Update zAI endpoint and subscription details

* fix: CreditLimitError should use server returned url when available

- Add useMemo hook for dashboard URL computation
- Display credit balance, spent, and promotions when available
- Replace inline styles with Tailwind CSS classes
- Simplify TaskServiceClient call by removing unnecessary properties
- Add proper conditional rendering for credit information
- Improve code organization and readability

* changeset added

* props

* Update storybook

.changeset/chatty-mails-sip.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Screen readers now properly announce buttons in history preview and history view screens.

.changeset/curvy-students-yell.md

@@ -2,4 +2,4 @@
 "claude-dev": patch
 ---
 
-Dify.ai api integration
+dev: set up storybook

.changeset/fluffy-toys-beam.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Fix Ollama connection issue to default endpoint at port 11434

.changeset/funny-ants-travel.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Optimized Cline for GPT-5 model family with an aligned system prompt

.changeset/great-jars-flow.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Update zAI endpoint, subscription plans, and usage details

.changeset/grumpy-crabs-develop.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Fix: CreditLimitError should use server returned url when available

.changeset/healthy-waves-eat.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-REfactoring Tool Executor

.changeset/hot-dancers-unite.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Adding Workspace path adapter and workspace hints logic for tools

.changeset/nice-mirrors-report.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+Updated Baseten models to use dynamic fetching, added docs

.changeset/rare-oranges-flash.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Add "Use custom prompt" option to Ollama provider

.changeset/seven-pumas-worry.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Screen readers properly announce buttons in the MCP servers / Cline rules / workflows screens. Reflects the current selection of Cline rules / workflows tab to screen readers.

.changeset/seven-years-jump.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+sap provider - set sapAiCoreUseOrchestrationMode in state-helper instead of in sap provider components

.changeset/short-gifts-promise.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Moving grpc recorder as unit tests

.changeset/sixty-taxis-doubt.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Add environment variable injection to esbuild config

.changeset/slimy-kids-sip.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Fix AutoApproveModal overflowing issue

.changeset/stale-balloons-scream.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-support orchestration mode for sap provider

.changeset/yellow-cycles-join.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Prompt changes for deep-planning in windows/powershell

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -1,64 +1,69 @@
 name: 🐛 Bug Report
 description: File a bug report
-labels: ["bug"]
+labels: ['bug']
 body:
-    - type: markdown
-      attributes:
-          value: |
-              **Important:** All bug reports must be reproducible using Claude 4 Sonnet. Cline uses complex prompts so less capable models may not work as expected.
-    - type: textarea
-      id: what-happened
-      attributes:
-          label: What happened?
-          description: Also tell us, what did you expect to happen?
-          placeholder: Tell us what you see!
-      validations:
-          required: true
-    - type: textarea
-      id: steps
-      attributes:
-          label: Steps to reproduce
-          description: How do you trigger this bug? Please walk us through it step by step.
-          value: |
-              1.
-              2.
-              3.
-      validations:
-          required: false
-    - type: textarea
-      id: logs
-      attributes:
-          label: Relevant API REQUEST output
-          description: Please copy and paste any relevant output. This will be automatically formatted into code, so no need for backticks.
-          render: shell
-    - type: input
-      id: provider-model
-      attributes:
-          label: Provider/Model
-          description: What provider and model were you using when the issue occurred?
-          placeholder: "e.g., cline:anthropic/claude-3.7-sonnet, gemini:gemini-2.5-pro-exp-03-25"
-      validations:
-          required: true
-    - type: textarea
-      id: system-info
-      attributes:
-          label: System Information
-          description: What operating system and hardware are you using?
-          placeholder: |
-              Operating System: Windows 11, macOS Sonoma, Ubuntu 22.04, etc.
-              Hardware: CPU, GPU, RAM specifications if relevant
-              e.g.,
-              OS: Windows 11
-              CPU: Intel Core i7-11700K
-              GPU: NVIDIA GeForce RTX 3070
-              RAM: 32GB DDR4
-      validations:
-          required: true
-    - type: input
-      id: cline-version
-      attributes:
-          label: Cline Version
-          description: What version of Cline are you using? (You can find this at the bottom of the Settings view)
-          placeholder: "e.g., 1.2.3"
-      validations:
-          required: true
+  - type: markdown
+    attributes:
+      value: |
+        **Important:** All bug reports must be reproducible using Claude Sonnet 4. Cline uses complex prompts so less capable models may not work as expected.
+  - type: dropdown
+    id: plugin-type
+    attributes:
+      label: Plugin Type
+      description: Which plugin are you reporting a bug for?
+      options:
+        - VSCode Extension
+        - JetBrains Plugin
+      default: 0
+    validations:
+      required: true
+  - type: input
+    id: cline-version
+    attributes:
+      label: Cline Version
+      description: What version of Cline are you using? (You can find this at the bottom of the Settings view)
+      placeholder: 'e.g., 1.2.3'
+    validations:
+      required: true
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: What happened?
+      description: Also tell us, what did you expect to happen?
+      placeholder: Tell us what you see!
+    validations:
+      required: true
+  - type: textarea
+    id: steps
+    attributes:
+      label: Steps to reproduce
+      description: How do you trigger this bug? Please walk us through it step by step.
+      value: |
+        1.
+        2.
+        3.
+    validations:
+      required: false
+  - type: input
+    id: provider-model
+    attributes:
+      label: Provider/Model
+      description: What provider and model were you using when the issue occurred?
+      placeholder: 'e.g., cline:anthropic/claude-sonnet-4, gemini:gemini-2.5-pro-exp-03-25'
+    validations:
+      required: false
+  - type: textarea
+    id: system-info
+    attributes:
+      label: System Information
+      description: What operating system and hardware are you using?
+      placeholder: |
+        Operating System: Windows 11, macOS Sonoma, Ubuntu 22.04, etc.
+        Hardware: CPU, GPU, RAM specifications if relevant
+        e.g.,
+        OS: Windows 11
+        CPU: Intel Core i7-11700K
+        GPU: NVIDIA GeForce RTX 3070
+        RAM: 32GB DDR4
+    validations:
+      required: false

.github/workflows/publish-nightly.yml

@@ -0,0 +1,75 @@
+name: "Publish Nightly Release"
+
+on:
+  schedule:
+    - cron: '0 12 * * *'  # 4 AM PST (UTC-8) = 12 UTC
+  workflow_dispatch:
+
+permissions:
+    contents: write
+    packages: write
+    checks: write
+    pull-requests: write
+
+jobs:
+    test:
+        uses: ./.github/workflows/test.yml
+
+    publish:
+        needs: test
+        name: Publish Cline (Nightly) Extension
+        if: github.repository == 'cline/cline'
+        runs-on: ubuntu-latest
+        environment: PublishNightly
+
+        steps:
+            - uses: actions/checkout@v4
+
+            - name: Check for recent commits
+              run: |
+                if [ $(git rev-list --count HEAD --since="24 hours ago") -eq 0 ]; then
+                  echo "No commits in last 24 hours, exiting"
+                  exit 0
+                fi
+                echo "Found recent commits, proceeding with build"
+                
+            - name: Setup Node.js
+              uses: actions/setup-node@v4
+              with:
+                  node-version: "lts/*"
+
+            # Cache root dependencies - only reuse if package-lock.json exactly matches
+            - name: Cache root dependencies
+              uses: actions/cache@v4
+              id: root-cache
+              with:
+                  path: node_modules
+                  key: ${{ runner.os }}-npm-${{ hashFiles('package-lock.json') }}
+
+            # Cache webview-ui dependencies - only reuse if package-lock.json exactly matches
+            - name: Cache webview-ui dependencies
+              uses: actions/cache@v4
+              id: webview-cache
+              with:
+                  path: webview-ui/node_modules
+                  key: ${{ runner.os }}-npm-webview-${{ hashFiles('webview-ui/package-lock.json') }}
+
+            - name: Install root dependencies
+              if: steps.root-cache.outputs.cache-hit != 'true'
+              run: npm ci --include=optional
+
+            - name: Install webview-ui dependencies
+              if: steps.webview-cache.outputs.cache-hit != 'true'
+              run: cd webview-ui && npm ci --include=optional
+
+            - name: Install Publishing Tools
+              run: npm install -g @vscode/vsce ovsx
+
+            - name: Publish Extension as Pre-release
+              env:
+                  VSCE_PAT: ${{ secrets.VSCE_PAT }}
+                  OVSX_PAT: ${{ secrets.OVSX_PAT }}
+                  TELEMETRY_SERVICE_API_KEY: ${{ secrets.TELEMETRY_SERVICE_API_KEY }}
+                  ERROR_SERVICE_API_KEY: ${{ secrets.ERROR_SERVICE_API_KEY }}
+                  CLINE_ENVIRONMENT: production
+              run: npm run publish:marketplace:nightly

.github/workflows/publish.yml

@@ -95,6 +95,8 @@ jobs:
                   VSCE_PAT: ${{ secrets.VSCE_PAT }}
                   OVSX_PAT: ${{ secrets.OVSX_PAT }}
                   CLINE_ENVIRONMENT: production
+                  TELEMETRY_SERVICE_API_KEY: ${{ secrets.TELEMETRY_SERVICE_API_KEY }}
+                  ERROR_SERVICE_API_KEY: ${{ secrets.ERROR_SERVICE_API_KEY }}
               run: |
                   # Required to generate the .vsix
                   vsce package  --allow-package-secrets sendgrid --out "cline-${{ steps.get_version.outputs.version }}.vsix"

.husky/pre-commit

@@ -1 +1 @@
-lint-staged --no-stash
+lint-staged

.mocharc.json

@@ -10,5 +10,6 @@
 		"source-map-support/register",
 		"./src/test/requires.ts"
 	],
-	"recursive": true
+	"recursive": true,
+	"exit": true
 }

.vscode/launch.json

@@ -12,6 +12,7 @@
 			"args": [
 				"--extensionDevelopmentPath=${workspaceFolder}",
 				"--disable-workspace-trust",
+				"--disable-extensions", // Avoid conflicts with installed extensions
 				"${workspaceFolder}"
 			],
 			"outFiles": [
@@ -31,6 +32,7 @@
 			"args": [
 				"--extensionDevelopmentPath=${workspaceFolder}",
 				"--disable-workspace-trust",
+				"--disable-extensions", // Avoid conflicts with installed extensions
 				"${workspaceFolder}"
 			],
 			"outFiles": [
@@ -50,6 +52,7 @@
 			"args": [
 				"--extensionDevelopmentPath=${workspaceFolder}",
 				"--disable-workspace-trust",
+				"--disable-extensions", // Avoid conflicts with installed extensions
 				"${workspaceFolder}"
 			],
 			"outFiles": [
@@ -71,7 +74,7 @@
 				"--user-data-dir=${workspaceFolder}/dist/tmp/user",
 				"--profile-temp",
 				"--sync=off",
-				"--disable-extensions",
+				"--disable-extensions", // Avoid conflicts with installed extensions
 				"--extensionDevelopmentPath=${workspaceFolder}",
 				"${workspaceFolder}"
 			],
@@ -91,7 +94,7 @@
 		{
 			"type": "node",
 			"request": "launch",
-			"name": "Run cline-core service",
+			"name": "Debug Test Standalone Core Api Server (test:sca-server)",
 			"skipFiles": [
 				"<node_internals>/**"
 			],
@@ -100,18 +103,62 @@
 				"${workspaceFolder}/**",
 				"!**/node_modules/**"
 			],
-			"cwd": "${workspaceFolder}/dist-standalone",
+			"cwd": "${workspaceFolder}",
 			"outFiles": [
+				"${workspaceFolder}/dist/**/*.js",
 				"${workspaceFolder}/dist-standalone/**/*.js"
 			],
 			"preLaunchTask": "compile-standalone",
+			"runtimeExecutable": "npx",
+			"runtimeArgs": [
+				"tsx"
+			],
+			"program": "scripts/test-standalone-core-api-server.ts",
 			"env": {
-				// Turns on grpc debug log.
-				//"GRPC_TRACE": "all",
-				//"GRPC_VERBOSITY": "DEBUG",
-				"NODE_PATH": "${workspaceFolder}/dist-standalone/node_modules"
+				"PROTOBUS_PORT": "26040",
+				"HOSTBRIDGE_PORT": "26041",
+				"WORKSPACE_DIR": "${workspaceFolder}",
+				"E2E_TEST": "true",
+				"CLINE_ENVIRONMENT": "local"
 			},
-			"program": "cline-core.js"
+			"console": "integratedTerminal",
+			"internalConsoleOptions": "neverOpen"
+		},
+		{
+			"type": "node",
+			"request": "launch",
+			"name": "Debug Current Test File",
+			"skipFiles": [
+				"<node_internals>/**"
+			],
+			"sourceMaps": true,
+			"resolveSourceMapLocations": [
+				"${workspaceFolder}/**",
+				"!**/node_modules/**"
+			],
+			"cwd": "${workspaceFolder}",
+			"runtimeExecutable": "npx",
+			"runtimeArgs": [
+				"mocha"
+			],
+			"args": [
+				"--require",
+				"ts-node/register",
+				"--require",
+				"source-map-support/register",
+				"--require",
+				"./src/test/requires.ts",
+				"--exit",
+				"${file}"
+			],
+			"env": {
+				"TS_NODE_PROJECT": "./tsconfig.unit-test.json",
+				"NODE_ENV": "test",
+				"IS_DEV": "true",
+				"CLINE_ENVIRONMENT": "local"
+			},
+			"console": "integratedTerminal",
+			"internalConsoleOptions": "openOnSessionStart"
 		}
 	]
 }

.vscode/settings.json

@@ -21,16 +21,11 @@
 	},
 	// Enable Lint and format using Biome
 	"biome.enabled": true,
-	"[typescript]": {
-		"editor.defaultFormatter": "biomejs.biome"
-	},
-	"[typescriptreact]": {
-		"editor.defaultFormatter": "biomejs.biome"
-	},
-	"[jsonc]": {
-		"editor.defaultFormatter": "biomejs.biome"
-	},
-	"[json]": {
-		"editor.defaultFormatter": "biomejs.biome"
+	"editor.defaultFormatter": "biomejs.biome",
+	"editor.codeActionsOnSave": {
+		"source.fixAll.biome": "explicit",
+		"source.removeUnused.biome": "always",
+		"source.removeUnusedImports": "always",
+		"source.organizeImports.biome": "always"
 	}
 }

.vscodeignore

@@ -64,3 +64,9 @@ old_docs/**
 e2e-build.mjs
 e2e.vsix
 test-results/
+
+# Ignore Storybook files
+**/*.stories.tsx
+*storybook.log
+storybook-static
+**/StorybookDecorator.tsx

CHANGELOG.md

@@ -1,5 +1,62 @@
 # Changelog
 
+## [3.28.4]
+
+- Fix bug where some Windows machines had API request hanging
+- Fix bug where 'Proceed while running' action button would be disabled after running an interactive command
+- Fix prompt cache info not being displayed in History
+
+## [3.28.3]
+
+- Fixed issue with start new task button
+- Feature to generate commit message for staged changes, with unstaged as fallback
+
+## [3.28.2]
+
+- Fix for focus chain settings
+
+## [3.28.1]
+
+- Requesty: use base URL to get models and API keys
+- Removed focus chain feature flag
+
+## [3.28.0]
+
+- Synchronized Task History: Real-time task history synchronization across all Cline instances
+- Optimized GPT-5 Integration: Fine-tuned system prompts for improved performance with GPT-5 model family
+- Deep Planning Improvements: Optimized prompts for Windows/PowerShell environments and dependency exclusion
+- Streamlined UI Experience: ESC key navigation, cleaner approve/reject buttons, and improved editor panel focus
+- Smart Provider Search: Improved search functionality in API provider dropdown for faster model selection
+- Added per-provider thinking tokens configurability
+- Added Ollama custom prompt options
+- Enhanced SAP AI Core Provider: Orchestration mode support and improved model visibility
+- Added Dify.ai API Integration
+- SambaNova Updates: Added DeepSeek-V3.1 model
+- Better Gemini rate limit handling
+- OpenAI Reasoning Effort: Minimal reasoning effort configuration for OpenAI models
+- Fixed LiteLLM Caching: Anthropic caching compatibility when using LiteLLM
+- Fixed Ollama default endpoint connections
+- Fixed AutoApprove menu overflow
+- Fixed extended thinking token issue with Anthropic models
+- Fixed issue with slash commands removing text from prompt
+
+## [3.27.2]
+
+- Remove `grok-code-fast-1` promotion deadline
+
+## [3.27.1]
+
+- Add new Kimi K2 model to groq and moonshot providers
+
+## [3.27.0]
+
+- Fix `grok-code-fast-1` model information
+- Add call to action for trying free `grok-code-fast-1` in Announcement banner
+
+## [3.26.7]
+
+- Add 200k context window variant for Claude Sonnet 4 to OpenRouter and Cline providers
+
 ## [3.26.6]
 
 - Add free Grok Coder model to Cline provider for users looking for a fast, free coding model option

CONTRIBUTING.md

@@ -157,6 +157,36 @@ Anyone can contribute code to Cline, but we ask that you follow these guidelines
     - Update existing tests if your changes affect them
     - Include both unit tests and integration tests where appropriate
 
+    **End-to-End (E2E) Testing**
+    
+    Cline includes comprehensive E2E tests using Playwright that simulate real user interactions with the extension in VS Code:
+    
+    - **Running E2E tests:**
+      ```bash
+      npm run test:e2e        # Build and run all E2E tests
+      npm run e2e             # Run tests without rebuilding
+      npm run test:e2e -- --debug  # Run with interactive debugger
+      ```
+    
+    - **Writing E2E tests:**
+      - Tests are located in `src/test/e2e/`
+      - Use the `e2e` fixture for single-root workspace tests
+      - Use `e2eMultiRoot` fixture for multi-root workspace tests
+      - Follow existing patterns in `auth.test.ts`, `chat.test.ts`, `diff.test.ts`, and `editor.test.ts`
+      - See `src/test/e2e/README.md` for detailed documentation
+    
+    - **Debug mode features:**
+      - Interactive Playwright Inspector for step-by-step debugging
+      - Record new interactions and generate test code automatically
+      - Visual VS Code instance for manual testing
+      - Element inspection and selector validation
+    
+    - **Test environment:**
+      - Automated VS Code setup with Cline extension loaded
+      - Mock API server for backend testing
+      - Temporary workspaces with test fixtures
+      - Video recording for failed tests
+
 4. **Version Management with Changesets**
 
     - Create a changeset for any user-facing changes using `npm run changeset`

README.md

@@ -30,9 +30,9 @@ English | <a href="https://github.com/cline/cline/blob/main/locales/es/README.md
 </table>
 </div>
 
-Meet Cline (pronounced /klaɪn/, like "Klein"), an AI assistant that can use your **CLI** a**N**d **E**ditor.
+Meet Cline, an AI assistant that can use your **CLI** a**N**d **E**ditor.
 
