quality issues
+   - Potential bugs
+   - Performance implications
+   - Security concerns
+   - Test coverage
+
+## 4. Ask for User Confirmation
+1. Before making a decision, ask the user if you should approve the PR, providing your assessment and justification:
+   ```xml
+   <ask_followup_question>
+   <question>Based on my review of PR #<PR-number>, I recommend [approving/requesting changes]. Here's my justification:
+   
+   [Detailed justification with key points about the PR quality, implementation, and any concerns]
+   
+   Would you like me to proceed with this recommendation?</question>
+   <options>["Yes, approve the PR", "Yes, request changes", "No, I'd like to discuss further"]</options>
+   </ask_followup_question>
+   ```
+
+## 5. Ask if User Wants a Comment Drafted
+1. After the user decides on approval/rejection, ask if they would like a comment drafted:
+   ```xml
+   <ask_followup_question>
+   <question>Would you like me to draft a comment for this PR that you can copy and paste?</question>
+   <options>["Yes, please draft a comment", "No, I'll handle the comment myself"]</options>
+   </ask_followup_question>
+   ```
+
+2. If the user wants a comment drafted, provide a well-structured comment they can copy:
+   ```
+   Thank you for this PR! Here's my assessment:
+
+   [Detailed assessment with key points about the PR quality, implementation, and any suggestions]
+
+   [Include specific feedback on code quality, functionality, and testing]
+   ```
+
+## 6. Make a Decision
+1. Approve the PR if it meets quality standards:
+   ```bash
+   # For single-line comments:
+   gh pr review <PR-number> --approve --body "Your approval message"
+   
+   # For multi-line comments with proper whitespace formatting:
+   cat << EOF | gh pr review <PR-number> --approve --body-file -
+   Thanks @username for this PR! The implementation looks good.
+
+   I particularly like how you've handled X and Y.
+
+   Great work!
+   EOF
+   ```
+
+2. Request changes if improvements are needed:
+   ```bash
+   # For single-line comments:
+   gh pr review <PR-number> --request-changes --body "Your feedback message"
+   
+   # For multi-line comments with proper whitespace formatting:
+   cat << EOF | gh pr review <PR-number> --request-changes --body-file -
+   Thanks @username for this PR!
+
+   The implementation looks promising, but there are a few things to address:
+
+   1. Issue one
+   2. Issue two
+
+   Please make these changes and we can merge this.
+   EOF
+   ```
+
+   Note: The `cat << EOF | ... --body-file -` approach preserves all whitespace and formatting without requiring temporary files. The `-` parameter tells the command to read from standard input.
+</detailed_sequence_of_steps>
+
+<example_review_process>
+# Example PR Review Process
+
+Let's walk through a real example of reviewing PR #3627 which fixes the thinking mode calculation for Claude 3.7 models.
+
+## Step 1: Gather PR Information
+
+```bash
+# Get PR details
+gh pr view 3627 --json title,body,comments
+
+# Get the full diff
+gh pr diff 3627
+```
+
+## Step 2: Understand the Context
+
+```xml
+# Examine the original files to understand what's being changed
+<read_file>
+<path>src/shared/api.ts</path>
+</read_file>
+
+# Look at the ThinkingBudgetSlider component implementation
+<read_file>
+<path>webview-ui/src/components/settings/ThinkingBudgetSlider.tsx</path>
+</read_file>
+
+# Check how thinking mode is currently handled in API providers
+<search_files>
+<path>src/api/providers</path>
+<regex>reasoningOn</regex>
+<file_pattern>*.ts</file_pattern>
+</search_files>
+```
+
+## Step 3: Analyze the Changes
+
+From the PR information and code examination, we can see that:
+
+1. The PR fixes an issue with the thinking mode budget calculation for Claude 3.7 models
+2. Currently, the thinking budget is incorrectly calculated as 80% of maxTokens (8192), resulting in 6553 tokens
+3. Claude 3.7 actually supports a much larger thinking budget (up to 64000 tokens)
+4. The PR adds a `thinkingConfig` property with `maxBudget: 64000` to model definitions
+5. It updates API handlers to use this value when reasoning mode is enabled
+6. It enhances the slider component to calculate max values based on model-specific percentages
+7. Comprehensive tests were added to verify the calculations
+
+## Step 4: Ask for User Confirmation
+
+```xml
+<ask_followup_question>
+<question>Based on my review of PR #3627, I recommend approving this PR. Here's my justification:
+
+1. The PR correctly fixes the thinking mode budget calculation for Claude 3.7 models
+2. It properly implements the thinkingConfig.maxBudget property (64000) for Claude 3.7 models
+3. It applies the appropriate percentage (50%) for the slider calculation
+4. The changes are well-tested with comprehensive unit tests
+5. The implementation is clean and follows the project's coding standards
+6. The PR includes helpful screenshots demonstrating the fix
+
+Would you like me to proceed with approving this PR?</question>
+<options>["Yes, approve the PR", "No, I'd like to discuss further", "Let me review it myself first"]</options>
+</ask_followup_question>
+```
+
+## Step 5: Ask if User Wants a Comment Drafted
+
+```xml
+<ask_followup_question>
+<question>Would you like me to draft a comment for this PR that you can copy and paste?</question>
+<options>["Yes, please draft a comment", "No, I'll handle the comment myself"]</options>
+</ask_followup_question>
+```
+
+## Step 6: Make a Decision
+
+```bash
+# Option 1: Simple one-line comment
+gh pr review 3627 --approve --body "This PR looks good! It correctly fixes the thinking mode budget calculation for Claude 3.7 models."
+
+# Option 2: Multi-line comment with proper whitespace formatting
+cat << EOF | gh pr review 3627 --approve --body-file -
+This PR looks good! It correctly fixes the thinking mode budget calculation for Claude 3.7 models.
+
+I particularly like:
+1. The proper implementation of thinkingConfig.maxBudget property (64000)
+2. The appropriate percentage (50%) for the slider calculation
+3. The comprehensive unit tests
+4. The clean implementation that follows project coding standards
+
+Great work!
+EOF
+```
+</example_review_process>
+
+<common_gh_commands>
+# Common GitHub CLI Commands for PR Review
+
+## Basic PR Commands
+```bash
+# List open PRs
+gh pr list
+
+# View a specific PR
+gh pr view <PR-number>
+
+# View PR with specific fields
+gh pr view <PR-number> --json title,body,comments,files,commits
+
+# Check PR status
+gh pr status
+```
+
+## Diff and File Commands
+```bash
+# Get the full diff of a PR
+gh pr diff <PR-number>
+
+# List files changed in a PR
+gh pr view <PR-number> --json files
+
+# Check out a PR locally
+gh pr checkout <PR-number>
+```
+
+## Review Commands
+```bash
+# Approve a PR (single-line comment)
+gh pr review <PR-number> --approve --body "Your approval message"
+
+# Approve a PR (multi-line comment with proper whitespace)
+cat << EOF | gh pr review <PR-number> --approve --body-file -
+Your multi-line
+approval message with
+
+proper whitespace formatting
+EOF
+
+# Request changes on a PR (single-line comment)
+gh pr review <PR-number> --request-changes --body "Your feedback message"
+
+# Request changes on a PR (multi-line comment with proper whitespace)
+cat << EOF | gh pr review <PR-number> --request-changes --body-file -
+Your multi-line
+change request with
+
+proper whitespace formatting
+EOF
+
+# Add a comment review (without approval/rejection)
+gh pr review <PR-number> --comment --body "Your comment message"
+
+# Add a comment review with proper whitespace
+cat << EOF | gh pr review <PR-number> --comment --body-file -
+Your multi-line
+comment with
+
+proper whitespace formatting
+EOF
+```
+
+## Additional Commands
+```bash
+# View PR checks status
+gh pr checks <PR-number>
+
+# View PR commits
+gh pr view <PR-number> --json commits
+
+# Merge a PR (if you have permission)
+gh pr merge <PR-number> --merge
+```
+</common_gh_commands>
+
+<general_guidelines_for_commenting>
+When reviewing a PR, please talk normally and like a friendly reviwer. You should keep it short, and start out by thanking the author of the pr and @ mentioning them. 
+
+Whether or not you approve the PR, you should then give a quick summary of the changes without being too verbose or definitive, staying humble like that this is your understanding of the changes. Kind of how I'm talking to you right now.
+
+If you have any suggestions, or things that need to be changed, request changes instead of approving the PR.
+
+Leaving inline comments in code is good, but only do so if you have something specific to say about the code. And make sure you leave those comments first, and then request changes in the PR with a short comment explaining the overall theme of what you're asking them to change.
+</general_guidelines_for_commenting>
+
+<example_comments_that_i_have_written_before>
+<brief_approve_comment>
+Looks good, though we should make this generic for all providers & models at some point
+</brief_approve_comment>
+<brief_approve_comment>
+Will this work for models that may not match across OR/Gemini? Like the thinking models?
+</brief_approve_comment>
+<approve_comment>
+This looks great! I like how you've handled the global endpoint support - adding it to the ModelInfo interface makes total sense since it's just another capability flag, similar to how we handle other model features.
+
+The filtered model list approach is clean and will be easier to maintain than hardcoding which models work with global endpoints. And bumping the genai library was obviously needed for this to work.
+
+Thanks for adding the docs about the limitations too - good for users to know they can't use context caches with global endpoints but might get fewer 429 errors.
+</approve_comment>
+<requesst_changes_comment>
+This is awesome. Thanks @scottsus.
+
+My main concern though - does this work for all the possible VS Code themes? We struggled with this initially which is why it's not super styled currently. Please test and share screenshots with the different themes to make sure before we can merge
+</request_changes_comment>
+<request_changes_comment>
+Hey, the PR looks good overall but I'm concerned about removing those timeouts. Those were probably there for a reason - VSCode's UI can be finicky with timing.
+
+Could you add back the timeouts after focusing the sidebar? Something like:
+
+```typescript
+await vscode.commands.executeCommand("claude-dev.SidebarProvider.focus")
+await setTimeoutPromise(100)  // Give UI time to update
+visibleWebview = WebviewProvider.getSidebarInstance()
+```
+</request_changes_comment>
+<request_changes_comment>
+Heya @alejandropta thanks for working on this! 
+
+A few notes:
+1 - Adding additional info to the environment variables is fairly problematic because env variables get appended to **every single message**. I don't think this is justifiable for a somewhat niche use case. 
+2 - Adding this option to settings to include that could be an option, but we want our options to be simple and straightforward for new users
+3 - We're working on revisualizing the way our settings page is displayed/organized, and this could potentially be reconciled once that is in and our settings page is more clearly delineated. 
+
+So until the settings page is update, and this is added to settings in a way that's clean and doesn't confuse new users, I don't think we can merge this. Please bear with us.
+</request_changes_comment>
+<request_changes_comment>
+Also, don't forget to add a changeset since this fixes a user-facing bug.
+
+The architectural change is solid - moving the focus logic to the command handlers makes sense. Just don't want to introduce subtle timing issues by removing those timeouts.
+</request_changes_comment>
+</example_comments_that_i_have_written_before>

.eslintrc.json

@@ -5,7 +5,7 @@
 		"ecmaVersion": 6,
 		"sourceType": "module"
 	},
-	"plugins": ["@typescript-eslint"],
+	"plugins": ["@typescript-eslint", "eslint-rules"],
 	"rules": {
 		"@typescript-eslint/naming-convention": [
 			"warn",
@@ -19,7 +19,9 @@
 		"eqeqeq": "warn",
 		"no-throw-literal": "warn",
 		"semi": "off",
-		"react-hooks/exhaustive-deps": "off"
+		"react-hooks/exhaustive-deps": "off",
+		"eslint-rules/no-protobuf-object-literals": "error",
+		"eslint-rules/no-grpc-client-object-literals": "error"
 	},
 	"ignorePatterns": ["out", "dist", "**/*.d.ts"]
 }

.github/workflows/stale.yml

@@ -0,0 +1,25 @@
+# This workflow will only label and/or close 30 issues at a time in order to avoid exceeding a rate limit.
+# More info: https://docs.github.com/en/actions/use-cases-and-examples/project-management/closing-inactive-issues
+name: Close inactive issues
+on:
+    schedule:
+        - cron: "30 1 * * *"
+
+jobs:
+    close-issues:
+        runs-on: ubuntu-latest
+        permissions:
+            issues: write
+            pull-requests: write
+        steps:
+            - uses: actions/stale@28ca103
+              with:
+                  days-before-issue-stale: 60
+                  days-before-issue-close: 14
+                  stale-issue-label: "stale"
+                  stale-issue-message: "This issue is stale because it has been open for 60 days with no activity."
+                  close-issue-message: "This issue was closed because it has been inactive for 14 days since being marked as stale."
+                  days-before-pr-stale: -1
+                  days-before-pr-close: -1
+                  exempt-issue-labels: "pinned,security"
+                  repo-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/test-stale.yml

@@ -0,0 +1,32 @@
+name: Test Stale Issues Workflow
+on:
+    workflow_dispatch:
+        inputs:
+            days-before-stale:
+                description: "Days before an issue becomes stale"
+                required: true
+                default: "1"
+            days-before-close:
+                description: "Days before a stale issue is closed"
+                required: true
+                default: "1"
+
+jobs:
+    test-stale:
+        runs-on: ubuntu-latest
+        permissions:
+            issues: write
+            pull-requests: write
+        steps:
+            - uses: actions/stale@28ca103
+              with:
+                  days-before-issue-stale: ${{ github.event.inputs.days-before-stale }}
+                  days-before-issue-close: ${{ github.event.inputs.days-before-close }}
+                  stale-issue-label: "stale"
+                  stale-issue-message: "This issue is stale because it has been open for ${{ github.event.inputs.days-before-stale }} days with no activity."
+                  close-issue-message: "This issue was closed because it has been inactive for ${{ github.event.inputs.days-before-close }} days since being marked as stale."
+                  days-before-pr-stale: -1
+                  days-before-pr-close: -1
+                  exempt-issue-labels: "pinned,security"
+                  repo-token: ${{ secrets.GITHUB_TOKEN }}
+                  debug-only: true

.github/workflows/test.yml

@@ -86,8 +86,9 @@ jobs:
             - name: Build Tests and Extension
               run: npm run pretest
 
-            - name: Unit Tests
-              run: npm run test:unit
+            # Unit Tests disabled due to module system conflicts between backend and webview-ui
+            # - name: Unit Tests
+            #   run: npm run test:unit
 
             # Run extension tests with coverage
             - name: Extension Tests with Coverage

.gitignore

@@ -20,3 +20,20 @@ coverage
 !.github/scripts/coverage/
 
 *evals.env
+
+# Generated proto files
+src/core/controller/*/methods.ts
+src/core/controller/*/index.ts
+src/core/controller/grpc-service-config.ts
+# Shared
+src/shared/proto/*.ts
+src/shared/proto/host/*.ts
+# Webview
+webview-ui/src/services/grpc-client.ts
+# Standalone
+src/standalone/server-setup.ts
+src/standalone/services/host-grpc-client.ts
+# Host bridge
+hosts/vscode/*/methods.ts
+hosts/vscode/*/index.ts
+hosts/vscode/host-grpc-service-config.ts

.mocharc.json

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

.prettierignore

@@ -3,3 +3,5 @@ node_modules
 webview-ui/build/
 *.md
 package-lock.json
+src/core/prompts/system.ts
+src/core/prompts/model_prompts/claude4.ts

.vscode/launch.json

@@ -52,7 +52,8 @@
 			"env": {
 				"GRPC_TRACE": "all",
 				"GRPC_VERBOSITY": "DEBUG",
-				"NODE_PATH": "${workspaceFolder}/dist-standalone/node_modules"
+				"NODE_PATH": "${workspaceFolder}/dist-standalone/node_modules",
+				"CLINE_DIR": "${userHome}/.cline-standalone"
 			},
 			"program": "standalone.js"
 		}

CHANGELOG.md

@@ -1,5 +1,103 @@
 # Changelog
 
+## [3.17.11]
+
+-   Add support for Gemini 2.5 Pro Preview 06-05 model to Vertex AI and Google Gemini providers
+
+## [3.17.10]
+
+-   Add support for Qwen 3 series models with thinking mode options (Thanks @Jonny-china!)
+-   Add new AskSage models: Claude 4 Sonnet, Claude 4 Opus, GPT 4.1, Gemini 2.5 Pro (Thanks @swhite24!)
+-   Add VSCode walkthrough to help new users get started with Cline
+-   Add support for streamable MCP servers
+-   Improve Ollama model selection with filterable dropdown instead of radio buttons (Thanks @paulgear!)
+-   Add setting to disable aggressive terminal reuse to help users experiencing task lockout issues
+-   Fix settings dialog applying changes even when cancel button is clicked
+
+## [3.17.9]
+
+-   Aligning Cline to work with Claude 4 model family (Experimental)
+-   Add task timeline scrolling feature
+-   Add support for uploading CSV and XLSX files for data analysis and processing
+-   Add stable Grok-3 models to xAI provider (grok-3, grok-3-fast, grok-3-mini, grok-3-mini-fast) and update default model from grok-3-beta to grok-3 (Thanks @PeterDaveHello!)
+-   Add new models to Vertex AI provider
+-   Add new model to Nebius AI Studio
+-   Remove hard-coded temperature from LM Studio API requests and add support for reasoning_content in LM Studio responses
+-   Display delay information when retrying API calls for better user feedback
+-   Fix AWS Bedrock credential caching issue where externally updated credentials (e.g., by AWS Identity Manager) were not detected, requiring extension restart (Thanks @DaveFres!)
+-   Fix search tool overloading conversation with massive outputs by setting maximum byte limit for responses
+-   Fix checkpoints functionality
+-   Fix token counting for xAI provider
+-   Fix Ollama provider issues
+-   Fix window title display for Windows users
+-   Improve chat box UI
+
+## [3.17.8]
+
+-   Fix bug where terminal would get stuck and output "capture failure"
+
+## [3.17.7]
+
+-   Fix diff editing reliability for Claude 4 family models by adding constraints to prevent errors with large replacements
+
+## [3.17.6]
+
+-   Add Cerebras as a new API provider with 5 high-performance models including reasoning-capable models (Thanks @kevint-cerebras!)
+-   Add support for uploading various file types (XML, JSON, TXT, LOG, MD, DOCX, IPYNB, PDF) alongside images
+-   Add improved onboarding experience for new users with guided setup
+-   Add prompt cache indicator for Gemini 2.5 Flash models
+-   Update SambaNova provider with new model list and documentation links (Thanks @luisfucros!)
+-   Fix diff editing support for Claude 4 family of models
+-   Improve telemetry and analytics for better user experience insights
+
+## [3.17.5]
+
+-   Fix issue with Claude 4 models where after several conversation turns, it would start making invalid diff edits
+
+## [3.17.4]
+
+-   Fix thinking budget slider for Claude 4
+
+## [3.17.3]
+
+-   Fix diff edit errors with Claude 4 models
+
+## [3.17.2]
+
+-   Add support for Claude 4 models (Sonnet 4 and Opus 4) in AWS Bedrock and Vertex AI providers
+-   Add support for global workflows, allowing workflows to be shared across workspaces with local workflows taking precedence
+-   Fix settings page z-index UI issues that caused display problems
+-   Fix AWS Bedrock environment variable handling to properly restore process.env after API calls (Thanks @DaveFres!)
+
+## [3.17.1]
+
+-   Add prompt caching for Claude 4 models on Cline and OpenRouter providers
+-   Increase max tokens for Claude Opus 4 from 4096 to 8192
+
+## [3.17.0]
+
+-   Add support for Anthropic Claude Sonnet 4 and Claude Opus 4 in both Anthropic and Vertex providers
+-   Add integration with Nebius AI Studio as a new provider (Thanks @Aktsvigun!)
+-   Add custom highlight and hotkey suggestion when the assistant prompts to switch to Act mode
+-   Update settings page design, now split into tabs for easier navigation (Thanks Yellow Bat @dlab-anton, and Roo Team!)
+-   Fix MCP Server configuration bug
+-   Fix model listing for Requesty provider
+-   Move all advanced settings to settings page
+
+## [3.16.3]
+
+-   Add devstral-small-2505 to the Mistral model list, a new specialized coding model from Mistral AI (Thanks @BarreiroT!)
+-   Add documentation links to rules & workflows UI
+-   Add support for Streameable HTTP Transport for MCPs (Thanks @alejandropta!)
+-   Improve error handling for Mistral SDK API
+
+## [3.16.2]
+
+-   Add support for Gemini 2.5 Flash Preview 05-20 model to Vertex AI provider with massive 1M token context window (Thanks @omercelik!)
+-   Add keyboard shortcut (Cmd+') to quickly focus Cline from anywhere in VS Code
+-   Add lightbulb actions for selected text with options to "Add to Cline", "Explain with Cline", and "Improve with Cline"
+-   Automatically focus Cline window after extension updates
+
 ## [3.16.1]
 
 -   Add Enable auto approve toggle switch, allowing users to easily turn auto-approve functionality on or off without losing their action settings

CONTRIBUTING.md

@@ -34,18 +34,20 @@ If you're planning to work on a bigger feature, please create a [feature request
 3. **Linux-specific Setup**
     VS Code extension tests on Linux require the following system libraries:
 
-    - `libatk1.0-0`
+    - `dbus`
+    - `libasound2`
     - `libatk-bridge2.0-0`
-    - `libxkbfile1`
+    - `libatk1.0-0`
+    - `libdrm2`
+    - `libgbm1`
+    - `libgtk-3-0`
+    - `libnss3`
     - `libx11-xcb1`
     - `libxcomposite1`
     - `libxdamage1`
     - `libxfixes3`
+    - `libxkbfile1`
     - `libxrandr2`
-    - `libgbm1`
-    - `libdrm2`
-    - `libgtk-3-0`
-    - `dbus`
     - `xvfb`
 
     These libraries provide necessary GUI components and system services for the test environment.
@@ -54,9 +56,21 @@ If you're planning to work on a bigger feature, please create a [feature request
     ```bash
     sudo apt update
     sudo apt install -y \
-      libatk1.0-0 libatk-bridge2.0-0 libxkbfile1 libx11-xcb1 \
-      libxcomposite1 libxdamage1 libxfixes3 libxrandr2 libgbm1 \
-      libdrm2 libgtk-3-0 dbus xvfb
+      dbus \
+      libasound2 \
+      libatk-bridge2.0-0 \
+      libatk1.0-0 \
+      libdrm2 \
+      libgbm1 \
+      libgtk-3-0 \
+      libnss3 \
+      libx11-xcb1 \
+      libxcomposite1 \
+      libxdamage1 \
+      libxfixes3 \
+      libxkbfile1 \
+      libxrandr2 \
+      xvfb
     ```
 
     - Run `npm run test:ci` to run tests locally

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, and GCP Vertex. 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, 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.
 
 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

@@ -74,8 +74,24 @@
 			{
 				"group": "Features",
 				"pages": [
+					"features/auto-approve",
+					"features/checkpoints",
 					"features/cline-rules",
+					"features/drag-and-drop",
+					"features/plan-and-act",
 					"features/slash-commands/workflows",
+					"features/editing-messages",
+					{
+						"group": "@ Mentions",
+						"pages": [
+							"features/at-mentions/overview",
+							"features/at-mentions/file-mentions",
+							"features/at-mentions/terminal-mentions",
+							"features/at-mentions/problem-mentions",
+							"features/at-mentions/git-mentions",
+							"features/at-mentions/url-mentions"
+						]
+					},
 					{
 						"group": "Slash Commands",
 						"pages": [
@@ -84,6 +100,16 @@
 							"features/slash-commands/smol",
 							"features/slash-commands/report-bug"
 						]
+					},
+					{
+						"group": "Commands & Shortcuts",
+						"pages": [
+							"features/commands-and-shortcuts/overview",
+							"features/commands-and-shortcuts/code-commands",
+							"features/commands-and-shortcuts/terminal-integration",
+							"features/commands-and-shortcuts/git-integration",
+							"features/commands-and-shortcuts/keyboard-shortcuts"
+						]
 					}
 				]
 			},
@@ -91,11 +117,8 @@
 				"group": "Exploring Cline's Tools",
 				"pages": [
 					"exploring-clines-tools/cline-tools-guide",
-					"exploring-clines-tools/plan-and-act-modes-a-guide-to-effective-ai-development",
-					"exploring-clines-tools/checkpoints",
 					"exploring-clines-tools/new-task-tool",
-					"exploring-clines-tools/remote-browser-support",
-					"exploring-clines-tools/slash-commands"
+					"exploring-clines-tools/remote-browser-support"
 				]
 			},
 			{
@@ -120,12 +143,22 @@
 				]
 			},
 			{
-				"group": "Custom Model Configurations",
+				"group": "Provider Configuration",
 				"pages": [
-					"custom-model-configs/aws-bedrock-with-credentials-authentication",
-					"custom-model-configs/aws-bedrock-with-profile-authentication",
-					"custom-model-configs/gcp-vertex-ai",
-					"custom-model-configs/litellm-and-cline-using-codestral"
+					"provider-config/anthropic",
+					"provider-config/aws-bedrock-with-credentials-authentication",
+					"provider-config/aws-bedrock-with-profile-authentication",
+					"provider-config/gcp-vertex-ai",
+					"provider-config/litellm-and-cline-using-codestral",
+					"provider-config/vscode-language-model-api",
+					"provider-config/xai-grok",
+					"provider-config/mistral-ai",
+					"provider-config/deepseek",
+					"provider-config/ollama",
+					"provider-config/openai",
+					"provider-config/openai-compatible",
+					"provider-config/openrouter",
+					"provider-config/requesty"
 				]
 			},
 			{

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

@@ -14,9 +14,9 @@ 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 Legacy IAM (AWS Credentials)](/custom-model-configs/aws-bedrock-with-credentials-authentication.mdx)
+#### [AWS Bedrock setup for Legacy IAM (AWS Credentials)](/provider-config/aws-bedrock-with-credentials-authentication)
 
-#### [AWS Bedrock setup for SSO token (AWS Profile)](/custom-model-configs/aws-bedrock-with-profile-authentication.mdx)
+#### [AWS Bedrock setup for SSO token (AWS Profile)](/provider-config/aws-bedrock-with-profile-authentication)
 
 #### VPC Endpoint Setup
 

docs/exploring-clines-tools/checkpoints.mdx

@@ -1,114 +0,0 @@
----
-title: "Checkpoints and Messages"
-description: "When working with AI coding assistants, it's easy to lose control as they make rapid changes to your codebase. That's why we built Checkpoints - your safety net for experimenting confidently."
----
-
-Checkpoints automatically save snapshots of your workspace after each step in a task. This powerful feature lets you:
-
--   Track and review changes made during a task
--   Roll back to any previous point if needed
--   Experiment confidently with auto-approve mode
--   Maintain full control over your workspace
-
-### ⚙️ How Checkpoints Work
-
-Cline creates a checkpoint after each tool use (file edits, commands, etc.). These checkpoints:
-
--   Work alongside your Git workflow without interference
--   Maintain context between restores
--   Use a shadow Git repository to track changes
-
-For example, if you're working on a feature and Cline makes multiple file changes, each change creates a checkpoint. This means you can review each modification and, if needed, roll back to any point without affecting your main Git repository.
-
-#### Viewing Changes & Restoring to Checkpoint
-
-After each tool use, you can:
-
-1. Click the "Compare" button to see modified files
-2. Click the "Restore" button to open restore options
-
-<Frame>
-	<img
-		src="https://storage.googleapis.com/cline_public_images/docs/assets/image%20(13).png"
-		alt="Checkpoint comparison and restore options"
-	/>
-</Frame>
-
-#### Rolling Back
-
-To restore to a previous point:
-
-1. Click the "Restore" button next to any step
-2. Choose from three options:
-    - **Restore Task and Workspace**: Reset both codebase and task to that point
-    - **Restore Task Only**: Keep codebase changes but revert task context
-    - **Restore Workspace Only**: Reset codebase while preserving task context
-
-Example: If Cline makes changes you don't like while styling a component, you can use "Restore Workspace Only" to revert the code changes while keeping the conversation context, allowing you to try a different approach.
-
-### 💡 Use Cases
-
-Checkpoints let you be more experimental with Cline. While human coding is often methodical and iterative, AI can make substantial changes quickly. Checkpoints help you track these changes and revert if needed.
-
-#### 1. Using Auto-Approve Mode
-
--   Provides safety net for rapid iterations
--   Makes it easy to undo unexpected results
-
-#### 2. Testing Different Approaches
-
--   Try multiple solutions confidently
--   Compare different implementations
--   Quickly revert to working states
--   Ideal for exploring different design patterns or architectural approaches
-
-<Frame caption="In this case, I didn't like the changes Cline made to my robot dog-walking website (still working on the robots) and I wanted to revert both the codebase and the task to before any changes were made so I could start fresh.">
-	<img src="https://storage.googleapis.com/cline_public_images/docs/assets/checkpointsDemo.gif" alt="Checkpoint restore demo" />
-</Frame>
-
-### ✨ Best Practices
-
-1. Use checkpoints as safety nets when experimenting
-2. Leverage auto-approve mode more confidently, knowing you can always roll back
-3. Restore selectively based on needs:
-
-    - Use "Restore Task and Workspace" for a fresh start, reversing changes to files and the task conversation.
-    - Use "Restore Task Only" to try different prompts, but leave all files as they exist
-    - Use "Restore Workspace Only" to attempt different implementations, or prune context from the task
-
-🛟 Checkpoints are your safety net when working with Cline, enabling you to experiment freely while maintaining full control over your codebase. Whether you're refactoring a complex component, trying different implementation approaches, or using auto-approve mode for rapid development, checkpoints ensure you can always review changes and roll back if needed.
-
-#### 🗑️ Deleting Checkpoints
-
-You can delete all checkpoints by using the **"Delete All History"** button in the task history menu. Note that this will also delete all tasks. Checkpoints are stored in VS Code's globalStorage.
-
----
-
-## Editing Messages
-
-Cline allows you to edit chat messages in a task after they've been submitted (with the exception of the message that started the task).
-
-Perhaps you didn't get the results you wanted, thought of a better way to phrase your request, or need to add more information. Editing your message allows you to re-submit a request without starting over or restoring your files or workspace with checkpoints. There are two Restore options:
-
--   **"Restore Chat"** restores just the task state and re-submits an API request to your provider with your edited message.
-
--   **"Restore All"** restores both the task state and workspace state before re-submitting an API request. "Workspace state" refers to the condition of your workspace (files, content, etc.) at different points in the conversation.
-
-**Interactive Editing:**
-
--   Messages can be clicked to enter edit mode
--   Cline automatically selects all text when entering edit mode
-
-**Keyboard Shortcuts:**
-
--   Escape: Exit edit mode
--   Enter: Restore just the task
--   Cmd/Ctrl + Enter: Restore the task and workspace
--   Shift + Enter: Insert new line / line break
-
-<Frame>
-	<img
-		src="https://storage.googleapis.com/cline_public_images/docs/assets/message-editing.png"
-		alt="Message editing interface"
-	/>
-</Frame>

docs/exploring-clines-tools/new-task-tool.mdx

@@ -29,6 +29,11 @@ As a quick alternative to Cline suggesting the `newtask` tool or defining comple
 -   **Action:** Cline will propose creating a new task, typically suggesting context based on the current session (similar to its default behavior when using the tool). You will still get the `ask_followup_question` prompt to confirm and potentially modify the context before the new task is created.
 -   **Benefit:** Provides a fast, user-initiated way to leverage the `new_task` functionality for branching explorations or managing long sessions without waiting for Cline to suggest it.
 