-Thanks to [Claude 3.7 Sonnet's agentic coding capabilities](https://www.anthropic.com/claude/sonnet), Cline can handle complex software development tasks step-by-step. With tools that let him create & edit files, explore large projects, use the browser, and execute terminal commands (after you grant permission), he can assist you in ways that go beyond code completion or tech support. Cline can even use the Model Context Protocol (MCP) to create new tools and extend his own capabilities. While autonomous AI scripts traditionally run in sandboxed environments, this extension provides a human-in-the-loop GUI to approve every file change and terminal command, providing a safe and accessible way to explore the potential of agentic AI.
+Thanks to [Claude Sonnet's agentic coding capabilities](https://www.anthropic.com/claude/sonnet), Cline can handle complex software development tasks step-by-step. With tools that let him create & edit files, explore large projects, use the browser, and execute terminal commands (after you grant permission), he can assist you in ways that go beyond code completion or tech support. Cline can even use the Model Context Protocol (MCP) to create new tools and extend his own capabilities. While autonomous AI scripts traditionally run in sandboxed environments, this extension provides a human-in-the-loop GUI to approve every file change and terminal command, providing a safe and accessible way to explore the potential of agentic AI.
 
 1. Enter your task and add images to convert mockups into functional apps or fix bugs with screenshots.
 2. Cline starts by analyzing your file structure & source code ASTs, running regex searches, and reading relevant files to get up to speed in existing projects. By carefully managing what information is added to context, Cline can provide valuable assistance even for large, complex projects without overwhelming the context window.
@@ -87,7 +87,7 @@ All changes made by Cline are recorded in your file's Timeline, providing an eas
 
 ### Use the Browser
 
-With Claude 3.5 Sonnet's new [Computer Use](https://www.anthropic.com/news/3-5-models-and-computer-use) capability, Cline can launch a browser, click elements, type text, and scroll, capturing screenshots and console logs at each step. This allows for interactive debugging, end-to-end testing, and even general web use! This gives him autonomy to fixing visual bugs and runtime issues without you needing to handhold and copy-pasting error logs yourself.
+With Claude Sonnet's new [Computer Use](https://www.anthropic.com/news/3-5-models-and-computer-use) capability, Cline can launch a browser, click elements, type text, and scroll, capturing screenshots and console logs at each step. This allows for interactive debugging, end-to-end testing, and even general web use! This gives him autonomy to fixing visual bugs and runtime issues without you needing to handhold and copy-pasting error logs yourself.
 
 Try asking Cline to "test the app", and watch as he runs a command like `npm run dev`, launches your locally running dev server in a browser, and performs a series of tests to confirm that everything works. [See a demo here.](https://x.com/sdrzn/status/1850880547825823989)
 

biome.jsonc

@@ -37,7 +37,8 @@
 				"useYield": "off",
 				"noConstructorReturn": "off",
 				"noInvalidPositionAtImportRule": "off",
-				"noSwitchDeclarations": "off"
+				"noSwitchDeclarations": "off",
+				"noUnusedImports": "error"
 			},
 			"a11y": "off",
 			"style": {
@@ -122,7 +123,8 @@
 			"!**/node_modules/**",
 			"!**/webview-ui/build/**",
 			"!**/generated/**",
-			"!**/proto/**"
+			"!**/proto/**",
+			"!**/tests/specs/**"
 		]
 	},
 	"plugins": [
@@ -134,7 +136,12 @@
 				"**",
 				"!**/hosts/vscode/**",
 				"!**/test/**",
-				"!src/extension.ts"
+				"!**/*.test.ts",
+				"!src/dev/**",
+				"!src/extension.ts",
+				"!src/integrations/git/commit-message-generator.ts",
+				"!src/integrations/terminal/**",
+				"!src/core/controller/ui/openWalkthrough.ts"
 			],
 			"plugins": [
 				"src/dev/grit/vscode-api.grit"
@@ -147,6 +154,7 @@
 				"!src/core/storage/FileContextTracker.ts",
 				"!src/core/context/context-tracking/FileContextTracker.ts",
 				"!src/common.ts",
+				"!src/services/logging/distinctId.ts",
 				"!src/core/storage/utils/state-helpers.ts",
 				"!src/extension.ts"
 			],

docs/docs.json

@@ -60,6 +60,7 @@
 					"getting-started/what-is-cline",
 					"getting-started/model-selection-guide",
 					"getting-started/installing-cline",
+					"getting-started/installing-cline-jetbrains",
 					"getting-started/task-management",
 					"getting-started/understanding-context-management",
 					{

docs/exploring-clines-tools/cline-tools-guide.mdx

@@ -56,7 +56,7 @@ Cline is your AI assistant that can:
 
 ## Available Tools
 
-For the most up-to-date implementation details, you can view the full source code in the [Cline repository](https://github.com/cline/cline/blob/main/src/core/Cline.ts).
+For the most up-to-date implementation details, you can view the full source code in the [Cline repository](https://github.com/cline/cline/blob/main/src/core/prompts/system-prompt/tools).
 
 Cline has access to the following tools for various tasks:
 

docs/getting-started/installing-cline-jetbrains.mdx

@@ -0,0 +1,135 @@
+---
+title: "Installing Cline for JetBrains (Early Access)"
+description: "Get early access to Cline in your favorite JetBrains IDE with the same powerful AI assistance you know from VSCode."
+---
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/jetbrains-logo.svg"
+		alt="JetBrains logo"
+		style={{ width: "200px", height: "auto", margin: "0 auto 20px auto", display: "block" }}
+	/>
+</Frame>
+
+Cline for JetBrains works almost identically to Cline in VSCode. All the core features work properly: diff editing, using tools, logging in with different providers, MCP servers, Cline rules and workflows, and more.
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/jetbrains-demo-hifi.gif"
+		alt="Cline running in JetBrains IDE showing AI assistance"
+	/>
+</Frame>
+
+<Note>Cline for JetBrains is in early access. All core features are functional, with ongoing improvements based on user feedback.</Note>
+
+## Installation
+
+As part of our early access program, Cline for JetBrains is available through direct download before its official marketplace release. You'll need to install it manually from a downloaded file:
+
+### Manual Installation from Disk
+
+1. **Download the Plugin:**
+   - Go to [https://plugins.jetbrains.com/plugin/28247-cline/versions/eap](https://plugins.jetbrains.com/plugin/28247-cline/versions/eap)
+   - Click **Download** to get the `.zip` file
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-marketplace-download.png"
+		alt="JetBrains plugin marketplace showing Cline download page"
+	/>
+</Frame>
+
+2. **Install from Disk:**
+   - Open your JetBrains IDE
+   - Go to **IntelliJ IDEA** (or whichever IDE you are in) → **Settings**
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-settings.png"
+		alt="JetBrains IDE settings dialog"
+	/>
+</Frame>
+
+   - Select **Plugins** from the left sidebar
+   - Click the gear icon ⚙️ and select **Install Plugin from Disk...**
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-install-disk.png"
+		alt="JetBrains IDE settings showing Install Plugin from Disk option"
+	/>
+</Frame>
+
+   - Select the downloaded `.zip` file
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-zip-file.png"
+		alt="File selection dialog showing Cline plugin zip file"
+	/>
+</Frame>
+
+   - Restart your IDE when prompted
+
+## Getting Started with Cline
+
+After installation, you'll find Cline in your IDE:
+
+1. **Open Cline:**
+   - Look for the Cline tool window (usually on the right side)
+   - Or go to **View** → **Tool Windows** → **Cline**
+
+2. **Sign In (optional, BYOK is also available):**
+   - Click **Sign In** in the Cline panel
+   - You'll be taken to [app.cline.bot](https://app.cline.bot) to create your account
+   - No credit card needed to get started with free credits
+
+3. **Start Coding:**
+   - Try this first prompt: "Hey Cline! Can you help me create a simple Hello World program in this project?"
+
+## Key Differences from VSCode
+
+While Cline for JetBrains includes all the same powerful features, there's one important difference to be aware of:
+
+**Terminal Integration:** The terminal inside JetBrains isn't integrated with Cline the same way it is in VSCode. Cline can execute commands, but the output will only appear in the webview if you expand the **Command Output** section.
+
+This means:
+- Commands still run successfully
+- You can see the output by clicking to expand Command Output in the chat
+- Terminal commands work the same way, just with a different display
+
+## What Works
+
+Everything else works exactly like VSCode:
+
+- **Diff Editing:** Cline can read, write, and edit files with the same precision
+- **Tool Usage:** All of Cline's tools (file operations, web browsing, etc.) work identically  
+- **API Providers:** Connect to Anthropic, OpenAI, local models, and more
+- **MCP Servers:** Full support for Model Context Protocol servers
+- **Cline Rules:** Custom instructions and workflows work the same way
+- **@ Mentions:** Reference files, folders, problems, and more
+- **Drag & Drop:** Add files and images to conversations
+
+## Tips for JetBrains Users
+
+- **Project Context:** Cline automatically understands your project structure, just like in VSCode
+- **Language Support:** Cline works with any language your JetBrains IDE supports
+- **Debugging Help:** Share error messages and stack traces directly in the chat
+- **Code Review:** Ask Cline to review your code changes before committing
+
+## Troubleshooting
+
+If you don't see the Cline tool window after installation:
+- Restart your IDE completely
+- Check **View** → **Tool Windows** → **Cline**
+- Ensure the plugin is enabled in **Settings** → **Plugins**
+
+Having other issues? Join our [Discord community](https://discord.gg/cline) for help from the team and other users.
+
+## Next Steps
+
+Now that you have Cline installed, you might want to:
+- Learn about [model selection](/getting-started/model-selection-guide) to choose the best AI provider
+- Explore [@ mentions](/features/at-mentions/overview) to reference files and context efficiently  
+- Set up [Cline rules](/features/cline-rules) for your specific workflow
+- Try [MCP servers](/mcp/mcp-overview) to extend Cline's capabilities

docs/hubspot.js

@@ -0,0 +1,14 @@
+// HubSpot Tracking Code for Cline Documentation
+;(() => {
+	// Check if HubSpot script is already loaded to prevent duplicates
+	if (!document.getElementById("hs-script-loader")) {
+		var script = document.createElement("script")
+		script.type = "text/javascript"
+		script.id = "hs-script-loader"
+		script.async = true
+		script.src = "https://js-na2.hs-scripts.com/243656267.js"
+
+		// Append the script to the document head
+		document.head.appendChild(script)
+	}
+})()

docs/provider-config/baseten.mdx

@@ -0,0 +1,114 @@
+---
+title: "Baseten"
+description: "Learn how to configure and use Baseten's Model APIs with Cline. Access frontier open-source models with enterprise-grade performance, reliability, and competitive pricing."
+---
+
+Baseten provides on-demand frontier model APIs designed for production applications, not just experimentation. Built on the Baseten Inference Stack, these APIs deliver enterprise-grade performance and reliability with optimized inference for leading open-source models from OpenAI, DeepSeek, Meta, Moonshot AI, and Alibaba Cloud.
+
+**Website:** [https://www.baseten.co/products/model-apis/](https://www.baseten.co/products/model-apis/)
+
+### Getting an API Key
+
+1.  **Sign Up/Sign In:** Go to [Baseten](https://www.baseten.co/) and create an account or sign in.
+2.  **Navigate to API Keys:** Access your dashboard and go to the API Keys section.
+3.  **Create a Key:** Generate a new API key. Give it a descriptive name (e.g., "Cline").
+4.  **Copy the Key:** Copy the API key immediately and store it securely.
+
+### Supported Models
+
+Cline supports all current models under Baseten Model APIs, including:
+
+**Reasoning Models:**
+-   `deepseek-ai/DeepSeek-R1` - DeepSeek's first-generation reasoning model (163K context) - $2.55/$5.95 per 1M tokens
+-   `deepseek-ai/DeepSeek-R1-0528` - Latest revision of DeepSeek's reasoning model (163K context) - $2.55/$5.95 per 1M tokens
+-   `deepseek-ai/DeepSeek-V3.1` - Hybrid reasoning with advanced tool calling (163K context) - $0.50/$1.50 per 1M tokens
+-   `deepseek-ai/DeepSeek-V3-0324` - Fast general-purpose with enhanced reasoning (163K context) - $0.77/$0.77 per 1M tokens
+
+**Flagship Models:**
+-   `openai/gpt-oss-120b` (OpenAI) - 120B MoE with strong reasoning capabilities (128K context) - $0.10/$0.50 per 1M tokens
+-   `moonshotai/Kimi-K2-Instruct` (Moonshot AI) - 1 trillion parameter model for agentic tasks (131K context) - $0.60/$2.50 per 1M tokens
+-   `moonshotai/Kimi-K2-Instruct-0905` (Moonshot AI) - September update with enhanced capabilities (262K context) - $0.60/$2.50 per 1M tokens
+
+**Meta Llama 4 Series:**
+-   `meta-llama/Llama-4-Maverick-17B-128E-Instruct` - High-efficiency processing (1M context!) - $0.19/$0.72 per 1M tokens
+-   `meta-llama/Llama-4-Scout-17B-16E-Instruct` - Precise context understanding (1M context!) - $0.13/$0.50 per 1M tokens
+
+**Coding Specialists:**
+-   `Qwen/Qwen3-Coder-480B-A35B-Instruct` (Alibaba Cloud) - Advanced coding and reasoning (262K context) - $0.38/$1.53 per 1M tokens
+-   `Qwen/Qwen3-235B-A22B-Instruct-2507` (Alibaba Cloud) - Math and reasoning expert (262K context) - $0.22/$0.80 per 1M tokens
+
+### Configuration in Cline
+
+1.  **Open Cline Settings:** Click the settings icon (⚙️) in the Cline panel.
+2.  **Select Provider:** Choose "Baseten" from the "API Provider" dropdown.
+3.  **Enter API Key:** Paste your Baseten API key into the "Baseten API Key" field.
+4.  **Select Model:** Choose your desired model from the "Model" dropdown.
+
+### Production-First Architecture
+
+Baseten's Model APIs are built for production environments with several key advantages:
+
+#### Enterprise-Grade Reliability
+- **Four nines of uptime** (99.99%) through active-active redundancy
+- **Cloud-agnostic, multi-cluster autoscaling** for consistent availability
+- **SOC 2 Type II certified** and **HIPAA compliant** for security requirements
+
+#### Optimized Performance
+- **Pre-optimized models** shipped with the Baseten Inference Stack
+- **Latest-generation GPUs** with multi-cloud infrastructure
+- **Ultra-fast inference** optimized from the bottom up for production workloads
+
+#### Cost Efficiency
+- **5-10x less expensive** than closed alternatives
+- **Optimized multi-cloud infrastructure** for efficient resource utilization
+- **Transparent pricing** with no hidden costs or rate limit surprises
+
+#### Developer Experience
+- **OpenAI compatible API** - migrate by swapping a single URL
+- **Drop-in replacement** for closed models with comprehensive observability
+- **Seamless scaling** from Model APIs to dedicated deployments
+
+### Special Features
+
+#### Function Calling & Tool Use
+All Baseten models support structured outputs, function calling, and tool use as part of the Baseten Inference Stack, making them ideal for agentic applications.
+
+#### Reasoning Capabilities
+DeepSeek models offer enhanced reasoning with step-by-step thought processes, while maintaining production-ready performance.
+
+#### Long Context Support
+- **Up to 1 million tokens** for Llama 4 models (Maverick and Scout)
+- **262K tokens** for Qwen3 models
+- **163K tokens** for DeepSeek models
+- **Perfect for code repositories** and complex multi-turn conversations
+
+#### Quantization Optimizations
+Models are deployed with advanced quantization techniques (fp4, fp8, fp16) for optimal performance while maintaining quality.
+
+### Migration from Other Providers
+
+Baseten's OpenAI compatibility makes migration straightforward:
+
+**From OpenAI:**
+- Swap `api.openai.com` with `inference.baseten.co/v1`
+- Keep existing request/response formats
+- Benefit from significant cost savings
+
+**From Other Providers:**
+- Use standard OpenAI SDK format
+- Maintain existing prompting strategies
+- Access to newer open-source models
+
+### Tips and Notes
+
+-   **Model Selection:** Choose models based on your specific use case - reasoning models for complex tasks, coding models for development work, and flagship models for general applications.
+-   **Cost Optimization:** Baseten offers some of the most competitive pricing in the market, especially for open-source models.
+-   **Context Windows:** Take advantage of large context windows (up to 1M tokens) for including substantial codebases and documentation.
+-   **Enterprise Ready:** Baseten is designed for production use with enterprise-grade security, compliance, and reliability.
+-   **Dynamic Model Updates:** Cline automatically fetches the latest model list from Baseten, ensuring access to new models as they're released.
+-   **Multi-Cloud Capacity Management (MCM):** Baseten's multi-cloud infrastructure ensures high availability and low latency globally.
+-   **Support:** Baseten provides dedicated support for production deployments and can work with you on dedicated resources as you scale.
+
+### Pricing Information
+
+Current pricing is highly competitive and transparent. For the most up-to-date pricing, visit the [Baseten Model APIs page](https://www.baseten.co/products/model-apis/). Prices typically range from $0.10-$6.00 per million tokens, making Baseten significantly more cost-effective than many closed-model alternatives while providing access to state-of-the-art open-source models.

docs/provider-config/zai.mdx

@@ -49,6 +49,59 @@ All models feature:
 4.  **Enter API Key:** Paste your Z AI API key into the "Z AI API Key" field.
 5.  **Select Model:** Choose your desired model from the "Model" dropdown.
 
+### GLM Coding Plans
+
+Z AI offers subscription plans specifically designed for coding applications. These plans provide cost-effective access to GLM-4.5 models through a prompt-based structure rather than traditional API usage billing.
+
+#### Plan Options
+
+**GLM Coding Lite** - $3/month
+- Powered by GLM-4.5
+- Up to ~120 prompts every 5 hours (about 3× the usage quota of the Claude Pro plan)
+- Works exclusively through coding tools like Cline
+
+**GLM Coding Pro** - $15/month
+- All Lite plan benefits
+- 5× Lite plan usage (~600 prompts every 5 hours, about 3× the usage quota of the Claude Max (5x) plan)
+- 40%–60% faster compared to Lite
+- Built-in image & video understanding and web search MCP
+
+**GLM Coding Max** - $30/month
+- All Pro plan benefits
+- 4× Pro plan usage (~2400 prompts every 5 hours)
+- Guaranteed peak-hour performance
+- Early access to new features
+
+All plans offer promotional pricing for the first month: Lite drops from $6 to $3, Pro drops from $30 to $15, and Max drops from $60 to $30.
+
+<Frame>
+  <img src="https://storage.googleapis.com/cline_public_images/docs/assets/zAI-coding-plan.png" alt="zAI subscription page showing GLM Coding Lite and Pro plans with pricing" />
+</Frame>
+
+#### Setting up GLM Coding Plans
+
+To use the GLM Coding Plans with Cline:
+
+1. **Subscribe:** Go to [https://z.ai/subscribe](https://z.ai/subscribe) and choose your plan.
+
+2. **Create API Key:** After subscribing, log into your zAI dashboard and create an API key for your coding plan.
+
+3. **Configure in Cline:** Open Cline settings, select "Z AI" as your provider, and paste your API key into the "Z AI API Key" field.
+
+<Frame>
+  <img src="https://storage.googleapis.com/cline_public_images/docs/assets/zAI-provider.png" alt="Cline settings with zAI provider selected and API key field highlighted" />
+</Frame>
+
+#### Usage Details
+
+In terms of token consumption, each prompt typically allows 15–20 model calls, giving a total monthly allowance of tens of billions of tokens — all at only ~1% of standard API pricing, making it extremely cost-effective.
+
+Once subscribed, GLM-4.5 is automatically available in the supported tools using your plan's quota—no additional configuration required. If the quota is exhausted, it will automatically reset at the start of the next 5-hour cycle. The system will not consume other resource packs or account balance. Users with a Coding Plan can only use the plan's quota in supported tools and cannot call the model separately via API.
+
+**Note:** API calls are billed separately and do not use the Coding Plan quota. Please refer to the API pricing for details.
+
+The setup connects your subscription directly to Cline, giving you access to GLM-4.5's tool-calling capabilities optimized for coding workflows.
+
 ### Z AI's Hybrid Intelligence
 
 Z AI's GLM-4.5 series introduces revolutionary capabilities that set it apart from conventional language models:

esbuild.mjs

@@ -130,7 +130,16 @@ const baseConfig = {
 	sourcemap: !production,
 	logLevel: "silent",
 	define: production
-		? { "import.meta.url": "_importMetaUrl", "process.env.IS_DEV": JSON.stringify(!production) }
+		? {
+				"import.meta.url": "_importMetaUrl",
+				"process.env.IS_DEV": JSON.stringify(!production),
+				...(process.env.TELEMETRY_SERVICE_API_KEY && process.env.ERROR_SERVICE_API_KEY
+					? {
+							"process.env.TELEMETRY_SERVICE_API_KEY": JSON.stringify(process.env.TELEMETRY_SERVICE_API_KEY),
+							"process.env.ERROR_SERVICE_API_KEY": JSON.stringify(process.env.ERROR_SERVICE_API_KEY),
+						}
+					: {}),
+			}
 		: { "import.meta.url": "_importMetaUrl" },
 	tsconfig: path.resolve(__dirname, "tsconfig.json"),
 	plugins: [
@@ -160,9 +169,9 @@ const standaloneConfig = {
 	...baseConfig,
 	entryPoints: ["src/standalone/cline-core.ts"],
 	outfile: `${destDir}/cline-core.js`,
-	// These gRPC protos need to load files from the module directory at runtime,
+	// These modules need to load files from the module directory at runtime,
 	// so they cannot be bundled.
-	external: ["vscode", "@grpc/reflection", "grpc-health-check"],
+	external: ["vscode", "@grpc/reflection", "grpc-health-check", "better-sqlite3"],
 }
 
 // E2E build script configuration

evals/diff-edits/types.ts

@@ -1,5 +1,6 @@
 import { Anthropic } from "@anthropic-ai/sdk"
-import { ToolUseName, ToolParamName } from "../../src/core/assistant-message"
+import { ToolParamName } from "../../src/core/assistant-message"
+import { ClineDefaultTool } from "../../src/shared/tools"
 
 export interface InputMessage {
 	role: "user" | "assistant"
@@ -88,7 +89,7 @@ export interface TestResult {
 }
 
 export interface ExtractedToolCall {
-	name: ToolUseName
+	name: ClineDefaultTool
 	input: Partial<Record<ToolParamName, string>>
 }
 

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "claude-dev",
-	"version": "3.26.6",
+	"version": "3.28.4",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "claude-dev",
-			"version": "3.26.6",
+			"version": "3.28.4",
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@anthropic-ai/sdk": "^0.37.0",
@@ -16,7 +16,7 @@
 				"@bufbuild/protobuf": "^2.2.5",
 				"@cerebras/cerebras_cloud_sdk": "^1.35.0",
 				"@google-cloud/vertexai": "^1.9.3",
-				"@google/genai": "1.0.0",
+				"@google/genai": "^1.11.0",
 				"@grpc/grpc-js": "^1.9.15",
 				"@grpc/reflection": "^1.0.4",
 				"@mistralai/mistralai": "^1.5.0",
@@ -66,7 +66,7 @@
 				"p-timeout": "^6.1.4",
 				"p-wait-for": "^5.0.2",
 				"pdf-parse": "^1.1.1",
-				"posthog-node": "^4.8.1",
+				"posthog-node": "^5.8.0",
 				"puppeteer-chromium-resolver": "^23.0.0",
 				"puppeteer-core": "^23.4.0",
 				"reconnecting-eventsource": "^1.6.4",
@@ -86,6 +86,7 @@
 				"@biomejs/biome": "^2.1.4",
 				"@bufbuild/buf": "^1.54.0",
 				"@changesets/cli": "^2.27.12",
+				"@types/better-sqlite3": "^7.6.13",
 				"@types/chai": "^5.0.1",
 				"@types/clone-deep": "^4.0.4",
 				"@types/diff": "^5.2.1",
@@ -109,6 +110,7 @@
 				"lint-staged": "^16.1.0",
 				"minimatch": "^3.0.3",
 				"npm-run-all": "^4.1.5",
+				"prebuild-install": "^7.1.3",
 				"protoc-gen-ts": "^0.8.7",
 				"proxyquire": "^2.1.3",
 				"rimraf": "^6.0.1",
@@ -2531,19 +2533,24 @@
 			}
 		},
 		"node_modules/@google/genai": {
-			"version": "1.0.0",
+			"version": "1.15.0",
+			"resolved": "https://registry.npmjs.org/@google/genai/-/genai-1.15.0.tgz",
+			"integrity": "sha512-4CSW+hRTESWl3xVtde7pkQ3E+dDFhDq+m4ztmccRctZfx1gKy3v0M9STIMGk6Nq0s6O2uKMXupOZQ1JGorXVwQ==",
 			"license": "Apache-2.0",
 			"dependencies": {
 				"google-auth-library": "^9.14.2",
-				"ws": "^8.18.0",
-				"zod": "^3.22.4",
-				"zod-to-json-schema": "^3.22.4"
+				"ws": "^8.18.0"
 			},
 			"engines": {
-				"node": ">=18.0.0"
+				"node": ">=20.0.0"
 			},
 			"peerDependencies": {
 				"@modelcontextprotocol/sdk": "^1.11.0"
+			},
+			"peerDependenciesMeta": {
+				"@modelcontextprotocol/sdk": {
+					"optional": true
+				}
 			}
 		},
 		"node_modules/@grpc/grpc-js": {
@@ -3685,6 +3692,12 @@
 				"node": ">=18"
 			}
 		},
+		"node_modules/@posthog/core": {
+			"version": "1.0.1",
+			"resolved": "https://registry.npmjs.org/@posthog/core/-/core-1.0.1.tgz",
+			"integrity": "sha512-bwXUeHe+MLgENm8+/FxEbiNocOw1Vjewmm+HEUaYQe6frq8OhZnrvtnzZU3Q3DF6N0UbAmD/q+iNfNgyx8mozg==",
+			"license": "MIT"
+		},
 		"node_modules/@protobufjs/aspromise": {
 			"version": "1.1.2",
 			"license": "BSD-3-Clause"
@@ -5079,6 +5092,16 @@
 			"dev": true,
 			"license": "MIT"
 		},
+		"node_modules/@types/better-sqlite3": {
+			"version": "7.6.13",
+			"resolved": "https://registry.npmjs.org/@types/better-sqlite3/-/better-sqlite3-7.6.13.tgz",
+			"integrity": "sha512-NMv9ASNARoKksWtsq/SHakpYAYnhBrQgGD8zkLYk/jaK8jUGn08CfEdTRgYhMypUQAfzSP8W6gNLe0q19/t4VA==",
+			"dev": true,
+			"license": "MIT",
+			"dependencies": {
+				"@types/node": "*"
+			}
+		},
 		"node_modules/@types/chai": {
 			"version": "5.0.1",
 			"dev": true,
@@ -7102,7 +7125,6 @@
 			"version": "6.0.0",
 			"dev": true,
 			"license": "MIT",
-			"optional": true,
 			"dependencies": {
 				"mimic-response": "^3.1.0"
 			},
@@ -7117,7 +7139,6 @@
 			"version": "3.1.0",
 			"dev": true,
 			"license": "MIT",
-			"optional": true,
 			"engines": {
 				"node": ">=10"
 			},
@@ -7140,7 +7161,6 @@
 			"version": "0.6.0",
 			"dev": true,
 			"license": "MIT",
-			"optional": true,
 			"engines": {
 				"node": ">=4.0.0"
 			}
@@ -8094,7 +8114,6 @@
 			"version": "2.0.3",
 			"dev": true,
 			"license": "(MIT OR WTFPL)",
-			"optional": true,
 			"engines": {
 				"node": ">=6"
 			}
@@ -8952,8 +8971,7 @@
 		"node_modules/github-from-package": {
 			"version": "0.0.0",
 			"dev": true,
-			"license": "MIT",
-			"optional": true
+			"license": "MIT"
 		},
 		"node_modules/glob": {
 			"version": "10.4.3",
@@ -9383,8 +9401,7 @@
 		"node_modules/ini": {
 			"version": "1.3.8",
 			"dev": true,
-			"license": "ISC",
-			"optional": true
+			"license": "ISC"
 		},
 		"node_modules/internal-slot": {
 			"version": "1.1.0",
@@ -10964,8 +10981,7 @@
 		"node_modules/mkdirp-classic": {
 			"version": "0.5.3",
 			"dev": true,
-			"license": "MIT",
-			"optional": true
+			"license": "MIT"
 		},
 		"node_modules/mocha": {
 			"version": "10.6.0",
@@ -11193,8 +11209,7 @@
 		"node_modules/napi-build-utils": {
 			"version": "2.0.0",
 			"dev": true,
-			"license": "MIT",
-			"optional": true
+			"license": "MIT"
 		},
 		"node_modules/negotiator": {
 			"version": "1.0.0",
@@ -11258,7 +11273,6 @@
 			"version": "3.75.0",
 			"dev": true,
 			"license": "MIT",
-			"optional": true,
 			"dependencies": {
 				"semver": "^7.3.5"
 			},
@@ -12387,20 +12401,23 @@
 			}
 		},
 		"node_modules/posthog-node": {
-			"version": "4.8.1",
+			"version": "5.8.0",
+			"resolved": "https://registry.npmjs.org/posthog-node/-/posthog-node-5.8.0.tgz",
+			"integrity": "sha512-Idj6TgjYN0POXvrGK97ZKTLbLEY7sUjsaeMaquKt9UlK3Z9ps0nj0wRkFYKEYvfQ8OMwTwgKaze+5hXgmudwdw==",
 			"license": "MIT",
 			"dependencies": {
-				"axios": "^1.7.4"
+				"@posthog/core": "1.0.1"
 			},
 			"engines": {
-				"node": ">=15.0.0"
+				"node": ">=20"
 			}
 		},
 		"node_modules/prebuild-install": {
 			"version": "7.1.3",
+			"resolved": "https://registry.npmjs.org/prebuild-install/-/prebuild-install-7.1.3.tgz",
+			"integrity": "sha512-8Mf2cbV7x1cXPUILADGI3wuhfqWvtiLA1iclTDbFRZkgRQS0NqsPZphna9V+HyTEadheuPmjaJMsbzKQFOzLug==",
 			"dev": true,
 			"license": "MIT",
-			"optional": true,
 			"dependencies": {
 				"detect-libc": "^2.0.0",
 				"expand-template": "^2.0.3",
@@ -12426,7 +12443,6 @@
 			"version": "4.1.0",
 			"dev": true,
 			"license": "MIT",
-			"optional": true,
 			"dependencies": {
 				"buffer": "^5.5.0",
 				"inherits": "^2.0.4",
@@ -12451,7 +12467,6 @@
 				}
 			],
 			"license": "MIT",
-			"optional": true,
 			"dependencies": {
 				"base64-js": "^1.3.1",
 				"ieee754": "^1.1.13"
@@ -12460,14 +12475,12 @@
 		"node_modules/prebuild-install/node_modules/chownr": {
 			"version": "1.1.4",
 			"dev": true,
-			"license": "ISC",
-			"optional": true
+			"license": "ISC"
 		},
 		"node_modules/prebuild-install/node_modules/detect-libc": {
 			"version": "2.0.4",
 			"dev": true,
 			"license": "Apache-2.0",
-			"optional": true,
 			"engines": {
 				"node": ">=8"
 			}
@@ -12476,7 +12489,6 @@
 			"version": "3.6.2",
 			"dev": true,
 			"license": "MIT",
-			"optional": true,
 			"dependencies": {
 				"inherits": "^2.0.3",
 				"string_decoder": "^1.1.1",
@@ -12490,7 +12502,6 @@
 			"version": "2.1.3",
 			"dev": true,
 			"license": "MIT",
-			"optional": true,
 			"dependencies": {
 				"chownr": "^1.1.1",
 				"mkdirp-classic": "^0.5.2",
@@ -12502,7 +12513,6 @@
 			"version": "2.2.0",
 			"dev": true,
 			"license": "MIT",
-			"optional": true,
 			"dependencies": {
 				"bl": "^4.0.3",
 				"end-of-stream": "^1.4.1",
@@ -12732,7 +12742,6 @@
 			"version": "1.2.8",
 			"dev": true,
 			"license": "(BSD-2-Clause OR MIT OR Apache-2.0)",
-			"optional": true,
 			"dependencies": {
 				"deep-extend": "^0.6.0",
 				"ini": "~1.3.0",
@@ -12758,7 +12767,6 @@
 			"version": "2.0.1",
 			"dev": true,
 			"license": "MIT",
-			"optional": true,
 			"engines": {
 				"node": ">=0.10.0"
 			}
@@ -13639,8 +13647,7 @@
 					"url": "https://feross.org/support"
 				}
 			],
-			"license": "MIT",
-			"optional": true
+			"license": "MIT"
 		},
 		"node_modules/simple-get": {
 			"version": "4.0.1",
@@ -13660,7 +13667,6 @@
 				}
 			],
 			"license": "MIT",
-			"optional": true,
 			"dependencies": {
 				"decompress-response": "^6.0.0",
 				"once": "^1.3.1",
@@ -14554,7 +14560,6 @@
 			"version": "0.6.0",
 			"dev": true,
 			"license": "Apache-2.0",
-			"optional": true,
 			"dependencies": {
 				"safe-buffer": "^5.0.1"
 			},