+<Note>
+	For more details on using the `/newtask` slash command, see the [New Task Command](/features/slash-commands/new-task)
+	documentation.
+</Note>
+
 #### Default Behavior (Without `.clinerules`)
 
 By default, without specific `.clinerules` dictating its behavior:

docs/exploring-clines-tools/slash-commands.mdx

@@ -1,57 +0,0 @@
----
-title: "Slash Commands"
----
-
-#### Overview
-
-Cline provides slash commands as a quick way to invoke specific tools or actions directly from the chat input, offering shortcuts for common operations. This page details the available slash commands and their usage.
-
-#### /newtask
-
-The `/newtask` slash command provides a fast, user-initiated way to leverage the `new_task` tool's functionality for branching explorations or managing long sessions without waiting for Cline to suggest it.
-
-**Functionality:**
-
-1. **Initiation:** Typing `/newtask` in the chat input signals Cline to prepare for starting a new task session.
-2. **Context Proposal:** Cline proposes creating a new task and typically suggests context to preload based on the current session (summarizing key aspects like current work, technical concepts, relevant files, problems solved, and next steps).
-3. **User Confirmation:** You will receive a confirmation prompt (via the `ask_followup_question` tool) displaying the proposed context. You can approve it directly or modify the context before the new task begins.
-4. **New Session:** Upon confirmation, Cline ends the current task session and immediately starts a new one, preloaded with the approved context.
-
-**Benefit:** Allows you to cleanly branch your work or start a new phase while carrying over essential background information ("knowledge transfer") without manual copying or losing the thread of the previous session.
-
-#### /smol (alias /compact)
-
-The `/smol` slash command (with `/compact` as an alias) allows you to condense the chat history **within your current task**. This is useful when a conversation becomes very long, potentially impacting performance or making it harder for the model to maintain focus.
-
-**Functionality:**
-
-1. **Initiation:** Typing `/smol` or `/compact` tells Cline you want to condense the current chat history. You can optionally add instructions after the command to guide the summarization process (e.g., `/smol focus only on the database changes` or `/smol be concise, use bullet points`).
-2. **Summarization:** Cline analyzes the conversation history, considering any additional instructions provided, and generates a summary focusing on key elements: recent discussion points, important decisions, technical concepts, relevant files, problems solved, and planned next steps. Cline determines the appropriate length and detail for the summary. It retains the beginning and very recent parts of the chat while summarizing the middle sections.
-3. **User Confirmation:** Cline presents this generated summary to you via a confirmation prompt and asks if it accurately reflects the essential context.
-4. **Condensing:** If you approve the summary, Cline replaces the summarized middle portion of the chat history in its active context with the generated summary. This reduces the overall token count for subsequent interactions within the _same task_.
-5. **Feedback:** If you reject the summary or provide feedback, Cline will retain the original history and incorporate your feedback for future actions.
-
-**Benefit:** Helps maintain focus and manage token usage during very long, continuous tasks (like deep debugging or extended feature development) without needing to start an entirely new task session. Allows user guidance on the summarization focus.
-
-#### When to Use Which?
-
-Choosing between `/newtask` and `/smol` depends on your goal:
-
--   Use `/smol` (or `/compact`) when:
-    -   You want to continue the **same task**, but the chat history has become very long or costly.
-    -   You need to reduce token usage for upcoming interactions within the current workflow.
-    -   Example: Deep debugging session where you want to summarize previous steps before continuing.
--   Use `/newtask` when:
-    -   You have finished one phase of work and want to start a **fresh, related task**.
-    -   You want to branch your exploration while preserving key context from the previous session.
-    -   Example: Moving from developing Feature A to starting work on Feature B, carrying over relevant architectural decisions.
-
-#### Why Manage Context?
-
-While Cline supports large context windows, actively managing context using tools and commands like `/newtask` and `/smol` is often beneficial:
-
--   **Performance:** Large language models can sometimes experience performance degradation or lose focus when context windows become extremely full (e.g., over 50-75% capacity, depending on the model). Condensing or resetting context can help maintain optimal performance.
--   **Relevance:** Summarizing or starting fresh ensures the most relevant information is prioritized in the context window.
--   **Cost:** Reducing the number of tokens sent to the model in each turn can help manage costs, especially with more expensive models.
-
-Using `/newtask` and `/smol` provides you with direct control over the conversation context, allowing for more efficient and effective interaction with Cline.

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

@@ -0,0 +1,45 @@
+---
+title: "File Mentions"
+sidebarTitle: "File Mentions"
+---
+
+File mentions let you pull any file from your workspace directly into your conversation with Cline. No more copying and pasting code snippets - just type `@/` and point to the file you need help with.
+
+When you type `@/` in the chat, Cline shows your workspace files. Navigate through folders, select the file you want, and it's instantly available to Cline - complete with all imports, related functions, and surrounding context.
+
+I use file mentions constantly when debugging. Instead of trying to figure out which parts of my code to copy over, I just reference the file directly:
+
+```
+I'm getting this error when my form submits: @terminal
+
+Here's my component: @/src/components/ContactForm.jsx
+
+And the API endpoint: @/src/api/contact.js
+
+What am I missing?
+```
+
+This gives Cline everything it needs - the error message, the component code, and the API endpoint - all without me having to copy anything. Cline can see imports, dependencies, and all the surrounding context that might be causing the issue.
+
+File mentions shine when you're dealing with complex bugs that span multiple files. Before, I'd have to carefully copy each relevant file, making sure I didn't miss anything important. Now I just reference each file with `@/` and Cline gets the complete picture.
+
+Next time you're stuck on a problem, try using file mentions instead of copying code. You'll save time and get better answers because Cline has all the context it needs.
+
+## How It Works Under the Hood
+
+When you use a file mention in your message, here's what happens behind the scenes:
+
+1. When you send your message, Cline detects the `@/path/to/file` pattern in your text
+2. The extension resolves the file path relative to your workspace root
+3. It checks if the file is binary (like an image) or text-based
+4. For text files, it reads the complete file content
+5. The file content is appended to your message in a structured format:
+    ```
+    <file_content path="path/to/file">
+    [Complete file content]
+    </file_content>
+    ```
+6. This enhanced message with the embedded file content is sent to the AI
+7. The AI can now "see" the complete file content as if you had copied and pasted it
+
+This seamless process happens automatically whenever you use a file mention, giving the AI full context without you having to manually copy anything.

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

@@ -0,0 +1,58 @@
+---
+title: "Folder Mentions"
+sidebarTitle: "Folder Mentions"
+---
+
+Folder mentions let you bring entire directories into your conversation with Cline. Just type `@/` followed by a folder path ending with a slash, and Cline gets access to the folder structure and its contents.
+
+When you type `@/` in chat, Cline shows your workspace files and folders. Navigate to the folder you want, make sure to include the trailing slash, and Cline will see the folder's structure and contents.
+
+I use folder mentions when I need help understanding or refactoring a whole section of my codebase. Instead of referencing individual files one by one, I can just point to the entire directory:
+
+```
+I'm trying to understand how the authentication flow works in my app.
+Can you explain the structure and relationships between the files in @/src/auth/?
+```
+
+Cline can then see all the files in the auth directory, their contents, and how they relate to each other. This gives it the full context to explain complex interactions between multiple files.
+
+Folder mentions are also perfect for getting help with project organization. When I'm unsure if my project structure makes sense, I'll ask Cline to review it:
+
+```
+I'm setting up a new React project. Does this folder structure make sense? @/src/
+What would you change to make it more maintainable as the project grows?
+```
+
+Next time you're working with multiple related files, try using folder mentions instead of referencing each file individually. You'll get more comprehensive help because Cline can see the bigger picture of how everything fits together.
+
+## How It Works Under the Hood
+
+When you use a folder mention in your message, here's what happens behind the scenes:
+
+1. When you send your message, Cline detects the `@/path/to/folder/` pattern (with trailing slash) in your text
+2. The extension resolves the folder path relative to your workspace root
+3. It calls `fs.readdir()` to get a list of all files and subdirectories in that folder
+4. For each file in the directory, it checks if it's binary or text-based
+5. For text files, it extracts the complete content
+6. The folder structure and file contents are appended to your message in a structured format:
+
+    ```
+    <folder_content path="path/to/folder">
+    ├── file1.txt
+    ├── file2.js
+    └── subfolder/
+
+    <file_content path="path/to/folder/file1.txt">
+    [File content]
+    </file_content>
+
+    <file_content path="path/to/folder/file2.js">
+    [File content]
+    </file_content>
+    </folder_content>
+    ```
+
+7. This enhanced message with the embedded folder structure and file contents is sent to the AI
+8. The AI can now "see" both the directory structure and the content of files within that directory
+
+This process happens automatically whenever you use a folder mention, giving the AI a comprehensive view of your project structure and file contents.

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

@@ -0,0 +1,84 @@
+---
+title: "Git Mentions"
+sidebarTitle: "Git Mentions"
+---
+
+Git mentions let you bring your repository's history and changes directly into your conversation with Cline. You can reference uncommitted changes with `@git-changes` or specific commits with `@[commit-hash]`.
+
+When you type `@` in chat, you can select "Git Changes" from the menu or type `@git-changes` directly. For specific commits, type `@` followed by the commit hash (at least 7 characters). Cline will immediately see the git status, diffs, commit messages, and other relevant information.
+
+I use git mentions constantly when I'm trying to understand code changes or troubleshoot issues introduced by recent commits. Instead of trying to copy and paste diffs or commit logs, I just ask:
+
+```
+I think this commit broke our authentication flow: @a1b2c3d
+
+Can you explain what changed and why it might be causing the issue?
+```
+
+This gives Cline the complete commit information, including the commit message, author, date, and the full diff. Cline can then analyze exactly what changed and how it might affect other parts of the codebase.
+
+The `@git-changes` mention is perfect when you're working on changes and want feedback before committing:
+
+```
+Here are my current changes: @git-changes
+
+I'm trying to implement a new feature for user profiles. Does my approach make sense?
+Are there any potential issues or improvements you'd suggest?
+```
+
+This shows Cline all your uncommitted changes, including new files, modified files, and their diffs. Cline can then review your changes and provide feedback on your implementation.
+
+Git mentions are especially powerful when combined with file mentions. When I'm investigating a bug, I'll often reference both:
+
+```
+I think this commit introduced a bug: @a1b2c3d
+
+Here's the current implementation: @/src/components/Auth.jsx
+
+How can I fix the issue while preserving the intended functionality?
+```
+
+Next time you're working with code changes or investigating issues, try using git mentions instead of manually describing or copying changes. You'll get more accurate help because Cline can see exactly what changed and in what context.
+
+## How It Works Under the Hood
+
+When you use git mentions in your message, here's what happens behind the scenes:
+
+### For Git Changes (`@git-changes`)
+
+1. When you send your message, Cline detects the `@git-changes` pattern in your text
+2. The extension runs git commands to get the current working state of your repository
+3. It captures the output of `git status` and `git diff` to see all uncommitted changes
+4. This information is appended to your message in a structured format:
+
+    ```
+    <git_working_state>
+    On branch main
+    Changes not staged for commit:
+      modified: src/components/Button.jsx
+      modified: src/styles/main.css
+
+    [Complete diff output with all changes]
+    </git_working_state>
+    ```
+
+### For Specific Commits (`@[commit-hash]`)
+
+1. When you send your message, Cline detects the `@` followed by a commit hash pattern
+2. The extension runs `git show` and related commands to get information about that commit
+3. It retrieves the commit message, author, date, and the complete diff
+4. This information is appended to your message in a structured format:
+
+    ```
+    <git_commit hash="a1b2c3d">
+    commit a1b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6q7r8s9t
+    Author: Developer Name <dev@example.com>
+    Date: Mon May 20 14:30:45 2025 -0700
+
+    Fix authentication bug in login form
+
+    [Complete diff output showing all changes in the commit]
+    </git_commit>
+    ```
+
+This process happens automatically whenever you use git mentions, giving the AI complete visibility into your code changes without you having to copy and paste diffs or commit logs.

docs/features/at-mentions/overview.mdx

@@ -0,0 +1,118 @@
+---
+title: "@ Mentions Overview"
+sidebarTitle: "Overview"
+---
+
+@ mentions are one of Cline's most powerful features, letting you seamlessly bring external context into your conversations. Instead of copying and pasting code, error messages, or documentation, you can simply reference them with an @ symbol.
+
+<Frame>
+	<img src="https://storage.googleapis.com/cline_public_images/docs/assets/at-mentions.png" alt="@ Mentions Overview" />
+</Frame>
+
+When you type `@` in the chat input, Cline shows a menu of available mention types. These mentions let you reference files, folders, problems, terminal output, git changes, and even web content directly in your conversations.
+
+## Available @ Mentions
+
+Cline supports several types of @ mentions, each designed to bring different kinds of context into your conversations:
+
+<Columns cols={2}>
+  <Card title="File Mentions" icon="file" href="/features/at-mentions/file-mentions">
+    Reference any file in your workspace with `@/path/to/file`. Cline sees the complete file content, including imports, related
+    functions, and surrounding context.
+  </Card>
+
+{" "}
+
+<Card title="Folder Mentions" icon="folder" href="/features/at-mentions/folder-mentions">
+	Reference entire directories with `@/path/to/folder/`. Cline sees the folder structure and all file contents, perfect for
+	understanding complex interactions between multiple files.
+</Card>
+
+{" "}
+
+<Card title="Problem Mentions" icon="triangle-exclamation" href="/features/at-mentions/problem-mentions">
+	Use `@problems` to show Cline all the errors and warnings in your workspace. Cline sees the complete list with file locations
+	and error messages.
+</Card>
+
+{" "}
+
+<Card title="Terminal Mentions" icon="terminal" href="/features/at-mentions/terminal-mentions">
+	Use `@terminal` to share your recent terminal output. Cline sees the complete output with formatting preserved, perfect for
+	debugging build errors or test failures.
+</Card>
+
+{" "}
+
+<Card title="Git Mentions" icon="code-branch" href="/features/at-mentions/git-mentions">
+	Reference uncommitted changes with `@git-changes` or specific commits with `@[commit-hash]`. Cline sees the complete diff,
+	commit message, and other relevant information.
+</Card>
+
+  <Card title="URL Mentions" icon="globe" href="/features/at-mentions/url-mentions">
+    Reference web content with `@https://example.com`. Cline fetches and sees the complete webpage content, perfect for
+    referencing documentation or GitHub issues.
+  </Card>
+</Columns>
+
+## Why @ Mentions Matter
+
+@ mentions transform how you interact with Cline by:
+
+1. **Eliminating copy-paste**: No more copying and pasting code, error messages, or terminal output. Just reference them directly.
+
+2. **Preserving context**: Cline sees the complete context, including imports, related functions, and surrounding code that might be relevant.
+
+3. **Maintaining formatting**: Terminal output, error messages, and web content keep their formatting, making them easier to understand.
+
+4. **Enabling complex workflows**: Combine multiple @ mentions to give Cline a complete picture of your problem:
+
+    ```
+    I'm getting these errors: @problems
+
+    Here's my component: @/src/components/Form.jsx
+    And the API endpoint: @/src/api/users.js
+
+    The error happens when I submit: @terminal
+
+    I think this commit might have caused it: @a1b2c3d
+    ```
+
+## Getting Started
+
+To use @ mentions:
+
+1. Type `@` in the chat input
+2. Select the type of mention from the menu or continue typing
+3. For files and folders, navigate through your workspace structure
+4. Send your message as usual
+
+Cline will automatically process the mentions and include the referenced content in the context sent to the AI.
+
+Try using @ mentions in your next conversation with Cline - you'll be amazed at how much more efficient and effective your interactions become when you can seamlessly bring in external context.
+
+## How It Works Under the Hood
+
+When you use @ mentions in your messages, there's a sophisticated process happening behind the scenes:
+
+1. **Detection**: When you send a message, Cline scans the text for @ mention patterns using regular expressions
+2. **Processing**: For each detected mention, Cline:
+    - Determines the mention type (file, folder, problems, terminal, git, URL)
+    - Fetches the relevant content (file contents, terminal output, etc.)
+    - Formats the content appropriately
+3. **Enhancement**: The original message is enhanced with structured data:
+
+    ```
+    Your original message with @/path/to/file
+
+    <file_content path="/path/to/file">
+    [Complete file content]
+    </file_content>
+    ```
+
+4. **Context Inclusion**: This enhanced message with all the embedded content is sent to the AI model
+5. **Seamless Response**: The AI can now "see" all the referenced content as if you had manually copied and pasted it
+
+This entire process happens automatically and seamlessly whenever you use @ mentions, giving the AI complete context without you having to manually copy anything.
+
+Each type of @ mention has its own specific implementation details, which you can find in their respective documentation pages.

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

@@ -0,0 +1,52 @@
+---
+title: "Problem Mentions"
+sidebarTitle: "Problem Mentions"
+---
+
+The problems mention gives Cline instant access to all the errors and warnings in your workspace. Just type `@problems` and Cline can see every diagnostic issue VSCode has detected.
+
+When you type `@` in chat, select "Problems" from the menu or just type `@problems` directly. Cline will immediately see all the errors and warnings from your workspace, complete with file locations and error messages.
+
+I use the problems mention constantly when I'm stuck on build errors or TypeScript issues. Instead of trying to describe the errors or copy them one by one, I just ask:
+
+```
+I'm getting these TypeScript errors and I'm not sure how to fix them: @problems
+
+Can you help me understand what's wrong and how to fix it?
+```
+
+This gives Cline the complete list of errors with their exact locations and messages. Cline can then analyze the patterns across multiple errors and suggest comprehensive solutions.
+
+The problems mention is especially powerful when combined with file mentions. When I'm dealing with complex type errors, I'll reference both:
+
+```
+I'm getting these type errors: @problems
+
+Here's my component: @/src/components/DataTable.tsx
+And the types file: @/src/types/api.ts
+
+How can I fix these issues?
+```
+
+This approach gives Cline everything it needs - the exact errors, the component code, and the type definitions - all without me having to copy anything manually.
+
+Next time you're stuck on errors, try using `@problems` instead of copying error messages. You'll get more accurate help because Cline can see the complete error context and locations.
+
+## How It Works Under the Hood
+
+When you use the problems mention in your message, here's what happens behind the scenes:
+
+1. When you send your message, Cline detects the `@problems` pattern in your text
+2. The extension calls VSCode's built-in `vscode.languages.getDiagnostics()` API to get all errors and warnings
+3. It formats these diagnostics into a structured text representation with file paths, line numbers, and error messages
+4. The formatted problems list is appended to your message in a structured format:
+    ```
+    <workspace_diagnostics>
+    /path/to/file.js:10:5 - error TS2322: Type 'string' is not assignable to type 'number'.
+    /path/to/file.js:15:3 - warning: This variable is never used.
+    </workspace_diagnostics>
+    ```
+5. This enhanced message with the embedded diagnostics is sent to the AI
+6. The AI can now "see" all the errors and warnings in your workspace, complete with their locations and messages
+
+This process happens automatically whenever you use the problems mention, giving the AI a comprehensive view of all the issues in your workspace without you having to copy them manually.

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

@@ -0,0 +1,60 @@
+---
+title: "Terminal Mentions"
+sidebarTitle: "Terminal Mentions"
+---
+
+The terminal mention lets you bring your terminal output directly into your conversation with Cline. Just type `@terminal` and Cline can see the recent output from your terminal.
+
+When you type `@` in chat, select "Terminal" from the menu or just type `@terminal` directly. Cline will immediately see the recent output from your active terminal, including error messages, build logs, or command results.
+
+I use the terminal mention all the time when I'm dealing with build errors, test failures, or debugging output. Instead of trying to copy and paste terminal output (which often loses formatting), I just ask:
+
+```
+I'm getting this error when running my tests: @terminal
+
+What's causing this and how can I fix it?
+```
+
+This gives Cline the complete terminal output with all its formatting intact. Cline can then analyze the error messages, stack traces, and surrounding context to provide more accurate help.
+
+The terminal mention is especially powerful when combined with file mentions. When I'm debugging a failed API call, I'll reference both:
+
+```
+I'm getting this error when calling my API: @terminal
+
+Here's my API client code: @/src/api/client.js
+And the endpoint implementation: @/src/server/routes/users.js
+
+What am I doing wrong?
+```
+
+This approach gives Cline everything it needs - the exact error output, the client code, and the server implementation - all without me having to copy anything manually.
+
+Next time you're running into issues with command output or build errors, try using `@terminal` instead of copying the output. You'll get more accurate help because Cline can see the complete terminal context with proper formatting.
+
+## How It Works Under the Hood
+
+When you use the terminal mention in your message, here's what happens behind the scenes:
+
+1. When you send your message, Cline detects the `@terminal` pattern in your text
+2. The extension calls `getLatestTerminalOutput()` which accesses VSCode's terminal API
+3. It captures the recent output buffer from your active terminal
+4. The terminal output is appended to your message in a structured format:
+
+    ```
+    <terminal_output>
+    $ npm run test
+    > project@1.0.0 test
+    > jest
+
+    FAIL src/components/__tests__/Button.test.js
+    ● Button component › renders correctly
+
+    [Complete terminal output with formatting preserved]
+    </terminal_output>
+    ```
+
+5. This enhanced message with the embedded terminal output is sent to the AI
+6. The AI can now "see" the complete terminal output with all formatting preserved
+
+This process happens automatically whenever you use the terminal mention, giving the AI access to your command results, error messages, and other terminal output without you having to copy it manually.

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

@@ -0,0 +1,65 @@
+---
+title: "URL Mentions"
+sidebarTitle: "URL Mentions"
+---
+
+URL mentions let you bring web content directly into your conversation with Cline. Just type `@` followed by any URL, and Cline can see the content of that webpage without you having to copy and paste anything.
+
+When you type `@` in chat followed by a URL (like `@https://example.com`), Cline will fetch the content of that webpage and include it in the context. This works for documentation pages, GitHub issues, Stack Overflow questions, or any other web content you want to reference.
+
+I use URL mentions constantly when I'm working with external APIs or libraries. Instead of trying to explain how an API works or copying documentation snippets, I just reference the docs directly:
+
+```
+I'm trying to implement authentication with this API: @https://api.example.com/docs/auth
+
+Can you help me write the code to get an access token based on these docs?
+```
+
+This gives Cline the complete documentation page, so it can see all the authentication requirements, endpoints, parameters, and examples. Cline can then provide more accurate and comprehensive help based on the official documentation.
+
+URL mentions are especially useful for referencing GitHub issues or discussions:
+
+```
+I'm trying to fix this issue in our project: @https://github.com/our-org/our-repo/issues/123
+
+Here's my current implementation: @/src/components/Feature.jsx
+
+What changes do I need to make to address the issue?
+```
+
+This shows Cline the complete GitHub issue, including the description, comments, and any code snippets or screenshots. Cline can then help you implement a solution that directly addresses the reported issue.
+
+Next time you're working with external documentation or online resources, try using URL mentions instead of copying and pasting content. You'll get more accurate help because Cline can see the complete context of the webpage, including formatting, code examples, and surrounding information.
+
+## How It Works Under the Hood
+
+When you use a URL mention in your message, here's what happens behind the scenes:
+
+1. When you send your message, Cline detects the `@http://...` or `@https://...` pattern in your text
+2. The extension launches a headless browser (Puppeteer) in the background
+3. It navigates to the URL and waits for the page to load completely
+4. The browser captures the page content, including text, formatting, and code examples
+5. The content is converted to a Markdown format that preserves the structure
+6. This content is appended to your message in a structured format:
+
+    ```
+    <url_content url="https://example.com/docs">
+    # Example API Documentation
+
+    ## Authentication
+
+    To authenticate with the API, you need to...
+
+    const token = await api.authenticate({
+      username: 'user',
+      password: 'pass'
+    });
+
+    [Complete webpage content in Markdown format]
+    </url_content>
+    ```
+
+7. The browser is then closed to free up resources
+8. This enhanced message with the embedded webpage content is sent to the AI
+
+This process happens automatically whenever you use a URL mention, giving the AI access to the complete content of the webpage without you having to copy and paste anything.

docs/features/auto-approve.mdx

@@ -0,0 +1,59 @@
+The Auto Approve menu lets you set fine-grained permissions on what you allow Cline to do in an automated way.
+
+<Frame>
+	<img src="https://storage.googleapis.com/cline_public_images/docs/assets/auto-approve.png" alt="Auto Approve" />
+</Frame>
+
+## How it works
+
+By default, Cline will ask for your permission before calling any tool, including reading or writing files.
+
+If you want to allow Cline to do something without asking, you can set the Auto Approve permission for that tool.
+
+## Permission Options
+
+-   **Read project files**
+
+    -   Allows Cline to read files within your current workspace without asking
+    -   **Read all files**
+        -   Extends read permission to files outside your workspace (system files, config files, etc.)
+
+-   **Edit project files**
+
+    -   Allows Cline to modify files within your current workspace without confirmation
+    -   **Edit all files**
+        -   Extends modification permission to files outside your workspace
+
+-   **Execute safe commands**
+
+    -   Allows execution of terminal commands that the model deems non-destructive
+    -   **Execute all commands**
+        -   Permits execution of any terminal command without asking
+
+-   **Use the browser**
+
+    -   Allows Cline to use the browser tool to fetch web content
+
+-   **Use MCP servers**
+
+    -   Permits connection to and usage of MCP servers for extended functionality
+
+-   **Maximum requests**
+    -   Sets the number of consecutive automated actions Cline can take before requiring your input
+
+## Best Practices
+
+Personally, I like to keep auto-editing disabled because it gives me a chance to review changes every step of the way.
+
+For most serious development workflows, I recommend starting with:
+
+-   Auto-approving read access to project files
+-   Setting a reasonable maximum request limit (10-20)
+
+This gives Cline enough freedom to explore your codebase without constant interruptions, while still requiring permission for edits or potentially destructive actions.
+
+As you build more trust in Cline's capabilities with your specific projects, you can gradually increase the permissions to match your comfort level.
+
+Remember that you can always adjust these settings as your needs change - tighten permissions for critical production work, or loosen them when prototyping and exploring.
+
+You can even use the quick "star" actions to quickly toggle your auto-approved selections on and off as you go.

docs/features/checkpoints.mdx

@@ -0,0 +1,79 @@
+---
+title: "Checkpoints"
+sidebarTitle: "Checkpoints"
+---
+
+Checkpoints automatically save snapshots of your workspace after each step in a task. This feature lets you track changes, roll back when needed, and experiment confidently with your code.
+
+## How Checkpoints Work
+
+Cline creates a checkpoint after each tool use (file edits, commands, etc.). These checkpoints:
+
+-   Work alongside your Git workflow without interference
+-   Maintain context between restores
+-   Use a shadow Git repository to track changes
+
+For example, if you're working on a feature and Cline makes multiple file changes, each change creates a checkpoint. This means you can review each modification and, if needed, roll back to any point without affecting your main Git repository.
+
+## Viewing Changes & Restoring
+
+After each tool use, you can:
+
+1. Click the "Compare" button to see modified files
+2. Click the "Restore" button to open restore options
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/image%20(13).png"
+		alt="Checkpoint comparison and restore options"
+	/>
+</Frame>
+
+## Restore Options
+
+To restore to a previous point:
+
+1. Click the "Restore" button next to any step
+2. Choose from three options:
+    - **Restore Task and Workspace**: Reset both codebase and task to that point
+    - **Restore Task Only**: Keep codebase changes but revert task context
+    - **Restore Workspace Only**: Reset codebase while preserving task context
+
+Example: If Cline makes changes you don't like while styling a component, you can use "Restore Workspace Only" to revert the code changes while keeping the conversation context, allowing you to try a different approach.
+
+<Frame caption="Reverting both codebase and task to before any changes were made to start fresh">
+	<img src="https://storage.googleapis.com/cline_public_images/docs/assets/checkpointsDemo.gif" alt="Checkpoint restore demo" />
+</Frame>
+
+## Use Cases
+
+Checkpoints let you be more experimental with Cline. While human coding is often methodical and iterative, AI can make substantial changes quickly. Checkpoints help you track these changes and revert if needed.
+
+### Using Auto-Approve Mode
+
+-   Provides safety net for rapid iterations
+-   Makes it easy to undo unexpected results
+
+### Testing Different Approaches
+
+-   Try multiple solutions confidently
+-   Compare different implementations
+-   Quickly revert to working states
+-   Ideal for exploring different design patterns or architectural approaches
+
+## Best Practices
+
+1. Use checkpoints as safety nets when experimenting
+2. Leverage auto-approve mode more confidently, knowing you can always roll back
+3. Restore selectively based on needs:
+    - Use "Restore Task and Workspace" for a fresh start
+    - Use "Restore Task Only" to try different prompts, but keep file changes
+    - Use "Restore Workspace Only" to attempt different implementations while preserving conversation context
+
+## Relationship with Message Editing
+
+The [message editing feature](/features/editing-messages) uses checkpoints under the hood when you select the "Restore All" option. This allows you to not only edit and resubmit your message but also restore your workspace to the state it was in at that point in the conversation.
+
+## Deleting Checkpoints
+
+You can delete all checkpoints by using the **"Delete All History"** button in the task history menu. Note that this will also delete all tasks. Checkpoints are stored in VS Code's globalStorage.

docs/features/commands-and-shortcuts/code-commands.mdx

@@ -0,0 +1,129 @@
+---
+title: "Code Commands"
+sidebarTitle: "Code Commands"
+---
+
+Cline's code commands bring AI assistance directly into your editor, letting you interact with your code without leaving your workflow. With a simple right-click, you can add code to Cline, and through the lightbulb menu, you can fix errors, get explanations, or improve your code.
+
+## Available Code Commands
+
+When you interact with code in your editor, you can access Cline commands in two ways:
+
+### Right-Click Context Menu
+
+When you right-click on selected code, you'll see:
+
+<Frame>
+	<img src="https://storage.googleapis.com/cline_public_images/docs/assets/code-commands.png" alt="Right Click Menu" />
+</Frame>
+
+#### Add to Cline
+
+The "Add to Cline" command sends your selected code to the Cline chat panel. This is perfect for:
+
+-   Asking questions about specific code snippets
+-   Requesting improvements or optimizations
+-   Getting explanations of complex logic
+
+When you use this command, Cline automatically includes:
+
+-   The file path (as a file mention)
+-   The selected code with proper formatting
+-   The programming language for accurate syntax highlighting
+
+### Lightbulb Menu (Code Actions)
+
+When you see a lightbulb icon in your editor, click it to access these Cline commands:
+
+<Frame>
+	<img src="https://storage.googleapis.com/cline_public_images/docs/assets/lightbulb-actions.png" alt="Lightbulb Menu" />
+</Frame>
+
+#### Fix with Cline
+
+The "Fix with Cline" command appears in the lightbulb menu when your code has errors or warnings. This command:
+
+1. Captures the selected code
+2. Identifies the errors or warnings from VSCode's diagnostics
+3. Sends both to Cline with a request to fix the issues
+4. Provides a solution that addresses the specific problems
+
+This is incredibly useful for quickly resolving syntax errors, linter warnings, or type issues without having to manually describe the problem.
+
+#### Explain with Cline
+
+The "Explain with Cline" command helps you understand complex code. When you select code and use this command from the lightbulb menu, Cline:
+
+1. Analyzes the selected code
+2. Provides a clear explanation of what the code does
+3. Breaks down complex logic into understandable parts
+4. Highlights important patterns or techniques used
+
+#### Improve with Cline
+
+The "Improve with Cline" command helps you enhance your code. When you select code and use this command from the lightbulb menu, Cline:
+
+1. Analyzes the selected code for potential improvements
+2. Suggests optimizations, refactorings, or better practices
+3. Explains the reasoning behind the suggested changes
+4. Provides improved code that maintains the original functionality
+
+## How to Use Code Commands
+
+Using Cline's code commands is simple:
+
+### For Right-Click Commands:
+
+1. Select the code you want to work with
+2. Right-click to open the context menu
+3. Choose "Add to Cline"
+4. View the result in the Cline chat panel
+
+### For Lightbulb Menu Commands:
+
+1. Select the code you want to work with
+2. Look for the lightbulb icon that appears in the editor gutter
+3. Click the lightbulb to see available actions
+4. Choose the appropriate Cline command (Fix, Explain, or Improve)
+5. View the result in the Cline chat panel
+
+After using any command, you can:
+
+-   Ask follow-up questions
+-   Request modifications to the solution
+-   Apply the changes back to your code
+
+## How It Works Under the Hood
+
+When you use a code command, here's what happens behind the scenes:
+
+1. **Code Selection**: The extension captures your selected code and its context
+2. **Metadata Collection**: Cline gathers important metadata:
+
+    - File path and name
+    - Programming language
+    - Any associated diagnostics (errors/warnings)
+    - Surrounding code context when relevant
+
+3. **Command Processing**:
+
+    - For "Add to Cline," the code is formatted and sent to the chat panel
+    - For "Fix with Cline," the code and diagnostics are analyzed and a fix is generated
+    - For "Explain with Cline," the code is analyzed to provide a clear explanation
+    - For "Improve with Cline," the code is analyzed for potential optimizations and improvements
+
+4. **Integration with Chat**: The results appear in the Cline chat panel, where you can:
+    - See the AI's response
+    - Ask follow-up questions
+    - Apply suggested changes
+
+This seamless integration between your editor and Cline's AI capabilities makes it easy to get assistance without disrupting your coding flow.
+
+## Tips for Effective Use
+
+-   **Select complete logical units**: When possible, select entire functions, classes, or modules to give Cline complete context
+-   **Include imports**: For language-specific help, include relevant imports so Cline understands dependencies
+-   **Combine with @ mentions**: For complex issues, use code commands along with file or problem mentions for more context
+-   **Use keyboard shortcuts**: Speed up your workflow by [assigning keyboard shortcuts](/features/commands-and-shortcuts/keyboard-shortcuts) to common code commands
+
+Next time you're struggling with a piece of code, try using Cline's code commands instead of switching to a separate chat interface. You'll be amazed at how much more efficient your workflow becomes when AI assistance is integrated directly into your editor.