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": "3.26.6",
+	"version": "3.28.4",
 	"icon": "assets/icons/icon.png",
 	"engines": {
 		"vscode": "^1.84.0"
@@ -102,15 +102,8 @@
 			"activitybar": [
 				{
 					"id": "claude-dev-ActivityBar",
-					"title": "Cline (⌘+')",
-					"icon": "assets/icons/icon.svg",
-					"when": "isMac"
-				},
-				{
-					"id": "claude-dev-ActivityBar",
-					"title": "Cline (Ctrl+')",
-					"icon": "assets/icons/icon.svg",
-					"when": "!isMac"
+					"title": "Cline",
+					"icon": "assets/icons/icon.svg"
 				}
 			]
 		},
@@ -348,7 +341,9 @@
 		"package": "npm run check-types && npm run build:webview && npm run lint && node esbuild.mjs --production",
 		"protos": "node scripts/build-proto.mjs",
 		"postprotos": "biome format src/shared/proto src/core/controller src/hosts/ webview-ui/src/services src/generated --write --no-errors-on-unmatched",
-		"clean": "rimraf dist dist-standalone webview-ui/build src/generated out/",
+		"clean:build": "rimraf dist dist-standalone webview-ui/build src/generated out/",
+		"clean:deps": "rimraf node_modules webview-ui/node_modules",
+		"clean:all": "npm run clean:build && npm run clean:deps",
 		"compile-tests": "node ./scripts/build-tests.js",
 		"watch-tests": "tsc -p . -w --outDir out",
 		"check-types": "npm run protos && npx tsc --noEmit && cd webview-ui && npx tsc -b --noEmit",
@@ -362,15 +357,18 @@
 		"test:integration": "vscode-test",
 		"test:unit": "TS_NODE_PROJECT='./tsconfig.unit-test.json' mocha",
 		"test:coverage": "vscode-test --coverage",
+		"test:sca-server": "npx tsx watch scripts/test-standalone-core-api-server.ts",
+		"test:tp-orchestrator": "npx tsx scripts/testing-platform-orchestrator.ts",
 		"e2e": "playwright test -c playwright.config.ts",
-		"test:e2e": "playwright install && vsce package --no-dependencies --allow-package-secrets sendgrid --out dist/e2e.vsix && node src/test/e2e/utils/build.mjs && playwright test",
-		"test:e2e:optimal": "vsce package --no-dependencies --allow-package-secrets sendgrid --out dist/e2e.vsix && node src/test/e2e/utils/build.mjs && playwright test",
+		"test:e2e": "playwright install && vsce package --allow-package-secrets sendgrid --out dist/e2e.vsix && node src/test/e2e/utils/build.mjs && playwright test",
+		"test:e2e:optimal": "vsce package --allow-package-secrets sendgrid --out dist/e2e.vsix && node src/test/e2e/utils/build.mjs && playwright test",
 		"install:all": "npm install && cd webview-ui && npm install",
 		"dev:webview": "cd webview-ui && npm run dev",
 		"build:webview": "cd webview-ui && npm run build",
 		"test:webview": "cd webview-ui && npm run test",
 		"publish:marketplace": "vsce publish --allow-package-secrets sendgrid && ovsx publish",
 		"publish:marketplace:prerelease": "vsce publish --allow-package-secrets sendgrid --pre-release && ovsx publish --pre-release",
+		"publish:marketplace:nightly": "node ./scripts/publish-nightly.mjs",
 		"prepare": "husky",
 		"changeset": "changeset",
 		"version-packages": "changeset version",
@@ -388,6 +386,7 @@
 		"@biomejs/biome": "^2.1.4",
 		"@bufbuild/buf": "^1.54.0",
 		"@changesets/cli": "^2.27.12",
+		"@types/better-sqlite3": "^7.6.13",
 		"@types/chai": "^5.0.1",
 		"@types/clone-deep": "^4.0.4",
 		"@types/diff": "^5.2.1",
@@ -411,6 +410,7 @@
 		"lint-staged": "^16.1.0",
 		"minimatch": "^3.0.3",
 		"npm-run-all": "^4.1.5",
+		"prebuild-install": "^7.1.3",
 		"protoc-gen-ts": "^0.8.7",
 		"proxyquire": "^2.1.3",
 		"rimraf": "^6.0.1",
@@ -426,12 +426,10 @@
 		"@anthropic-ai/vertex-sdk": "^0.6.4",
 		"@aws-sdk/client-bedrock-runtime": "^3.840.0",
 		"@aws-sdk/credential-providers": "^3.840.0",
-		"@sap-ai-sdk/ai-api": "^1.17.0",
-		"@sap-ai-sdk/orchestration": "^1.17.0",
 		"@bufbuild/protobuf": "^2.2.5",
 		"@cerebras/cerebras_cloud_sdk": "^1.35.0",
 		"@google-cloud/vertexai": "^1.9.3",
-		"@google/genai": "1.0.0",
+		"@google/genai": "^1.11.0",
 		"@grpc/grpc-js": "^1.9.15",
 		"@grpc/reflection": "^1.0.4",
 		"@mistralai/mistralai": "^1.5.0",
@@ -443,6 +441,8 @@
 		"@opentelemetry/sdk-trace-node": "^1.30.1",
 		"@opentelemetry/semantic-conventions": "^1.30.0",
 		"@playwright/test": "^1.53.2",
+		"@sap-ai-sdk/ai-api": "^1.17.0",
+		"@sap-ai-sdk/orchestration": "^1.17.0",
 		"@sentry/browser": "^9.12.0",
 		"@streamparser/json": "^0.0.22",
 		"@types/uuid": "^10.0.0",
@@ -479,7 +479,7 @@
 		"p-timeout": "^6.1.4",
 		"p-wait-for": "^5.0.2",
 		"pdf-parse": "^1.1.1",
-		"posthog-node": "^4.8.1",
+		"posthog-node": "^5.8.0",
 		"puppeteer-chromium-resolver": "^23.0.0",
 		"puppeteer-core": "^23.4.0",
 		"reconnecting-eventsource": "^1.6.4",

proto/cline/account.proto

@@ -38,6 +38,9 @@ service AccountService {
   rpc setUserOrganization(UserOrganizationUpdateRequest) returns (Empty);
 
   rpc openrouterAuthClicked(EmptyRequest) returns (Empty);
+
+  // Returns a link the webview can use to redirect back to the user's IDE.
+  rpc getRedirectUrl(EmptyRequest) returns (String);
 }
 
 message AuthStateChangedRequest {

proto/cline/browser.proto

@@ -2,6 +2,7 @@ syntax = "proto3";
 
 package cline;
 import "cline/common.proto";
+import "cline/state.proto";
 option java_package = "bot.cline.proto";
 option java_multiple_files = true;
 
@@ -10,7 +11,6 @@ service BrowserService {
   rpc testBrowserConnection(StringRequest) returns (BrowserConnection);
   rpc discoverBrowser(EmptyRequest) returns (BrowserConnection);
   rpc getDetectedChromePath(EmptyRequest) returns (ChromePath);
-  rpc updateBrowserSettings(UpdateBrowserSettingsRequest) returns (Boolean);
   rpc relaunchChromeDebugMode(EmptyRequest) returns (String);
 }
 
@@ -31,11 +31,6 @@ message ChromePath {
   bool is_bundled = 2;
 }
 
-message Viewport {
-  int32 width = 1;
-  int32 height = 2;
-}
-
 message BrowserSettings {
   Viewport viewport = 1;
   optional string remote_browser_host = 2;

proto/cline/common.proto

@@ -8,19 +8,16 @@ message Metadata {
 }
 
 message EmptyRequest {
-  Metadata metadata = 1;
 }
 
 message Empty {
 }
 
 message StringRequest {
-  Metadata metadata = 1;
   string value = 2;
 }
 
 message StringArrayRequest {
-  Metadata metadata = 1;
   repeated string value = 2;
 }
 
@@ -29,7 +26,6 @@ message String {
 }
 
 message Int64Request {
-  Metadata metadata = 1;
   int64 value = 2;
 }
 
@@ -38,7 +34,6 @@ message Int64 {
 }
 
 message BytesRequest {
-  Metadata metadata = 1;
   bytes value = 2;
 }
 
@@ -47,7 +42,6 @@ message Bytes {
 }
 
 message BooleanRequest {
-  Metadata metadata = 1;
   bool value = 2;
 }
 

proto/cline/models.proto

@@ -50,20 +50,20 @@ message LanguageModelChatSelector {
 
 // Price tier for tiered pricing models
 message PriceTier {
-  int32 token_limit = 1;  // Upper limit (inclusive) of input tokens for this price
+  int64 token_limit = 1;  // Upper limit (inclusive) of input tokens for this price
   double price = 2;       // Price per million tokens for this tier
 }
 
 // Thinking configuration for models that support thinking/reasoning
 message ThinkingConfig {
-  optional int32 max_budget = 1;                    // Max allowed thinking budget tokens
+  optional int64 max_budget = 1;                    // Max allowed thinking budget tokens
   optional double output_price = 2;                 // Output price per million tokens when budget > 0
   repeated PriceTier output_price_tiers = 3;        // Optional: Tiered output price when budget > 0
 }
 
 // Model tier for tiered pricing structures
 message ModelTier {
-  int32 context_window = 1;
+  int64 context_window = 1;
   optional double input_price = 2;
   optional double output_price = 3;
   optional double cache_writes_price = 4;
@@ -108,9 +108,16 @@ message SapAiCoreModelsRequest {
   string resource_group = 6;
 }
 
+// SAP AI Core model with deployment information
+message SapAiCoreModelDeployment {
+  string model_name = 1;
+  string deployment_id = 2;
+}
+
+
 // Response for SAP AI Core models with orchestration availability
 message SapAiCoreModelsResponse {
-  repeated string model_names = 1;
+  repeated SapAiCoreModelDeployment deployments = 1;
   bool orchestration_available = 2;
 }
 
@@ -161,8 +168,8 @@ enum ApiProvider {
 
 // Model info for OpenAI-compatible models
 message OpenAiCompatibleModelInfo {
-  optional int32 max_tokens = 1;
-  optional int32 context_window = 2;
+  optional int64 max_tokens = 1;
+  optional int64 context_window = 2;
   optional bool supports_images = 3;
   bool supports_prompt_cache = 4;
   optional double input_price = 5;
@@ -179,8 +186,8 @@ message OpenAiCompatibleModelInfo {
 
 // Model info for LiteLLM models
 message LiteLLMModelInfo {
-  optional int32 max_tokens = 1;
-  optional int32 context_window = 2;
+  optional int64 max_tokens = 1;
+  optional int64 context_window = 2;
   optional bool supports_images = 3;
   bool supports_prompt_cache = 4;
   optional double input_price = 5;
@@ -232,8 +239,8 @@ message ModelsApiConfiguration {
   optional string requesty_base_url = 33;
   optional string together_api_key = 34;
   optional string fireworks_api_key = 35;
-  optional int32 fireworks_model_max_completion_tokens = 36;
-  optional int32 fireworks_model_max_tokens = 37;
+  optional int64 fireworks_model_max_completion_tokens = 36;
+  optional int64 fireworks_model_max_tokens = 37;
   optional string qwen_api_key = 38;
   optional string doubao_api_key = 39;
   optional string mistral_api_key = 40;
@@ -245,7 +252,7 @@ message ModelsApiConfiguration {
   optional string xai_api_key = 46;
   optional string sambanova_api_key = 47;
   optional string cerebras_api_key = 48;
-  optional int32 request_timeout_ms = 49;
+  optional int64 request_timeout_ms = 49;
   optional string sap_ai_core_client_id = 50;
   optional string sap_ai_core_client_secret = 51;
   optional string sap_ai_resource_group = 52;
@@ -273,7 +280,7 @@ message ModelsApiConfiguration {
   // Plan mode configurations
   optional ApiProvider plan_mode_api_provider = 100;
   optional string plan_mode_api_model_id = 101;
-  optional int32 plan_mode_thinking_budget_tokens = 102;
+  optional int64 plan_mode_thinking_budget_tokens = 102;
   optional string plan_mode_reasoning_effort = 103;
   optional LanguageModelChatSelector plan_mode_vs_code_lm_model_selector = 104;
   optional bool plan_mode_aws_bedrock_custom_selected = 105;
@@ -291,21 +298,23 @@ message ModelsApiConfiguration {
   optional string plan_mode_together_model_id = 117;
   optional string plan_mode_fireworks_model_id = 118;
   optional string plan_mode_sap_ai_core_model_id = 119;
-  optional string plan_mode_groq_model_id = 120;
-  optional OpenRouterModelInfo plan_mode_groq_model_info = 121;
-  optional string plan_mode_hugging_face_model_id = 122;
-  optional OpenRouterModelInfo plan_mode_hugging_face_model_info = 123;
-  optional string plan_mode_huawei_cloud_maas_model_id = 124;
-  optional OpenRouterModelInfo plan_mode_huawei_cloud_maas_model_info = 125; 
-  optional string plan_mode_baseten_model_id = 126;
-  optional OpenRouterModelInfo plan_mode_baseten_model_info = 127;
-  optional string plan_mode_vercel_ai_gateway_model_id = 128;
-  optional OpenRouterModelInfo plan_mode_vercel_ai_gateway_model_info = 129;
+  optional string plan_mode_sap_ai_core_deployment_id = 120;
+  optional string plan_mode_groq_model_id = 121;
+  optional OpenRouterModelInfo plan_mode_groq_model_info = 122;
+  optional string plan_mode_hugging_face_model_id = 123;
+  optional OpenRouterModelInfo plan_mode_hugging_face_model_info = 124;
+  optional string plan_mode_huawei_cloud_maas_model_id = 125;
+  optional OpenRouterModelInfo plan_mode_huawei_cloud_maas_model_info = 126; 
+  optional string plan_mode_baseten_model_id = 127;
+  optional OpenRouterModelInfo plan_mode_baseten_model_info = 128;
+  optional string plan_mode_vercel_ai_gateway_model_id = 129;
+  optional OpenRouterModelInfo plan_mode_vercel_ai_gateway_model_info = 130;
+
 
   // Act mode configurations
   optional ApiProvider act_mode_api_provider = 200;
   optional string act_mode_api_model_id = 201;
-  optional int32 act_mode_thinking_budget_tokens = 202;
+  optional int64 act_mode_thinking_budget_tokens = 202;
   optional string act_mode_reasoning_effort = 203;
   optional LanguageModelChatSelector act_mode_vs_code_lm_model_selector = 204;
   optional bool act_mode_aws_bedrock_custom_selected = 205;
@@ -323,16 +332,15 @@ message ModelsApiConfiguration {
   optional string act_mode_together_model_id = 217;
   optional string act_mode_fireworks_model_id = 218;
   optional string act_mode_sap_ai_core_model_id = 219;
-  optional string act_mode_groq_model_id = 220;
-  optional OpenRouterModelInfo act_mode_groq_model_info = 221;
-  optional string act_mode_hugging_face_model_id = 222;
-  optional OpenRouterModelInfo act_mode_hugging_face_model_info = 223;
-  optional string act_mode_huawei_cloud_maas_model_id = 224;
-  optional OpenRouterModelInfo act_mode_huawei_cloud_maas_model_info = 225;
-  optional string act_mode_baseten_model_id = 226;
-  optional OpenRouterModelInfo act_mode_baseten_model_info = 227;
-  optional string act_mode_vercel_ai_gateway_model_id = 228;
-  optional OpenRouterModelInfo act_mode_vercel_ai_gateway_model_info = 229;
-
-  repeated string favorited_model_ids = 300;
+  optional string act_mode_sap_ai_core_deployment_id = 220;
+  optional string act_mode_groq_model_id = 221;
+  optional OpenRouterModelInfo act_mode_groq_model_info = 222;
+  optional string act_mode_hugging_face_model_id = 223;
+  optional OpenRouterModelInfo act_mode_hugging_face_model_info = 224;
+  optional string act_mode_huawei_cloud_maas_model_id = 225;
+  optional OpenRouterModelInfo act_mode_huawei_cloud_maas_model_info = 226;
+  optional string act_mode_baseten_model_id = 227;
+  optional OpenRouterModelInfo act_mode_baseten_model_info = 228;
+  optional string act_mode_vercel_ai_gateway_model_id = 229;
+  optional OpenRouterModelInfo act_mode_vercel_ai_gateway_model_info = 230;
 }

proto/cline/state.proto

@@ -1,6 +1,7 @@
 syntax = "proto3";
 package cline;
 import "cline/common.proto";
+import "cline/models.proto";
 option java_package = "bot.cline.proto";
 option java_multiple_files = true;
 
@@ -8,7 +9,6 @@ service StateService {
   rpc getLatestState(EmptyRequest) returns (State);
   rpc updateTerminalConnectionTimeout(UpdateTerminalConnectionTimeoutRequest) returns (UpdateTerminalConnectionTimeoutResponse);
   rpc updateTerminalReuseEnabled(BooleanRequest) returns (Empty);
-  rpc updateDefaultTerminalProfile(StringRequest) returns (TerminalProfileUpdateResponse);
   rpc getAvailableTerminalProfiles(EmptyRequest) returns (TerminalProfiles);
   rpc subscribeToState(EmptyRequest) returns (stream State);
   rpc toggleFavoriteModel(StringRequest) returns (Empty);
@@ -56,6 +56,7 @@ enum OpenaiReasoningEffort {
   LOW = 0;
   MEDIUM = 1;
   HIGH = 2;
+  MINIMAL = 3;
 }
 
 enum McpDisplayMode {
@@ -106,6 +107,16 @@ message TelemetrySettingRequest {
   TelemetrySettingEnum setting = 2;
 }
 
+// Browser settings for UpdateSettingsRequest
+message BrowserSettingsUpdate {
+  optional Viewport viewport = 1;
+  optional string remote_browser_host = 2;
+  optional bool remote_browser_enabled = 3;
+  optional string chrome_executable_path = 4;
+  optional bool disable_tool_use = 5;
+  optional string custom_args = 6;
+}
+
 // Message for updating settings
 message UpdateSettingsRequest {
   Metadata metadata = 1;
@@ -126,6 +137,9 @@ message UpdateSettingsRequest {
   optional FocusChainSettings focus_chain_settings = 17;
   optional bool use_auto_condense = 18;
   optional string custom_prompt = 19;
+  optional BrowserSettingsUpdate browser_settings = 20;
+  optional string default_terminal_profile = 21;
+  optional bool yolo_mode_toggled = 22;
 }
 
 // Complete API Configuration message
@@ -137,10 +151,10 @@ message ApiConfiguration {
   optional string lite_llm_base_url = 4;
   optional string lite_llm_api_key = 5;
   optional bool lite_llm_use_prompt_cache = 6;
-  optional string openai_headers = 7; // JSON string
+  map<string, string> open_ai_headers = 7;
   optional string anthropic_base_url = 8;
-  optional string openrouter_api_key = 9;
-  optional string openrouter_provider_sorting = 10;
+  optional string open_router_api_key = 9;
+  optional string open_router_provider_sorting = 10;
   optional string aws_access_key = 11;
   optional string aws_secret_key = 12;
   optional string aws_session_token = 13;
@@ -153,14 +167,14 @@ message ApiConfiguration {
   optional string claude_code_path = 20;
   optional string vertex_project_id = 21;
   optional string vertex_region = 22;
-  optional string openai_base_url = 23;
-  optional string openai_api_key = 24;
+  optional string open_ai_base_url = 23;
+  optional string open_ai_api_key = 24;
   optional string ollama_base_url = 25;
   optional string ollama_api_options_ctx_num = 26;
   optional string lm_studio_base_url = 27;
   optional string gemini_api_key = 28;
   optional string gemini_base_url = 29;
-  optional string openai_native_api_key = 30;
+  optional string open_ai_native_api_key = 30;
   optional string deep_seek_api_key = 31;
   optional string requesty_api_key = 32;
   optional string requesty_base_url = 33;
@@ -198,59 +212,56 @@ message ApiConfiguration {
   optional string dify_base_url = 65;
   
   // Plan mode configurations
-  optional string plan_mode_api_provider = 100;
+  optional ApiProvider plan_mode_api_provider = 100;
   optional string plan_mode_api_model_id = 101;
   optional int32 plan_mode_thinking_budget_tokens = 102;
   optional string plan_mode_reasoning_effort = 103;
-  optional string plan_mode_vscode_lm_model_selector = 104; // JSON string
+  optional LanguageModelChatSelector plan_mode_vs_code_lm_model_selector = 104;
   optional bool plan_mode_aws_bedrock_custom_selected = 105;
   optional string plan_mode_aws_bedrock_custom_model_base_id = 106;
-  optional string plan_mode_openrouter_model_id = 107;
-  optional string plan_mode_openrouter_model_info = 108; // JSON string
-  optional string plan_mode_openai_model_id = 109;
-  optional string plan_mode_openai_model_info = 110; // JSON string
+  optional string plan_mode_open_router_model_id = 107;
+  optional OpenRouterModelInfo plan_mode_open_router_model_info = 108;
+  optional string plan_mode_open_ai_model_id = 109;
+  optional OpenAiCompatibleModelInfo plan_mode_open_ai_model_info = 110;
   optional string plan_mode_ollama_model_id = 111;
   optional string plan_mode_lm_studio_model_id = 112;
   optional string plan_mode_lite_llm_model_id = 113;
-  optional string plan_mode_lite_llm_model_info = 114; // JSON string
+  optional LiteLLMModelInfo plan_mode_lite_llm_model_info = 114;
   optional string plan_mode_requesty_model_id = 115;
-  optional string plan_mode_requesty_model_info = 116; // JSON string
+  optional OpenRouterModelInfo plan_mode_requesty_model_info = 116;
   optional string plan_mode_together_model_id = 117;
   optional string plan_mode_fireworks_model_id = 118;
   optional string plan_mode_sap_ai_core_model_id = 119;
   optional string plan_mode_huawei_cloud_maas_model_id = 120;
-  optional string plan_mode_huawei_cloud_maas_model_info = 121;
+  optional OpenRouterModelInfo plan_mode_huawei_cloud_maas_model_info = 121;
   optional string plan_mode_vercel_ai_gateway_model_id = 122;
-  optional string plan_mode_vercel_ai_gateway_model_info = 123;
+  optional OpenRouterModelInfo plan_mode_vercel_ai_gateway_model_info = 123;
   
   // Act mode configurations
-  optional string act_mode_api_provider = 200;
+  optional ApiProvider act_mode_api_provider = 200;
   optional string act_mode_api_model_id = 201;
   optional int32 act_mode_thinking_budget_tokens = 202;
   optional string act_mode_reasoning_effort = 203;
-  optional string act_mode_vscode_lm_model_selector = 204; // JSON string
+  optional LanguageModelChatSelector act_mode_vs_code_lm_model_selector = 204;
   optional bool act_mode_aws_bedrock_custom_selected = 205;
   optional string act_mode_aws_bedrock_custom_model_base_id = 206;
-  optional string act_mode_openrouter_model_id = 207;
-  optional string act_mode_openrouter_model_info = 208; // JSON string
-  optional string act_mode_openai_model_id = 209;
-  optional string act_mode_openai_model_info = 210; // JSON string
+  optional string act_mode_open_router_model_id = 207;
+  optional OpenRouterModelInfo act_mode_open_router_model_info = 208;
+  optional string act_mode_open_ai_model_id = 209;
+  optional OpenAiCompatibleModelInfo act_mode_open_ai_model_info = 210;
   optional string act_mode_ollama_model_id = 211;
   optional string act_mode_lm_studio_model_id = 212;
   optional string act_mode_lite_llm_model_id = 213;
-  optional string act_mode_lite_llm_model_info = 214; // JSON string
+  optional LiteLLMModelInfo act_mode_lite_llm_model_info = 214;
   optional string act_mode_requesty_model_id = 215;
-  optional string act_mode_requesty_model_info = 216; // JSON string
+  optional OpenRouterModelInfo act_mode_requesty_model_info = 216;
   optional string act_mode_together_model_id = 217;
   optional string act_mode_fireworks_model_id = 218;
   optional string act_mode_sap_ai_core_model_id = 219;
   optional string act_mode_huawei_cloud_maas_model_id = 220;
-  optional string act_mode_huawei_cloud_maas_model_info = 221;
+  optional OpenRouterModelInfo act_mode_huawei_cloud_maas_model_info = 221;
   optional string act_mode_vercel_ai_gateway_model_id = 222;
-  optional string act_mode_vercel_ai_gateway_model_info = 223;
-  
-  // Favorited model IDs
-  repeated string favorited_model_ids = 300;
+  optional OpenRouterModelInfo act_mode_vercel_ai_gateway_model_info = 223;
 
   // Extension fields for Bedrock Api Keys
   optional string aws_authentication = 301;
@@ -268,6 +279,11 @@ message FocusChainSettings {
   int32 remind_cline_interval = 2;
 }
 
+message Viewport {
+  int32 width = 1;
+  int32 height = 2;
+}
+
 message UpdateTerminalConnectionTimeoutResponse {
   optional int32 timeout_ms = 1;
 }

proto/host/env.proto

@@ -17,7 +17,20 @@ service EnvService {
   // Returns a stable machine identifier for telemetry distinctId purposes.
   rpc getMachineId(cline.EmptyRequest) returns (cline.String);
 
+  // Returns the name and version of the host IDE or environment.
   rpc getHostVersion(cline.EmptyRequest) returns (GetHostVersionResponse);
+
+  // Returns a URI that will redirect to the host environment.
+  // e.g. vscode://saoudrizwan.claude-dev, idea://, pycharm://, etc. 
+  // If the host does not support URIs it should return empty.
+  rpc getIdeRedirectUri(cline.EmptyRequest) returns (cline.String);
+
+  // Returns the telemetry settings of the host environment. This may return UNSUPPORTED
+  // if the host does not specify telemetry settings for the plugin.
+  rpc getTelemetrySettings(cline.EmptyRequest) returns (GetTelemetrySettingsResponse);
+
+  // Returns events when the telemetry settings change.
+  rpc subscribeToTelemetrySettings(cline.EmptyRequest) returns (stream TelemetrySettingsEvent);
 }
 
 message GetHostVersionResponse {
@@ -26,3 +39,16 @@ message GetHostVersionResponse {
   // The version of the host platform, e.g. 1.103.0
   optional string version = 2;
 }
+
+enum Setting {
+  UNSUPPORTED = 0; // This host does not support this setting.
+  ENABLED = 1;
+  DISABLED = 2;
+}
+message GetTelemetrySettingsResponse {
+  Setting is_enabled = 1;
+}
+
+message TelemetrySettingsEvent {
+  Setting is_enabled = 1; 
+}

proto/host/watch.proto

@@ -1,36 +0,0 @@
-syntax = "proto3";
-
-package host;
-option java_package = "bot.cline.host.proto";
-option java_multiple_files = true;
-
-import "cline/common.proto";
-
-/** 
- * The watch service is only here as example of a streaming rpc in the host bridge. 
- * This being replaced with a native JS file watcher.
- */
-// WatchService provides methods for watching files in the IDE
-service WatchService {
-  // Subscribe to file changes
-  rpc subscribeToFile(SubscribeToFileRequest) returns (stream FileChangeEvent);
-}
-
-// Request to subscribe to file changes
-message SubscribeToFileRequest {
-  cline.Metadata metadata = 1;
-  string path = 2;
-}
-
-// Event representing a file change
-message FileChangeEvent {
-  enum ChangeType {
-    CREATED = 0;
-    CHANGED = 1;
-    DELETED = 2;
-  }
-  
-  string path = 1;
-  ChangeType type = 2;
-  string content = 3; // Optional content of the file after change
-}

proto/host/window.proto

@@ -4,8 +4,6 @@ package host;
 option java_package = "bot.cline.host.proto";
 option java_multiple_files = true;
 
-import "cline/common.proto";
-
 // Provides methods for working with IDE windows and editors.
 service WindowService {
   // Opens a text document in the IDE editor and returns editor information.
@@ -40,7 +38,6 @@ service WindowService {
 }
 
 message ShowTextDocumentRequest {
-  cline.Metadata metadata = 1;
   string path = 2;
   optional ShowTextDocumentOptions options = 3;
 }
@@ -59,7 +56,6 @@ message TextEditorInfo {
 }
 
 message ShowOpenDialogueRequest {
-  cline.Metadata metadata = 1;
   optional bool can_select_many = 2;
   optional string open_label = 3;
   optional ShowOpenDialogueFilterOption filters = 4;

proto/host/workspace.proto

@@ -18,14 +18,15 @@ service WorkspaceService {
 
   // Get diagnostics from the workspace.
   rpc getDiagnostics(GetDiagnosticsRequest) returns (GetDiagnosticsResponse);
-  // Returns workspace items (files/folders) matching a query for mention autocomplete
-  rpc searchWorkspaceItems(SearchWorkspaceItemsRequest) returns (SearchWorkspaceItemsResponse);
 
   // Makes the problems panel/pane visible in the IDE and focuses it.
   rpc openProblemsPanel(OpenProblemsPanelRequest) returns (OpenProblemsPanelResponse);
 
   // Opens the IDE file explorer panel and selects a file or directory.
   rpc openInFileExplorerPanel(OpenInFileExplorerPanelRequest) returns (OpenInFileExplorerPanelResponse); 
+
+  // Opens and focuses the Cline sidebar panel in the host IDE.
+  rpc openClineSidebarPanel(OpenClineSidebarPanelRequest) returns (OpenClineSidebarPanelResponse);
 }
 
 message GetWorkspacePathsRequest {
@@ -86,3 +87,7 @@ message OpenInFileExplorerPanelRequest {
   string path = 1;
 }
 message OpenInFileExplorerPanelResponse {}
+
+// Request/response for opening the Cline sidebar
+message OpenClineSidebarPanelRequest {}
+message OpenClineSidebarPanelResponse {}

scripts/build-proto.mjs

@@ -10,7 +10,6 @@ import * as path from "path"
 import { rmrf } from "./file-utils.mjs"
 import { main as generateHostBridgeClient } from "./generate-host-bridge-client.mjs"
 import { main as generateProtoBusSetup } from "./generate-protobus-setup.mjs"
-import { loadProtoDescriptorSet } from "./proto-utils.mjs"
 
 const require = createRequire(import.meta.url)
 const PROTOC = path.join(require.resolve("grpc-tools"), "../bin/protoc")
@@ -31,14 +30,13 @@ const TS_PROTO_OPTIONS = [
 	"esModuleInterop=true",
 	"outputServices=generic-definitions", // output generic ServiceDefinitions
 	"outputIndex=true", // output an index file for each package which exports all protos in the package.
-	"useOptionals=messages", // Message fields are optional, scalars are not.
+	"useOptionals=none", // scalar and message fields are required unless they are marked as optional.
 	"useDate=false", // Timestamp fields will not be automatically converted to Date.
 ]
 
 async function main() {
 	await cleanup()
 	await compileProtos()
-	await checkProtos()
 	await generateProtoBusSetup()
 	await generateHostBridgeClient()
 }
@@ -59,7 +57,7 @@ async function compileProtos() {
 
 	tsProtoc(TS_OUT_DIR, protoFiles, TS_PROTO_OPTIONS)
 	// grpc-js is used to generate service impls for the ProtoBus service.
-	tsProtoc(GRPC_JS_OUT_DIR, protoFiles, ["outputServices=grpc-js,outputClientImpl=false", ...TS_PROTO_OPTIONS])
+	tsProtoc(GRPC_JS_OUT_DIR, protoFiles, ["outputServices=grpc-js", ...TS_PROTO_OPTIONS])
 	// nice-js is used for the Host Bridge client impls because it uses promises.
 	tsProtoc(NICE_JS_OUT_DIR, protoFiles, ["outputServices=nice-grpc,useExactTypes=false", ...TS_PROTO_OPTIONS])
 