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

@@ -0,0 +1,71 @@
+---
+title: "Generate Commit Message"
+sidebarTitle: "Generate Commit Message"
+---
+
+Cline's Git integration brings AI assistance directly to your version control workflow. Generate commit messages without leaving your editor.
+
+## Generate Commit Message
+
+One of the most useful Git integrations is the ability to automatically generate meaningful commit messages:
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/generate-commit-message-with-cline.png"
+		alt="Generate Commit Message with Cline"
+	/>
+</Frame>
+
+1. Make your changes and stage them in Git
+2. Click the robot icon in the Source Control view or run the "Generate Commit Message with Cline" command
+3. Cline analyzes your changes and generates a descriptive commit message
+4. The message is automatically inserted into the commit message input box
+
+The generated commit messages:
+
+-   Start with a concise summary (50-72 characters)
+-   Use imperative mood (e.g., "Add feature" not "Added feature")
+-   Describe what was changed and why
+-   Follow Git best practices
+
+This feature saves time and ensures your commit history is consistent and informative.
+
+<Tip>
+	For information about using `@git-changes` and `@[commit-hash]` mentions in your chat messages, see the [Git
+	Mentions](/features/at-mentions/git-mentions) documentation.
+</Tip>
+
+## How It Works
+
+When you use Cline's commit message generation feature, here's what happens behind the scenes:
+
+1. Cline retrieves the current Git diff using `getWorkingState()`
+2. It formats this diff into a specialized prompt for the AI
+3. The AI analyzes the changes and generates an appropriate commit message
+4. The message is extracted and inserted into the Git commit message input box
+
+This process uses your current Cline API configuration, so the quality of the generated messages matches your chosen AI model.
+
+## Tips for Effective Use
+
+-   **Generate commit messages for complex changes**: The AI excels at summarizing multiple related changes into a coherent message.
+
+-   **Review and edit generated messages**: While the AI generates high-quality messages, it's always good practice to review and adjust them if needed.
+
+-   **Stage related changes together**: For the best results, stage related changes together so the AI can generate a cohesive message.
+
+-   **Use for consistent commit history**: Using the generate commit message feature helps maintain a consistent style across your commit history.
+
+## How It Works Under the Hood
+
+The commit message generation leverages VSCode's Git extension API to access repository information:
+
+1. When you trigger the command:
+    - Cline gets the current diff
+    - It sends this to the AI with specific instructions for commit message formatting
+    - It parses the AI's response
+    - It accesses the Git extension API to set the commit message
+
+This integration with Git makes it easy to generate high-quality commit messages without disrupting your workflow.
+
+Next time you're struggling to write a good commit message, try using Cline's commit message generation. You'll save time and improve your version control workflow with AI assistance right where you need it.

docs/features/commands-and-shortcuts/keyboard-shortcuts.mdx

@@ -0,0 +1,103 @@
+---
+title: "Keyboard Shortcuts"
+sidebarTitle: "Keyboard Shortcuts"
+---
+
+Cline's keyboard shortcuts let you access AI assistance without taking your hands off the keyboard. Speed up your workflow by using hotkeys for common Cline actions.
+
+## Default Keyboard Shortcuts
+
+Cline comes with the following built-in keyboard shortcuts to streamline your workflow:
+
+| Action                  | Windows/Linux | macOS   | Condition                    | Description                               |
+| ----------------------- | ------------- | ------- | ---------------------------- | ----------------------------------------- |
+| Add to Cline            | `Ctrl+'`      | `Cmd+'` | When text is selected        | Adds selected code to Cline chat          |
+| Focus Chat Input        | `Ctrl+'`      | `Cmd+'` | When no text is selected     | Focuses the Cline chat input field        |
+| Generate Commit Message | (unset)       | (unset) | When Git is the SCM provider | Available through the Source Control view |
+
+## Available Commands for Custom Shortcuts
+
+While Cline has only a few default keyboard shortcuts, you can assign your own shortcuts to any of these commands:
+
+| Command ID                                                                               | Description                                   |
+| ---------------------------------------------------------------------------------------- | --------------------------------------------- |
+| [`cline.openInNewTab`](/features/commands-and-shortcuts/overview)                        | Opens Cline in a new editor tab               |
+| [`cline.addToChat`](/features/commands-and-shortcuts/code-commands)                      | Adds selected code to Cline chat              |
+| [`cline.addTerminalOutputToChat`](/features/commands-and-shortcuts/terminal-integration) | Adds terminal output to Cline                 |
+| `cline.focusChatInput`                                                                   | Focuses the Cline chat input field            |
+| [`cline.generateGitCommitMessage`](/features/commands-and-shortcuts/git-integration)     | Generates a commit message for staged changes |
+| [`cline.explainCode`](/features/commands-and-shortcuts/code-commands)                    | Explains selected code                        |
+| [`cline.improveCode`](/features/commands-and-shortcuts/code-commands)                    | Suggests improvements for selected code       |
+| [`cline.fixWithCline`](/features/commands-and-shortcuts/code-commands)                   | Fixes code with errors                        |
+| `claude-dev.SidebarProvider.focus`                                                       | Opens and focuses the Cline sidebar           |
+
+## Customizing Keyboard Shortcuts
+
+You can customize Cline's keyboard shortcuts to match your preferences:
+
+1. Open the Keyboard Shortcuts editor in VSCode:
+
+    - Press `Ctrl+K Ctrl+S` (Windows/Linux) or `Cmd+K Cmd+S` (macOS)
+    - Or go to File > Preferences > Keyboard Shortcuts
+
+2. Search for "Cline" to see all available commands
+
+3. Click on the pencil icon next to any command to change its shortcut
+
+4. Press the keys you want to assign to that command
+
+5. Press Enter to save the new shortcut
+
+## Suggested Custom Shortcuts
+
+Here are some suggested shortcuts you might find useful:
+
+| Action                | Suggested Shortcut             | Command ID                                | Description                   |
+| --------------------- | ------------------------------ | ----------------------------------------- | ----------------------------- |
+| Open Cline Sidebar    | `Ctrl+Shift+C` / `Cmd+Shift+C` | `claude-dev.SidebarProvider.focus`        | Opens the Cline sidebar panel |
+| New Task              | `Alt+N`                        | `cline.plusButtonClicked`                 | Starts a new Cline task       |
+| Add Terminal to Cline | `Alt+T`                        | `cline.addTerminalOutputToChat`           | Adds terminal output to Cline |
+| Clear Current Task    | `Alt+C`                        | (Requires custom keybinding to UI action) | Clears the current task       |
+
+## Keyboard-Only Workflow
+
+With the right shortcuts, you can use Cline without ever touching the mouse:
+
+1. Select code with keyboard navigation (`Shift+Arrow` keys)
+2. Send to Cline with `Ctrl+'` / `Cmd+'`
+3. Type your question and press Enter
+4. Review the response and apply suggestions
+
+## Editor Integration Shortcuts
+
+Cline's keyboard shortcuts integrate seamlessly with VSCode's built-in shortcuts:
+
+-   Use VSCode's selection shortcuts (`Ctrl+L` / `Cmd+L` to select line, etc.) before sending code to Cline
+-   Combine with VSCode's split editor shortcuts to view code and Cline side by side
+-   Use VSCode's terminal focus shortcut (`` Ctrl+` `` / `` Cmd+` ``) before capturing terminal output
+
+## Tips for Effective Use
+
+-   **Learn the default shortcut first**: The `Ctrl+'` / `Cmd+'` shortcut is versatile - it adds selected code to chat when text is selected, or focuses the chat input when nothing is selected
+-   **Create muscle memory**: Use keyboard shortcuts consistently to build habits
+-   **Customize for your workflow**: Assign shortcuts to commands you use frequently
+-   **Consider ergonomics**: Choose shortcuts that are comfortable for your keyboard layout
+
+Keyboard shortcuts may seem like a small optimization, but they can significantly speed up your workflow when using Cline regularly. By keeping your hands on the keyboard, you maintain your coding flow while still getting AI assistance exactly when you need it.
+
+## How to Find All Available Commands
+
+To see all Cline commands that can be assigned shortcuts:
+
+1. Open the Command Palette (`Ctrl+Shift+P` / `Cmd+Shift+P`)
+2. Type "Cline" to filter the list
+3. Browse the available commands
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/editor-integration.png"
+		alt="Editor Integration Overview"
+	/>
+</Frame>
+
+This helps you discover features you might not have known about and assign shortcuts to the ones you use most frequently.

docs/features/commands-and-shortcuts/overview.mdx

@@ -0,0 +1,65 @@
+---
+title: "Commands & Shortcuts Overview"
+sidebarTitle: "Overview"
+---
+
+Cline integrates directly into VSCode's interface, letting you access AI assistance without disrupting your workflow. These integrations appear as commands in context menus, keyboard shortcuts, and quick fixes throughout the editor.
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/editor-integration.png"
+		alt="Editor Integration Overview"
+	/>
+</Frame>
+
+### What are Editor Integrations?
+
+Editor integrations are commands and shortcuts that let you use Cline right where you're working. Instead of switching to the Cline panel first, you can select code, right-click, and immediately send it to Cline for help.
+These integrations appear in different places throughout VSCode:
+
+-   In the editor context menu (right-click menu) - "Add to Cline"
+-   In the terminal context menu - "Add to Cline"
+-   In the Source Control view - "Generate Commit Message"
+-   As keyboard shortcuts - Various Cline commands
+-   As Quick Fix options (lightbulb menu) - "Fix with Cline", "Explain with Cline", "Improve with Cline"
+
+### Available Editor Integrations
+
+Cline offers several editor integrations, each designed to enhance different aspects of your development workflow:
+
+<Columns cols={2}>
+  <Card title="Code Commands" icon="code" href="/features/commands-and-shortcuts/code-commands">
+    Right-click on code to add it to Cline, or use the lightbulb menu to fix errors, explain code, or improve it. Cline sees the complete code context, including imports and surrounding functions.
+  </Card>
+
+{" "}
+
+<Card title="Terminal Integration" icon="terminal" href="/features/commands-and-shortcuts/terminal-integration">
+	Add terminal output to Cline with a right-click or use `@terminal` mentions. Perfect for debugging build errors, test
+	failures, or runtime issues.
+</Card>
+
+{" "}
+
+<Card title="Git Integration" icon="code-branch" href="/features/commands-and-shortcuts/git-integration">
+	Generate commit messages, explain diffs, or analyze changes with Cline's Git integration. Cline understands your version
+	control context.
+</Card>
+
+{" "}
+
+<Card title="Keyboard Shortcuts" icon="keyboard" href="/features/commands-and-shortcuts/keyboard-shortcuts">
+	Speed up your workflow with keyboard shortcuts for common Cline actions. Quickly add code to chat, fix errors, or improve your code.
+</Card>
+</Columns>
+
+### How They Work
+
+When you use these commands, Cline:
+
+-   Captures the relevant context (selected code, file path, terminal output, etc.)
+-   Focuses the Cline interface
+-   Creates a conversation with the captured context
+-   In some cases, automatically generates a suggested prompt
+
+Behind the scenes, these commands use VSCode's extension API to register commands, access editor state, and control VSCode's interface.

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

@@ -0,0 +1,81 @@
+---
+title: "Terminal Integration"
+sidebarTitle: "Terminal Integration"
+---
+
+Cline's terminal integration lets you bring your terminal output directly into your conversations with Cline. Instead of copying and pasting error messages or command results, you can send them to Cline with a simple right-click in the terminal.
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/terminal-integration.png"
+		alt="Terminal Integration"
+	/>
+</Frame>
+
+## Right-Click Terminal Integration
+
+When you're working in the VSCode terminal and see output you want to discuss with Cline:
+
+1. Right-click in the terminal
+2. Select "Add to Cline" from the context menu
+3. The terminal output is immediately sent to the Cline chat panel
+
+This is perfect for:
+
+-   Debugging build errors
+-   Understanding test failures
+-   Analyzing command output
+-   Getting help with error messages
+
+The right-click terminal integration is especially useful when you're already working in the terminal and encounter an issue.
+
+Instead of switching context to the Cline chat panel and typing a description of the problem, you can send the terminal output directly to Cline with just a couple of clicks.
+
+Alternatively, you can use the [`@terminal`](/features/at-mentions/terminal-mentions) mention to send the full terminal output to Cline.
+
+<Tip>
+	For information about using `@terminal` mentions in your chat messages, see the [Terminal
+	Mentions](/features/at-mentions/terminal-mentions) documentation.
+</Tip>
+
+## How Terminal Integration Works
+
+When you use the right-click terminal integration, Cline:
+
+1. Captures the terminal output with all formatting preserved
+2. Includes the complete context, including command history and results
+3. Formats it appropriately for the AI to understand
+4. Enables the AI to see exactly what you're seeing
+
+This gives Cline the full context it needs to provide accurate help with terminal-related issues.
+
+## Behind the Scenes
+
+The terminal integration uses a clever technique to capture terminal output:
+
+1. When you trigger the integration, Cline:
+
+    - Temporarily saves your current clipboard content
+    - Selects all terminal content (or uses your existing selection)
+    - Copies it to the clipboard
+    - Reads the clipboard to get the terminal content
+    - Restores your original clipboard content
+
+2. The terminal content is then:
+    - Formatted with proper syntax highlighting
+    - Added to your message or sent as a new message
+    - Enhanced with additional context when needed
+
+This approach ensures that all terminal output, including colors and formatting, is accurately captured without affecting your clipboard.
+
+## Tips for Effective Use
+
+-   **Use terminal integration for error messages**: When you encounter an error in the terminal, sending it to Cline often results in faster resolution than trying to describe the error.
+
+-   **Select specific output when needed**: By default, the integration captures all terminal content, but you can also select specific lines before right-clicking to focus on just the relevant output.
+
+-   **Combine with file mentions**: After sending terminal output to Cline, you can enhance your question by mentioning relevant files using the @ mentions feature.
+
+-   **Use for build and test output**: Terminal integration is particularly useful for understanding complex build errors or test failures that span multiple lines.
+
+Next time you're staring at a cryptic error message in your terminal, try using Cline's terminal integration instead of copying and pasting. You'll get more accurate help because Cline can see the complete terminal context with proper formatting.

docs/features/drag-and-drop.mdx

@@ -0,0 +1,14 @@
+---
+title: "Drag & Drop"
+sidebarTitle: "Drag & Drop"
+---
+
+Dragging and dropping files into Cline is a quick way to add images, code, and other files to your conversations.
+
+<Note>Due to VS Code quirks, to drag and drop files into the Cline chat input, you need to hold `Shift` while dragging.</Note>
+
+Dragging and dropping workspace files into Cline will automatically create a [file mention](/features/at-mentions/file-mentions). This allows you to reference the file in your conversation without needing to type out the path.
+
+### Supported File Types
+
+Cline supports dragging external images from your file system, as well as files from your workspace.

docs/features/editing-messages.mdx

@@ -0,0 +1,67 @@
+---
+title: "Editing Messages"
+sidebarTitle: "Editing Messages"
+---
+
+Cline allows you to edit chat messages in a task after they've been submitted. This feature lets you refine your requests without starting a new task, helping you get better results with minimal disruption to your workflow.
+
+## When to Edit Messages
+
+You might want to edit a message when:
+
+-   You didn't get the results you wanted
+-   You thought of a better way to phrase your request
+-   You need to add more information or context
+-   You made a typo or error in your original message
+
+## How to Edit Messages
+
+1. Click on any message in the conversation (except the initial task message)
+2. Edit the text as needed
+3. Use the restore options to resubmit your request
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/message-editing.png"
+		alt="Message editing interface"
+	/>
+</Frame>
+
+## Restore Options
+
+When you edit a message, you have two options for restoring:
+
+### Restore Chat
+
+The "Restore Chat" option:
+
+-   Restores just the task state
+-   Re-submits an API request with your edited message
+-   Preserves all file changes made up to that point
+-   Is useful when you want to keep the current state of your workspace
+
+### Restore All
+
+The "Restore All" option:
+
+-   Restores both the task state and workspace state
+-   Re-submits an API request with your edited message
+-   Reverts your workspace to how it was at that point in the conversation
+-   Uses [checkpoints](/features/checkpoints) under the hood to restore your workspace
+-   Is useful when you want to try a completely different approach
+
+## Keyboard Shortcuts
+
+When editing a message, you can use these keyboard shortcuts:
+
+-   **Escape**: Exit edit mode without making changes
+-   **Enter**: Restore just the task (equivalent to "Restore Chat")
+-   **Cmd/Ctrl + Enter**: Restore the task and workspace (equivalent to "Restore All")
+-   **Shift + Enter**: Insert a new line / line break in your message
+
+## Best Practices
+
+-   Use message editing for minor adjustments to your requests
+-   For major changes in direction, consider starting a new task
+-   When using "Restore All," be aware that any file changes made after that message will be reverted
+-   Edit messages closer to the beginning of a conversation to avoid losing significant progress

docs/features/plan-and-act.mdx

@@ -1,33 +1,37 @@
 ---
-title: "Plan & Act Modes: A Guide to Effective AI Development"
+title: "Plan & Act"
+sidebarTitle: "Plan & Act"
 ---
 
-## Overview
-
 Plan & Act modes represent Cline's approach to structured AI development, emphasizing thoughtful planning before implementation. This dual-mode system helps developers create more maintainable, accurate code while reducing iteration time.
 
 <Frame>
-	<img
-		src="https://storage.googleapis.com/cline_public_images/docs/assets/planningThenActing%20(1).gif"
-		alt="Use Plan to gather context before using Act to implement the plan"
-	/>
+	<iframe
+		style={{ width: "100%", aspectRatio: "16/9" }}
+		src="https://www.youtube.com/embed/b7o6URFPp64"
+		title="YouTube video player"
+		frameBorder="0"
+		allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
+		allowFullScreen></iframe>
 </Frame>
 
-### Understanding the Modes
+#### Plan Mode: Think First
 
-#### Plan Mode
+Plan mode is where you and Cline figure out what you're trying to build and how you'll build it. In this mode, Cline:
 
--   Optimized for context gathering and strategy
--   Cannot make changes to your codebase
--   Focused on understanding requirements and creating implementation plans
--   Enables full file reading for comprehensive project understanding
+-   Can read your entire codebase to understand the context
+-   Won't make any changes to your files
+-   Focuses on understanding requirements and creating a strategy
+-   Helps identify potential issues before you write a single line of code
 
-#### Act Mode
+#### Act Mode: Build It
 
--   Streamlined for implementation based on established plans
--   Has access to all of Cline's building capabilities
--   Maintains context from the planning phase
--   Can execute changes to your codebase
+Once you've got a plan, you switch to Act mode. Now Cline:
+
+-   Has all the building capabilities at its disposal
+-   Can make changes to your codebase
+-   Still remembers everything from your planning session
+-   Executes the strategy you worked out together
 
 <Frame>
 	<img src="https://storage.googleapis.com/cline_public_images/docs/assets/image%20(5).png" alt="Act mode capabilities" />
@@ -35,6 +39,14 @@ Plan & Act modes represent Cline's approach to structured AI development, emphas
 
 ### Workflow Guide
 
+When I'm working on a new feature or fixing a complex bug, here's what works for me:
+
+1. I start in Plan mode and tell Cline what I want to build
+2. Cline helps me explore the codebase, looking at relevant files
+3. Together we figure out the best approach, considering edge cases and potential issues
+4. When I'm confident in our plan, I switch to Act mode
+5. Cline implements the solution based on our planning
+
 #### 1. Start with Plan Mode
 
 Begin every significant development task in Plan mode:
@@ -108,24 +120,26 @@ Complex projects often require multiple plan-act cycles:
 
 -   Use Plan mode to explore edge cases before implementation
 -   Switch back to Plan when encountering unexpected complexity
--   Leverage file reading to validate assumptions early
+-   Leverage [file reading](/features/at-mentions/file-mentions) to validate assumptions early
 -   Have Cline write markdown files of the plan for future reference
 
 ### Common Patterns
 
-#### When to Use Plan Mode
+#### When to Use Each Mode
 
--   Starting new features
--   Debugging complex issues
--   Architectural decisions
--   Requirements analysis
+I've found Plan mode works best when:
 
-#### When to Use Act Mode
+-   Starting something new where the approach isn't obvious
+-   Debugging a tricky issue where I'm not sure what's wrong
+-   Making architectural decisions that will affect multiple parts of the codebase
+-   Trying to understand a complex workflow or feature
 
--   Implementing agreed solutions
--   Making routine changes
--   Following established patterns
--   Executing test cases
+And Act mode is perfect for:
+
+-   Implementing a solution we've already planned out
+-   Making routine changes where the approach is clear
+-   Following established patterns in the codebase
+-   Running tests and making minor adjustments
 
 <Frame>
 	<img src="https://storage.googleapis.com/cline_public_images/docs/assets/image%20(6).png" alt="Mode usage patterns" />
@@ -142,4 +156,4 @@ Share your experiences and improvements:
 
 ---
 
-Remember: The time invested in planning pays dividends in implementation quality and maintenance efficiency
+Remember: The time invested in planning pays dividends in implementation quality and maintenance efficiency.

docs/features/slash-commands/workflows.mdx

@@ -9,7 +9,7 @@ To invoke a workflow, type `/[workflow-name.md]` in the chat.
 
 ## How to Create and Use Workflows
 
-Workflows live alongside Cline Rules. Creating one is straightforward:
+Workflows live alongside [Cline Rules](/features/cline-rules). Creating one is straightforward:
 
 <Frame>
 	<img src="https://storage.googleapis.com/cline_public_images/docs/assets/workflows.png" alt="Workflows tab in Cline" />
@@ -22,9 +22,9 @@ Workflows live alongside Cline Rules. Creating one is straightforward:
 
 The real power comes from how you structure your workflow files. You can:
 
--   Leverage Cline's built-in tools like `ask_followup_question`, `read_file`, and `search_files`
+-   Leverage Cline's [built-in tools](/exploring-clines-tools/cline-tools-guide) like `ask_followup_question`, `read_file`, `search_files`, and `new_task`
 -   Use command-line tools you already have installed like `gh` or `docker`
--   Reference external MCP tool calls like Slack or Whatsapp
+-   Reference external [MCP tool calls](/mcp/mcp-overview) like Slack or Whatsapp
 -   Chain multiple actions together in a specific sequence
 
 ## Real-world Example
@@ -133,13 +133,39 @@ You have access to the `gh` terminal command. I already authenticated it for you
 1. Approve the PR if it meets quality standards:
 
     ```bash
+    # For single-line comments:
     gh pr review <PR-number> --approve --body "Your approval message"
+
+    # For multi-line comments with proper whitespace formatting:
+    cat << EOF | gh pr review <PR-number> --approve --body-file -
+    Thanks @username for this PR! The implementation looks good.
+
+    I particularly like how you've handled X and Y.
+
+    Great work!
+    EOF
     ```
 
 2. Request changes if improvements are needed:
+
     ```bash
+    # For single-line comments:
     gh pr review <PR-number> --request-changes --body "Your feedback message"
+
+    # For multi-line comments with proper whitespace formatting:
+    cat << EOF | gh pr review <PR-number> --request-changes --body-file -
+    Thanks @username for this PR!
+
+    The implementation looks promising, but there are a few things to address:
+
+    1. Issue one
+    2. Issue two
+
+    Please make these changes and we can merge this.
+    EOF
     ```
+
+    Note: The `cat << EOF | ... --body-file -` approach preserves all whitespace and formatting without requiring temporary files. The `-` parameter tells the command to read from standard input.
     </detailed_sequence_of_steps>
 
 <example_review_process>
@@ -221,7 +247,21 @@ Would you like me to proceed with approving this PR?</question>
 ## Step 6: Make a Decision
 
 ```bash
-gh pr review 3627 --approve --body "This PR looks good! It correctly fixes the thinking mode budget calculation for Claude 3.7 models by using the appropriate maxBudget value (64000) and applying the right percentage (50%) for the slider. The changes are well-tested and the implementation is clean."
+# Option 1: Simple one-line comment
+gh pr review 3627 --approve --body "This PR looks good! It correctly fixes the thinking mode budget calculation for Claude 3.7 models."
+
+# Option 2: Multi-line comment with proper whitespace formatting
+cat << EOF | gh pr review 3627 --approve --body-file -
+This PR looks good! It correctly fixes the thinking mode budget calculation for Claude 3.7 models.
+
+I particularly like:
+1. The proper implementation of thinkingConfig.maxBudget property (64000)
+2. The appropriate percentage (50%) for the slider calculation
+3. The comprehensive unit tests
+4. The clean implementation that follows project coding standards
+
+Great work!
+EOF
 ```
 
 </example_review_process>
@@ -262,14 +302,38 @@ gh pr checkout <PR-number>
 ## Review Commands
 
 ```bash
-# Approve a PR
+# Approve a PR (single-line comment)
 gh pr review <PR-number> --approve --body "Your approval message"
 
-# Request changes on a PR
+# Approve a PR (multi-line comment with proper whitespace)
+cat << EOF | gh pr review <PR-number> --approve --body-file -
+Your multi-line
+approval message with
+
+proper whitespace formatting
+EOF
+
+# Request changes on a PR (single-line comment)
 gh pr review <PR-number> --request-changes --body "Your feedback message"
 
+# Request changes on a PR (multi-line comment with proper whitespace)
+cat << EOF | gh pr review <PR-number> --request-changes --body-file -
+Your multi-line
+change request with
+
+proper whitespace formatting
+EOF
+
 # Add a comment review (without approval/rejection)
 gh pr review <PR-number> --comment --body "Your comment message"
+
+# Add a comment review with proper whitespace
+cat << EOF | gh pr review <PR-number> --comment --body-file -
+Your multi-line
+comment with
+
+proper whitespace formatting
+EOF
 ```
 
 ## Additional Commands
@@ -286,6 +350,64 @@ gh pr merge <PR-number> --merge
 ```
 