@@ -187,51 +185,6 @@ function checkAppleSiliconCompatibility() {
 	}
 }
 
-const int64TypeNames = ["TYPE_INT64", "TYPE_UINT64", "TYPE_SINT64", "TYPE_FIXED64", "TYPE_SFIXED64"]
-
-async function checkProtos() {
-	const proto = await loadProtoDescriptorSet()
-	const int64Fields = []
-
-	for (const [packageName, packageDef] of Object.entries(proto)) {
-		for (const [messageName, def] of Object.entries(packageDef)) {
-			// Skip service definitions
-			if (def && typeof def === "object" && "service" in def) {
-				continue
-			}
-			// Check message fields
-			if (def && def.type && def.type.field) {
-				for (const field of def.type.field) {
-					if (int64TypeNames.includes(field.type)) {
-						const name = `${packageName}.${messageName}.${field.name}`
-						int64Fields.push({
-							name: name,
-							type: field.type,
-						})
-					}
-				}
-			}
-		}
-	}
-
-	if (int64Fields.length > 0) {
-		console.log(chalk.yellow(`\nWarning: Found ${int64Fields.length} fields using 64-bit integer types`))
-		for (const field of int64Fields) {
-			const typeNames = {
-				TYPE_INT64: "int64",
-				TYPE_UINT64: "uint64",
-				TYPE_SINT64: "sint64",
-				TYPE_FIXED64: "fixed64",
-				TYPE_SFIXED64: "sfixed64",
-			}
-			log_verbose(chalk.yellow(`  - ${field.name} (${typeNames[field.type]})`))
-		}
-		log_verbose(chalk.yellow("\nWARNING: 64-bit integer fields detected in proto definitions"))
-		log_verbose(chalk.yellow("JavaScript cannot safely represent integers larger than 2^53-1 (Number.MAX_SAFE_INTEGER)."))
-		log_verbose(chalk.yellow("Consider using string representation for large numbers or implementing BigInt support.\n"))
-	}
-}
-
 function log_verbose(s) {
 	if (process.argv.includes("-v") || process.argv.includes("--verbose")) {
 		console.log(s)

scripts/package-standalone.mjs

@@ -6,40 +6,102 @@ import fs from "fs"
 import { cp } from "fs/promises"
 import { glob } from "glob"
 import minimatch from "minimatch"
+import os from "os"
 import path from "path"
+import { rmrf } from "./file-utils.mjs"
 
 const BUILD_DIR = "dist-standalone"
+const BINARIES_DIR = `${BUILD_DIR}/binaries`
 const RUNTIME_DEPS_DIR = "standalone/runtime-files"
+const IS_DEBUG_BUILD = process.env.IS_DEBUG_BUILD === "true"
+
+// This should match the node version packaged with the JetBrains plugin.
+const TARGET_NODE_VERSION = "22.15.0"
+const TARGET_PLATFORMS = [
+	{ platform: "win32", arch: "x64", targetDir: "win-x64" },
+	{ platform: "darwin", arch: "x64", targetDir: "darwin-x64" },
+	{ platform: "darwin", arch: "arm64", targetDir: "darwin-arm64" },
+	{ platform: "linux", arch: "x64", targetDir: "linux-x64" },
+]
+const SUPPORTED_BINARY_MODULES = ["better-sqlite3"]
+
+const UNIVERSAL_BUILD = !process.argv.includes("-s")
+const IS_VERBOSE = process.argv.includes("-v") || process.argv.includes("--verbose")
 
 async function main() {
 	await installNodeDependencies()
+	if (UNIVERSAL_BUILD) {
+		console.log("Building universal package for all platforms...")
+		await packageAllBinaryDeps()
+	} else {
+		console.log(`Building package for ${os.platform()}-${os.arch()}...`)
+	}
 	await zipDistribution()
 }
 
 async function installNodeDependencies() {
+	// Clean modules from any previous builds
+	await rmrf(path.join(BUILD_DIR, "node_modules"))
+	await rmrf(path.join(BINARIES_DIR))
+
 	await cpr(RUNTIME_DEPS_DIR, BUILD_DIR)
 
 	console.log("Running npm install in distribution directory...")
-	const cwd = process.cwd()
-	process.chdir(BUILD_DIR)
+	execSync("npm install", { stdio: "inherit", cwd: BUILD_DIR })
 
-	try {
-		execSync("npm install", { stdio: "inherit" })
-		// Move the vscode directory into node_modules.
-		// It can't be installed using npm because it will create a symlink which cannot be unzipped correctly on windows.
-		fs.renameSync("vscode", path.join("node_modules", "vscode"))
-	} catch (error) {
-		console.error("Error during setup:", error)
+	// Move the vscode directory into node_modules.
+	// It can't be installed using npm because it will create a symlink which cannot be unzipped correctly on windows.
+	fs.renameSync(`${BUILD_DIR}/vscode`, `${BUILD_DIR}/node_modules/vscode`)
+}
+
+/**
+ * Downloads prebuilt binaries for each platform for the modules that include binaries. It uses `npx prebuild-install`
+ * to download the binary.
+ *
+ * The modules are downloaded to dist-standalone/binaries/{os}-{platform}/.
+ * When cline-core is installed, the installer should use the correct module for the current platform.
+ */
+async function packageAllBinaryDeps() {
+	// Check for native .node modules.
+	const allNativeModules = await glob("**/*.node", { cwd: path.join(BUILD_DIR, "node_modules"), nodir: true })
+	const isAllowed = (path) => SUPPORTED_BINARY_MODULES.some((allowed) => path.includes(allowed))
+	const blocked = allNativeModules.filter((x) => !isAllowed(x))
+
+	if (blocked.length > 0) {
+		console.error(`Error: Native node modules cannot be included in the standalone distribution:\n\n${blocked.join("\n")}`)
+		console.error(
+			"\nThese modules must support prebuilt-install and be added to the supported list in scripts/package-standalone.mjs",
+		)
 		process.exit(1)
-	} finally {
-		process.chdir(cwd)
 	}
 
-	// Check for native .node modules.
-	const nativeModules = await glob("**/*.node", { cwd: BUILD_DIR, nodir: true })
-	if (nativeModules.length > 0) {
-		console.error("Native node modules cannot be included in the standalone distribution:\n", nativeModules.join("\n"))
-		process.exit(1)
+	for (const module of SUPPORTED_BINARY_MODULES) {
+		console.log(`Installing binaries for ${module}...`)
+		const src = path.join(BUILD_DIR, "node_modules", module)
+		if (!fs.existsSync(src)) {
+			console.warn(`Warning: Trying to install binaries for the module '${module}', but it is not being used by cline.`)
+			continue
+		}
+
+		for (const { platform, arch, targetDir } of TARGET_PLATFORMS) {
+			const binaryDir = `${BINARIES_DIR}/${targetDir}/node_modules`
+			fs.mkdirSync(binaryDir, { recursive: true })
+
+			// Copy the module from the build dir
+			const dest = path.join(binaryDir, module)
+			await cpr(src, dest)
+
+			// Download the binary libs
+			const v = IS_VERBOSE ? "--verbose" : ""
+			const cmd = `npx prebuild-install --platform=${platform} --arch=${arch} --target=${TARGET_NODE_VERSION} ${v}`
+			log_verbose(`${module}: ${cmd}`)
+			execSync(cmd, { cwd: dest, stdio: "inherit" })
+			log_verbose("")
+		}
+		// Remove the original module with the host platform binaries installed directly into node_modules.
+		log_verbose(`Cleaning up host version of ${module}`)
+		await rmrf(src)
+		log_verbose("")
 	}
 }
 
@@ -47,10 +109,13 @@ async function zipDistribution() {
 	// Zip the build directory (excluding any pre-existing output zip).
 	const zipPath = path.join(BUILD_DIR, "standalone.zip")
 	const output = fs.createWriteStream(zipPath)
-	const archive = archiver("zip", { zlib: { level: 3 } })
+	const startTime = Date.now()
+	const archive = archiver("zip", { zlib: { level: 6 } })
 
 	output.on("close", () => {
-		console.log(`Created ${zipPath} (${(archive.pointer() / 1024 / 1024).toFixed(1)} MB)`)
+		const endTime = Date.now()
+		const duration = (endTime - startTime) / 1000
+		console.log(`Created ${zipPath} (${(archive.pointer() / 1024 / 1024).toFixed(1)} MB) in ${duration.toFixed(2)} seconds`)
 	})
 	archive.on("warning", (err) => {
 		console.warn(`Warning: ${err}`)
@@ -73,7 +138,7 @@ async function zipDistribution() {
 	// Add the whole cline directory under "extension", except the for the ignored files.
 	archive.directory(process.cwd(), "extension", (entry) => {
 		if (isIgnored(entry.name)) {
-			log_verbose("Ignoring", entry.name)
+			//log_verbose("Ignoring", entry.name)
 			return false
 		}
 		return entry
@@ -145,7 +210,7 @@ function createIsIgnored(standaloneIgnores) {
 	let allIgnore = [...defaultIgnore, ...expandedIgnore, ...standaloneIgnores]
 
 	// Map files need to be included in the debug build. Remove .map ignores when IS_DEBUG_BUILD is set
-	if (process.env.IS_DEBUG_BUILD) {
+	if (IS_DEBUG_BUILD) {
 		allIgnore = allIgnore.filter((pattern) => !pattern.endsWith(".map"))
 		console.log("Debug build: Including .map files in package")
 	}
@@ -167,6 +232,7 @@ function createIsIgnored(standaloneIgnores) {
 
 /* cp -r */
 async function cpr(source, dest) {
+	log_verbose(`Copying ${source} -> ${dest}`)
 	await cp(source, dest, {
 		recursive: true,
 		preserveTimestamps: true,
@@ -175,7 +241,7 @@ async function cpr(source, dest) {
 }
 
 function log_verbose(...args) {
-	if (process.argv.includes("-v") || process.argv.includes("--verbose")) {
+	if (IS_VERBOSE) {
 		console.log(...args)
 	}
 }