 </common_gh_commands>
+
+<general_guidelines_for_commenting>
+When reviewing a PR, please talk normally and like a friendly reviwer. You should keep it short, and start out by thanking the author of the pr and @ mentioning them.
+
+Whether or not you approve the PR, you should then give a quick summary of the changes without being too verbose or definitive, staying humble like that this is your understanding of the changes. Kind of how I'm talking to you right now.
+
+If you have any suggestions, or things that need to be changed, request changes instead of approving the PR.
+
+Leaving inline comments in code is good, but only do so if you have something specific to say about the code. And make sure you leave those comments first, and then request changes in the PR with a short comment explaining the overall theme of what you're asking them to change.
+</general_guidelines_for_commenting>
+
+<example_comments_that_i_have_written_before>
+<brief_approve_comment>
+Looks good, though we should make this generic for all providers & models at some point
+</brief_approve_comment>
+<brief_approve_comment>
+Will this work for models that may not match across OR/Gemini? Like the thinking models?
+</brief_approve_comment>
+<approve_comment>
+This looks great! I like how you've handled the global endpoint support - adding it to the ModelInfo interface makes total sense since it's just another capability flag, similar to how we handle other model features.
+
+The filtered model list approach is clean and will be easier to maintain than hardcoding which models work with global endpoints. And bumping the genai library was obviously needed for this to work.
+
+Thanks for adding the docs about the limitations too - good for users to know they can't use context caches with global endpoints but might get fewer 429 errors.
+</approve_comment>
+<requesst_changes_comment>
+This is awesome. Thanks @scottsus.
+
+My main concern though - does this work for all the possible VS Code themes? We struggled with this initially which is why it's not super styled currently. Please test and share screenshots with the different themes to make sure before we can merge
+</request_changes_comment>
+<request_changes_comment>
+Hey, the PR looks good overall but I'm concerned about removing those timeouts. Those were probably there for a reason - VSCode's UI can be finicky with timing.
+
+Could you add back the timeouts after focusing the sidebar? Something like:
+
+```typescript
+await vscode.commands.executeCommand("claude-dev.SidebarProvider.focus")
+await setTimeoutPromise(100) // Give UI time to update
+visibleWebview = WebviewProvider.getSidebarInstance()
+```
+
+</request_changes_comment>
+<request_changes_comment>
+Heya @alejandropta thanks for working on this!
+
+A few notes:
+1 - Adding additional info to the environment variables is fairly problematic because env variables get appended to **every single message**. I don't think this is justifiable for a somewhat niche use case.
+2 - Adding this option to settings to include that could be an option, but we want our options to be simple and straightforward for new users
+3 - We're working on revisualizing the way our settings page is displayed/organized, and this could potentially be reconciled once that is in and our settings page is more clearly delineated.
+
+So until the settings page is update, and this is added to settings in a way that's clean and doesn't confuse new users, I don't think we can merge this. Please bear with us.
+</request_changes_comment>
+<request_changes_comment>
+Also, don't forget to add a changeset since this fixes a user-facing bug.
+
+The architectural change is solid - moving the focus logic to the command handlers makes sense. Just don't want to introduce subtle timing issues by removing those timeouts.
+</request_changes_comment>
+</example_comments_that_i_have_written_before>
 ````
 
 When I get a new PR to review, I used to manually gather context: checking the PR description, examining the diff, looking at surrounding files, and finally forming an opinion. Now I just:
@@ -294,7 +416,7 @@ When I get a new PR to review, I used to manually gather context: checking the P
 2. Paste in the PR number
 3. Let Cline handle everything else
 
-My workflow uses the `gh` command-line tool to:
+My workflow uses the `gh` command-line tool and Cline's built in `ask_followup_question` to:
 
 -   Pull the PR description and comments
 -   Examine the diff

docs/getting-started/for-new-coders.mdx

@@ -13,35 +13,13 @@ Before you jump into coding, make sure you have these essentials ready:
 
 A popular, free, and powerful code editor.
 
--   [Download VS Code](https://code.visualstudio.com/)
+-   [<u>Download VS Code</u>](https://code.visualstudio.com/)
 
-📺 **Recommended YouTube Tutorial:** [How to Install VS Code](https://www.youtube.com/watch?v=MlIzFUI1QGA)
+📺 **Recommended YouTube Tutorial:** [<u>How to Install VS Code</u>](https://www.youtube.com/watch?v=MlIzFUI1QGA)
 
 > ✅ **Pro Tip:** Install VS Code in your Applications folder (macOS) or Program Files (Windows) for easy access from your dock or start menu.
 
-#### 2. **Essential Development Tools**
-
-Basic software required for coding efficiently:
-
--   Homebrew (macOS)
--   Node.js
--   Git
-
-👉 Follow our detailed guide on Installing Essential Development Tools with step-by-step help from Cline.
-
-📺 **Recommended YouTube Tutorials:**
-
--   **For macOS:**
-    -   [Install Homebrew on Mac](https://www.youtube.com/watch?v=hwGNgVbqasc)
-    -   [Install Git on MacOS 2024](https://www.youtube.com/watch?v=B4qsvQ5IqWk)
-    -   [Install Node.js on Mac (M1 | M2 | M3)](https://www.youtube.com/watch?v=I8H4wolRFBk)
--   **For Windows:**
-    -   [Install Git on Windows 10/11 (2024)](https://www.youtube.com/watch?v=yjxv1HuRQy0)
-    -   [Install Node.js in Windows 10/11](https://www.youtube.com/watch?v=uCgAuOYpJd0)
-
-> ⚠️ **Note:** If you run into permission issues during installation, try running your terminal or command prompt as an administrator.
-
-#### 3. **Organize Your Projects**
+#### 2. **Organize Your Projects**
 
 Create a dedicated folder named `Cline` in your Documents folder for all your coding projects:
 
@@ -55,14 +33,36 @@ Inside your `Cline` folder, structure projects clearly:
 
 > 💡 **Tip:** Keeping your projects organized from the start will save you time and confusion later!
 
-#### 4. **Install the Cline VS Code Extension**
+#### 3. **Install the Cline VS Code Extension**
 
 Enhance your coding workflow by installing the Cline extension directly within VS Code:
 
 -   Get Started with Cline Extension Tutorial
 
-📺 **Recommended YouTube Tutorial:** [How To Install Extensions in VS Code](https://www.youtube.com/watch?v=E7trgwZa-mk)
+📺 **Recommended YouTube Tutorial:** [<u>How To Install Extensions in VS Code</u>](https://www.youtube.com/watch?v=E7trgwZa-mk)
 
 > ✅ **Pro Tip:** After installing, reload VS Code to ensure the extension is activated properly.
 
+#### 4. **Essential Development Tools**
+
+Basic software required for coding efficiently:
+
+-   Homebrew (macOS)
+-   Node.js
+-   Git
+
+👉 [<u>Follow our detailed guide on Installing Essential Development Tools with step-by-step help from Cline.</u>](https://docs.cline.bot/getting-started/installing-dev-essentials#installing-dev-essentials)
+
+📺 **Recommended YouTube Tutorials for Manual Installation:**
+
+-   **For macOS:**
+    -   [<u>Install Homebrew on Mac</u>](https://www.youtube.com/watch?v=hwGNgVbqasc)
+    -   [<u>Install Git on macOS 2024</u>](https://www.youtube.com/watch?v=B4qsvQ5IqWk)
+    -   [<u>Install Node.js on Mac (M1 | M2 | M3)</u>](https://www.youtube.com/watch?v=I8H4wolRFBk)
+-   **For Windows:**
+    -   [<u>Install Git on Windows 10/11 (2024)</u>](https://www.youtube.com/watch?v=yjxv1HuRQy0)
+    -   [<u>Install Node.js in Windows 10/11</u>](https://www.youtube.com/watch?v=uCgAuOYpJd0)
+
+> ⚠️ **Note:** If you run into permission issues during installation, try running your terminal or command prompt as an administrator.
+
 🎉 You're all set! Dive in and start coding smarter and faster with **Cline**.

docs/getting-started/installing-cline.mdx

@@ -60,7 +60,6 @@ Now that you have Cline installed, let's get you set up with your account:
     - DeepSeek Chat (cost-effective alternative)
     - Google Gemini 2.0 Flash
     - And more — all through your Cline account.
-4.  -
 
 ### 💻 Your First Interaction with Cline
 

docs/getting-started/our-favorite-tech-stack.mdx

@@ -69,9 +69,9 @@ Choose your AI assistant based on your needs:
 ### Getting Started
 
 1. Install the development essentials:
-    - Follow our [Development Essentials Installation Guide](https://docs.cline.bot/getting-started/getting-started-new-coders/installing-dev-essentials)
+    - Follow our [Development Essentials Installation Guide](https://docs.cline.bot/getting-started/installing-dev-essentials)
 2. Set up Cline's Memory Bank:
-    - Follow the [Memory Bank setup instructions](https://docs.cline.bot/improving-your-prompting-skills/custom-instructions-library/cline-memory-bank)
+    - Follow the [Memory Bank setup instructions](https://docs.cline.bot/prompting/cline-memory-bank)
     - Create an empty `cline_docs` folder in your project root
     - Create `projectBrief.md` in the `cline_docs` folder (see example below)
     - Tell Cline to "initialize memory bank"
@@ -197,20 +197,20 @@ git push origin main                        # Upload to GitHub
 1.  **Start of day**: Get latest changes
 
     ```bash
-    bashCopygit pull origin main                     # Download latest code
+    git pull origin main                     # Download latest code
     ```
 
 2.  **During development**: Save work regularly
 
     ```bash
-    bashCopygit add .
+    git add .
     git commit -m "Clear message about changes"
     ```
 
 3.  **End of day**: Share your progress
 
     ```bash
-    bashCopygit push origin main                     # Upload to GitHub
+    git push origin main                     # Upload to GitHub
     ```
 
 **Best Practices**

docs/getting-started/understanding-context-management.mdx

@@ -38,7 +38,7 @@ Cline actively builds context in two ways:
     - Guide focus areas
     - Share design thoughts and requirements
 
-💡 **Key Point**: Cline isn't passive - it actively seeks to understand your project. You can either let it explore or guide its focus, especially in [Plan](https://docs.cline.bot/exploring-clines-tools/plan-and-act-modes-a-guide-to-effective-ai-development) mode.
+💡 **Key Point**: Cline isn't passive - it actively seeks to understand your project. You can either let it explore or guide its focus, especially in [Plan](https://docs.cline.bot/features/plan-and-act) mode.
 
 ### Context & Context Windows
 
@@ -93,7 +93,7 @@ Context files help maintain understanding across sessions. They serve as documen
 
 #### Approaches to Context Files
 
-1. **Evergreen Project Context (i.e.** [**Memory Bank**](https://docs.cline.bot/improving-your-prompting-skills/custom-instructions-library/cline-memory-bank)**)**
+1. **Evergreen Project Context (i.e.** [**Memory Bank**](https://docs.cline.bot/prompting/cline-memory-bank)**)**
     - Living documentation that evolves with your project
     - Updated as architecture and patterns emerge
     - Example: The Memory Bank pattern maintains files like `techContext.md` and `systemPatterns.md`
@@ -151,7 +151,7 @@ Context files help maintain understanding across sessions. They serve as documen
     - Use Plan mode for complex discussions
     - Start fresh sessions when needed
 3. **Team Projects**
-    - Share common context files (consider using [.clinerules](https://docs.cline.bot/improving-your-prompting-skills/prompting) files in project roots)
+    - Share common context files (consider using [.clinerules](https://docs.cline.bot/features/cline-rules) files in project roots)
     - Document architectural decisions
     - Maintain consistent patterns
     - Keep documentation current

docs/provider-config/anthropic.mdx

@@ -0,0 +1,61 @@
+---
+title: "Anthropic"
+description: "Learn how to configure and use Anthropic Claude models with Cline. Covers API key setup, model selection, and advanced features like prompt caching."
+---
+
+**Website:** [https://www.anthropic.com/](https://www.anthropic.com/)
+
+### Getting an API Key
+
+1.  **Sign Up/Sign In:** Go to the [Anthropic Console](https://console.anthropic.com/). Create an account or sign in.
+2.  **Navigate to API Keys:** Go to the [API keys](https://console.anthropic.com/settings/keys) section.
+3.  **Create a Key:** Click "Create Key". Give your key a descriptive name (e.g., "Cline").
+4.  **Copy the Key:** **Important:** Copy the API key _immediately_. You will not be able to see it again. Store it securely.
+
+### Supported Models
+
+Cline supports the following Anthropic Claude models:
+
+-   `claude-opus-4-20250514`
+-   `claude-opus-4-20250514:thinking` (Extended Thinking variant)
+-   `claude-sonnet-4-20250514` (Recommended)
+-   `claude-sonnet-4-20250514:thinking` (Extended Thinking variant)
+-   `claude-3-7-sonnet-20250219`
+-   `claude-3-7-sonnet-20250219:thinking` (Extended Thinking variant)
+-   `claude-3-5-sonnet-20241022`
+-   `claude-3-5-haiku-20241022`
+-   `claude-3-opus-20240229`
+-   `claude-3-haiku-20240307`
+
+See [Anthropic's Model Documentation](https://docs.anthropic.com/en/docs/about-claude/models) for more details on each model's capabilities.
+
+### Configuration in Cline
+
+1.  **Open Cline Settings:** Click the settings icon (⚙️) in the Cline panel.
+2.  **Select Provider:** Choose "Anthropic" from the "API Provider" dropdown.
+3.  **Enter API Key:** Paste your Anthropic API key into the "Anthropic API Key" field.
+4.  **Select Model:** Choose your desired Claude model from the "Model" dropdown.
+5.  **(Optional) Custom Base URL:** If you need to use a custom base URL for the Anthropic API, check "Use custom base URL" and enter the URL. Most users won't need to adjust this setting.
+
+### Extended Thinking
+
+Anthropic models offer an "Extended Thinking" feature, designed to give them enhanced reasoning capabilities for complex tasks. This feature allows the model to output its step-by-step thought process before delivering a final answer, providing transparency and enabling more thorough analysis for challenging prompts.
+
+When extended thinking is in Cline, the model generates `thinking` content blocks that detail its internal reasoning. These insights are then incorporated into its final response.
+Cline users can leverage this by checking the `Enable Extended Thinking` box below the model selection menu after selecting a Claude Model from any provider.
+
+**Key Aspects of Extended Thinking:**
+
+-   **Supported Models:** This feature is available for select models, including variants of Claude Opus 4, Claude Sonnet 4, and Claude Sonnet 3.7. The specific models listed in the "Supported Models" section above with the `:thinking` suffix are pre-configured in Cline to utilize this.
+-   **Summarized Thinking (Claude 4):** For Claude 4 models, the API returns a summary of the full thinking process to balance insight with efficiency and prevent misuse. You are billed for the full thinking tokens, not just the summary.
+-   **Streaming:** Extended thinking responses, including the `thinking` blocks, can be streamed.
+-   **Tool Use & Prompt Caching:** Extended thinking interacts with tool use (requiring thinking blocks to be passed back) and prompt caching (with specific behaviors around cache invalidation and context).
+
+For comprehensive details on how extended thinking works, including API examples, interaction with tool use, prompt caching, and pricing, please refer to the [official Anthropic documentation on Extended Thinking](https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking).
+
+### Tips and Notes
+
+-   **Prompt Caching:** Claude 3 models support [prompt caching](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching), which can significantly reduce costs and latency for repeated prompts.
+-   **Context Window:** Claude models have large context windows (200,000 tokens), allowing you to include a significant amount of code and context in your prompts.
+-   **Pricing:** Refer to the [Anthropic Pricing](https://www.anthropic.com/pricing) page for the latest pricing information.
+-   **Rate Limits:** Anthropic has strict rate limits based on [usage tiers](https://docs.anthropic.com/en/api/rate-limits#requirements-to-advance-tier). If you're repeatedly hitting rate limits, consider contacting Anthropic sales or accessing Claude through a different provider like [OpenRouter](/provider-config/openrouter) or [Requesty](/provider-config/requesty).

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

@@ -25,12 +25,41 @@ description: "Learn how to set up AWS Bedrock with Cline using credentials authe
 
 #### 1.2 Attach the Required Policies
 
-1. **Attach the Managed Policy:**
-    - Attach the **`AmazonBedrockFullAccess`** managed policy to your user/role.\
-      [View AmazonBedrockFullAccess Policy Details](https://docs.aws.amazon.com/bedrock/latest/userguide/security-iam.html)
-2. **Confirm Additional Permissions:**
-    - Ensure your policy includes permissions for model invocation (e.g., `bedrock:InvokeModel` and `bedrock:InvokeModelWithResponseStream`), model listing, and AWS Marketplace actions (like `aws-marketplace:Subscribe`).
-    - _Enterprise Tip:_ Apply least-privilege practices by scoping resource ARNs and using [Service Control Policies (SCPs)](https://docs.aws.amazon.com/organizations/latest/userguide/orgs_manage_policies_scps.html) to restrict access where necessary.
+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:
+
+-   `bedrock:InvokeModel`
+-   `bedrock:InvokeModelWithResponseStream`
+
+You can create a custom IAM policy with these permissions and attach it to your IAM user or role.
+
+**Option 1: Minimal Permissions (Recommended for Production & Least Privilege)**
+
+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"],
+    			"Resource": "*" // For enhanced security, scope this to specific model ARNs if possible.
+    		}
+    	]
+    }
+    ```
+3.  Name the policy (e.g., `ClineBedrockInvokeAccess`) and attach it to your IAM user or role.
+
+**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)
+
+**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), ensure you have active AWS Marketplace subscriptions. This is typically managed in the AWS Bedrock console under "Model access" and might require `aws-marketplace:Subscribe` permissions if not already handled.
+-   _Enterprise Tip:_ Always apply least-privilege practices. Where possible, scope resource ARNs in your IAM policies to specific models or regions. Utilize [Service Control Policies (SCPs)](https://docs.aws.amazon.com/organizations/latest/userguide/orgs_manage_policies_scps.html) for overarching governance in AWS Organizations.
 
 ---
 

docs/provider-config/deepseek.mdx

@@ -0,0 +1,33 @@
+---
+title: "DeepSeek"
+description: "Learn how to configure and use DeepSeek models like deepseek-chat and deepseek-reasoner with Cline."
+---
+
+Cline supports accessing models through the DeepSeek API, including `deepseek-chat` and `deepseek-reasoner`.
+
+**Website:** [https://platform.deepseek.com/](https://platform.deepseek.com/)
+
+### Getting an API Key
+
+1.  **Sign Up/Sign In:** Go to the [DeepSeek Platform](https://platform.deepseek.com/). Create an account or sign in.
+2.  **Navigate to API Keys:** Find your API keys in the [API keys](https://platform.deepseek.com/api_keys) section of the platform.
+3.  **Create a Key:** Click "Create new API key". Give your key a descriptive name (e.g., "Cline").
+4.  **Copy the Key:** **Important:** Copy the API key _immediately_. You will not be able to see it again. Store it securely.
+
+### Supported Models
+
+Cline supports the following DeepSeek models:
+
+-   `deepseek-v3-0324` (Recommended for coding tasks)
+-   `deepseek-r1` (Recommended for reasoning tasks)
+
+### Configuration in Cline
+
+1.  **Open Cline Settings:** Click the ⚙️ icon in the Cline panel.
+2.  **Select Provider:** Choose "DeepSeek" from the "API Provider" dropdown.
+3.  **Enter API Key:** Paste your DeepSeek API key into the "DeepSeek API Key" field.
+4.  **Select Model:** Choose your desired model from the "Model" dropdown.
+
+### Tips and Notes
+
+-   **Pricing:** Refer to the [DeepSeek Pricing](https://api-docs.deepseek.com/quick_start/pricing/) page for details on model costs.

docs/provider-config/mistral-ai.mdx

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

docs/provider-config/ollama.mdx

@@ -0,0 +1,78 @@
+---
+title: "Ollama"
+---
+
+Cline supports running models locally using Ollama. This approach offers privacy, offline access, and potentially reduced costs. It requires some initial setup and a sufficiently powerful computer. Because of the present state of consumer hardware, it's not recommended to use Ollama with Cline as performance will likely be poor for average hardware configurations.
+
+**Website:** [https://ollama.com/](https://ollama.com/)
+
+### Setting up Ollama
+
+1.  **Download and Install Ollama:**
+    Obtain the Ollama installer for your operating system from the [Ollama website](https://ollama.com/) and follow their installation guide. Ensure Ollama is running. You can typically start it with:
+
+    ```bash
+    ollama serve
+    ```
+
+2.  **Download a Model:**
+    Ollama supports a wide variety of models. A list of available models can be found on the [Ollama model library](https://ollama.com/library). Some models recommended for coding tasks include:
+
+    -   `codellama:7b-code` (a good, smaller starting point)
+    -   `codellama:13b-code` (offers better quality, larger size)
+    -   `codellama:34b-code` (provides even higher quality, very large)
+    -   `qwen2.5-coder:32b`
+    -   `mistralai/Mistral-7B-Instruct-v0.1` (a solid general-purpose model)
+    -   `deepseek-coder:6.7b-base` (effective for coding)
+    -   `llama3:8b-instruct-q5_1` (suitable for general tasks)
+
+    To download a model, open your terminal and execute:
+
+    ```bash
+    ollama pull <model_name>
+    ```
+
+    For instance:
+
+    ```bash
+    ollama pull qwen2.5-coder:32b
+    ```
+
+3.  **Configure the Model's Context Window:**
+    By default, Ollama models often use a context window of 2048 tokens, which can be insufficient for many Cline requests. A minimum of 12,000 tokens is advisable for decent results, with 32,000 tokens being ideal. To adjust this, you'll modify the model's parameters and save it as a new version.
+
+    First, load the model (using `qwen2.5-coder:32b` as an example):
+
+    ```bash
+    ollama run qwen2.5-coder:32b
+    ```
+
+    Once the model is loaded within the Ollama interactive session, set the context size parameter:
+
+    ```
+    /set parameter num_ctx 32768
+    ```
+
+    Then, save this configured model with a new name:
+
+    ```
+    /save your_custom_model_name
+    ```
+
+    (Replace `your_custom_model_name` with a name of your choice.)
+
+4.  **Configure Cline:**
+    -   Open the Cline sidebar (usually indicated by the Cline icon).
+    -   Click the settings gear icon (⚙️).
+    -   Select "ollama" as the API Provider.
+    -   Enter the Model name you saved in the previous step (e.g., `your_custom_model_name`).
+    -   (Optional) Adjust the base URL if Ollama is running on a different machine or port. The default is `http://localhost:11434`.
+    -   (Optional) Configure the Model context size in Cline's Advanced settings. This helps Cline manage its context window effectively with your customized Ollama model.
+
+### Tips and Notes
+
+-   **Resource Demands:** Running large language models locally can be demanding on system resources. Ensure your computer meets the requirements for your chosen model.
+-   **Model Choice:** Experiment with various models to discover which best fits your specific tasks and preferences.
+-   **Offline Capability:** After downloading a model, you can use Cline with that model even without an internet connection.
+-   **Token Usage Tracking:** Cline tracks token usage for models accessed via Ollama, allowing you to monitor consumption.
+-   **Ollama's Own Documentation:** For more detailed information, consult the official [Ollama documentation](https://ollama.com/docs).

docs/provider-config/openai-compatible.mdx

@@ -0,0 +1,72 @@
+---
+title: "OpenAI Compatible"
+description: "Learn how to configure Cline with various AI model providers that offer OpenAI-compatible APIs."
+---
+
+Cline supports a wide range of AI model providers that offer APIs compatible with the OpenAI API standard. This allows you to use models from providers _other than_ OpenAI, while still utilizing a familiar API interface. This includes providers such as:
+
+-   **Local models** running through tools like Ollama and LM Studio (which are covered in their respective sections).
+-   **Cloud providers** like Perplexity, Together AI, Anyscale, and many others.
+-   **Any other provider** that offers an OpenAI-compatible API endpoint.
+
+This document focuses on setting up providers _other than_ the official OpenAI API (which has its own [dedicated configuration page](/provider-config/openai)).
+
+### General Configuration
+
+The key to using an OpenAI-compatible provider with Cline is to configure these main settings:
+
+1.  **Base URL:** This is the API endpoint specific to the provider. It will _not_ be `https://api.openai.com/v1` (that URL is for the official OpenAI API).
+2.  **API Key:** This is the secret key you obtain from your chosen provider.
+3.  **Model ID:** This is the specific name or identifier for the model you wish to use.
+
+You'll find these settings in the Cline settings panel (click the ⚙️ icon):
+
+-   **API Provider:** Select "OpenAI Compatible".
+-   **Base URL:** Enter the base URL provided by your chosen provider. **This is a crucial step.**
+-   **API Key:** Enter your API key from the provider.
+-   **Model:** Choose or enter the model ID.
+-   **Model Configuration:** This section allows you to customize advanced parameters for the model, such as:
+    -   Max Output Tokens
+    -   Context Window size
+    -   Image Support capabilities
+    -   Computer Use (e.g., for models with tool/function calling)
+    -   Input Price (per token/million tokens)
+    -   Output Price (per token/million tokens)
+
+### Supported Models (for OpenAI Native Endpoint)
+
+While the "OpenAI Compatible" provider type allows connecting to various endpoints, if you are connecting directly to the official OpenAI API (or an endpoint that mirrors it exactly), Cline recognizes the following model IDs based on the `openAiNativeModels` definition in its source code:
+
+-   `o3-mini`
+-   `o3-mini-high`
+-   `o3-mini-low`
+-   `o1`
+-   `o1-preview`
+-   `o1-mini`
+-   `gpt-4.5-preview`
+-   `gpt-4o`
+-   `gpt-4o-mini`
+
+**Note:** If you are using a different OpenAI-compatible provider (such as Together AI, Anyscale, etc.), the available model IDs will differ. Always refer to your specific provider's documentation for their supported model names and any unique configuration details.
+
+### v0 (Vercel SDK) in Cline:
+
+-   For developers working with v0, their [AI SDK documentation](https://vercel.com/docs/v0/cline) provides valuable insights and examples for integrating various models, many of which are OpenAI-compatible. This can be a helpful resource for understanding how to structure calls and manage configurations when using Cline with services deployed on or integrated with Vercel.
+
+-   v0 can be used in Cline with the OpenAI Compatible provider.
+
+-   ### Quickstart
+
+-   1. With the OpenAI Compatible provider selected, set the Base URL to https://api.v0.dev/v1.
+-   2. Paste in your v0 API Key
+-   3. Set the Model ID: v0-1.0-md
+-   4. Click Verify to confirm the connection.
+
+### Troubleshooting
+
+-   **"Invalid API Key":** Double-check that you've entered the API key correctly and that it's for the correct provider.
+-   **"Model Not Found":** Ensure you're using a valid model ID for your chosen provider and that it's available at the specified Base URL.
+-   **Connection Errors:** Verify the Base URL is correct, that your provider's API is accessible from your machine, and that there are no firewall or network issues.
+-   **Unexpected Results:** If you're getting unexpected outputs, try a different model or double-check all configuration parameters.
+
+By using an OpenAI-compatible provider, you can leverage the flexibility of Cline with a wider array of AI models. Remember to always consult your provider's documentation for the most accurate and up-to-date information.

docs/provider-config/openai.mdx

@@ -0,0 +1,48 @@
+---
+title: "OpenAI"
+description: "Learn how to configure and use official OpenAI models with Cline."
+---
+
+Cline supports accessing models directly through the official OpenAI API.
+
+**Website:** [https://openai.com/](https://openai.com/)
+
+### Getting an API Key
+
+1.  **Sign Up/Sign In:** Visit the [OpenAI Platform](https://platform.openai.com/). You'll need to create an account or sign in if you already have one.
+2.  **Navigate to API Keys:** Once logged in, go to the [API keys section](https://platform.openai.com/api-keys) of your account.
+3.  **Create a Key:** Click on "Create new secret key". It's good practice to give your key a descriptive name (e.g., "Cline API Key").
+4.  **Copy the Key:** **Crucial:** Copy the generated API key immediately. For security reasons, OpenAI will not show it to you again. Store this key in a safe and secure location.
+
+### Supported Models
+
+Cline is compatible with a variety of OpenAI models, including but not limited to:
+
+-   'o3'
+-   `o3-mini` (medium reasoning effort)
+-   'o4-mini'
+-   `o3-mini-high` (high reasoning effort)
+-   `o3-mini-low` (low reasoning effort)
+-   `o1`
+-   `o1-preview`
+-   `o1-mini`
+-   `gpt-4.5-preview`
+-   `gpt-4o`
+-   `gpt-4o-mini`
+-   'gpt-4.1'
+-   'gpt-4.1-mini'
+
+For the most current list of available models and their capabilities, please refer to the official [OpenAI Models documentation](https://platform.openai.com/docs/models).
+
+### Configuration in Cline
+
+1.  **Open Cline Settings:** Click the settings gear icon (⚙️) in the Cline panel.
+2.  **Select Provider:** Choose "OpenAI" from the "API Provider" dropdown menu.
+3.  **Enter API Key:** Paste your OpenAI API key into the "OpenAI API Key" field.
+4.  **Select Model:** Choose your desired model from the "Model" dropdown list.
+5.  **(Optional) Base URL:** If you need to use a proxy or a custom base URL for the OpenAI API, you can enter it here. Most users will not need to change this from the default.
+
+### Tips and Notes
+
+-   **Pricing:** Be sure to review the [OpenAI Pricing page](https://openai.com/pricing) for detailed information on the costs associated with different models.
+-   **Azure OpenAI Service:** If you are looking to use the Azure OpenAI service, please note that specific documentation for Azure OpenAI with Cline may be found separately, or you might need to configure it as an OpenAI-compatible endpoint if such functionality is supported by Cline for custom configurations.

docs/provider-config/openrouter.mdx

@@ -0,0 +1,40 @@
+---
+title: "OpenRouter"
+description: "Learn how to use OpenRouter with Cline to access a wide variety of language models through a single API."
+---
+
+OpenRouter is an AI platform that provides access to a wide variety of language models from different providers, all through a single API. This can simplify setup and allow you to easily experiment with different models.
+
+**Website:** [https://openrouter.ai/](https://openrouter.ai/)
+
+### Getting an API Key
+
+1.  **Sign Up/Sign In:** Go to the [OpenRouter website](https://openrouter.ai/). Sign in with your Google or GitHub account.
+2.  **Get an API Key:** Go to the [keys page](https://openrouter.ai/keys). You should see an API key listed. If not, create a new key.
+3.  **Copy the Key:** Copy the API key.
+
+### Supported Models
+
+OpenRouter supports a large and growing number of models. Cline automatically fetches the list of available models. Refer to the [OpenRouter Models page](https://openrouter.ai/models) for the complete and up-to-date list.
+
+### Configuration in Cline
+
+1.  **Open Cline Settings:** Click the settings icon (⚙️) in the Cline panel.
+2.  **Select Provider:** Choose "OpenRouter" from the "API Provider" dropdown.
+3.  **Enter API Key:** Paste your OpenRouter API key into the "OpenRouter API Key" field.
+4.  **Select Model:** Choose your desired model from the "Model" dropdown.
+5.  **(Optional) Custom Base URL:** If you need to use a custom base URL for the OpenRouter API, check "Use custom base URL" and enter the URL. Leave this blank for most users.
+
+### Supported Transforms
+
+OpenRouter provides an [optional "middle-out" message transform](https://openrouter.ai/docs/features/message-transforms) to help with prompts that exceed the maximum context size of a model. You can enable it by checking the "Compress prompts and message chains to the context size" box.
+
+### Tips and Notes
+
+-   **Model Selection:** OpenRouter offers a wide range of models. Experiment to find the best one for your needs.
+-   **Pricing:** OpenRouter charges based on the underlying model's pricing. See the [OpenRouter Models page](https://openrouter.ai/models) for details.
+-   **Prompt Caching:**
+    -   OpenRouter passes caching requests to underlying models that support it. Check the [OpenRouter Models page](https://openrouter.ai/models) to see which models offer caching.
+    -   For most models, caching should activate automatically if supported by the model itself (similar to how Requesty works).
+    -   **Exception for Gemini Models via OpenRouter:** Due to potential response delays sometimes observed with Google's caching mechanism when accessed via OpenRouter, a manual activation step is required _specifically for Gemini models_.
+    -   If using a **Gemini model** via OpenRouter, you **must manually check** the "Enable Prompt Caching" box in the provider settings to activate caching for that model. This checkbox serves as a temporary workaround. For non-Gemini models on OpenRouter, this checkbox is not necessary for caching.

docs/provider-config/requesty.mdx

@@ -0,0 +1,38 @@
+---
+title: "Requesty"
+description: "Learn how to use Requesty with Cline to access and optimize over 150 large language models."
+---
+
+Cline supports accessing models through the [Requesty](https://www.requesty.ai/) AI platform. Requesty provides an easy and optimized API for interacting with 150+ large language models (LLMs).
+
+**Website:** [https://www.requesty.ai/](https://www.requesty.ai/)
+
+### Getting an API Key
+
+1.  **Sign Up/Sign In:** Go to the [Requesty website](https://www.requesty.ai/) and create an account or sign in.
+2.  **Get API Key:** You can get an API key from the [API Management](https://app.requesty.ai/manage-api) section of your Requesty dashboard.
+
+### Supported Models
+
+Requesty provides access to a wide range of models. Cline will automatically fetch the latest list of available models. You can see the full list of available models on the [Model List](https://app.requesty.ai/router/list) page.
+
+### Configuration in Cline
+
+1.  **Open Cline Settings:** Click the settings icon (⚙️) in the Cline panel.
+2.  **Select Provider:** Choose "Requesty" from the "API Provider" dropdown.
+3.  **Enter API Key:** Paste your Requesty API key into the "Requesty API Key" field.
+4.  **Select Model:** Choose your desired model from the "Model" dropdown.
+
+### Tips and Notes
+
+-   **Optimizations**: Requesty offers a range of in-flight cost optimizations to lower your costs.
+-   **Unified and simplified billing**: Unrestricted access to all providers and models, automatic balance top ups and more via a single [API key](https://app.requesty.ai/manage-api).
+-   **Cost tracking**: Track cost per model, coding language, changed file, and more via the [Cost dashboard](https://app.requesty.ai/cost-management) or the [Requesty VS Code extension](https://marketplace.visualstudio.com/items?itemName=Requesty.requesty).
+-   **Stats and logs**: See your [coding stats dashboard](https://app.requesty.ai/usage-stats) or go through your [LLM interaction logs](https://app.requesty.ai/logs).
+-   **Fallback policies**: Keep your LLM working for you with fallback policies when providers are down.
+-   **Prompt Caching:** Some providers support prompt caching. [Search models with caching](https://app.requesty.ai/router/list).
+
+### Relevant resources
+
+-   [Requesty Youtube channel](https://www.youtube.com/@requestyAI)
+-   [Requesty Discord](https://requesty.ai/discord)

docs/provider-config/vscode-language-model-api.mdx

@@ -0,0 +1,51 @@
+---
+title: "VS Code Language Model API"
+description: "Learn how to use Cline with the experimental VS Code Language Model API, enabling access to models from GitHub Copilot and other compatible extensions."
+---
+
+Cline offers _experimental_ support for the [VS Code Language Model API](https://code.visualstudio.com/api/extension-guides/language-model). This API enables extensions to grant access to language models directly within the VS Code environment. Consequently, you might be able to leverage models from:
+
+-   **GitHub Copilot:** Provided you have an active Copilot subscription and the extension installed.
+-   **Other VS Code Extensions:** Any extension that implements the Language Model API.
+
+**Important Note:** This integration is currently in an experimental phase and might not perform as anticipated. Its functionality relies on other extensions correctly implementing the VS Code Language Model API.
+
+### Prerequisites
+
+-   **VS Code:** The Language Model API is accessible via VS Code (it is not currently supported by Cursor).
+-   **A Language Model Provider Extension:** An extension that furnishes a language model is required. Examples include:
+    -   **GitHub Copilot:** With a Copilot subscription, the GitHub Copilot and GitHub Copilot Chat extensions can serve as model providers.
+    -   **Alternative Extensions:** Explore the VS Code Marketplace for extensions mentioning "Language Model API" or "lm". Other experimental options may be available
+
+### Configuration Steps
+
+1. **Ensure Copilot Account is Active and Extensions are installed:** User logged into either the Copilot or Copilot Chat extension should be able to gain access via Cline.
+2. **Access Cline Settings:** Click the gear icon (⚙️) located in the Cline panel.
+3. **Choose Provider:** Select "VS Code LM API" from the "API Provider" dropdown menu.
+4. **Select Model:** If the Copilot extension(s) are installed and the user is logged into their Copilot account, the "Language Model" dropdown will populate with available models after a short time. The naming convention is `vendor/family`. For instance, if Copilot is active, you might encounter options such as:
+    - `copilot - gpt-3.5-turbo`
+    - `copilot - gpt-4o-mini`
+    - `copilot - gpt-4`
+    - `copilot - gpt-4-turbo`
+    - `copilot - gpt-4o`
+    - `copilot - claude-3.5-sonnet` **NOTE:** this model does not work.
+    - `copilot - gemini-2.0-flash`
+    - `copilot - gpt-4.1`
+
+For best results with the VSCode LM API Provider, we suggest using the OpenAI Models (GPT 3, 4, 4.1, 4o etc.)
+
+### Current Limitations
+
+-   **Experimental API Status:** The VS Code Language Model API is still under active development. Anticipate potential changes and instability.
+-   **Dependency on Extensions:** This feature is entirely contingent on other extensions making models available. Cline does not directly control the list of accessible models.
+-   **Restricted Functionality:** The VS Code Language Model API might not encompass all features available through other API providers (e.g., image input capabilities, streaming responses, detailed usage metrics).
+-   **No Direct Cost Management:** Users are subject to the pricing structures and terms of service of the extension providing the model. Cline cannot directly monitor or regulate associated costs.
+-   **GitHub Copilot Rate Throttling:** When employing the VS Code LM API with GitHub Copilot, be mindful that GitHub may enforce rate limits on Copilot usage. These limitations are governed by GitHub, not Cline.
+
+### Troubleshooting Tips
+
+-   **Models Not Appearing:**
+    -   Confirm that VS Code is installed.
+    -   Verify that a language model provider extension (e.g., GitHub Copilot, GitHub Copilot Chat) is installed and enabled.
+    -   If utilizing Copilot, ensure you have previously sent a Copilot Chat message using the desired model.
+-   **Unexpected Operation:** Should you encounter unforeseen behavior, it is likely an issue stemming from the underlying Language Model API or the provider extension. Consider reporting the problem to the developers of the provider extension.

docs/provider-config/xai-grok.mdx

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

esbuild.js

@@ -134,14 +134,6 @@ const baseConfig = {
 		aliasResolverPlugin,
 		/* add to the end of plugins array */
 		esbuildProblemMatcherPlugin,
-		{
-			name: "alias-plugin",
-			setup(build) {
-				build.onResolve({ filter: /^pkce-challenge$/ }, (args) => {
-					return { path: require.resolve("pkce-challenge/dist/index.browser.js") }
-				})
-			},
-		},
 	],
 	format: "cjs",
 	sourcesContent: false,

eslint-rules/__tests__/no-grpc-client-object-literals.test.ts

@@ -0,0 +1,174 @@
+const { RuleTester: GrpcRuleTester } = require("eslint")
+const grpcRule = require("../no-grpc-client-object-literals")
+
+const grpcRuleTester = new GrpcRuleTester({
+	parser: require.resolve("@typescript-eslint/parser"),
+	parserOptions: {
+		ecmaVersion: 2020,
+		sourceType: "module",
+		ecmaFeatures: {
+			jsx: true,
+		},
+	},
+})
+
+grpcRuleTester.run("no-grpc-client-object-literals", grpcRule, {
+	valid: [
+		// Valid case: Using .create() method with gRPC client
+		{
+			code: `
+                import { TogglePlanActModeRequest } from '@shared/proto/state';
+                import { StateServiceClient } from '../services/grpc-client';
+                
+                StateServiceClient.togglePlanActMode(
+                    TogglePlanActModeRequest.create({
+                        chatSettings: {
+                            mode: PlanActMode.PLAN,
+                            preferredLanguage: 'en',
+                        },
+                    })
+                );
+            `,
+		},
+		// Valid case: Using .fromPartial() method with gRPC client
+		{
+			code: `
+                import { TogglePlanActModeRequest, ChatSettings } from '@shared/proto/state';
+                import { StateServiceClient } from '../services/grpc-client';
+                
+                const chatSettings = ChatSettings.fromPartial({
+                    mode: PlanActMode.PLAN,
+                    preferredLanguage: 'en',
+                });
+                
+                StateServiceClient.togglePlanActMode(
+                    TogglePlanActModeRequest.create({
+                        chatSettings: chatSettings,
+                    })
+                );
+            `,
+		},
+		// Valid case: Regular function call with object literal (not a gRPC client)
+		{
+			code: `
+                function processData(data) {
+                    console.log(data);
+                }
+                
+                processData({
+                    id: 123,
+                    name: 'test',
+                });
+            `,
+		},
+		// Valid case: Using proper nested protobuf objects
+		{
+			code: `
+                import { TogglePlanActModeRequest, ChatSettings } from '@shared/proto/state';
+                import { StateServiceClient } from '../services/grpc-client';
+                
+                // Using proper nested protobuf objects
+                const chatSettings = ChatSettings.create({
+                    mode: 0,
+                    preferredLanguage: 'en',
+                });
+                
+                const request = TogglePlanActModeRequest.create({
+                    chatSettings: chatSettings,
+                });
+                
+                StateServiceClient.togglePlanActMode(request);
+            `,
+		},
+		// Valid case: Object literal in second parameter (should not be checked)
+		{
+			code: `
+                import { StateSubscribeRequest } from '@shared/proto/state';
+                import { StateServiceClient } from '../services/grpc-client';
+                
+                const request = StateSubscribeRequest.create({
+                    topics: ['apiConfig', 'tasks']
+                });
+                
+                // Second parameter is an object literal but should not trigger the rule
+                StateServiceClient.subscribe(request, {
+                    metadata: {
+                        userId: 123,
+                        sessionId: "abc-123"
+                    }
+                });
+            `,
+		},
+	],
+	invalid: [
+		// Invalid case: Using object literal directly with gRPC client
+		{
+			code: `
+                import { StateServiceClient } from '../services/grpc-client';
+                
+                StateServiceClient.togglePlanActMode({
+                    chatSettings: {
+                        mode: 0,
+                        preferredLanguage: 'en',
+                    },
+                });
+            `,
+			errors: [{ messageId: "useProtobufMethod" }],
+		},
+		// Invalid case: Using object literal with nested properties
+		{
+			code: `
+                import { ChatSettings } from '@shared/proto/state';
+                import { StateServiceClient } from '../services/grpc-client';
+                
+                const chatSettings = ChatSettings.create({
+                    mode: 0,
+                    preferredLanguage: 'en',
+                });
+                
+                StateServiceClient.togglePlanActMode({
+                    chatSettings: {
+                        mode: 1,
+                        preferredLanguage: 'fr',
+                    },
+                });
+            `,
+			errors: [{ messageId: "useProtobufMethod" }],
+		},
+		// Invalid case: Nested object literal in protobuf create method
+		{
+			code: `
+                import { TogglePlanActModeRequest, ChatSettings } from '@shared/proto/state';
+                import { StateServiceClient } from '../services/grpc-client';
+                
+                // Using nested object literal instead of ChatSettings.create()
+                const request = TogglePlanActModeRequest.create({
+                    chatSettings: {
+                        mode: 0,
+                        preferredLanguage: 'en',
+                    },
+                });
+                
+                StateServiceClient.togglePlanActMode(request);
+            `,
+			errors: [{ messageId: "useProtobufMethod" }],
+		},
+		// Invalid case: Object literal as first parameter to subscribe method
+		{
+			code: `
+                import { StateServiceClient } from '../services/grpc-client';
+                
+                // First parameter is an object literal, which should trigger the rule
+                StateServiceClient.subscribe({
+                    topics: ['apiConfig', 'tasks']
+                }, {
+                    metadata: {
+                        userId: 123,
+                        sessionId: "abc-123"
+                    }
+                });
+            `,
+			errors: [{ messageId: "useProtobufMethod" }],
+		},
+	],
+})

eslint-rules/__tests__/no-protobuf-object-literals.test.ts

@@ -0,0 +1,214 @@
+const { RuleTester } = require("eslint")
+const rule = require("../no-protobuf-object-literals")
+
+const ruleTester = new RuleTester({
+	parser: require.resolve("@typescript-eslint/parser"),
+	parserOptions: {
+		ecmaVersion: 2020,
+		sourceType: "module",
+		ecmaFeatures: {
+			jsx: true,
+		},
+	},
+})
+
+ruleTester.run("no-protobuf-object-literals", rule, {
+	valid: [
+		// Valid case: Using .create() method
+		{
+			code: `
+        import { State } from '@shared/proto/state';
+        
+        const state = State.create({
+          stateJson: '{"apiConfig":{"provider":"anthropic","model":"claude-3-haiku"}}'
+        });
+      `,
+		},
+		// Valid case: Using .fromPartial() method
+		{
+			code: `
+        import { ChatSettings } from '@shared/proto/state';
+        
+        const settings = ChatSettings.fromPartial({
+          mode: 0,
+          preferredLanguage: 'en',
+          openAiReasoningEffort: 'thorough'
+        });
+      `,
+		},
+		// Valid case: Object literal not used with protobuf type
+		{
+			code: `
+        interface MyInterface {
+          id: number;
+          name: string;
+        }
+        
+        const obj: MyInterface = {
+          id: 123,
+          name: 'test'
+        };
+      `,
+		},
+		// Valid case: Using object literal for non-protobuf import
+		{
+			code: `
+        import { SomeType } from '@some/other/package';
+
+        const obj: SomeType = {
+          id: 123,
+          name: 'test'
+        };
+      `,
+		},
+		// Valid case: Regular function call with object literal (should not be flagged)
+		{
+			code: `
+        import { State } from '@shared/proto/state';
+
+        // This should not be flagged because it's a regular function call
+        // not directly tied to a protobuf type
+        process({
+          id: 123,
+          name: 'test',
+          data: { nested: true }
+        });
+      `,
+		},
+	],
+	invalid: [
+		// Invalid case: Using object literal with imported protobuf type
+		{
+			code: `
+        import { State } from '@shared/proto/state';
+
+        const state: State = {
+          stateJson: '{"apiConfig":{"provider":"anthropic","model":"claude-3-haiku"}}'
+        };
+      `,
+			output: `
+        import { State } from '@shared/proto/state';
+
+        const state: State = State.create({
+          stateJson: '{"apiConfig":{"provider":"anthropic","model":"claude-3-haiku"}}'
+        });
+      `,
+			errors: [{ messageId: "useProtobufMethod" }],
+		},
+		// Invalid case: Using object literal with namespaced protobuf type
+		{
+			code: `
+        import * as stateProto from '@shared/proto/state';
+
+        const state: stateProto.State = {
+          stateJson: '{"apiConfig":{"provider":"anthropic","model":"claude-3-haiku"}}'
+        };
+      `,
+			output: `
+        import * as stateProto from '@shared/proto/state';
+
+        const state: stateProto.State = stateProto.State.create({
+          stateJson: '{"apiConfig":{"provider":"anthropic","model":"claude-3-haiku"}}'
+        });
+      `,
+			errors: [{ messageId: "useProtobufMethodGeneric" }],
+		},
+		// Invalid case: Using object literal in a return statement (with protobuf return type)
+		{
+			code: `
+        import { ChatSettings } from '@shared/proto/state';
+
+        function createSettings(): ChatSettings {
+          return {
+            mode: 0,
+            preferredLanguage: 'en',
+            openAiReasoningEffort: 'thorough'
+          };
+        }
+      `,
+			output: `
+        import { ChatSettings } from '@shared/proto/state';
+
+        function createSettings(): ChatSettings {
+          return ChatSettings.create({
+            mode: 0,
+            preferredLanguage: 'en',
+            openAiReasoningEffort: 'thorough'
+          });
+        }
+      `,
+			errors: [{ messageId: "useProtobufMethod" }],
+		},
+		// Invalid case: Using object literal in a function parameter (with protobuf types imported)
+		{
+			code: `
+        import { ChatContent } from '@shared/proto/state';
+
+        function processContent(content: ChatContent) {
+          // process the content
+        }
+
+        processContent({
+          message: 'Hello, this is a test message',
+          images: ['image1.png', 'image2.jpg'],
+          files: ['file1.txt', 'file2.pdf']
+        });
+      `,
+			output: `
+        import { ChatContent } from '@shared/proto/state';
+
+        function processContent(content: ChatContent) {
+          // process the content
+        }
+
+        processContent(ChatContent.create({
+          message: 'Hello, this is a test message',
+          images: ['image1.png', 'image2.jpg'],
+          files: ['file1.txt', 'file2.pdf']
+        }));
+      `,
+			errors: [{ messageId: "useProtobufMethodGeneric" }],
+		},
+		// Invalid case: Using object literal in assignment expression
+		{
+			code: `
+        import { State } from '@shared/proto/state';
+
+        let state: State;
+        state = {
+          stateJson: '{"apiConfig":{"provider":"anthropic","model":"claude-3-haiku"}}'
+        };
+      `,
+			output: `
+        import { State } from '@shared/proto/state';
+
+        let state: State;
+        state = State.create({
+          stateJson: '{"apiConfig":{"provider":"anthropic","model":"claude-3-haiku"}}'
+        });
+      `,
+			errors: [{ messageId: "useProtobufMethod" }],
+		},
+		// Test with custom protobufPackages option
+		{
+			code: `
+        import { CustomProto } from 'custom/proto/package';
+
+        const obj: CustomProto = {
+          field1: 'value',
+          field2: 123
+        };
+      `,
+			output: `
+        import { CustomProto } from 'custom/proto/package';
+
+        const obj: CustomProto = CustomProto.create({
+          field1: 'value',
+          field2: 123
+        });
+      `,
+			options: [{ protobufPackages: ["custom/proto"] }],
+			errors: [{ messageId: "useProtobufMethod" }],
+		},
+	],
+})

eslint-rules/index.js

@@ -0,0 +1,19 @@
+// eslint-rules/index.js
+const noProtobufObjectLiterals = require("./no-protobuf-object-literals")
+const noGrpcClientObjectLiterals = require("./no-grpc-client-object-literals")
+
+module.exports = {
+	rules: {
+		"no-protobuf-object-literals": noProtobufObjectLiterals,
+		"no-grpc-client-object-literals": noGrpcClientObjectLiterals,
+	},
+	configs: {
+		recommended: {
+			plugins: ["local"],
+			rules: {
+				"local/no-protobuf-object-literals": "error",
+				"local/no-grpc-client-object-literals": "error",
+			},
+		},
+	},
+}

eslint-rules/no-grpc-client-object-literals.js

@@ -0,0 +1,216 @@
+const { ESLintUtils } = require("@typescript-eslint/utils")
+
+const createRule = ESLintUtils.RuleCreator((name) => `https://cline.bot/eslint-rules/${name}`)
+
+module.exports = createRule({
+	name: "no-grpc-client-object-literals",
+	meta: {
+		type: "problem",
+		docs: {
+			description:
+				"Enforce using .create() or .fromPartial() for gRPC service client parameters instead of object literals",
+			recommended: "error",
+		},
+		messages: {
+			useProtobufMethod:
+				"Use the appropriate protobuf .create() or .fromPartial() method instead of " +
+				"object literal for gRPC client parameters.\n" +
+				"Found: {{code}}\n" +
+				"gRPC client methods should always receive properly created protobuf objects.",
+		},
+		schema: [],
+	},
+	defaultOptions: [],
+
+	create(context) {
+		// Check if a name matches the gRPC service client pattern using regex
+		// Must start with an uppercase letter and end with ServiceClient
+		const isGrpcServiceClient = (name) => {
+			return typeof name === "string" && /^[A-Z].*ServiceClient$/.test(name)
+		}
+
+		const safeObjectExpressions = new Map() // Track object expressions in create/fromPartial calls
+
+		return {
+			// Skip object literals inside create() or fromPartial() method calls
+			CallExpression(node) {
+				if (
+					node.callee &&
+					node.callee.type === "MemberExpression" &&
+					(node.callee.property.name === "create" || node.callee.property.name === "fromPartial") &&
+					node.arguments.length > 0 &&
+					node.arguments[0].type === "ObjectExpression"
+				) {
+					// Track this object expression as being used with create/fromPartial
+					safeObjectExpressions.set(node.arguments[0], { isProblematic: false })
+				}
+			},
+
+			// Track create/fromPartial calls that contain nested object literals
+			"CallExpression[callee.type='MemberExpression'][callee.property.name=/^(create|fromPartial)$/]"(node) {
+				if (node.arguments.length > 0 && node.arguments[0].type === "ObjectExpression") {
+					// Track problematic nested object literals
+					const nestedObjectLiterals = new Map() // Map of object expressions to their containing property paths
+
+					// Search for nested object literals
+					const queue = [
+						...node.arguments[0].properties.map((prop) => ({
+							property: prop,
+							path: prop.key && prop.key.name ? prop.key.name : "unknown",
+						})),
+					]
+
+					while (queue.length > 0) {
+						const { property, path } = queue.shift()
+
+						// Skip spread elements
+						if (property.type !== "Property") continue
+
+						// If this is an object literal, mark it as problematic
+						if (property.value.type === "ObjectExpression") {
+							nestedObjectLiterals.set(property.value, path)
+
+							// Add nested properties to queue
+							queue.push(
+								...property.value.properties.map((prop) => ({
+									property: prop,
+									path: `${path}.${prop.key && prop.key.name ? prop.key.name : "unknown"}`,
+								})),
+							)
+						}
+					}
+
+					// For each problematic nested object, track it with its path
+					nestedObjectLiterals.forEach((path, objectExpr) => {
+						safeObjectExpressions.set(objectExpr, {
+							isProblematic: true,
+							path: path,
+							parentNode: node,
+						})
+					})
+				}
+			},
+
+			// Check calls to gRPC service clients
+			"CallExpression[callee.type='MemberExpression']"(node) {
+				// Get the object (left side) of the member expression
+				const callee = node.callee
+				if (callee.object && callee.object.type === "Identifier") {
+					const objectName = callee.object.name
+
+					// Check if this is a call to one of our gRPC service clients
+					if (isGrpcServiceClient(objectName)) {
+						// Only check the first argument of gRPC service client calls
+						if (node.arguments.length > 0) {
+							const arg = node.arguments[0] // Only check the first parameter
+							if (arg.type === "ObjectExpression" && !safeObjectExpressions.has(arg)) {
+								// This is an object literal being passed directly to a gRPC client
+								const sourceCode = context.getSourceCode()
+								const callText = sourceCode.getText(node).trim()
+
+								context.report({
+									node: arg,
+									messageId: "useProtobufMethod",
+									data: {
+										code: callText,
+									},
+								})
+							} else if (arg.type === "ObjectExpression") {
+								// Search for nested object literals that aren't protected
+								const queue = [...arg.properties]
+								while (queue.length > 0) {
+									const property = queue.shift()
+
+									// Skip spread elements
+									if (property.type !== "Property") continue
+
+									// Check value
+									if (
+										property.value.type === "ObjectExpression" &&
+										!safeObjectExpressions.has(property.value)
+									) {
+										// Found a nested object literal
+										const sourceCode = context.getSourceCode()
+										const propertyText = sourceCode.getText(property).trim()
+
+										context.report({
+											node: property.value,
+											messageId: "useProtobufMethod",
+											data: {
+												code: `${objectName}.${callee.property.name}(... ${propertyText} ...)`,
+											},
+										})
+									}
+
+									// Add any nested properties to the queue
+									if (property.value.type === "ObjectExpression") {
+										queue.push(...property.value.properties)
+									}
+								}
+							} else if (arg.type === "Identifier") {
+								// This is a variable - check if it references a problematic protobuf object
+								const varName = arg.name
+								const sourceCode = context.getSourceCode()
+								const scope = sourceCode.getScope(node)
+
+								// Find the variable declaration
+								const variable = scope.variables.find((v) => v.name === varName)
+								if (variable && variable.references && variable.references.length > 0) {
+									// Look for definitions
+									const def = variable.defs.find(
+										(d) => d.node && d.node.type === "VariableDeclarator" && d.node.init,
+									)
+
+									if (
+										def &&
+										def.node.init.type === "CallExpression" &&
+										def.node.init.callee.type === "MemberExpression" &&
+										(def.node.init.callee.property.name === "create" ||
+											def.node.init.callee.property.name === "fromPartial")
+									) {
+										// Flag if we find problematic nested object literals in this create/fromPartial call
+										const callText = sourceCode.getText(node).trim()
+										const initCallText = sourceCode.getText(def.node.init).trim()
+
+										// Check for nested object literals in init node
+										let foundNestedLiteral = false
+										if (
+											def.node.init.arguments.length > 0 &&
+											def.node.init.arguments[0].type === "ObjectExpression"
+										) {
+											// Find any nested object literals
+											const queue = [...def.node.init.arguments[0].properties]
+											while (queue.length > 0 && !foundNestedLiteral) {
+												const property = queue.shift()
+
+												// Skip spread elements
+												if (property.type !== "Property") continue
+
+												if (property.value.type === "ObjectExpression") {
+													foundNestedLiteral = true
+
+													context.report({
+														node,
+														messageId: "useProtobufMethod",
+														data: {
+															code: `${callText} - using request created with nested object literal at: ${property.key.name}`,
+														},
+													})
+												}
+
+												// Add any nested properties to the queue
+												if (property.value.type === "ObjectExpression") {
+													queue.push(...property.value.properties)
+												}
+											}
+										}
+									}
+								}
+							}
+						}
+					}
+				}
+			},
+		}
+	},
+})