scripts/publish-nightly.mjs

@@ -0,0 +1,377 @@
+#!/usr/bin/env node
+
+/**
+ * Nightly publish script for VS Code extension
+ * Converts package.json to testing version, packages, publishes, and restores
+ *
+ * This script:
+ * 1. Backs up the original package.json
+ * 2. Updates package.json with:
+ *    - New version (major.minor.timestamp format)
+ *    - Changes name to "cline-nightly"
+ *    - Changes displayName to "Cline (Nightly)"
+ * 3. Packages the extension as a .vsix file
+ * 4. Publishes to VS Code Marketplace (if VSCE_PAT is set)
+ * 5. Publishes to OpenVSX Registry (if OVSX_PAT is set)
+ * 6. Restores the original package.json
+ *
+ * Usage:
+ *   npm run publish:marketplace:nightly
+ *   npm run publish:marketplace:nightly -- --dry-run
+ *
+ * Environment variables:
+ *   VSCE_PAT  - Personal Access Token for VS Code Marketplace
+ *   OVSX_PAT  - Personal Access Token for OpenVSX Registry
+ *
+ * Dependencies:
+ *   - vsce (VS Code Extension Manager)
+ *   - ovsx (OpenVSX CLI)
+ */
+
+import { execFileSync, execSync } from "node:child_process"
+import fs from "node:fs"
+import path from "node:path"
+import { fileURLToPath } from "node:url"
+
+// Get __dirname equivalent in ES modules
+const __filename = fileURLToPath(import.meta.url)
+const __dirname = path.dirname(__filename)
+
+// ANSI color codes for console output
+const colors = {
+	reset: "\x1b[0m",
+	red: "\x1b[31m",
+	green: "\x1b[32m",
+	yellow: "\x1b[33m",
+}
+
+// Logging utilities
+const log = {
+	info: (msg) => console.log(`${colors.green}[INFO]${colors.reset} ${msg}`),
+	warn: (msg) => console.log(`${colors.yellow}[WARN]${colors.reset} ${msg}`),
+	error: (msg) => console.error(`${colors.red}[ERROR]${colors.reset} ${msg}`),
+}
+
+// Configuration
+const config = {
+	// The name and display name for the nightly version
+	nightlyName: "cline-nightly",
+	nightlyDisplayName: "Cline (Nightly)",
+	projectRoot: path.join(__dirname, ".."),
+	get packageJsonPath() {
+		return path.join(this.projectRoot, "package.json")
+	},
+	get packageBackupPath() {
+		return path.join(this.projectRoot, "package.json.backup")
+	},
+	get distDir() {
+		return path.join(this.projectRoot, "dist")
+	},
+	get vsixPath() {
+		return path.join(this.distDir, "cline-nightly.vsix")
+	},
+}
+
+// Utility class for managing the publish process
+class NightlyPublisher {
+	constructor() {
+		this.originalPackageJson = null
+		this.hasBackup = false
+	}
+
+	/**
+	 * Check if required dependencies are installed
+	 */
+	checkDependencies() {
+		const dependencies = [
+			{ name: "vsce", check: "vsce --version" },
+			{ name: "npx", check: "npx --version" },
+		]
+
+		const missing = []
+
+		for (const dep of dependencies) {
+			try {
+				execSync(dep.check, { stdio: "ignore" })
+			} catch {
+				missing.push(dep.name)
+			}
+		}
+
+		if (missing.length > 0) {
+			throw new Error(
+				`Missing required dependencies: ${missing.join(", ")}. Please install them before running this script.`,
+			)
+		}
+
+		log.info("All dependencies are installed")
+	}
+
+	/**
+	 * Check if a command exists
+	 */
+	commandExists(command) {
+		try {
+			execSync(`which ${command}`, { stdio: "ignore" })
+			return true
+		} catch {
+			return false
+		}
+	}
+
+	/**
+	 * Create backup of package.json
+	 */
+	backupPackageJson() {
+		if (!fs.existsSync(config.packageJsonPath)) {
+			throw new Error(`package.json not found at ${config.packageJsonPath}`)
+		}
+
+		log.info("Backing up original package.json")
+		this.originalPackageJson = fs.readFileSync(config.packageJsonPath, "utf-8")
+		fs.writeFileSync(config.packageBackupPath, this.originalPackageJson)
+		this.hasBackup = true
+	}
+
+	/**
+	 * Restore original package.json
+	 */
+	restorePackageJson() {
+		if (this.hasBackup && fs.existsSync(config.packageBackupPath)) {
+			log.info("Restoring original package.json")
+			fs.writeFileSync(config.packageJsonPath, this.originalPackageJson)
+			fs.unlinkSync(config.packageBackupPath)
+			this.hasBackup = false
+		}
+	}
+
+	/**
+	 * Generate new version with timestamp
+	 * Format: major.minor.timestamp
+	 */
+	generateVersion(currentVersion) {
+		// Extract major.minor from current version (e.g., "3.27.1" -> "3.27")
+		const versionParts = currentVersion.split(".")
+		if (versionParts.length < 2) {
+			throw new Error(`Invalid version format: ${currentVersion}`)
+		}
+
+		const major = versionParts[0]
+		const minor = versionParts[1]
+		const timestamp = Math.floor(Date.now() / 1000)
+
+		return `${major}.${minor}.${timestamp}`
+	}
+
+	/**
+	 * Update package.json with nightly configuration
+	 */
+	updatePackageJson() {
+		// Replace any occurrences cline. or claude-dev with nightly name
+		const rawContent = fs.readFileSync(config.packageJsonPath, "utf-8")
+		const content = rawContent.replaceAll("claude-dev", config.nightlyName).replaceAll('"cline.', `"${config.nightlyName}.`)
+
+		const pkg = JSON.parse(content)
+		const currentVersion = pkg.version
+
+		if (!currentVersion) {
+			throw new Error("Could not read version from package.json")
+		}
+
+		log.info(`Current version: ${currentVersion}`)
+
+		const newVersion = this.generateVersion(currentVersion)
+		log.info(`New version: ${newVersion}`)
+
+		// Update package.json fields
+		pkg.version = newVersion
+		pkg.name = config.nightlyName
+		pkg.displayName = config.nightlyDisplayName
+		pkg.contributes.viewsContainers.activitybar.title = config.nightlyDisplayName
+
+		// Save updated package.json
+		log.info("Updating package.json for nightly build")
+		fs.writeFileSync(config.packageJsonPath, JSON.stringify(pkg, null, "\t"))
+
+		return newVersion
+	}
+
+	/**
+	 * Package the extension
+	 */
+	packageExtension() {
+		// Ensure dist directory exists
+		if (!fs.existsSync(config.distDir)) {
+			fs.mkdirSync(config.distDir, { recursive: true })
+		}
+
+		log.info("Packaging extension")
+
+		const args = ["package", "--pre-release", "--no-update-package-json", "--no-git-tag-version", "--out", config.vsixPath]
+
+		try {
+			execFileSync("vsce", args, {
+				stdio: "inherit",
+				cwd: config.projectRoot,
+			})
+			log.info(`Package created: ${config.vsixPath}`)
+		} catch (error) {
+			throw new Error(`Failed to package extension: ${error.message}`)
+		}
+	}
+
+	/**
+	 * Publish to VS Code Marketplace
+	 */
+	publishToVSCodeMarketplace() {
+		const token = process.env.VSCE_PAT
+
+		if (!token) {
+			log.warn("VSCE_PAT not set, skipping VS Code Marketplace publish")
+			return false
+		}
+
+		log.info("Publishing to VS Code Marketplace")
+
+		const args = ["publish", "--pre-release", "--no-git-tag-version", "--packagePath", config.vsixPath]
+
+		try {
+			execFileSync("vsce", args, {
+				env: { ...process.env, VSCE_PAT: token },
+				stdio: "inherit",
+				cwd: config.projectRoot,
+			})
+			log.info("Successfully published to VS Code Marketplace")
+			return true
+		} catch (error) {
+			throw new Error(`Failed to publish to VS Code Marketplace: ${error.message}`)
+		}
+	}
+
+	/**
+	 * Publish to OpenVSX Registry
+	 */
+	publishToOpenVSX() {
+		const token = process.env.OVSX_PAT
+
+		if (!token) {
+			log.warn("OVSX_PAT not set, skipping OpenVSX Registry publish")
+			return false
+		}
+
+		log.info("Publishing to OpenVSX Registry")
+
+		const args = ["ovsx", "publish", "--pre-release", "--packagePath", config.vsixPath, "--pat", token]
+
+		try {
+			execFileSync("npx", args, {
+				stdio: "inherit",
+				cwd: config.projectRoot,
+			})
+			log.info("Successfully published to OpenVSX Registry")
+			return true
+		} catch (error) {
+			throw new Error(`Failed to publish to OpenVSX Registry: ${error.message}`)
+		}
+	}
+
+	/**
+	 * Main execution flow
+	 */
+	async run(isDryRun = false) {
+		try {
+			log.info(`Starting nightly publish process${isDryRun ? " (dry run)" : ""}`)
+
+			// Step 1: Check dependencies
+			this.checkDependencies()
+
+			// Step 2: Backup package.json
+			this.backupPackageJson()
+
+			// Step 3: Update package.json
+			const newVersion = this.updatePackageJson()
+
+			// Step 4: Package extension
+			this.packageExtension()
+
+			// Step 5: Publish to marketplaces (skip if dry run)
+			let vsCodePublished = false
+			let openVSXPublished = false
+
+			if (isDryRun) {
+				log.info("Dry run mode: Skipping marketplace publishing")
+			} else {
+				vsCodePublished = this.publishToVSCodeMarketplace()
+				openVSXPublished = this.publishToOpenVSX()
+			}
+
+			// Summary
+			log.info(`Nightly publish process completed successfully${isDryRun ? " (dry run)" : ""}`)
+			log.info(`Package created for v${newVersion}: ${config.vsixPath}`)
+
+			if (!isDryRun && !vsCodePublished && !openVSXPublished) {
+				log.warn("Extension was packaged but not published to any marketplace")
+				log.warn("Set VSCE_PAT and/or OVSX_PAT environment variables to enable publishing")
+			}
+		} catch (error) {
+			log.error(`Publish failed: ${error.message}`)
+			process.exit(1)
+		} finally {
+			// Always restore package.json
+			this.restorePackageJson()
+		}
+	}
+}
+
+// Handle cleanup on process exit
+const publisher = new NightlyPublisher()
+
+process.on("exit", () => {
+	publisher.restorePackageJson()
+})
+
+process.on("SIGINT", () => {
+	log.info("\nInterrupted, cleaning up...")
+	publisher.restorePackageJson()
+	process.exit(130)
+})
+
+process.on("SIGTERM", () => {
+	log.info("\nTerminated, cleaning up...")
+	publisher.restorePackageJson()
+	process.exit(143)
+})
+
+// Parse command line arguments
+const args = process.argv.slice(2)
+const isDryRun = args.includes("--dry-run") || args.includes("-n")
+const showHelp = args.includes("--help") || args.includes("-h")
+
+if (showHelp) {
+	console.log(`
+Nightly publish script for VS Code extension
+
+Usage:
+  npm run publish:marketplace:nightly [options]
+
+Options:
+  --dry-run, -n    Run without actually publishing (package only)
+  --help, -h       Show this help message
+
+Environment variables:
+  VSCE_PAT         Personal Access Token for VS Code Marketplace
+  OVSX_PAT         Personal Access Token for OpenVSX Registry
+
+Examples:
+  npm run publish:marketplace:nightly                    # Full publish
+  npm run publish:marketplace:nightly  -- --dry-run      # Package only
+  VSCE_PAT="token" npm run publish:marketplace:nightly   # Publish to VS Code only
+`)
+	process.exit(0)
+}
+
+// Run the publisher
+publisher.run(isDryRun).catch((error) => {
+	log.error(error.message)
+	process.exit(1)
+})

scripts/test-hostbridge-server.ts

@@ -3,7 +3,11 @@ import * as grpc from "@grpc/grpc-js"
 import { ReflectionService } from "@grpc/reflection"
 import * as health from "grpc-health-check"
 import * as os from "os"
-import { host } from "src/generated/grpc-js/index"
+import { type DiffServiceServer, DiffServiceService } from "../src/generated/grpc-js/host/diff"
+import { type EnvServiceServer, EnvServiceService } from "../src/generated/grpc-js/host/env"
+import { type TestingServiceServer, TestingServiceService } from "../src/generated/grpc-js/host/testing"
+import { type WindowServiceServer, WindowServiceService } from "../src/generated/grpc-js/host/window"
+import { type WorkspaceServiceServer, WorkspaceServiceService } from "../src/generated/grpc-js/host/workspace"
 import { getPackageDefinition } from "./proto-utils.mjs"
 
 export async function startTestHostBridgeServer() {
@@ -14,11 +18,11 @@ export async function startTestHostBridgeServer() {
 	healthImpl.addToServer(server)
 
 	// Add host bridge services using the mock implementations
-	server.addService(host.WorkspaceServiceService, createMockService<host.WorkspaceServiceServer>("WorkspaceService"))
-	server.addService(host.WindowServiceService, createMockService<host.WindowServiceServer>("WindowService"))
-	server.addService(host.EnvServiceService, createMockService<host.EnvServiceServer>("EnvService"))
-	server.addService(host.DiffServiceService, createMockService<host.DiffServiceServer>("DiffService"))
-	server.addService(host.WatchServiceService, createMockService<host.WatchServiceServer>("WatchService"))
+	server.addService(WorkspaceServiceService, createMockService<WorkspaceServiceServer>("WorkspaceService"))
+	server.addService(WindowServiceService, createMockService<WindowServiceServer>("WindowService"))
+	server.addService(EnvServiceService, createMockService<EnvServiceServer>("EnvService"))
+	server.addService(DiffServiceService, createMockService<DiffServiceServer>("DiffService"))
+	server.addService(TestingServiceService, createMockService<TestingServiceServer>("TestingService"))
 
 	// Load package definition for reflection service
 	const packageDefinition = await getPackageDefinition()
@@ -58,8 +62,9 @@ function createMockService<T extends grpc.UntypedServiceImplementation>(serviceN
 				// Special cases that need specific return values
 				switch (prop) {
 					case "getWorkspacePaths":
+						const workspaceDir = process.env.TEST_HOSTBRIDGE_WORKSPACE_DIR || "/test-workspace"
 						callback(null, {
-							paths: ["/test-workspace"],
+							paths: [workspaceDir],
 						})
 						return
 
@@ -69,6 +74,12 @@ function createMockService<T extends grpc.UntypedServiceImplementation>(serviceN
 						})
 						return
 
+					case "getTelemetrySettings":
+						callback(null, {
+							isEnabled: 2, // Setting.DISABLED
+						})
+						return
+
 					case "clipboardReadText":
 						callback(null, {
 							value: "",
@@ -115,8 +126,8 @@ function createMockService<T extends grpc.UntypedServiceImplementation>(serviceN
 						})
 						return
 
-					// For streaming methods (like subscribeToFile)
-					case "subscribeToFile":
+					// For streaming methods (like subscribeToTelemetrySettings)
+					case "subscribeToTelemetrySettings":
 						// Just end the stream immediately
 						call.end()
 						return

scripts/test-standalone-core-api-server.ts

@@ -0,0 +1,178 @@
+#!/usr/bin/env npx tsx
+
+/**
+ * Simple Cline gRPC Server
+ *
+ * This script provides a minimal way to run the Cline core gRPC service
+ * without requiring the full installation, while automatically mocking all external services. Simply run:
+ *
+ *   # One-time setup (generates protobuf files)
+ *	 npm run compile-standalone
+ *   npm run test:sca-server
+ *
+ * The following components are started automatically:
+ *   1. HostBridge test server
+ *   2. ClineApiServerMock (mock implementation of the Cline API)
+ *   3. AuthServiceMock (activated if E2E_TEST="true")
+ *
+ * Environment Variables for Customization:
+ *   PROJECT_ROOT - Override project root directory (default: parent of scripts dir)
+ *   CLINE_DIST_DIR - Override distribution directory (default: PROJECT_ROOT/dist-standalone)
+ *   CLINE_CORE_FILE - Override core file name (default: cline-core.js)
+ *   PROTOBUS_PORT - gRPC server port (default: 26040)
+ *   HOSTBRIDGE_PORT - HostBridge server port (default: 26041)
+ *   WORKSPACE_DIR - Working directory (default: current directory)
+ *   E2E_TEST - Enable E2E test mode (default: true)
+ *   CLINE_ENVIRONMENT - Environment setting (default: local)
+ *
+ * Ideal for local development, testing, or lightweight E2E scenarios.
+ */
+
+import { mkdtempSync, rmSync } from "node:fs"
+import * as os from "node:os"
+import { ChildProcess, execSync, spawn } from "child_process"
+import * as fs from "fs"
+import * as path from "path"
+import { ClineApiServerMock } from "../src/test/e2e/fixtures/server/index"
+
+// Configuration
+const PROTOBUS_PORT = process.env.PROTOBUS_PORT || "26040"
+const HOSTBRIDGE_PORT = process.env.HOSTBRIDGE_PORT || "26041"
+const WORKSPACE_DIR = process.env.WORKSPACE_DIR || process.cwd()
+const E2E_TEST = process.env.E2E_TEST || "true"
+const CLINE_ENVIRONMENT = process.env.CLINE_ENVIRONMENT || "local"
+
+// Locate the standalone build directory and core file with flexible path resolution
+const projectRoot = process.env.PROJECT_ROOT || path.resolve(__dirname, "..")
+const distDir = process.env.CLINE_DIST_DIR || path.join(projectRoot, "dist-standalone")
+const clineCoreFile = process.env.CLINE_CORE_FILE || "cline-core.js"
+const coreFile = path.join(distDir, clineCoreFile)
+
+async function main(): Promise<void> {
+	console.log("Starting Simple Cline gRPC Server...")
+	console.log(`Workspace: ${WORKSPACE_DIR}`)
+	console.log(`ProtoBus Port: ${PROTOBUS_PORT}`)
+	console.log(`HostBridge Port: ${HOSTBRIDGE_PORT}`)
+
+	console.log(`Looking for standalone build at: ${coreFile}`)
+
+	if (!fs.existsSync(coreFile)) {
+		console.error(`Standalone build not found at: ${coreFile}`)
+		console.error("Available environment variables for customization:")
+		console.error("  PROJECT_ROOT - Override project root directory")
+		console.error("  CLINE_DIST_DIR - Override distribution directory")
+		console.error("  CLINE_CORE_FILE - Override core file name")
+		console.error("")
+		console.error("To build the standalone version, run: npm run compile-standalone")
+		process.exit(1)
+	}
+
+	try {
+		await ClineApiServerMock.startGlobalServer()
+		console.log("Cline API Server started in-process")
+	} catch (error) {
+		console.error("Failed to start Cline API Server:", error)
+		process.exit(1)
+	}
+
+	// Create temporary directories like e2e tests
+	const userDataDir = mkdtempSync(path.join(os.tmpdir(), "vsce"))
+	const extensionsDir = mkdtempSync(path.join(os.tmpdir(), "vsce"))
+	const clineTestWorkspace = mkdtempSync(path.join(os.tmpdir(), "cline-test-workspace-"))
+
+	// Start hostbridge test server in background.
+	// We run it as a child process to emulate how the extension currently operates
+	console.log("Starting HostBridge test server...")
+	const hostbridge: ChildProcess = spawn("npx", ["tsx", path.join(__dirname, "test-hostbridge-server.ts")], {
+		stdio: "pipe",
+		detached: false,
+		env: {
+			...process.env,
+			TEST_HOSTBRIDGE_WORKSPACE_DIR: clineTestWorkspace,
+		},
+	})
+
+	console.log(`Temp user data dir: ${userDataDir}`)
+	console.log(`Temp extensions dir: ${extensionsDir}`)
+
+	// Extract standalone.zip to the extensions directory
+	const standaloneZipPath = path.join(distDir, "standalone.zip")
+	if (!fs.existsSync(standaloneZipPath)) {
+		console.error(`standalone.zip not found at: ${standaloneZipPath}`)
+		process.exit(1)
+	}
+
+	console.log("Extracting standalone.zip to extensions directory...")
+	try {
+		execSync(`unzip -q "${standaloneZipPath}" -d "${extensionsDir}"`, { stdio: "inherit" })
+		console.log(`Successfully extracted standalone.zip to: ${extensionsDir}`)
+	} catch (error) {
+		console.error("Failed to extract standalone.zip:", error)
+		process.exit(1)
+	}
+
+	// Start the core service
+	// We run it as a child process to emulate how the extension currently operates
+	console.log("Starting Cline Core Service...")
+	const coreService: ChildProcess = spawn("node", [clineCoreFile], {
+		cwd: distDir,
+		env: {
+			...process.env,
+			NODE_PATH: "./node_modules",
+			DEV_WORKSPACE_FOLDER: WORKSPACE_DIR,
+			PROTOBUS_ADDRESS: `127.0.0.1:${PROTOBUS_PORT}`,
+			HOST_BRIDGE_ADDRESS: `localhost:${HOSTBRIDGE_PORT}`,
+			E2E_TEST: E2E_TEST,
+			CLINE_ENVIRONMENT: CLINE_ENVIRONMENT,
+			CLINE_DIR: userDataDir,
+			INSTALL_DIR: extensionsDir,
+		},
+		stdio: "inherit",
+	})
+
+	// Handle graceful shutdown
+	const shutdown = async (): Promise<void> => {
+		console.log(`\n Shutting down services...\n${userDataDir}\n${extensionsDir}\n${clineTestWorkspace}\n`)
+		hostbridge.kill()
+		coreService.kill()
+		await ClineApiServerMock.stopGlobalServer()
+
+		// Cleanup temp directories
+		try {
+			rmSync(userDataDir, { recursive: true, force: true })
+			rmSync(extensionsDir, { recursive: true, force: true })
+			rmSync(clineTestWorkspace, { recursive: true, force: true })
+			console.log("Cleaned up temporary directories")
+		} catch (error) {
+			console.warn("Failed to cleanup temp directories:", error)
+		}
+
+		process.exit(0)
+	}
+
+	process.on("SIGINT", shutdown)
+	process.on("SIGTERM", shutdown)
+
+	coreService.on("exit", (code) => {
+		console.log(`Core service exited with code ${code}`)
+		hostbridge.kill()
+		process.exit(code || 0)
+	})
+
+	hostbridge.on("exit", (code) => {
+		console.log(`HostBridge exited with code ${code}`)
+		coreService.kill()
+		process.exit(code || 0)
+	})
+
+	console.log("Cline gRPC Server is running!")
+	console.log(`Connect to: 127.0.0.1:${PROTOBUS_PORT}`)
+	console.log("Press Ctrl+C to stop")
+}
+
+if (require.main === module) {
+	main().catch((error) => {
+		console.error("Failed to start simple Cline server:", error)
+		process.exit(1)
+	})
+}