eslint-rules/no-protobuf-object-literals.js

@@ -0,0 +1,556 @@
+const { ESLintUtils } = require("@typescript-eslint/utils")
+
+const createRule = ESLintUtils.RuleCreator((name) => `https://cline.bot/eslint-rules/${name}`)
+
+module.exports = createRule({
+	name: "no-protobuf-object-literals",
+	meta: {
+		type: "problem",
+		docs: {
+			description: "Enforce using .create() or .fromPartial() for protobuf objects instead of object literals",
+			recommended: "error",
+		},
+		fixable: "code",
+		messages: {
+			useProtobufMethod:
+				"Use {{typeName}}.create() or {{typeName}}.fromPartial() instead of " +
+				"object literal for protobuf type from @shared/proto\n" +
+				"Found: {{code}}\n  Suggestion: " +
+				"{{typeName}}.create({{objectContent}})",
+			useProtobufMethodGeneric:
+				"Use .create() or .fromPartial() instead of object literal for protobuf " +
+				"type from @shared/proto\n  Found: {{code}}",
+		},
+		schema: [
+			{
+				type: "object",
+				properties: {
+					protobufPackages: {
+						type: "array",
+						items: { type: "string" },
+						default: ["shared/proto/"],
+					},
+				},
+				additionalProperties: false,
+			},
+		],
+	},
+	defaultOptions: [{ protobufPackages: ["shared/proto/"] }],
+
+	create(context, [options]) {
+		const protobufPackages = options.protobufPackages
+		const protobufImports = new Set() // Set of imported protobuf types
+		const protobufNamespaceImports = new Set() // For namespace imports like "import * as proto"
+		const safeObjectExpressions = new Set() // Track object expressions in create/fromPartial calls
+
+		return {
+			// Skip object literals inside create() or fromPartial() method calls
+			CallExpression(node) {
+				if (
+					node.callee &&
+					node.callee.type === "MemberExpression" &&
+					(node.callee.property.name === "create" || node.callee.property.name === "fromPartial") &&
+					node.arguments.length > 0 &&
+					node.arguments[0].type === "ObjectExpression"
+				) {
+					// Track this object expression as being used with create/fromPartial
+					safeObjectExpressions.add(node.arguments[0])
+				}
+			},
+
+			// Track imports from protobuf packages
+			ImportDeclaration(node) {
+				const packageName = node.source.value
+
+				if (matchesProtobufPackage(packageName, protobufPackages)) {
+					// This is a protobuf package.
+					node.specifiers.forEach((spec) => {
+						if (spec.type === "ImportSpecifier") {
+							// import { MyRequest } from '@shared/proto'
+							protobufImports.add(spec.imported.name)
+						} else if (spec.type === "ImportNamespaceSpecifier") {
+							// import * as proto from '@shared/proto'
+							protobufNamespaceImports.add(spec.local.name)
+						}
+					})
+				}
+			},
+
+			// Check variable declarations with type annotations
+			"VariableDeclarator > ObjectExpression"(node) {
+				// Skip if this is inside a create/fromPartial call
+				if (safeObjectExpressions.has(node)) {
+					return
+				}
+
+				// Found object literal in variable declaration
+				const declarator = node.parent
+
+				if (declarator.id && declarator.id.typeAnnotation) {
+					const typeName = getTypeName(declarator.id.typeAnnotation.typeAnnotation)
+					if (typeName) {
+						// Check if it's a direct protobuf import
+						if (protobufImports.has(typeName)) {
+							//console.log('🚨 VIOLATION: Using object literal for protobuf type:', typeName);
+							const sourceCode = context.getSourceCode()
+							const declaratorText = sourceCode.getText(declarator)
+							const objectText = sourceCode.getText(node)
+
+							context.report({
+								node,
+								messageId: "useProtobufMethod",
+								data: {
+									typeName,
+									code: declaratorText,
+									objectContent: objectText,
+								},
+								fix(fixer) {
+									// Replace the object literal with Type.create() call
+									return fixer.replaceText(node, `${typeName}.create(${objectText})`)
+								},
+							})
+							return
+						}
+
+						// Check if it's a namespaced protobuf type (e.g., proto.MyRequest)
+						if (isNamespacedProtobufType(protobufNamespaceImports, typeName)) {
+							//console.log('🚨 VIOLATION: Using object literal for namespaced protobuf type:', typeName);
+							const sourceCode = context.getSourceCode()
+							const declaratorText = sourceCode.getText(declarator)
+							context.report({
+								node,
+								messageId: "useProtobufMethodGeneric",
+								data: { code: declaratorText },
+								fix(fixer) {
+									// For namespaced types, use the full type name to call create()
+									return fixer.replaceText(node, `${typeName}.create(${sourceCode.getText(node)})`)
+								},
+							})
+						}
+					}
+				}
+			},
+
+			// Check assignment expressions
+			"AssignmentExpression > ObjectExpression"(node) {
+				// Skip if this is inside a create/fromPartial call
+				if (safeObjectExpressions.has(node)) {
+					return
+				}
+
+				const assignment = node.parent
+
+				// For assignment to variables without inline type annotation
+				if (assignment.left && assignment.right === node) {
+					let typeName = null
+
+					// Check if there's a typeAnnotation directly on the left
+					if (assignment.left.typeAnnotation) {
+						typeName = getTypeName(assignment.left.typeAnnotation.typeAnnotation)
+					}
+					// Otherwise try to infer from the variable name if it's a simple identifier
+					else if (assignment.left.type === "Identifier") {
+						const varName = assignment.left.name
+						// Check variable declarations in the current scope
+						const sourceCode = context.getSourceCode()
+						const scope = sourceCode.getScope(node)
+						const variable = scope.variables.find((v) => v.name === varName)
+						if (variable && variable.defs.length > 0) {
+							const def = variable.defs[0]
+							if (def.node.id && def.node.id.typeAnnotation) {
+								typeName = getTypeName(def.node.id.typeAnnotation.typeAnnotation)
+							}
+						}
+					}
+
+					if (typeName && protobufImports.has(typeName)) {
+						//console.log('🚨 VIOLATION: Using object literal in assignment for protobuf type:', typeName);
+						const sourceCode = context.getSourceCode()
+						const assignmentText = sourceCode.getText(assignment.left) + " = "
+						const objectText = sourceCode.getText(node)
+
+						context.report({
+							node,
+							messageId: "useProtobufMethod",
+							data: {
+								typeName,
+								code: assignmentText + "{",
+								objectContent: objectText,
+							},
+							fix(fixer) {
+								// Replace the object literal with Type.create() call in assignments
+								return fixer.replaceText(node, `${typeName}.create(${objectText})`)
+							},
+						})
+					}
+				}
+			},
+
+			// Check return statements
+			"ReturnStatement > ObjectExpression"(node) {
+				// Skip if this is inside a create/fromPartial call
+				if (safeObjectExpressions.has(node)) {
+					return
+				}
+
+				// Find the parent function to get its return type
+				const functionNode = findParentFunction(node)
+				if (!functionNode) {
+					return
+				}
+
+				// Try to get the return type using our enhanced helper
+				const sourceCode = context.getSourceCode()
+				let returnTypeName = getFunctionReturnType(functionNode, sourceCode)
+
+				// For async functions with Promise<Type> return type, extract the inner type
+				if (returnTypeName && returnTypeName.startsWith("Promise<") && returnTypeName.endsWith(">")) {
+					returnTypeName = returnTypeName.slice(8, -1)
+				}
+
+				// Check if the return type is a protobuf type
+				if (returnTypeName) {
+					if (protobufImports.has(returnTypeName)) {
+						//console.log('🚨 VIOLATION: Return type is a protobuf type:', returnTypeName);
+						const sourceCode = context.getSourceCode()
+						const returnText = sourceCode.getText(node.parent)
+						context.report({
+							node,
+							messageId: "useProtobufMethod",
+							data: {
+								typeName: returnTypeName,
+								code: returnText,
+								objectContent: sourceCode.getText(node),
+							},
+							fix(fixer) {
+								// Replace the object literal with Type.create() call in return statements
+								return fixer.replaceText(node, `${returnTypeName}.create(${sourceCode.getText(node)})`)
+							},
+						})
+						return
+					}
+
+					// Check if it's a namespaced protobuf type
+					if (isNamespacedProtobufType(protobufNamespaceImports, returnTypeName)) {
+						const sourceCode = context.getSourceCode()
+						const returnText = sourceCode.getText(node.parent)
+						//console.log('🚨 VIOLATION: Return type is a namespaced protobuf type:', returnTypeName);
+						context.report({
+							node,
+							messageId: "useProtobufMethodGeneric",
+							data: { code: returnText },
+							fix(fixer) {
+								// For namespaced types in return statements, we need to extract the full type name
+								const objectCode = sourceCode.getText(node)
+								// Since we may not know the exact type, we'll use the more generic namespaced type
+								return fixer.replaceText(node, `${returnTypeName}.create(${objectCode})`)
+							},
+						})
+						return
+					}
+				}
+
+				// Final fallback - if there are any protobuf imports and the function signature
+				// mentions a return type that matches one of the imported types
+				const functionText = functionNode ? sourceCode.getText(functionNode) : ""
+
+				for (const protoType of protobufImports) {
+					// Use more precise regex to match return type patterns specifically
+					// Rather than just checking if the type name appears anywhere in the signature
+					const returnTypeRegex = new RegExp(
+						// Match arrow function return type
+						`=>\\s*:?\\s*${protoType}\\b|` +
+							// Match function declaration return type
+							`\\)\\s*:?\\s*${protoType}\\b|` +
+							// Match Promise return type
+							`\\)\\s*:?\\s*Promise<\\s*${protoType}\\s*>|` +
+							// Match function type in variable declaration
+							`:\\s*\\(.*\\)\\s*=>\\s*${protoType}\\b`,
+					)
+
+					if (returnTypeRegex.test(functionText)) {
+						const returnText = sourceCode.getText(node.parent)
+						//console.log('🚨 VIOLATION: regex matched protobuf type:', functionText);
+						context.report({
+							node,
+							messageId: "useProtobufMethod",
+							data: {
+								typeName: protoType,
+								code: returnText,
+								objectContent: sourceCode.getText(node),
+							},
+							fix(fixer) {
+								// Replace the object literal with Type.create() call
+								return fixer.replaceText(node, `${protoType}.create(${sourceCode.getText(node)})`)
+							},
+						})
+						return
+					}
+				}
+				// Check for namespace imports too
+				for (const namespace of protobufNamespaceImports) {
+					// Similar to above, but for namespaced types
+					const namespaceReturnTypeRegex = new RegExp(
+						// Match arrow function return type
+						`=>\\s*:?\\s*${namespace}\\.\\w+\\b|` +
+							// Match function declaration return type
+							`\\)\\s*:?\\s*${namespace}\\.\\w+\\b|` +
+							// Match Promise return type
+							`\\)\\s*:?\\s*Promise<\\s*${namespace}\\.\\w+\\s*>|` +
+							// Match function type in variable declaration
+							`:\\s*\\(.*\\)\\s*=>\\s*${namespace}\\.\\w+\\b`,
+					)
+
+					if (namespaceReturnTypeRegex.test(functionText)) {
+						const returnText = sourceCode.getText(node.parent)
+						//console.log('🚨 VIOLATION: regex matched namespaced protobuf type:', functionText, "namespace:", namespace);
+						context.report({
+							node,
+							messageId: "useProtobufMethodGeneric",
+							data: { code: returnText },
+							fix(fixer) {
+								// For namespaced types based on function signature patterns
+								// Extract the namespace and type from the function text using more precise patterns
+								const match = functionText.match(
+									new RegExp(
+										// Match return type patterns more precisely
+										`\\)\\s*:?\\s*(${namespace}\\.[\\w]+)\\b|` + // Function declaration
+											`=>\\s*:?\\s*(${namespace}\\.[\\w]+)\\b|` + // Arrow function
+											`Promise<\\s*(${namespace}\\.[\\w]+)\\s*>`, // Promise wrapped
+									),
+								)
+								if (match) {
+									const fullType = match[1] || match[2]
+									return fixer.replaceText(node, `${fullType}.create(${sourceCode.getText(node)})`)
+								}
+								// Fallback - we can't determine the exact type, but we know it's from the namespace
+								// Use a namespace-based approach
+								return fixer.replaceText(node, `${namespace}.create(${sourceCode.getText(node)})`)
+							},
+						})
+						return
+					}
+				}
+			},
+
+			// Check function call arguments (more selective approach)
+			"CallExpression > ObjectExpression"(node) {
+				// Skip if this is inside a create/fromPartial call
+				if (safeObjectExpressions.has(node)) {
+					return
+				}
+
+				// We need to be more selective to avoid false positives
+				// Only warn if:
+				// 1. The function is called on a protobuf namespace
+				// 2. The call argument has a type annotation that matches a protobuf type
+				// 3. The call is to a function that we know takes a protobuf type
+
+				// Check if it's a call on a protobuf namespace
+				if (
+					node.parent.callee &&
+					node.parent.callee.type === "MemberExpression" &&
+					node.parent.callee.object.type === "Identifier"
+				) {
+					const namespace = node.parent.callee.object.name
+					if (protobufNamespaceImports.has(namespace)) {
+						const sourceCode = context.getSourceCode()
+						const callText = sourceCode.getText(node.parent)
+						//console.log('🚨 VIOLATION: Check function call arguments object literal:', callText);
+						context.report({
+							node,
+							messageId: "useProtobufMethodGeneric",
+							data: { code: callText },
+							fix(fixer) {
+								// For calls on a protobuf namespace
+								const memberExpr = node.parent.callee
+								// Try to determine if this is calling a method that expects a specific type
+								const methodName = memberExpr.property.name
+
+								// If method name looks like 'create' + Type, we can infer the type
+								const possibleTypeName = methodName.replace(/^create/, "")
+
+								// Check if namespace has a type with this name
+								// Since we can't directly check at lint time, we'll use the namespace + inferred type
+								if (possibleTypeName && possibleTypeName !== methodName) {
+									return fixer.replaceText(
+										node,
+										`${namespace}.${possibleTypeName}.create(${sourceCode.getText(node)})`,
+									)
+								}
+
+								// Fallback - use a more generic approach with namespace
+								return fixer.replaceText(node, `${namespace}.create(${sourceCode.getText(node)})`)
+							},
+						})
+						return
+					}
+				}
+
+				// For regular function calls with object literals, check if there are protobuf imports
+				// and if the function might expect a protobuf type
+				if (node.parent.callee) {
+					// This is a more permissive check to catch cases like processContent({ ... })
+					// which might be passing a protobuf type
+					const sourceCode = context.getSourceCode()
+					const scope = sourceCode.getScope(node)
+
+					// Try to find the function definition
+					if (node.parent.callee.type === "Identifier") {
+						const functionName = node.parent.callee.name
+						const variable = scope.variables.find((v) => v.name === functionName)
+
+						// If we found the function and it has parameter type annotations
+						// that match protobuf types, flag it
+						if (variable && variable.defs.length > 0) {
+							const def = variable.defs[0]
+							if (def.node.params && node.parent.arguments.indexOf(node) < def.node.params.length) {
+								const param = def.node.params[node.parent.arguments.indexOf(node)]
+								if (param.typeAnnotation) {
+									const typeName = getTypeName(param.typeAnnotation.typeAnnotation)
+									if (
+										typeName &&
+										(protobufImports.has(typeName) ||
+											isNamespacedProtobufType(protobufNamespaceImports, typeName))
+									) {
+										const callText = sourceCode.getText(node.parent)
+										//console.log('🚨 VIOLATION: Function call arguments object literal:', callText);
+										context.report({
+											node,
+											messageId: "useProtobufMethodGeneric",
+											data: { code: callText },
+											fix(fixer) {
+												// For function calls with protobuf type parameters
+												return fixer.replaceText(node, `${typeName}.create(${sourceCode.getText(node)})`)
+											},
+										})
+										return
+									}
+								}
+							}
+						}
+					}
+				}
+			},
+		}
+	},
+})
+
+// Helper functions
+function getTypeName(typeAnnotation) {
+	if (!typeAnnotation) {
+		return null
+	}
+
+	if (typeAnnotation.type === "TSTypeReference") {
+		if (typeAnnotation.typeName.type === "Identifier") {
+			return typeAnnotation.typeName.name
+		} else if (typeAnnotation.typeName.type === "TSQualifiedName") {
+			// Handle namespaced types like proto.MyRequest
+			return `${typeAnnotation.typeName.left.name}.${typeAnnotation.typeName.right.name}`
+		}
+	}
+	return null
+}
+
+function matchesProtobufPackage(packageName, protobufPackages) {
+	return protobufPackages.some((protobufPackage) => {
+		// Remove leading and trailing @ and / from protobufPackage
+		const cleanedPackage = protobufPackage.replace(/^[@\/]/, "").replace(/[\/]$/, "")
+		const pattern = new RegExp(`(.*[@/]|)${escapeRegex(cleanedPackage)}[/].*`)
+		return pattern.test(packageName)
+	})
+}
+
+// Helper function to escape special regex characters
+function escapeRegex(string) {
+	return string.replace(/[.*+?^${}()|[\]\\]/g, "\\$&")
+}
+
+// Helper to extract function return type more reliably
+function getFunctionReturnType(functionNode, sourceCode) {
+	// 1. Check explicit return type annotation
+	if (functionNode.returnType) {
+		return getTypeName(functionNode.returnType.typeAnnotation)
+	}
+
+	// 2. For variable declarations like const foo: (arg: Type) => ReturnType = ...
+	if (functionNode.parent && functionNode.parent.type === "VariableDeclarator") {
+		const declarator = functionNode.parent
+		if (declarator.id && declarator.id.typeAnnotation) {
+			const typeAnnotation = declarator.id.typeAnnotation.typeAnnotation
+
+			// Handle function type annotations
+			if (typeAnnotation.type === "TSFunctionType" && typeAnnotation.typeAnnotation) {
+				return getTypeName(typeAnnotation.typeAnnotation)
+			}
+
+			// Handle type references to function types
+			if (typeAnnotation.type === "TSTypeReference") {
+				// This might be a type like Promise<ReturnType>
+				if (
+					typeAnnotation.typeName.name === "Promise" &&
+					typeAnnotation.typeParameters &&
+					typeAnnotation.typeParameters.params.length > 0
+				) {
+					return getTypeName(typeAnnotation.typeParameters.params[0])
+				}
+			}
+		}
+	}
+
+	// 3. For class methods, check if it's part of an interface implementation
+	if (
+		functionNode.parent &&
+		functionNode.parent.type === "MethodDefinition" &&
+		functionNode.parent.parent &&
+		functionNode.parent.parent.type === "ClassBody"
+	) {
+		const className = getEnclosingClassName(functionNode)
+		const methodName = functionNode.parent.key.name
+
+		if (className && methodName) {
+			// Look for interface declarations in the scope
+			const scope = sourceCode.getScope(functionNode)
+			// This would require more complex scope analysis which is limited in ESLint
+			// For now, we'll return null and rely on other methods
+		}
+	}
+
+	return null
+}
+
+// Helper to get the class name for a method
+function getEnclosingClassName(node) {
+	let current = node.parent
+	while (current) {
+		if (current.type === "ClassDeclaration" && current.id) {
+			return current.id.name
+		}
+		current = current.parent
+	}
+	return null
+}
+function isNamespacedProtobufType(protobufNamespaceImports, typeName) {
+	if (!typeName.includes(".")) {
+		return false
+	}
+
+	const namespace = typeName.split(".")[0]
+	return protobufNamespaceImports.has(namespace)
+}
+
+function findParentFunction(node) {
+	let current = node.parent
+	while (current) {
+		if (
+			current.type === "FunctionDeclaration" ||
+			current.type === "FunctionExpression" ||
+			current.type === "ArrowFunctionExpression"
+		) {
+			return current
+		}
+		current = current.parent
+	}
+	return null
+}

eslint-rules/package.json

@@ -0,0 +1,31 @@
+{
+	"name": "eslint-plugin-eslint-rules",
+	"version": "1.0.0",
+	"description": "Custom ESLint rules for Cline",
+	"main": "index.js",
+	"scripts": {
+		"test": "mocha --no-config --require ts-node/register __tests__/**/*.test.ts"
+	},
+	"keywords": [
+		"eslint",
+		"eslintplugin"
+	],
+	"author": "Cline Bot Inc.",
+	"license": "Apache-2.0",
+	"dependencies": {
+		"@typescript-eslint/utils": "^8.33.0"
+	},
+	"devDependencies": {
+		"@types/eslint": "^8.0.0",
+		"@types/mocha": "^10.0.7",
+		"@types/node": "^20.0.0",
+		"@typescript-eslint/parser": "^7.14.1",
+		"eslint": "^8.57.0",
+		"mocha": "^10.0.0",
+		"ts-node": "^10.9.2",
+		"typescript": "^5.4.5"
+	},
+	"peerDependencies": {
+		"eslint": ">=8.0.0"
+	}
+}

eslint-rules/tsconfig.json

@@ -0,0 +1,16 @@
+{
+	"compilerOptions": {
+		"target": "es2020",
+		"module": "commonjs",
+		"moduleResolution": "node",
+		"esModuleInterop": true,
+		"strict": true,
+		"skipLibCheck": true,
+		"forceConsistentCasingInFileNames": true,
+		"outDir": "dist",
+		"resolveJsonModule": true,
+		"declaration": true
+	},
+	"include": ["**/*.ts", "**/*.js", "**/*.tsx", "__tests__/**/*"],
+	"exclude": ["node_modules", "dist"]
+}

hosts/vscode/host-grpc-handler.ts

@@ -0,0 +1,197 @@
+import { v4 as uuidv4 } from "uuid"
+import { hostServiceHandlers } from "./host-grpc-service-config"
+import { GrpcRequestRegistry } from "../../src/core/controller/grpc-request-registry"
+
+/**
+ * Type definition for a streaming response handler
+ */
+export type StreamingResponseHandler = (response: any, isLast?: boolean, sequenceNumber?: number) => Promise<void>
+
+// Registry to track active gRPC requests and their cleanup functions
+const requestRegistry = new GrpcRequestRegistry()
+
+/**
+ * Callback interface for streaming requests
+ */
+export interface StreamingCallbacks<T = any> {
+	onResponse: (response: T) => void
+	onError?: (error: Error) => void
+	onComplete?: () => void
+}
+
+/**
+ * Handles gRPC requests from the webview
+ */
+export class GrpcHandler {
+	constructor() {}
+
+	/**
+	 * Handle a gRPC request from the webview
+	 * @param service The service name
+	 * @param method The method name
+	 * @param message The request message
+	 * @param requestId The request ID for response correlation
+	 * @param streamingCallbacks Optional callbacks for streaming responses
+	 * @returns For unary requests: the response message or error. For streaming requests: a cancel function.
+	 */
+	async handleRequest<T = any>(
+		service: string,
+		method: string,
+		message: any,
+		requestId: string,
+		streamingCallbacks?: StreamingCallbacks<T>,
+	): Promise<
+		| {
+				message?: any
+				error?: string
+				request_id: string
+		  }
+		| (() => void)
+	> {
+		// If streaming callbacks are provided, handle as a streaming request
+		if (streamingCallbacks) {
+			let completionCalled = false
+
+			// Create a response handler that will call the client's callbacks
+			const responseHandler: StreamingResponseHandler = async (response, isLast = false, sequenceNumber) => {
+				try {
+					// Call the client's onResponse callback with the response
+					streamingCallbacks.onResponse(response)
+
+					// If this is the last response, call the onComplete callback
+					if (isLast && streamingCallbacks.onComplete && !completionCalled) {
+						completionCalled = true
+						streamingCallbacks.onComplete()
+					}
+				} catch (error) {
+					// If there's an error in the callback, call the onError callback
+					if (streamingCallbacks.onError) {
+						streamingCallbacks.onError(error instanceof Error ? error : new Error(String(error)))
+					}
+				}
+			}
+
+			// Register the response handler with the registry
+			requestRegistry.registerRequest(
+				requestId,
+				() => {
+					console.log(`[DEBUG] Cleaning up streaming request: ${requestId}`)
+					if (streamingCallbacks.onComplete && !completionCalled) {
+						completionCalled = true
+						streamingCallbacks.onComplete()
+					}
+				},
+				{ type: "streaming_request", service, method },
+				responseHandler,
+			)
+
+			// Call the streaming handler directly
+			console.log(`[DEBUG] Streaming gRPC host call to ${service}.${method} req:${requestId}`)
+			try {
+				await this.handleStreamingRequest(service, method, message, requestId)
+			} catch (error) {
+				if (streamingCallbacks.onError) {
+					streamingCallbacks.onError(error instanceof Error ? error : new Error(String(error)))
+				}
+			}
+
+			// Return a function to cancel the stream
+			return () => {
+				console.log(`[DEBUG] Cancelling streaming request: ${requestId}`)
+				this.cancelRequest(requestId)
+			}
+		}
+
+		// Handle as a unary request
+		try {
+			// Get the service handler from the config
+			const serviceConfig = hostServiceHandlers[service]
+			if (!serviceConfig) {
+				throw new Error(`Unknown service: ${service}`)
+			}
+
+			// Handle unary request
+			return {
+				message: await serviceConfig.requestHandler(method, message),
+				request_id: requestId,
+			}
+		} catch (error) {
+			return {
+				error: error instanceof Error ? error.message : String(error),
+				request_id: requestId,
+			}
+		}
+	}
+
+	/**
+	 * Cancel a gRPC request
+	 * @param requestId The request ID to cancel
+	 * @returns True if the request was found and cancelled, false otherwise
+	 */
+	public async cancelRequest(requestId: string): Promise<boolean> {
+		const cancelled = requestRegistry.cancelRequest(requestId)
+
+		if (cancelled) {
+			// Get the registered response handler from the registry
+			const requestInfo = requestRegistry.getRequestInfo(requestId)
+			if (requestInfo && requestInfo.responseStream) {
+				try {
+					// Send cancellation confirmation using the registered response handler
+					await requestInfo.responseStream(
+						{ cancelled: true },
+						true, // Mark as last message
+					)
+				} catch (e) {
+					console.error(`Error sending cancellation response for ${requestId}:`, e)
+				}
+			}
+		} else {
+			console.log(`[DEBUG] Request not found for cancellation: ${requestId}`)
+		}
+
+		return cancelled
+	}
+
+	/**
+	 * Handle a streaming gRPC request
+	 * @param service The service name
+	 * @param method The method name
+	 * @param message The request message
+	 * @param requestId The request ID for response correlation
+	 */
+	private async handleStreamingRequest(service: string, method: string, message: any, requestId: string): Promise<void> {
+		// Get the service handler from the config
+		const serviceConfig = hostServiceHandlers[service]
+		if (!serviceConfig) {
+			throw new Error(`Unknown service: ${service}`)
+		}
+
+		// Check if the service supports streaming
+		if (!serviceConfig.streamingHandler) {
+			throw new Error(`Service ${service} does not support streaming`)
+		}
+
+		// Get the registered response handler from the registry
+		const requestInfo = requestRegistry.getRequestInfo(requestId)
+		if (!requestInfo || !requestInfo.responseStream) {
+			throw new Error(`No response handler registered for request: ${requestId}`)
+		}
+
+		// Use the registered response handler
+		const responseStream = requestInfo.responseStream
+
+		// Handle streaming request and pass the requestId to all streaming handlers
+		await serviceConfig.streamingHandler(method, message, responseStream, requestId)
+
+		// Don't send a final message here - the stream should stay open for future updates
+		// The stream will be closed when the client disconnects or when the service explicitly ends it
+	}
+}
+
+/**
+ * Get the request registry instance
+ * This allows other parts of the code to access the registry
+ */
+export function getRequestRegistry(): GrpcRequestRegistry {
+	return requestRegistry
+}

hosts/vscode/host-grpc-service.ts

@@ -0,0 +1,138 @@
+import { StreamingResponseHandler } from "./host-grpc-handler"
+
+/**
+ * Generic type for service method handlers
+ */
+export type ServiceMethodHandler = (message: any) => Promise<any>
+
+/**
+ * Type for streaming method handlers
+ */
+export type StreamingMethodHandler = (message: any, responseStream: StreamingResponseHandler, requestId?: string) => Promise<void>
+
+/**
+ * Method metadata including streaming information
+ */
+export interface MethodMetadata {
+	isStreaming: boolean
+}
+
+/**
+ * Generic service registry for gRPC services
+ */
+export class ServiceRegistry {
+	private serviceName: string
+	private methodRegistry: Record<string, ServiceMethodHandler> = {}
+	private streamingMethodRegistry: Record<string, StreamingMethodHandler> = {}
+	private methodMetadata: Record<string, MethodMetadata> = {}
+
+	/**
+	 * Create a new service registry
+	 * @param serviceName The name of the service (used for logging)
+	 */
+	constructor(serviceName: string) {
+		this.serviceName = serviceName
+	}
+
+	/**
+	 * Register a method handler
+	 * @param methodName The name of the method to register
+	 * @param handler The handler function for the method
+	 * @param metadata Optional metadata about the method
+	 */
+	registerMethod(methodName: string, handler: ServiceMethodHandler | StreamingMethodHandler, metadata?: MethodMetadata): void {
+		const isStreaming = metadata?.isStreaming || false
+
+		if (isStreaming) {
+			this.streamingMethodRegistry[methodName] = handler as StreamingMethodHandler
+		} else {
+			this.methodRegistry[methodName] = handler as ServiceMethodHandler
+		}
+
+		this.methodMetadata[methodName] = { isStreaming, ...metadata }
+		console.log(`Registered ${this.serviceName} method: ${methodName}${isStreaming ? " (streaming)" : ""}`)
+	}
+
+	/**
+	 * Check if a method is a streaming method
+	 * @param method The method name
+	 * @returns True if the method is a streaming method
+	 */
+	isStreamingMethod(method: string): boolean {
+		return this.methodMetadata[method]?.isStreaming || false
+	}
+
+	/**
+	 * Get a streaming method handler
+	 * @param method The method name
+	 * @returns The streaming method handler or undefined if not found
+	 */
+	getStreamingHandler(method: string): StreamingMethodHandler | undefined {
+		return this.streamingMethodRegistry[method]
+	}
+
+	/**
+	 * Handle a service request
+	 * @param method The method name
+	 * @param message The request message
+	 * @returns The response message
+	 */
+	async handleRequest(method: string, message: any): Promise<any> {
+		const handler = this.methodRegistry[method]
+
+		if (!handler) {
+			if (this.isStreamingMethod(method)) {
+				throw new Error(`Method ${method} is a streaming method and should be handled with handleStreamingRequest`)
+			}
+			throw new Error(`Unknown ${this.serviceName} method: ${method}`)
+		}
+
+		return handler(message)
+	}
+
+	/**
+	 * Handle a streaming service request
+	 * @param method The method name
+	 * @param message The request message
+	 * @param responseStream The streaming response handler
+	 * @param requestId The request ID for correlation and cleanup
+	 */
+	async handleStreamingRequest(
+		method: string,
+		message: any,
+		responseStream: StreamingResponseHandler,
+		requestId?: string,
+	): Promise<void> {
+		const handler = this.streamingMethodRegistry[method]
+
+		if (!handler) {
+			if (this.methodRegistry[method]) {
+				throw new Error(`Method ${method} is not a streaming method and should be handled with handleRequest`)
+			}
+			throw new Error(`Unknown ${this.serviceName} streaming method: ${method}`)
+		}
+
+		await handler(message, responseStream, requestId)
+	}
+}
+
+/**
+ * Create a service registry factory function
+ * @param serviceName The name of the service
+ * @returns An object with register and handle functions
+ */
+export function createServiceRegistry(serviceName: string) {
+	const registry = new ServiceRegistry(serviceName)
+
+	return {
+		registerMethod: (methodName: string, handler: ServiceMethodHandler | StreamingMethodHandler, metadata?: MethodMetadata) =>
+			registry.registerMethod(methodName, handler, metadata),
+
+		handleRequest: (method: string, message: any) => registry.handleRequest(method, message),
+
+		handleStreamingRequest: (method: string, message: any, responseStream: StreamingResponseHandler, requestId?: string) =>
+			registry.handleStreamingRequest(method, message, responseStream, requestId),
+
+		isStreamingMethod: (method: string) => registry.isStreamingMethod(method),
+	}
+}

hosts/vscode/uri/file.ts

@@ -0,0 +1,20 @@
+import * as vscode from "vscode"
+import { Uri } from "../../../src/shared/proto/host/uri"
+import { StringRequest } from "../../../src/shared/proto/common"
+
+/**
+ * Creates a file URI from a file path
+ * @param request The request containing the file path
+ * @returns A URI object representing the file
+ */
+export async function file(request: StringRequest): Promise<Uri> {
+	const uri = vscode.Uri.file(request.value)
+	return Uri.create({
+		scheme: uri.scheme,
+		authority: uri.authority,
+		path: uri.path,
+		query: uri.query,
+		fragment: uri.fragment,
+		fsPath: uri.fsPath,
+	})
+}

hosts/vscode/uri/joinPath.ts

@@ -0,0 +1,28 @@
+import * as vscode from "vscode"
+import { JoinPathRequest, Uri } from "../../../src/shared/proto/host/uri"
+
+/**
+ * Joins a URI with additional path segments
+ * @param request The request containing the base URI and path segments
+ * @returns A new URI with the path segments joined
+ */
+export async function joinPath(request: JoinPathRequest): Promise<Uri> {
+	// Convert proto Uri to vscode.Uri
+	if (!request.base) {
+		throw new Error("Base URI is required")
+	}
+	const baseUri = vscode.Uri.parse(`${request.base.scheme}://${request.base.authority}${request.base.path}`)
+
+	// Join paths
+	const result = vscode.Uri.joinPath(baseUri, ...request.pathSegments)
+
+	// Convert back to proto Uri
+	return Uri.create({
+		scheme: result.scheme,
+		authority: result.authority,
+		path: result.path,
+		query: result.query,
+		fragment: result.fragment,
+		fsPath: result.fsPath,
+	})
+}

hosts/vscode/uri/parse.ts

@@ -0,0 +1,20 @@
+import * as vscode from "vscode"
+import { Uri } from "../../../src/shared/proto/host/uri"
+import { StringRequest } from "../../../src/shared/proto/common"
+
+/**
+ * Parses a string URI into a Uri object
+ * @param request The request containing the URI string
+ * @returns A URI object representing the parsed URI
+ */
+export async function parse(request: StringRequest): Promise<Uri> {
+	const uri = vscode.Uri.parse(request.value)
+	return Uri.create({
+		scheme: uri.scheme,
+		authority: uri.authority,
+		path: uri.path,
+		query: uri.query,
+		fragment: uri.fragment,
+		fsPath: uri.fsPath,
+	})
+}

hosts/vscode/watch/subscribeToFile.ts

@@ -0,0 +1,225 @@
+import * as fs from "fs/promises"
+import * as fsSync from "fs"
+import { SubscribeToFileRequest, FileChangeEvent, FileChangeEvent_ChangeType } from "../../../src/shared/proto/host/watch"
+import { StreamingResponseHandler, getRequestRegistry } from "../host-grpc-handler"
+
+// Debounce configuration
+const DEBOUNCE_DELAY = 100 // ms
+
+// Keep track of active file watchers
+const fileWatchers = new Map<
+	string,
+	{
+		watcher: fsSync.FSWatcher
+		subscribers: Set<StreamingResponseHandler>
+		lastEventTime: Map<FileChangeEvent_ChangeType, number> // Track last event time by event type
+	}
+>()
+
+/**
+ * Subscribe to file changes
+ * @param request The request containing the file path
+ * @param responseStream The streaming response handler
+ * @param requestId The ID of the request (passed by the gRPC handler)
+ */
+export async function subscribeToFile(
+	request: SubscribeToFileRequest,
+	responseStream: StreamingResponseHandler,
+	requestId?: string,
+): Promise<void> {
+	const filePath = request.path
+	console.log(`[DEBUG] Setting up file subscription for ${filePath}`)
+
+	try {
+		// We don't send an initial event to avoid triggering handlers immediately
+		console.log(`[DEBUG] Now watching file: ${filePath}`)
+
+		// Set up or reuse file watcher
+		if (!fileWatchers.has(filePath)) {
+			// Create a new watcher for this file using Node.js fs.watch API
+			// This is more reliable than the VSCode FileSystemWatcher for detecting file saves
+			const watcher = fsSync.watch(filePath, { persistent: true }, async (eventType, filename) => {
+				if (eventType === "change") {
+					try {
+						const content = await fs.readFile(filePath, "utf8")
+						console.log(`[DEBUG] File changed: ${filePath}`)
+
+						// Get the watcher info
+						const watcherInfo = fileWatchers.get(filePath)
+						if (watcherInfo) {
+							// Check if this event should be debounced
+							const eventType = FileChangeEvent_ChangeType.CHANGED
+							const now = Date.now()
+							const lastTime = watcherInfo.lastEventTime.get(eventType) || 0
+
+							if (now - lastTime < DEBOUNCE_DELAY) {
+								console.log(
+									`[DEBUG] Debouncing change event for ${filePath} (${now - lastTime}ms since last event)`,
+								)
+								return // Skip this event due to debounce
+							}
+
+							// Update the last event time
+							watcherInfo.lastEventTime.set(eventType, now)
+
+							// Notify all subscribers
+							for (const subscriber of watcherInfo.subscribers) {
+								try {
+									await subscriber({
+										path: filePath,
+										type: eventType,
+										content,
+									})
+								} catch (error) {
+									console.error(`Error sending file change event: ${error}`)
+									watcherInfo.subscribers.delete(subscriber)
+								}
+							}
+						}
+					} catch (error) {
+						console.error(`Error reading changed file: ${error}`)
+					}
+				} else if (eventType === "rename") {
+					// In Node.js fs.watch, 'rename' can mean either creation or deletion
+					// We need to check if the file exists to determine which it is
+					try {
+						await fs.access(filePath)
+						// File exists, so it was created or renamed
+						const content = await fs.readFile(filePath, "utf8")
+						console.log(`[DEBUG] File created/renamed: ${filePath}`)
+
+						// Get the watcher info
+						const watcherInfo = fileWatchers.get(filePath)
+						if (watcherInfo) {
+							// Check if this event should be debounced
+							const eventType = FileChangeEvent_ChangeType.CREATED
+							const now = Date.now()
+							const lastTime = watcherInfo.lastEventTime.get(eventType) || 0
+
+							if (now - lastTime < DEBOUNCE_DELAY) {
+								console.log(
+									`[DEBUG] Debouncing creation event for ${filePath} (${now - lastTime}ms since last event)`,
+								)
+								return // Skip this event due to debounce
+							}
+
+							// Update the last event time
+							watcherInfo.lastEventTime.set(eventType, now)
+
+							// Notify all subscribers
+							for (const subscriber of watcherInfo.subscribers) {
+								try {
+									await subscriber({
+										path: filePath,
+										type: eventType,
+										content,
+									})
+								} catch (error) {
+									console.error(`Error sending file creation event: ${error}`)
+									watcherInfo.subscribers.delete(subscriber)
+								}
+							}
+						}
+					} catch (error) {
+						// File doesn't exist, so it was deleted
+						console.log(`[DEBUG] File deleted: ${filePath}`)
+
+						// Get the watcher info
+						const watcherInfo = fileWatchers.get(filePath)
+						if (watcherInfo) {
+							// Check if this event should be debounced
+							const eventType = FileChangeEvent_ChangeType.DELETED
+							const now = Date.now()
+							const lastTime = watcherInfo.lastEventTime.get(eventType) || 0
+
+							if (now - lastTime < DEBOUNCE_DELAY) {
+								console.log(
+									`[DEBUG] Debouncing deletion event for ${filePath} (${now - lastTime}ms since last event)`,
+								)
+								return // Skip this event due to debounce
+							}
+
+							// Update the last event time
+							watcherInfo.lastEventTime.set(eventType, now)
+
+							// Notify all subscribers
+							for (const subscriber of watcherInfo.subscribers) {
+								try {
+									await subscriber({
+										path: filePath,
+										type: eventType,
+										content: "",
+									})
+								} catch (error) {
+									console.error(`Error sending file deletion event: ${error}`)
+									watcherInfo.subscribers.delete(subscriber)
+								}
+							}
+
+							// Clean up the watcher
+							cleanupWatcher(filePath)
+						}
+					}
+				}
+			})
+
+			// Set up the watcher info
+			const watcherInfo = {
+				watcher,
+				subscribers: new Set<StreamingResponseHandler>(),
+				lastEventTime: new Map<FileChangeEvent_ChangeType, number>(),
+			}
+
+			fileWatchers.set(filePath, watcherInfo)
+		}
+
+		// Add this subscriber to the watcher
+		const watcherInfo = fileWatchers.get(filePath)!
+		watcherInfo.subscribers.add(responseStream)
+
+		// Register cleanup when the connection is closed
+		const cleanup = () => {
+			console.log(`[DEBUG] Cleaning up file subscription for ${filePath}`)
+			const watcherInfo = fileWatchers.get(filePath)
+			if (watcherInfo) {
+				watcherInfo.subscribers.delete(responseStream)
+
+				// If no subscribers left, clean up the watcher
+				if (watcherInfo.subscribers.size === 0) {
+					cleanupWatcher(filePath)
+				}
+			}
+		}
+
+		// Register the cleanup function with the request registry
+		if (requestId) {
+			getRequestRegistry().registerRequest(
+				requestId,
+				cleanup,
+				{ type: "file_subscription", path: filePath },
+				responseStream,
+			)
+		}
+	} catch (error) {
+		console.error(`Error setting up file subscription: ${error}`)
+		// Send an error response
+		await responseStream({
+			path: filePath,
+			type: FileChangeEvent_ChangeType.DELETED,
+			content: `Error: ${error instanceof Error ? error.message : String(error)}`,
+		})
+	}
+}
+
+/**
+ * Clean up a file watcher
+ * @param filePath The path of the file to clean up
+ */
+function cleanupWatcher(filePath: string): void {
+	const watcherInfo = fileWatchers.get(filePath)
+	if (watcherInfo) {
+		watcherInfo.watcher.close()
+		fileWatchers.delete(filePath)
+		console.log(`[DEBUG] Removed file watcher for ${filePath}`)
+	}
+}

locales/ar-sa/README.md

@@ -32,7 +32,7 @@
 
 التقى Cline، مساعد الذكاء الاصطناعي الذي يمكنه استخدام **سطر الأوامر** و **محرر النصوص** الخاص بك.
 
-بفضل [قدرات Claude 3.7 Sonnet على التعليمات البرمجية الوكيلة](https://www.anthropic.com/claude/sonnet)، يمكن لـ Cline التعامل مع مهام تطوير البرامج المعقدة خطوة بخطوة. مع الأدوات التي تسمح له بإنشاء وتعديل الملفات، واستكشاف المشاريع الكبيرة، واستخدام المتصفح، وتنفيذ أوامر الطرفية (بعد منحك الإذن)، يمكنه مساعدتك بطرق تتجاوز إكمال الكود أو الدعم الفني. يمكن لـ Cline أيضًا استخدام بروتوكول سياق النموذج (MCP) لإنشاء أدوات جديدة وتوسيع قدراته الخاصة. في حين تعمل النصوص البرمجية الآلية المستقلة تقليديًا في بيئات محاصرة، توفر هذه الإضافة واجهة رسومية لموافقة المستخدم على كل تغيير في الملف وأمر طرفية، مما يوفر طريقة آمنة وسهلة الاستخدام لاستكشاف إمكانات الذكاء الاصطناعي الوكيل.
+بفضل [قدرات Claude 4 Sonnet على التعليمات البرمجية الوكيلة](https://www.anthropic.com/claude/sonnet)، يمكن لـ Cline التعامل مع مهام تطوير البرامج المعقدة خطوة بخطوة. مع الأدوات التي تسمح له بإنشاء وتعديل الملفات، واستكشاف المشاريع الكبيرة، واستخدام المتصفح، وتنفيذ أوامر الطرفية (بعد منحك الإذن)، يمكنه مساعدتك بطرق تتجاوز إكمال الكود أو الدعم الفني. يمكن لـ Cline أيضًا استخدام بروتوكول سياق النموذج (MCP) لإنشاء أدوات جديدة وتوسيع قدراته الخاصة. في حين تعمل النصوص البرمجية الآلية المستقلة تقليديًا في بيئات محاصرة، توفر هذه الإضافة واجهة رسومية لموافقة المستخدم على كل تغيير في الملف وأمر طرفية، مما يوفر طريقة آمنة وسهلة الاستخدام لاستكشاف إمكانات الذكاء الاصطناعي الوكيل.
 
 1. أدخل مهمتك وأضف الصور لتحويل المحاكاة إلى تطبيقات وظيفية أو إصلاح الأخطاء مع لقطات الشاشة.
 2. يبدأ Cline بتحليل هيكل الملفات الخاصة بك وشجرة التعريف المصدرية، وإجراء عمليات بحث regex، وقراءة الملفات ذات الصلة للاطلاع على المشاريع الحالية. من خلال إدارة المعلومات التي يتم إضافتها إلى السياق بعناية، يمكن لـ Cline تقديم مساعدة قيمة حتى للمشاريع الكبيرة والمعقدة دون إرهاق نافذة السياق.
@@ -87,7 +87,7 @@
 
 ### استخدم المتصفح
 
-مع قدرة [استخدام الكمبيوتر](https://www.anthropic.com/news/3-5-models-and-computer-use) الجديدة لـ Claude 3.5 Sonnet، يمكن لـ Cline إطلاق متصفح، والنقر على العناصر، وكتابة النص، والتمرير، والتقاط لقطات الشاشة وسجلات وحدة التحكم في كل خطوة. يسمح له هذا بالتصحيح التفاعلي، واختبار نهاية إلى نهاية، وحتى الاستخدام العام للويب! يمنحه هذا الاستقلالية لإصلاح الأخطاء البصرية وأخطاء وقت التشغيل دون الحاجة إلى نسخ ولصق سجلات الأخطاء بنفسك.
+مع قدرة [استخدام الكمبيوتر](https://www.anthropic.com/news/3-5-models-and-computer-use) الجديدة لـ Claude 4 Sonnet، يمكن لـ Cline إطلاق متصفح، والنقر على العناصر، وكتابة النص، والتمرير، والتقاط لقطات الشاشة وسجلات وحدة التحكم في كل خطوة. يسمح له هذا بالتصحيح التفاعلي، واختبار نهاية إلى نهاية، وحتى الاستخدام العام للويب! يمنحه هذا الاستقلالية لإصلاح الأخطاء البصرية وأخطاء وقت التشغيل دون الحاجة إلى نسخ ولصق سجلات الأخطاء بنفسك.
 
 حاول طلب من Cline "اختبار التطبيق"، وشاهده يشغل أمرًا مثل `npm run dev`، ويطلق خادم التطوير المحلي في متصفح، ويجري سلسلة من الاختبارات للتأكد من أن كل شيء يعمل. [شاهد عرضًا توضيحيًا هنا.](https://x.com/sdrzn/status/1850880547825823989)
 

locales/de/README.md

@@ -28,7 +28,7 @@
 
 Lernen Sie Cline kennen, einen KI-Assistenten, der Ihre **CLI** u**N**d **E**ditor nutzen kann.
 
-Dank der [agentischen Codierungsfähigkeiten von Claude 3.7 Sonnet](https://www.anthropic.com/claude/sonnet) kann Cline komplexe Softwareentwicklungsaufgaben Schritt für Schritt bewältigen. Mit Werkzeugen, die ihm das Erstellen und Bearbeiten von Dateien, das Erkunden großer Projekte, die Nutzung des Browsers und das Ausführen von Terminalbefehlen (nach Ihrer Genehmigung) ermöglichen, kann er Ihnen auf eine Weise helfen, die über die Codevervollständigung oder technischen Support hinausgeht. Cline kann sogar das Model Context Protocol (MCP) verwenden, um neue Werkzeuge zu erstellen und seine eigenen Fähigkeiten zu erweitern. Während autonome KI-Skripte traditionell in sandboxed Umgebungen laufen, bietet diese Erweiterung eine Mensch-in-der-Schleife-GUI, um jede Dateiänderung und jeden Terminalbefehl zu genehmigen, was eine sichere und zugängliche Möglichkeit bietet, das Potenzial agentischer KI zu erkunden.
+Dank der [agentischen Codierungsfähigkeiten von Claude 4 Sonnet](https://www.anthropic.com/claude/sonnet) kann Cline komplexe Softwareentwicklungsaufgaben Schritt für Schritt bewältigen. Mit Werkzeugen, die ihm das Erstellen und Bearbeiten von Dateien, das Erkunden großer Projekte, die Nutzung des Browsers und das Ausführen von Terminalbefehlen (nach Ihrer Genehmigung) ermöglichen, kann er Ihnen auf eine Weise helfen, die über die Codevervollständigung oder technischen Support hinausgeht. Cline kann sogar das Model Context Protocol (MCP) verwenden, um neue Werkzeuge zu erstellen und seine eigenen Fähigkeiten zu erweitern. Während autonome KI-Skripte traditionell in sandboxed Umgebungen laufen, bietet diese Erweiterung eine Mensch-in-der-Schleife-GUI, um jede Dateiänderung und jeden Terminalbefehl zu genehmigen, was eine sichere und zugängliche Möglichkeit bietet, das Potenzial agentischer KI zu erkunden.
 
 1. Geben Sie Ihre Aufgabe ein und fügen Sie Bilder hinzu, um Mockups in funktionale Apps zu konvertieren oder Fehler mit Screenshots zu beheben.
 2. Cline beginnt mit der Analyse Ihrer Dateistruktur und Quellcode-ASTs, führt Regex-Suchen durch und liest relevante Dateien, um sich in bestehenden Projekten zurechtzufinden. Durch sorgfältiges Management der hinzugefügten Informationen kann Cline wertvolle Unterstützung auch bei großen, komplexen Projekten bieten, ohne das Kontextfenster zu überladen.
@@ -83,7 +83,7 @@ Alle von Cline vorgenommenen Änderungen werden in der Timeline Ihrer Datei aufg
 
 ### Den Browser verwenden
 
-Mit der neuen [Computer Use](https://www.anthropic.com/news/3-5-models-and-computer-use) Fähigkeit von Claude 3.5 Sonnet kann Cline einen Browser starten, Elemente anklicken, Text eingeben und scrollen, dabei Screenshots und Konsolenprotokolle bei jedem Schritt erfassen. Dies ermöglicht interaktives Debugging, End-to-End-Tests und sogar allgemeine Webnutzung! Dies gibt ihm die Autonomie, visuelle Fehler und Laufzeitprobleme zu beheben, ohne dass Sie selbst Fehlerprotokolle kopieren und einfügen müssen.
+Mit der neuen [Computer Use](https://www.anthropic.com/news/3-5-models-and-computer-use) Fähigkeit von Claude 4 Sonnet kann Cline einen Browser starten, Elemente anklicken, Text eingeben und scrollen, dabei Screenshots und Konsolenprotokolle bei jedem Schritt erfassen. Dies ermöglicht interaktives Debugging, End-to-End-Tests und sogar allgemeine Webnutzung! Dies gibt ihm die Autonomie, visuelle Fehler und Laufzeitprobleme zu beheben, ohne dass Sie selbst Fehlerprotokolle kopieren und einfügen müssen.
 
 Versuchen Sie, Cline zu bitten, "die App zu testen", und sehen Sie zu, wie er einen Befehl wie `npm run dev` ausführt, Ihren lokal laufenden Dev-Server in einem Browser startet und eine Reihe von Tests durchführt, um zu bestätigen, dass alles funktioniert. [Sehen Sie sich hier eine Demo an.](https://x.com/sdrzn/status/1850880547825823989)
 

locales/es/README.md

@@ -28,7 +28,7 @@
 
 Conozca a Cline, un asistente de IA que puede usar su **CLI** y **E**ditor.
 
-Gracias a las [habilidades de codificación agencial de Claude 3.7 Sonnet](https://www.anthropic.com/claude/sonnet), Cline puede abordar tareas complejas de desarrollo de software paso a paso. Con herramientas que le permiten crear y editar archivos, explorar grandes proyectos, usar el navegador y ejecutar comandos de terminal (con su aprobación), puede ayudarle de una manera que va más allá de la autocompletación de código o el soporte técnico. Cline incluso puede usar el Model Context Protocol (MCP) para crear nuevas herramientas y expandir sus propias capacidades. Mientras que los scripts de IA autónomos tradicionalmente se ejecutan en entornos aislados, esta extensión ofrece una GUI con un humano en el bucle para aprobar cada cambio de archivo y comando de terminal, proporcionando una forma segura y accesible de explorar el potencial de la IA agencial.
+Gracias a las [habilidades de codificación agencial de Claude 4 Sonnet](https://www.anthropic.com/claude/sonnet), Cline puede abordar tareas complejas de desarrollo de software paso a paso. Con herramientas que le permiten crear y editar archivos, explorar grandes proyectos, usar el navegador y ejecutar comandos de terminal (con su aprobación), puede ayudarle de una manera que va más allá de la autocompletación de código o el soporte técnico. Cline incluso puede usar el Model Context Protocol (MCP) para crear nuevas herramientas y expandir sus propias capacidades. Mientras que los scripts de IA autónomos tradicionalmente se ejecutan en entornos aislados, esta extensión ofrece una GUI con un humano en el bucle para aprobar cada cambio de archivo y comando de terminal, proporcionando una forma segura y accesible de explorar el potencial de la IA agencial.
 
 1. Ingrese su tarea y agregue imágenes para convertir maquetas en aplicaciones funcionales o solucionar errores con capturas de pantalla.
 2. Cline comenzará analizando su estructura de archivos y ASTs de código fuente, realizando búsquedas Regex y leyendo archivos relevantes para orientarse en proyectos existentes. Al gestionar cuidadosamente la información agregada, Cline puede proporcionar asistencia valiosa incluso en proyectos grandes y complejos sin sobrecargar la ventana de contexto.
@@ -83,7 +83,7 @@ Todos los cambios realizados por Cline se registran en la línea de tiempo de su
 
 ### Usar el navegador
 
-Con la nueva [habilidad de uso de computadora](https://www.anthropic.com/news/3-5-models-and-computer-use) de Claude 3.5 Sonnet, Cline puede iniciar un navegador, hacer clic en elementos, escribir texto y desplazarse, capturando capturas de pantalla y registros de consola. Esto permite la depuración interactiva, pruebas de extremo a extremo e incluso el uso general de la web. Esto le da la autonomía para solucionar errores visuales y problemas de tiempo de ejecución sin que tenga que copiar y pegar registros de errores.
+Con la nueva [habilidad de uso de computadora](https://www.anthropic.com/news/3-5-models-and-computer-use) de Claude 4 Sonnet, Cline puede iniciar un navegador, hacer clic en elementos, escribir texto y desplazarse, capturando capturas de pantalla y registros de consola. Esto permite la depuración interactiva, pruebas de extremo a extremo e incluso el uso general de la web. Esto le da la autonomía para solucionar errores visuales y problemas de tiempo de ejecución sin que tenga que copiar y pegar registros de errores.
 
 Intente pedirle a Cline que "pruebe la aplicación" y observe cómo ejecuta un comando como `npm run dev`, inicia su servidor de desarrollo local en un navegador y realiza una serie de pruebas para confirmar que todo funciona. [Vea una demostración aquí.](https://x.com/sdrzn/status/1850880547825823989)
 

locales/ja/README.md

@@ -28,7 +28,7 @@
 
 Clineは、**CLI**と**エディター**を使用できるAIアシスタントです。
 
-[Claude 3.7 Sonnetのエージェント的コーディング機能](https://www.anthropic.com/claude/sonnet)のおかげで、Clineは複雑なソフトウェア開発タスクをステップバイステップで処理できます。ファイルの作成と編集、大規模プロジェクトの探索、ブラウザの使用、ターミナルコマンドの実行（許可後）などのツールを使用して、コード補完や技術サポートを超えた支援を提供します。Clineは、Model Context Protocol (MCP)を使用して新しいツールを作成し、自身の機能を拡張することもできます。自律的なAIスクリプトは通常サンドボックス環境で実行されますが、この拡張機能はファイル変更やターミナルコマンドを承認するための人間インターフェースを提供し、エージェント的AIの可能性を安全かつアクセスしやすい方法で探求できます。
+[Claude 4 Sonnetのエージェント的コーディング機能](https://www.anthropic.com/claude/sonnet)のおかげで、Clineは複雑なソフトウェア開発タスクをステップバイステップで処理できます。ファイルの作成と編集、大規模プロジェクトの探索、ブラウザの使用、ターミナルコマンドの実行（許可後）などのツールを使用して、コード補完や技術サポートを超えた支援を提供します。Clineは、Model Context Protocol (MCP)を使用して新しいツールを作成し、自身の機能を拡張することもできます。自律的なAIスクリプトは通常サンドボックス環境で実行されますが、この拡張機能はファイル変更やターミナルコマンドを承認するための人間インターフェースを提供し、エージェント的AIの可能性を安全かつアクセスしやすい方法で探求できます。
 
 1. タスクを入力し、モックアップを機能するアプリに変換したり、スクリーンショットでバグを修正したりします。
 2. Clineは、ファイル構造とソースコードASTの分析、正規表現検索の実行、関連ファイルの読み取りから始め、既存プロジェクトに精通します。コンテキストに追加される情報を慎重に管理することで、大規模で複雑なプロジェクトでもコンテキストウィンドウを圧倒することなく貴重な支援を提供できます。
@@ -83,7 +83,7 @@ Clineによるすべての変更はファイルのタイムラインに記録さ
 
 ### ブラウザの使用
 
-Claude 3.5 Sonnetの新しい[コンピュータ使用](https://www.anthropic.com/news/3-5-models-and-computer-use)機能により、Clineはブラウザを起動し、要素をクリック、テキストを入力、スクロールし、各ステップでスクリーンショットとコンソールログをキャプチャできます。これにより、インタラクティブなデバッグ、エンドツーエンドテスト、さらには一般的なウェブ使用が可能になります。これにより、エラーログを手動でコピー＆ペーストすることなく、視覚的なバグやランタイムの問題を自律的に修正できます。
+Claude 4 Sonnetの新しい[コンピュータ使用](https://www.anthropic.com/news/3-5-models-and-computer-use)機能により、Clineはブラウザを起動し、要素をクリック、テキストを入力、スクロールし、各ステップでスクリーンショットとコンソールログをキャプチャできます。これにより、インタラクティブなデバッグ、エンドツーエンドテスト、さらには一般的なウェブ使用が可能になります。これにより、エラーログを手動でコピー＆ペーストすることなく、視覚的なバグやランタイムの問題を自律的に修正できます。
 
 Clineに「アプリをテストして」と頼んでみてください。彼は`npm run dev`のようなコマンドを実行し、ローカルで実行中の開発サーバーをブラウザで起動し、一連のテストを実行してすべてが正常に動作することを確認します。[デモはこちら。](https://x.com/sdrzn/status/1850880547825823989)
 

locales/ko/README.md

@@ -28,7 +28,7 @@
 
 Cline을 만나보세요, **CLI** 및 **에디터**를 활용할 수 있는 AI 어시스턴트입니다.
 
-[Claude 3.7 Sonnet의 에이전트형 코딩 기능](https://www.anthropic.com/claude/sonnet) 덕분에, Cline은 복잡한 소프트웨어 개발 작업을 단계별로 처리할 수 있습니다. 파일 생성과 편집, 대규모 프로젝트 탐색, 브라우저 사용, 터미널 명령 실행(권한 허가 필요) 등의 도구를 사용하여 단순 코드 완성이나 기술 지원을 넘어서는 도움을 제공합니다. Cline은 Model Context Protocol(MCP)를 사용하여 새로운 도구를 만들고 자신의 기능을 확장할 수도 있습니다. 자율적인 AI 스크립트는 일반적으로 샌드박스 환경에서 실행되지만, 이 확장 프로그램은 모든 파일 변경 및 터미널 명령을 승인할 수 있는 사람이 개입가능한 GUI를 제공하여, 에이전트형 AI의 잠재력을 보다 안전하고 쉽게 탐색할 수 있도록 합니다.
+[Claude 4 Sonnet의 에이전트형 코딩 기능](https://www.anthropic.com/claude/sonnet) 덕분에, Cline은 복잡한 소프트웨어 개발 작업을 단계별로 처리할 수 있습니다. 파일 생성과 편집, 대규모 프로젝트 탐색, 브라우저 사용, 터미널 명령 실행(권한 허가 필요) 등의 도구를 사용하여 단순 코드 완성이나 기술 지원을 넘어서는 도움을 제공합니다. Cline은 Model Context Protocol(MCP)를 사용하여 새로운 도구를 만들고 자신의 기능을 확장할 수도 있습니다. 자율적인 AI 스크립트는 일반적으로 샌드박스 환경에서 실행되지만, 이 확장 프로그램은 모든 파일 변경 및 터미널 명령을 승인할 수 있는 사람이 개입가능한 GUI를 제공하여, 에이전트형 AI의 잠재력을 보다 안전하고 쉽게 탐색할 수 있도록 합니다.
 
 1. 작업을 입력하고, 목업을 기능하는 앱으로 변환하거나 스크린샷으로 버그를 수정합니다.
 2. Cline은 파일 구조와 소스코드 AST의 분석, 정규식 검색 실행, 관련 파일 읽기부터 시작하여 기존 프로젝트를 파악합니다. 또한, 어떤 정보를 컨텍스트에 추가할지를 신중하게 관리하여, 대규모 복잡한 프로젝트에서도 컨텍스트 윈도우를 과부하시키지 않으면서도 효과적인 지원을 제공합니다.
@@ -78,7 +78,7 @@ Cline에 의한 모든 변경은 파일의 타임라인에 기록되어 필요
 
 ### 브라우저 사용
 
-Claude 3.5 Sonnet의 새로운 [컴퓨터 사용](https://www.anthropic.com/news/3-5-models-and-computer-use) 기능으로 인해, Cline은 브라우저를 실행하고 요소를 클릭하고 텍스트를 입력하고 스크롤하며 각 단계에서 스크린샷과 콘솔 로그를 캡처할 수 있습니다. 이를 통해 인터랙티브한 디버깅, 엔드투엔드 테스트, 심지어 일반적인 웹 탐색까지 가능해집니다. 이로 인해 오류 로그를 수동으로 복사 & 붙여넣기 할 필요 없이 시각적 버그나 런타임 문제를 자율적으로 수정할 수 있습니다.
+Claude 4 Sonnet의 새로운 [컴퓨터 사용](https://www.anthropic.com/news/3-5-models-and-computer-use) 기능으로 인해, Cline은 브라우저를 실행하고 요소를 클릭하고 텍스트를 입력하고 스크롤하며 각 단계에서 스크린샷과 콘솔 로그를 캡처할 수 있습니다. 이를 통해 인터랙티브한 디버깅, 엔드투엔드 테스트, 심지어 일반적인 웹 탐색까지 가능해집니다. 이로 인해 오류 로그를 수동으로 복사 & 붙여넣기 할 필요 없이 시각적 버그나 런타임 문제를 자율적으로 수정할 수 있습니다.
 
 Cline에게 "앱을 테스트해줘"라고 요청하면, `npm run dev`와 같은 명령을 실행하고 로컬에서 실행 중인 개발 서버를 브라우저에서 실행하여 일련의 테스트를 수행하고 모든 것이 정상적으로 작동하는지 확인합니다. [데모는 여기를 참조하세요.](https://x.com/sdrzn/status/1850880547825823989)
 

locales/pt-BR/README.md

@@ -28,7 +28,7 @@
 
 Conheça o Cline: um assistente de IA que pode usar seu **CLI** e **Editor**.
 
-Graças às [habilidades avançadas do Claude 3.7 Sonnet](https://www.anthropic.com/claude/sonnet), o Cline pode lidar com tarefas complexas de desenvolvimento de software passo a passo. Com ferramentas que permitem criar e editar arquivos, explorar grandes projetos, usar o navegador e executar comandos no terminal (com sua aprovação), ele pode ajudar você de maneiras que vão além da inclusão de código ou suporte técnico. O Cline pode é capaz inclusive de usar o Model Context Protocol (MCP) para criar novas ferramentas e expandir seus próprios recursos. Embora os scripts de IA autônomas tradicionalmente sejam executados em ambientes isolados, esta extensão oferece uma GUI com um humano no circuito para aprovar cada alteração de arquivo e comando de terminal, fornecendo uma maneira segura e acessível de explorar todo o potencial da IA.
+Graças às [habilidades avançadas do Claude 4 Sonnet](https://www.anthropic.com/claude/sonnet), o Cline pode lidar com tarefas complexas de desenvolvimento de software passo a passo. Com ferramentas que permitem criar e editar arquivos, explorar grandes projetos, usar o navegador e executar comandos no terminal (com sua aprovação), ele pode ajudar você de maneiras que vão além da inclusão de código ou suporte técnico. O Cline pode é capaz inclusive de usar o Model Context Protocol (MCP) para criar novas ferramentas e expandir seus próprios recursos. Embora os scripts de IA autônomas tradicionalmente sejam executados em ambientes isolados, esta extensão oferece uma GUI com um humano no circuito para aprovar cada alteração de arquivo e comando de terminal, fornecendo uma maneira segura e acessível de explorar todo o potencial da IA.
 
 1. Insira sua tarefa e adicione imagens para transformar mockups em aplicativos funcionais ou corrigir erros através de capturas de tela.
 
@@ -83,7 +83,7 @@ Todas as alterações feitas pelo Cline são registradas na Linha do tempo do ar
 
 ### Uso do navegador
 
-Com a nova habilidade de [uso de computador](https://www.anthropic.com/news/3-5-models-and-computer-use) do Claude Sonnet 3.5, Cline pode abrir um navegador, clicar em elementos, digitar texto e rolar, capturando a tela e logs de console. Isso permite depurar de maneira interativa, testes end-to-end e até mesmo uso geral da web. Isso lhe dá autonomia para solucionar erros visuais e problemas em tempo de execução sem precisar copiar e colar logs dos erros.
+Com a nova habilidade de [uso de computador](https://www.anthropic.com/news/3-5-models-and-computer-use) do Claude Sonnet 4, Cline pode abrir um navegador, clicar em elementos, digitar texto e rolar, capturando a tela e logs de console. Isso permite depurar de maneira interativa, testes end-to-end e até mesmo uso geral da web. Isso lhe dá autonomia para solucionar erros visuais e problemas em tempo de execução sem precisar copiar e colar logs dos erros.
 
 Tente pedir a Cline para "testar o aplicativo" e observe enquanto o Cline executa um comando como `npm run dev`, inicia seu servidor de desenvolvimento local em um navegador e executa uma série de testes para confirmar se tudo funciona. [Veja uma demonstração aqui.](https://x.com/sdrzn/status/1850880547825823989)
 

locales/zh-cn/README.md

@@ -28,7 +28,7 @@
 
 认识 Cline —— 一个可以使用你的 **终端** 和 **编辑器** 的 AI 助手。
 
-得益于 [Claude 3.7 Sonnet 的代理式编码能力](https://www.anthropic.com/claude/sonnet)，Cline 能够逐步处理复杂的软件开发任务。借助于一系列工具，他可以创建和编辑文件、浏览大型项目、使用浏览器，并在你授权后执行终端命令，从而在代码补全或技术支持之外提供更深入的帮助。Cline 甚至还能使用 Model Context Protocol（MCP）来创建新工具，并扩展自身的能力。虽然传统的自动化 AI 脚本通常运行在沙盒环境中，但这个扩展提供了一个人类参与审核的图形界面（GUI），用于审批每一次文件变更和终端命令，从而为探索代理式 AI 的潜力提供了一种安全且易于使用的方式。
+得益于 [Claude 4 Sonnet 的代理式编码能力](https://www.anthropic.com/claude/sonnet)，Cline 能够逐步处理复杂的软件开发任务。借助于一系列工具，他可以创建和编辑文件、浏览大型项目、使用浏览器，并在你授权后执行终端命令，从而在代码补全或技术支持之外提供更深入的帮助。Cline 甚至还能使用 Model Context Protocol（MCP）来创建新工具，并扩展自身的能力。虽然传统的自动化 AI 脚本通常运行在沙盒环境中，但这个扩展提供了一个人类参与审核的图形界面（GUI），用于审批每一次文件变更和终端命令，从而为探索代理式 AI 的潜力提供了一种安全且易于使用的方式。
 
 1. 输入你的任务，并添加图片，以将界面原型（mockup）转换为功能应用，或通过截图修复 bug。
 2. Cline 会从分析你的文件结构和源代码的抽象语法树（AST）开始，同时执行正则搜索并读取相关文件，以便尽快熟悉项目上下文。通过精细地管理上下文中引入的信息，即使面对大型复杂项目，Cline 也能在不超出上下文窗口限制的前提下提供有效协助。
@@ -83,7 +83,7 @@ Cline 所做的所有更改都会记录在你的文件时间轴中，提供了
 
 ### 使用浏览器
 
-借助 Claude 3.5 Sonnet 的新 [计算机使用](https://www.anthropic.com/news/3-5-models-and-computer-use) 功能，Cline 可以启动浏览器，点击元素，输入文本和滚动，在每一步捕获截图和控制台日志。这允许进行交互式调试、端到端测试，甚至是一般的网页使用！这使他能够自主修复视觉错误和运行时问题，而无需你亲自操作和复制粘贴错误日志。
+借助 Claude 4 Sonnet 的新 [计算机使用](https://www.anthropic.com/news/3-5-models-and-computer-use) 功能，Cline 可以启动浏览器，点击元素，输入文本和滚动，在每一步捕获截图和控制台日志。这允许进行交互式调试、端到端测试，甚至是一般的网页使用！这使他能够自主修复视觉错误和运行时问题，而无需你亲自操作和复制粘贴错误日志。
 
 试试让 Cline “测试应用程序”，看看他如何运行 `npm run dev` 命令，在浏览器中启动你本地运行的开发服务器，并执行一系列测试以确认一切正常。[在这里查看演示。](https://x.com/sdrzn/status/1850880547825823989)
 

locales/zh-tw/README.md

@@ -32,7 +32,7 @@
 
 認識 Cline，一個可以使用您的**命令列介面** (CLI) 和**程式編輯器** (Editor) 的 AI 助理。
 
-感謝 [Claude 3.7 Sonnet 的代理式程式設計能力](https://www.anthropic.com/claude/sonnet)，Cline 能夠逐步處理複雜的軟體開發任務。透過能讓他建立和編輯檔案、探索大型專案、使用瀏覽器，以及執行終端機指令（在您授權後）的工具，從而在程式碼補全或技術支援之外提供更深入的協助。Cline 甚至能使用模型上下文協定（Model Context Protocol，MCP）來建立新工具並擴展自己的功能。雖然自主 AI 腳本傳統上會在沙箱環境中執行，但這個擴充套件提供了人機互動的圖形介面，讓您可以核准每個檔案變更和終端機指令，提供一個安全且容易使用的方式來探索代理式 AI 的潛力。
+感謝 [Claude 4 Sonnet 的代理式程式設計能力](https://www.anthropic.com/claude/sonnet)，Cline 能夠逐步處理複雜的軟體開發任務。透過能讓他建立和編輯檔案、探索大型專案、使用瀏覽器，以及執行終端機指令（在您授權後）的工具，從而在程式碼補全或技術支援之外提供更深入的協助。Cline 甚至能使用模型上下文協定（Model Context Protocol，MCP）來建立新工具並擴展自己的功能。雖然自主 AI 腳本傳統上會在沙箱環境中執行，但這個擴充套件提供了人機互動的圖形介面，讓您可以核准每個檔案變更和終端機指令，提供一個安全且容易使用的方式來探索代理式 AI 的潛力。
 
 1. 輸入您的任務，並可以加入圖片來將設計稿轉換成功能性應用程式，或使用截圖來修正錯誤。
 2. Cline 會先分析您的檔案結構和程式碼 AST、執行正規表達式搜尋，並讀取相關檔案，以便在現有專案中快速掌握狀況。透過仔細管理加入上下文的資訊，Cline 可以在不超過上下文視窗的情況下，為大型且複雜的專案提供有價值的協助。
@@ -84,7 +84,7 @@ Cline 可以直接在您的編輯器中建立和編輯檔案，並顯示變更
 
 ### 使用瀏覽器
 
-透過 Claude 3.5 Sonnet 的新[電腦使用](https://www.anthropic.com/news/3-5-models-and-computer-use)功能，Cline 可以啟動瀏覽器、點選元素、輸入文字和捲動，在每個步驟擷取螢幕截圖和主控台記錄。這讓互動式除錯、端對端測試，甚至一般網頁使用成為可能！這讓他能獨立修正視覺問題和執行時錯誤，而不需要您手動複製錯誤記錄。
+透過 Claude 4 Sonnet 的新[電腦使用](https://www.anthropic.com/news/3-5-models-and-computer-use)功能，Cline 可以啟動瀏覽器、點選元素、輸入文字和捲動，在每個步驟擷取螢幕截圖和主控台記錄。這讓互動式除錯、端對端測試，甚至一般網頁使用成為可能！這讓他能獨立修正視覺問題和執行時錯誤，而不需要您手動複製錯誤記錄。
 
 試著請 Cline 「測試應用程式」，觀察他如何執行 `npm run dev`、在瀏覽器中啟動您的本機開發伺服器，並執行一系列測試來確認一切正常運作。[點此觀看示範](https://x.com/sdrzn/status/1850880547825823989)。
 
@@ -108,10 +108,13 @@ Cline 可以直接在您的編輯器中建立和編輯檔案，並顯示變更
 
 ### 新增上下文
 
-**`@url`：**貼上網址讓擴充套件擷取並轉換為 Markdown，當您想給 Cline 最新文件時很有用
-**`@problems`：**新增工作區的錯誤和警告（「問題」面板）給 Cline 修正
-**`@file`：**新增檔案內容，讓您不必浪費 API 請求來核准讀取檔案（+ 輸入以搜尋檔案）
-**`@folder`：**一次新增整個資料夾的檔案，讓您的工作流程更快速
+**`@url`**：貼上網址讓擴充套件擷取並轉換為 Markdown，當您想給 Cline 最新文件時很有用
+
+**`@problems`**：新增工作區的錯誤和警告（「問題」面板）給 Cline 修正
+
+**`@file`**：新增檔案內容，讓您不必浪費 API 請求來核准讀取檔案（+ 輸入以搜尋檔案）
+
+**`@folder`**：一次新增整個資料夾的檔案，讓您的工作流程更快速
 
 <!-- 透明像素用於浮動圖片後的換行 -->
 <img width="2000" height="0" src="https://github.com/user-attachments/assets/ee14e6f7-20b8-4391-9091-8e8e25561929"><br>

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": "3.16.1",
+	"version": "3.17.11",
 	"icon": "assets/icons/icon.png",
 	"engines": {
 		"vscode": "^1.84.0"
@@ -46,12 +46,71 @@
 	],
 	"main": "./dist/extension.js",
 	"contributes": {
+		"walkthroughs": [
+			{
+				"id": "ClineWalkthrough",
+				"title": "Meet Cline, your new coding partner",
+				"description": "Cline codes like a developer because it thinks like one. Here are 5 ways to put it to work:",
+				"steps": [
+					{
+						"id": "welcome",
+						"title": "Start with a Goal, Not Just a Prompt",
+						"description": "Tell Cline what you want to achieve. It plans, asks, and then codes, like a true partner.",
+						"media": {
+							"markdown": "walkthrough/step1.md"
+						}
+					},
+					{
+						"id": "learn",
+						"title": "Let Cline Learn Your Codebase",
+						"description": "Point Cline to your project. It builds understanding to make smart, context-aware changes.",
+						"media": {
+							"markdown": "walkthrough/step2.md"
+						}
+					},
+					{
+						"id": "advanced-features",
+						"title": "Always Use the Best AI Models",
+						"description": "Cline empowers you with State-of-the-Art AI, connecting to top models (Anthropic, Gemini, OpenAI & more).",
+						"media": {
+							"markdown": "walkthrough/step3.md"
+						}
+					},
+					{
+						"id": "mcp",
+						"title": "Extend with Powerful Tools (MCP)",
+						"description": "Connect to databases, APIs, or discover new capabilities in the MCP Marketplace.",
+						"media": {
+							"markdown": "walkthrough/step4.md"
+						}
+					},
+					{
+						"id": "getting-started",
+						"title": "You're Always in Control",
+						"description": "Review Cline's plans and diffs. Approve changes before they happen. No surprises.",
+						"media": {
+							"markdown": "walkthrough/step5.md"
+						},
+						"content": {
+							"path": "walkthrough/step5.md"
+						}
+					}
+				]
+			}
+		],
 		"viewsContainers": {
 			"activitybar": [
 				{
 					"id": "claude-dev-ActivityBar",
-					"title": "Cline",
-					"icon": "assets/icons/icon.svg"
+					"title": "Cline (⌘+')",
+					"icon": "assets/icons/icon.svg",
+					"when": "isMac"
+				},
+				{
+					"id": "claude-dev-ActivityBar",
+					"title": "Cline (Ctrl+')",
+					"icon": "assets/icons/icon.svg",
+					"when": "!isMac"
 				}
 			]
 		},
@@ -126,6 +185,21 @@
 				"title": "Generate Commit Message with Cline",
 				"category": "Cline",
 				"icon": "$(robot)"
+			},
+			{
+				"command": "cline.explainCode",
+				"title": "Explain with Cline",
+				"category": "Cline"
+			},
+			{
+				"command": "cline.improveCode",
+				"title": "Improve with Cline",
+				"category": "Cline"
+			},
+			{
+				"command": "cline.openWalkthrough",
+				"title": "Open Walkthrough",
+				"category": "Cline"
 			}
 		],
 		"keybindings": [
@@ -140,6 +214,14 @@
 			{
 				"command": "cline.generateGitCommitMessage",
 				"when": "scmProvider == git"
+			},
+			{
+				"command": "cline.focusChatInput",
+				"key": "cmd+'",
+				"mac": "cmd+'",
+				"win": "ctrl+'",
+				"linux": "ctrl+'",
+				"when": "!editorHasSelection"
 			}
 		],
 		"menus": {
@@ -242,19 +324,19 @@
 	"scripts": {
 		"vscode:prepublish": "npm run package",
 		"compile": "npm run check-types && npm run lint && node esbuild.js",
-		"compile-standalone": "npm run protos && npm run check-types && npm run lint && node esbuild.js --standalone",
+		"compile-standalone": "npm run check-types && npm run lint && node esbuild.js --standalone",
 		"postcompile-standalone": "node scripts/package-standalone.mjs",
 		"watch": "npm-run-all -p watch:*",
 		"watch:esbuild": "node esbuild.js --watch",
 		"watch:tsc": "tsc --noEmit --watch --project tsconfig.json",
-		"package": "npm run build:webview && npm run check-types && npm run lint && node esbuild.js --production",
+		"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",
 		"postprotos": "prettier src/shared/proto src/core/controller webview-ui/src/services src/standalone/server-setup.ts --write --log-level silent",
 		"compile-tests": "node ./scripts/build-tests.js",
 		"watch-tests": "tsc -p . -w --outDir out",
-		"pretest": "npm run compile-tests && npm run compile && npm run lint",
-		"check-types": "tsc --noEmit",
-		"lint": "eslint src --ext ts && eslint webview-ui/src --ext ts",
+		"pretest": "npm run compile-tests && npm run compile && npm run compile-standalone && npm run lint",
+		"check-types": "npm run protos && tsc --noEmit",
+		"lint": "eslint src --ext ts && eslint webview-ui/src --ext ts && cd webview-ui && npm run lint",
 		"format": "prettier . --check",
 		"format:fix": "prettier . --write",
 		"test": "npm-run-all test:unit test:integration",
@@ -291,13 +373,15 @@
 		"@types/turndown": "^5.0.5",
 		"@types/vscode": "^1.84.0",
 		"@typescript-eslint/eslint-plugin": "^7.14.1",
-		"@typescript-eslint/parser": "^7.11.0",
+		"@typescript-eslint/parser": "^7.18.0",
+		"@typescript-eslint/utils": "^8.33.0",
 		"@vscode/test-cli": "^0.0.10",
 		"@vscode/test-electron": "^2.4.1",
 		"chai": "^4.3.10",
 		"chalk": "^5.3.0",
 		"esbuild": "^0.25.0",
 		"eslint": "^8.57.0",
+		"eslint-plugin-eslint-rules": "file:eslint-rules",
 		"grpc-tools": "^1.13.0",
 		"husky": "^9.1.7",
 		"mintlify": "^4.0.515",
@@ -316,14 +400,15 @@
 		"@anthropic-ai/bedrock-sdk": "^0.12.4",
 		"@anthropic-ai/sdk": "^0.37.0",
 		"@anthropic-ai/vertex-sdk": "^0.6.4",
-		"@aws-sdk/client-bedrock-runtime": "^3.758.0",
+		"@aws-sdk/client-bedrock-runtime": "^3.821.0",
 		"@bufbuild/protobuf": "^2.2.5",
+		"@cerebras/cerebras_cloud_sdk": "^1.35.0",
 		"@google-cloud/vertexai": "^1.9.3",
 		"@google/genai": "^0.13.0",
 		"@grpc/grpc-js": "^1.9.15",
 		"@grpc/reflection": "^1.0.4",
 		"@mistralai/mistralai": "^1.5.0",
-		"@modelcontextprotocol/sdk": "^1.7.0",
+		"@modelcontextprotocol/sdk": "^1.11.1",
 		"@opentelemetry/api": "^1.4.1",
 		"@opentelemetry/exporter-trace-otlp-http": "^0.39.1",
 		"@opentelemetry/resources": "^1.30.1",
@@ -331,6 +416,7 @@
 		"@opentelemetry/sdk-trace-node": "^1.30.1",
 		"@opentelemetry/semantic-conventions": "^1.30.0",
 		"@sentry/browser": "^9.12.0",
+		"@streamparser/json": "^0.0.22",
 		"@vscode/codicons": "^0.0.36",
 		"archiver": "^7.0.1",
 		"axios": "^1.8.2",
@@ -340,6 +426,7 @@
 		"clone-deep": "^4.0.1",
 		"default-shell": "^2.2.0",
 		"diff": "^5.2.0",
+		"exceljs": "^4.4.0",
 		"execa": "^9.5.2",
 		"fast-deep-equal": "^3.1.3",
 		"firebase": "^11.2.0",
@@ -365,12 +452,14 @@
 		"posthog-node": "^4.8.1",
 		"puppeteer-chromium-resolver": "^23.0.0",
 		"puppeteer-core": "^23.4.0",
+		"reconnecting-eventsource": "^1.6.4",
 		"serialize-error": "^11.0.3",
 		"simple-git": "^3.27.0",
 		"strip-ansi": "^7.1.0",
 		"tree-sitter-wasms": "^0.1.11",
 		"ts-morph": "^25.0.1",
 		"turndown": "^7.2.0",
+		"vscode-uri": "^3.1.0",
 		"web-tree-sitter": "^0.22.6",
 		"zod": "^3.24.2"
 	}

proto/account.proto

@@ -16,4 +16,7 @@ service AccountService {
     // 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);
 }

proto/browser.proto

@@ -12,6 +12,7 @@ service BrowserService {
   rpc discoverBrowser(EmptyRequest) returns (BrowserConnection);
   rpc getDetectedChromePath(EmptyRequest) returns (ChromePath);
   rpc updateBrowserSettings(UpdateBrowserSettingsRequest) returns (Boolean);
+  rpc relaunchChromeDebugMode(EmptyRequest) returns (String);
 }
 
 message BrowserConnectionInfo {

proto/build-proto.js

@@ -6,16 +6,21 @@ import { fileURLToPath } from "url"
 import { execSync } from "child_process"
 import { globby } from "globby"
 import chalk from "chalk"
+import os from "os"
 
 import { createRequire } from "module"
 const require = createRequire(import.meta.url)
 const protoc = path.join(require.resolve("grpc-tools"), "../bin/protoc")
-const tsProtoPlugin = require.resolve("ts-proto/protoc-gen-ts_proto")
 
 const __filename = fileURLToPath(import.meta.url)
 const SCRIPT_DIR = path.dirname(__filename)
 const ROOT_DIR = path.resolve(SCRIPT_DIR, "..")
 
+const isWindows = process.platform === "win32"
+const tsProtoPlugin = isWindows
+	? path.join(ROOT_DIR, "node_modules", ".bin", "protoc-gen-ts_proto.cmd") // Use the .bin directory path for Windows
+	: require.resolve("ts-proto/protoc-gen-ts_proto")
+
 // List of gRPC services
 // To add a new service, simply add it to this map and run this script
 // The service handler will be automatically discovered and used by grpc-handler.ts
@@ -30,17 +35,30 @@ const serviceNameMap = {
 	web: "cline.WebService",
 	models: "cline.ModelsService",
 	slash: "cline.SlashService",
+	ui: "cline.UiService",
 	// Add new services here - no other code changes needed!
 }
 const serviceDirs = Object.keys(serviceNameMap).map((serviceKey) => path.join(ROOT_DIR, "src", "core", "controller", serviceKey))
 
+// List of host gRPC services (IDE API bridge)
+// These services are implemented in the IDE extension and called by the standalone Cline Core
+const hostServiceNameMap = {
+	uri: "host.UriService",
+	watch: "host.WatchService",
+	// Add new host services here
+}
+const hostServiceDirs = Object.keys(hostServiceNameMap).map((serviceKey) => path.join(ROOT_DIR, "hosts", "vscode", serviceKey))
+
 async function main() {
 	console.log(chalk.bold.blue("Starting Protocol Buffer code generation..."))
 
+	// Check for Apple Silicon compatibility before proceeding
+	checkAppleSiliconCompatibility()
+
 	// Define output directories
 	const TS_OUT_DIR = path.join(ROOT_DIR, "src", "shared", "proto")
 
-	// Create output directory if it doesn't exist
+	// Create output directories if they don't exist
 	await fs.mkdir(TS_OUT_DIR, { recursive: true })
 
 	// Clean up existing generated files
@@ -55,7 +73,7 @@ async function main() {
 
 	// Process all proto files
 	console.log(chalk.cyan("Processing proto files from"), SCRIPT_DIR)
-	const protoFiles = await globby("*.proto", { cwd: SCRIPT_DIR, absolute: true })
+	const protoFiles = await globby("**/*.proto", { cwd: SCRIPT_DIR, realpath: true })
 
 	// Build the protoc command with proper path handling for cross-platform
 	const tsProtocCommand = [
@@ -63,6 +81,8 @@ async function main() {
 		`--proto_path="${SCRIPT_DIR}"`,
 		`--plugin=protoc-gen-ts_proto="${tsProtoPlugin}"`,
 		`--ts_proto_out="${TS_OUT_DIR}"`,
+		"--ts_proto_opt=exportCommonSymbols=false",
+		"--ts_proto_opt=outputIndex=true",
 		"--ts_proto_opt=outputServices=generic-definitions,env=node,esModuleInterop=true,useDate=false,useOptionals=messages",
 		...protoFiles,
 	].join(" ")
@@ -76,7 +96,6 @@ async function main() {
 
 	const descriptorOutDir = path.join(ROOT_DIR, "dist-standalone", "proto")
 	await fs.mkdir(descriptorOutDir, { recursive: true })
-
 	const descriptorFile = path.join(descriptorOutDir, "descriptor_set.pb")
 	const descriptorProtocCommand = [
 		protoc,
@@ -97,8 +116,11 @@ async function main() {
 	console.log(chalk.green(`TypeScript files generated in: ${TS_OUT_DIR}`))
 
 	await generateMethodRegistrations()
+	await generateHostMethodRegistrations()
 	await generateServiceConfig()
+	await generateHostServiceConfig()
 	await generateGrpcClientConfig()
+	await generateHostGrpcClientConfig()
 }
 
 /**
@@ -241,7 +263,7 @@ async function generateMethodRegistrations() {
 // Import all method implementations
 import { registerMethod } from "./index"\n`
 
-		// Add imports for all implementation files
+		// Import implementations directly
 		for (const file of implementationFiles) {
 			const baseName = path.basename(file, ".ts")
 			methodsContent += `import { ${baseName} } from "./${baseName}"\n`
@@ -415,6 +437,242 @@ service ${serviceClassName} {
 	}
 }
 
+/**
+ * Generate method registration files for host services
+ */
+async function generateHostMethodRegistrations() {
+	console.log(chalk.cyan("Generating host method registration files..."))
+
+	// 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"))
+
+	for (const serviceDir of hostServiceDirs) {
+		try {
+			await fs.access(serviceDir)
+		} catch (error) {
+			console.log(chalk.cyan(`Creating directory ${serviceDir} for new host service`))
+			await fs.mkdir(serviceDir, { recursive: true })
+		}
+
+		const serviceName = path.basename(serviceDir)
+		const registryFile = path.join(serviceDir, "methods.ts")
+		const indexFile = path.join(serviceDir, "index.ts")
+
+		const fullServiceName = hostServiceNameMap[serviceName]
+		const streamingMethods = streamingMethodsMap.get(fullServiceName) || []
+
+		console.log(chalk.cyan(`Generating method registrations for host ${serviceName}...`))
+
+		// Get all TypeScript files in the service directory
+		const files = await globby("*.ts", { cwd: serviceDir })
+
+		// Filter out index.ts and methods.ts
+		const implementationFiles = files.filter((file) => file !== "index.ts" && file !== "methods.ts")
+
+		// Create the methods.ts file with header
+		let methodsContent = `// AUTO-GENERATED FILE - DO NOT MODIFY DIRECTLY
+// Generated by proto/build-proto.js
+
+// Import all method implementations
+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`
+		}
+
+		// Add streaming methods information
+		if (streamingMethods.length > 0) {
+			methodsContent += `\n// Streaming methods for this service
+export const streamingMethods = ${JSON.stringify(
+				streamingMethods.map((m) => m.name),
+				null,
+				2,
+			)}\n`
+		}
+
+		// Add registration function
+		methodsContent += `\n// Register all ${serviceName} service methods
+export function registerAllMethods(): void {
+\t// Register each method with the registry\n`
+
+		// Add registration statements
+		for (const file of implementationFiles) {
+			const baseName = path.basename(file, ".ts")
+			const isStreaming = streamingMethods.some((m) => m.name === baseName)
+
+			if (isStreaming) {
+				methodsContent += `\tregisterMethod("${baseName}", ${baseName}, { isStreaming: true })\n`
+			} else {
+				methodsContent += `\tregisterMethod("${baseName}", ${baseName})\n`
+			}
+		}
+
+		// Close the function
+		methodsContent += `}`
+
+		// Write the methods.ts file
+		await fs.writeFile(registryFile, methodsContent)
+		console.log(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
+
+import { createServiceRegistry, ServiceMethodHandler, StreamingMethodHandler } from "../host-grpc-service"
+import { StreamingResponseHandler } from "../host-grpc-handler"
+import { registerAllMethods } from "./methods"
+
+// Create ${serviceName} service registry
+const ${serviceName}Service = createServiceRegistry("${serviceName}")
+
+// Export the method handler types and registration function
+export type ${capitalizedServiceName}MethodHandler = ServiceMethodHandler
+export type ${capitalizedServiceName}StreamingMethodHandler = StreamingMethodHandler
+export const registerMethod = ${serviceName}Service.registerMethod
+
+// Export the request handlers
+export const handle${capitalizedServiceName}ServiceRequest = ${serviceName}Service.handleRequest
+export const handle${capitalizedServiceName}ServiceStreamingRequest = ${serviceName}Service.handleStreamingRequest
+export const isStreamingMethod = ${serviceName}Service.isStreamingMethod
+
+// Register all ${serviceName} methods
+registerAllMethods()`
+
+		// Write the index.ts file
+		await fs.writeFile(indexFile, indexContent)
+		console.log(chalk.green(`Generated ${indexFile}`))
+	}
+
+	console.log(chalk.green("Host method registration files generated successfully."))
+}
+
+/**
+ * Generate a service configuration file for host services
+ */
+async function generateHostServiceConfig() {
+	console.log(chalk.cyan("Generating host service configuration file..."))
+
+	const serviceImports = []
+	const serviceConfigs = []
+
+	// Add all services from the hostServiceNameMap
+	for (const [dirName, fullServiceName] of Object.entries(hostServiceNameMap)) {
+		const capitalizedName = dirName.charAt(0).toUpperCase() + dirName.slice(1)
+		serviceImports.push(
+			`import { handle${capitalizedName}ServiceRequest, handle${capitalizedName}ServiceStreamingRequest } from "./${dirName}/index"`,
+		)
+		serviceConfigs.push(`
+  "${fullServiceName}": {
+    requestHandler: handle${capitalizedName}ServiceRequest,
+    streamingHandler: handle${capitalizedName}ServiceStreamingRequest
+  }`)
+	}
+
+	const content = `// AUTO-GENERATED FILE - DO NOT MODIFY DIRECTLY
+// Generated by proto/build-proto.js
+
+import { StreamingResponseHandler } from "./host-grpc-handler"
+${serviceImports.join("\n")}
+
+/**
+ * Configuration for a host service handler
+ */
+export interface HostServiceHandlerConfig {
+  requestHandler: (method: string, message: any) => Promise<any>;
+  streamingHandler: (method: string, message: any, responseStream: StreamingResponseHandler, requestId?: string) => Promise<void>;
+}
+
+/**
+ * Map of host service names to their handler configurations
+ */
+export const hostServiceHandlers: Record<string, HostServiceHandlerConfig> = {${serviceConfigs.join(",")}
+};`
+
+	const configPath = path.join(ROOT_DIR, "hosts", "vscode", "host-grpc-service-config.ts")
+	await fs.mkdir(path.dirname(configPath), { recursive: true })
+	await fs.writeFile(configPath, content)
+	console.log(chalk.green(`Generated host service configuration at ${configPath}`))
+}
+
+/**
+ * Generate a gRPC client configuration file for host services
+ */
+async function generateHostGrpcClientConfig() {
+	console.log(chalk.cyan("Generating host gRPC client configuration..."))
+
+	const serviceImports = []
+	const serviceClientCreations = []
+	const serviceExports = []
+
+	// Process each service in the hostServiceNameMap
+	for (const [dirName, fullServiceName] of Object.entries(hostServiceNameMap)) {
+		const capitalizedName = dirName.charAt(0).toUpperCase() + dirName.slice(1)
+
+		// Add import statement
+		serviceImports.push(`import { ${capitalizedName}ServiceDefinition } from "@shared/proto/host/${dirName}"`)
+
+		// Add client creation
+		serviceClientCreations.push(
+			`const ${capitalizedName}ServiceClient = createGrpcClient(${capitalizedName}ServiceDefinition)`,
+		)
+
+		// Add to exports
+		serviceExports.push(`${capitalizedName}ServiceClient`)
+	}
+
+	// Generate the file content
+	const content = `// AUTO-GENERATED FILE - DO NOT MODIFY DIRECTLY
+// Generated by proto/build-proto.js
+
+import { createGrpcClient } from "./host-grpc-client-base"
+${serviceImports.join("\n")}
+
+${serviceClientCreations.join("\n")}
+
+export {
+	${serviceExports.join(",\n\t")}
+}`
+
+	const configPath = path.join(ROOT_DIR, "src", "standalone", "services", "host-grpc-client.ts")
+	await fs.mkdir(path.dirname(configPath), { recursive: true })
+	await fs.writeFile(configPath, content)
+	console.log(chalk.green(`Generated host gRPC client at ${configPath}`))
+}
+
+// Check for Apple Silicon compatibility
+function checkAppleSiliconCompatibility() {
+	// Only run check on macOS
+	if (process.platform !== "darwin") {
+		return
+	}
+
+	// Check if running on Apple Silicon
+	const cpuArchitecture = os.arch()
+	if (cpuArchitecture === "arm64") {
+		try {
+			// Check if Rosetta is installed
+			const rosettaCheck = execSync('/usr/bin/pgrep oahd || echo "NOT_INSTALLED"').toString().trim()
+
+			if (rosettaCheck === "NOT_INSTALLED") {
+				console.log(chalk.yellow("Detected Apple Silicon (ARM64) architecture."))
+				console.log(
+					chalk.red("Rosetta 2 is NOT installed. The npm version of protoc is not compatible with Apple Silicon."),
+				)
+				console.log(chalk.cyan("Please install Rosetta 2 using the following command:"))
+				console.log(chalk.cyan("  softwareupdate --install-rosetta --agree-to-license"))
+				console.log(chalk.red("Aborting build process."))
+				process.exit(1)
+			}
+		} catch (error) {
+			console.log(chalk.yellow("Could not determine Rosetta installation status. Proceeding anyway."))
+		}
+	}
+}
+
 // Run the main function
 main().catch((error) => {
 	console.error(chalk.red("Error:"), error)

proto/common.proto

@@ -58,3 +58,13 @@ message Boolean {
 message StringArray {
   repeated string values = 1;
 }
+
+message StringArrays {
+  repeated string values1 = 1;
+  repeated string values2 = 2;
+}
+
+message KeyValuePair {
+  string key = 1;
+  string value = 2;
+}