scripts/testing-platform-orchestrator.ts

@@ -0,0 +1,159 @@
+#!/usr/bin/env npx tsx
+/**
+ * Test Orchestrator
+ *
+ * Automates server lifecycle for running spec files against the standalone server.
+ *
+ * Prerequisites:
+ *   Build standalone first: `npm run compile-standalone`
+ *
+ * Usage:
+ *   - Single file:   `npm run test:tp-orchestrator path/to/spec.json`
+ *   - All specs dir: `npm run test:tp-orchestrator tests/specs`
+ *
+ * Flags:
+ *   --server-logs        Show server logs (hidden by default)
+ *   --count=<number>     Repeat execution N times (default: 1)
+ *
+ * Environment Variables:
+ *   HOSTBRIDGE_PORT      gRPC server port (default: 26040)
+ *   SERVER_BOOT_DELAY    Server startup delay in ms (default: 3000)
+ */
+
+import { ChildProcess, spawn } from "child_process"
+import fs from "fs"
+import minimist from "minimist"
+import path from "path"
+
+const STANDALONE_GRPC_SERVER_PORT = process.env.STANDALONE_GRPC_SERVER_PORT || "26040"
+const SERVER_BOOT_DELAY = Number(process.env.SERVER_BOOT_DELAY) || 3000
+
+let showServerLogs = false
+
+function startServer(): Promise<ChildProcess> {
+	return new Promise((resolve, reject) => {
+		const server = spawn("npx", ["tsx", "scripts/test-standalone-core-api-server.ts"], {
+			stdio: showServerLogs ? "inherit" : "ignore",
+		})
+
+		server.once("error", reject)
+
+		setTimeout(() => {
+			if (server.killed) {
+				reject(new Error("Server died during startup"))
+			} else {
+				resolve(server)
+			}
+		}, SERVER_BOOT_DELAY)
+	})
+}
+
+function stopServer(server: ChildProcess): Promise<void> {
+	return new Promise((resolve) => {
+		server.once("exit", () => resolve())
+		server.kill("SIGINT")
+		setTimeout(() => {
+			if (!server.killed) {
+				server.kill("SIGKILL")
+				resolve()
+			}
+		}, 5000)
+	})
+}
+
+function runTestingPlatform(specFile: string): Promise<void> {
+	return new Promise((resolve, reject) => {
+		const testProcess = spawn("npx", ["ts-node", "index.ts", specFile], {
+			cwd: path.join(process.cwd(), "testing-platform"),
+			stdio: "inherit",
+			env: {
+				...process.env,
+				HOSTBRIDGE_PORT: STANDALONE_GRPC_SERVER_PORT,
+			},
+		})
+
+		testProcess.once("error", reject)
+		testProcess.once("exit", (code) => {
+			code === 0 ? resolve() : reject(new Error(`Exit code ${code}`))
+		})
+	})
+}
+
+async function runSpec(specFile: string): Promise<void> {
+	const server = await startServer()
+	try {
+		await runTestingPlatform(specFile)
+		console.log(`✅ ${path.basename(specFile)} passed`)
+	} finally {
+		await stopServer(server)
+	}
+}
+
+function collectSpecFiles(inputPath: string): string[] {
+	const fullPath = path.resolve(inputPath)
+	if (!fs.existsSync(fullPath)) throw new Error(`Path does not exist: ${fullPath}`)
+
+	const stat = fs.statSync(fullPath)
+	if (stat.isDirectory()) {
+		return fs
+			.readdirSync(fullPath)
+			.filter((f) => f.endsWith(".json"))
+			.map((f) => path.join(fullPath, f))
+	}
+	if (fullPath.endsWith(".json")) return [fullPath]
+	throw new Error("Spec path must be a JSON file or a folder containing JSON files")
+}
+
+async function runAll(inputPath: string, count: number) {
+	const specFiles = collectSpecFiles(inputPath)
+	if (specFiles.length === 0) {
+		console.warn(`⚠️ No spec files found in ${inputPath}`)
+		return
+	}
+
+	let success = 0
+	let failure = 0
+	const totalStart = Date.now()
+
+	for (let i = 0; i < count; i++) {
+		console.log(`\n🔁 Run #${i + 1} of ${count}`)
+		for (const specFile of specFiles) {
+			try {
+				await runSpec(specFile)
+				success++
+			} catch (err) {
+				console.error(`❌ run #${i + 1}: ${path.basename(specFile)} failed:`, (err as Error).message)
+				failure++
+			}
+		}
+
+		if (failure > 0) process.exitCode = 1
+	}
+
+	console.log(`✅ Passed: ${success}`)
+	if (failure > 0) console.log(`❌ Failed: ${failure}`)
+	console.log(`📋 Total specs: ${specFiles.length} Total runs: ${specFiles.length * count}`)
+	const totalElapsed = ((Date.now() - totalStart) / 1000).toFixed(2)
+	console.log(`\n🏁 All runs completed in ${totalElapsed}s`)
+}
+
+async function main() {
+	const args = minimist(process.argv.slice(2), { default: { count: 1 } })
+	const inputPath = args._[0]
+	const count = Number(args.count)
+	showServerLogs = Boolean(args["server-logs"])
+
+	if (!inputPath) {
+		console.error("Usage: npx tsx scripts/testing-platform-orchestrator.ts <spec-file-or-folder> [--count=N] [--server-logs]")
+		process.exit(1)
+	}
+
+	await runAll(inputPath, count)
+}
+
+if (require.main === module) {
+	main().catch((err) => {
+		console.error("❌ Fatal error:", err)
+		process.exit(1)
+	})
+}

src/api/providers/dify.ts

@@ -1,15 +1,20 @@
 import { Anthropic } from "@anthropic-ai/sdk"
-import { ApiHandlerOptions, ModelInfo } from "@shared/api"
+import { ModelInfo } from "@shared/api"
 import { ApiHandler } from "../../core/api/index"
 import { ApiStream } from "../../core/api/transform/stream"
 
+interface DifyHandlerOptions {
+	difyApiKey?: string
+	difyBaseUrl?: string
+}
+
 export class DifyHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: DifyHandlerOptions
 	private baseUrl: string
 	private apiKey: string
 	private conversationId: string | null = null
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: DifyHandlerOptions) {
 		this.options = options
 		this.apiKey = options.difyApiKey || ""
 		this.baseUrl = options.difyBaseUrl || ""

src/common.ts

@@ -1,19 +1,23 @@
 import * as vscode from "vscode"
 import {
 	migrateCustomInstructionsToGlobalRules,
+	migrateTaskHistoryToFile,
 	migrateWelcomeViewCompleted,
 	migrateWorkspaceToGlobalStorage,
 } from "./core/storage/state-migrations"
 import { WebviewProvider } from "./core/webview"
 import { Logger } from "./services/logging/Logger"
-import { PostHogClientProvider } from "./services/posthog/PostHogClientProvider"
-import { EmptyRequest } from "./shared/proto/cline/common"
 import { WebviewProviderType } from "./shared/webview/types"
 import "./utils/path" // necessary to have access to String.prototype.toPosix
 
 import { HostProvider } from "@/hosts/host-provider"
 import { FileContextTracker } from "./core/context/context-tracking/FileContextTracker"
-import { telemetryService } from "./services/posthog/PostHogClientProvider"
+import { ExtensionRegistryInfo } from "./registry"
+import { ErrorService } from "./services/error"
+import { featureFlagsService } from "./services/feature-flags"
+import { initializeDistinctId } from "./services/logging/distinctId"
+import { PostHogClientProvider } from "./services/posthog/PostHogClientProvider"
+import { telemetryService } from "./services/telemetry"
 import { ShowMessageType } from "./shared/proto/host/window"
 import { getLatestAnnouncementId } from "./utils/announcements"
 /**
@@ -23,18 +27,15 @@ import { getLatestAnnouncementId } from "./utils/announcements"
  * @returns The webview provider
  */
 export async function initialize(context: vscode.ExtensionContext): Promise<WebviewProvider> {
+	// Set the distinct ID for logging and telemetry
+	await initializeDistinctId(context)
+
 	// Initialize PostHog client provider
-	let distinctId = context.globalState.get<string>("cline.distinctId")
-	if (!distinctId) {
-		try {
-			const response = await HostProvider.env.getMachineId(EmptyRequest.create({}))
-			distinctId = response.value
-		} catch (e) {
-			Logger.warn(`Failed to get machine ID: ${e instanceof Error ? e.message : String(e)}`)
-			// PostHogProvider will fall back to uuid
-		}
-	}
-	PostHogClientProvider.getInstance(distinctId)
+	PostHogClientProvider.getInstance()
+
+	// Setup the external services
+	await ErrorService.initialize()
+	await featureFlagsService.poll()
 
 	// Migrate custom instructions to global Cline rules (one-time cleanup)
 	await migrateCustomInstructionsToGlobalRules(context)
@@ -45,6 +46,9 @@ export async function initialize(context: vscode.ExtensionContext): Promise<Webv
 	// Migrate workspace storage values back to global storage (reverting previous migration)
 	await migrateWorkspaceToGlobalStorage(context)
 
+	// Ensure taskHistory.json exists and migrate legacy state (runs once)
+	await migrateTaskHistoryToFile(context)
+
 	// Clean up orphaned file context warnings (startup cleanup)
 	await FileContextTracker.cleanupOrphanedWarnings(context)
 
@@ -59,7 +63,7 @@ export async function initialize(context: vscode.ExtensionContext): Promise<Webv
 
 async function showVersionUpdateAnnouncement(context: vscode.ExtensionContext) {
 	// Version checking for autoupdate notification
-	const currentVersion = context.extension.packageJSON.version
+	const currentVersion = ExtensionRegistryInfo.version
 	const previousVersion = context.globalState.get<string>("clineVersion")
 	// Perform post-update actions if necessary
 	try {
@@ -68,14 +72,14 @@ async function showVersionUpdateAnnouncement(context: vscode.ExtensionContext) {
 
 			// Use the same condition as announcements: focus when there's a new announcement to show
 			const lastShownAnnouncementId = context.globalState.get<string>("lastShownAnnouncementId")
-			const latestAnnouncementId = getLatestAnnouncementId(context)
+			const latestAnnouncementId = getLatestAnnouncementId()
 
 			if (lastShownAnnouncementId !== latestAnnouncementId) {
 				// Focus Cline when there's a new announcement to show (major/minor updates or fresh installs)
 				const message = previousVersion
 					? `Cline has been updated to v${currentVersion}`
 					: `Welcome to Cline v${currentVersion}`
-				await vscode.commands.executeCommand("claude-dev.SidebarProvider.focus")
+				await HostProvider.workspace.openClineSidebarPanel({})
 				await new Promise((resolve) => setTimeout(resolve, 200))
 				HostProvider.window.showMessage({
 					type: ShowMessageType.INFORMATION,
@@ -96,7 +100,9 @@ async function showVersionUpdateAnnouncement(context: vscode.ExtensionContext) {
  */
 export async function tearDown(): Promise<void> {
 	PostHogClientProvider.getInstance().dispose()
-
+	telemetryService.dispose()
+	ErrorService.get().dispose()
+	featureFlagsService.dispose()
 	// Dispose all webview instances
 	await WebviewProvider.disposeAllInstances()
 }

src/core/api/index.ts

@@ -210,6 +210,7 @@ function createHandlerForProvider(
 			})
 		case "qwen-code":
 			return new QwenCodeHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				qwenCodeOauthPath: options.qwenCodeOauthPath,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
@@ -312,6 +313,7 @@ function createHandlerForProvider(
 			})
 		case "baseten":
 			return new BasetenHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				basetenApiKey: options.basetenApiKey,
 				basetenModelId: mode === "plan" ? options.planModeBasetenModelId : options.actModeBasetenModelId,
 				basetenModelInfo: mode === "plan" ? options.planModeBasetenModelInfo : options.actModeBasetenModelInfo,
@@ -329,6 +331,7 @@ function createHandlerForProvider(
 				thinkingBudgetTokens:
 					mode === "plan" ? options.planModeThinkingBudgetTokens : options.actModeThinkingBudgetTokens,
 				reasoningEffort: mode === "plan" ? options.planModeReasoningEffort : options.actModeReasoningEffort,
+				deploymentId: mode === "plan" ? options.planModeSapAiCoreDeploymentId : options.actModeSapAiCoreDeploymentId,
 				sapAiCoreUseOrchestrationMode: options.sapAiCoreUseOrchestrationMode,
 			})
 		case "claude-code":
@@ -341,6 +344,7 @@ function createHandlerForProvider(
 			})
 		case "huawei-cloud-maas":
 			return new HuaweiCloudMaaSHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				huaweiCloudMaasApiKey: options.huaweiCloudMaasApiKey,
 				huaweiCloudMaasModelId:
 					mode === "plan" ? options.planModeHuaweiCloudMaasModelId : options.actModeHuaweiCloudMaasModelId,
@@ -348,16 +352,13 @@ function createHandlerForProvider(
 					mode === "plan" ? options.planModeHuaweiCloudMaasModelInfo : options.actModeHuaweiCloudMaasModelInfo,
 			})
 		case "dify": // Add Dify.ai handler
-			console.log("[DIFY DEBUG] Instantiating DifyHandler with options:", {
-				difyApiKeyPresent: !!options.difyApiKey,
-				difyBaseUrl: options.difyBaseUrl,
-			})
 			return new DifyHandler({
 				difyApiKey: options.difyApiKey,
 				difyBaseUrl: options.difyBaseUrl,
 			})
 		case "vercel-ai-gateway":
 			return new VercelAIGatewayHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				vercelAiGatewayApiKey: options.vercelAiGatewayApiKey,
 				vercelAiGatewayModelId:
 					mode === "plan" ? options.planModeVercelAiGatewayModelId : options.actModeVercelAiGatewayModelId,
@@ -366,6 +367,7 @@ function createHandlerForProvider(
 			})
 		case "zai":
 			return new ZAiHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				zaiApiLine: options.zaiApiLine,
 				zaiApiKey: options.zaiApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
@@ -395,7 +397,7 @@ export function buildApiHandler(configuration: ApiConfiguration, mode: Mode): Ap
 			const handler = createHandlerForProvider(apiProvider, options, mode)
 
 			const modelInfo = handler.getModel().info
-			if (modelInfo.maxTokens && thinkingBudgetTokens > modelInfo.maxTokens) {
+			if (modelInfo?.maxTokens && modelInfo.maxTokens > 0 && thinkingBudgetTokens > modelInfo.maxTokens) {
 				const clippedValue = modelInfo.maxTokens - 1
 				if (mode === "plan") {
 					options.planModeThinkingBudgetTokens = clippedValue

src/core/api/providers/__tests__/bedrock.test.ts

@@ -1,7 +1,7 @@
 import "should"
 import { ConverseStreamCommand } from "@aws-sdk/client-bedrock-runtime"
-import { ApiHandlerOptions } from "@shared/api"
 import { Readable } from "stream"
+import type { AwsBedrockHandlerOptions } from "../bedrock"
 import { AwsBedrockHandler } from "../bedrock"
 
 describe("AwsBedrockHandler", () => {
@@ -202,8 +202,8 @@ describe("AwsBedrockHandler", () => {
 		})
 	})
 
-	const mockOptions: ApiHandlerOptions = {
-		actModeApiModelId: "anthropic.claude-3-7-sonnet-20250219-v1:0",
+	const mockOptions: AwsBedrockHandlerOptions = {
+		apiModelId: "anthropic.claude-3-7-sonnet-20250219-v1:0",
 		awsRegion: "us-east-1",
 		awsAccessKey: "test-key",
 		awsSecretKey: "test-secret",
@@ -214,9 +214,9 @@ describe("AwsBedrockHandler", () => {
 		awsBedrockUsePromptCache: false,
 		awsUseCrossRegionInference: false,
 		awsBedrockEndpoint: "",
-		actModeAwsBedrockCustomSelected: false,
-		actModeAwsBedrockCustomModelBaseId: undefined,
-		actModeThinkingBudgetTokens: 1600,
+		awsBedrockCustomSelected: false,
+		awsBedrockCustomModelBaseId: undefined,
+		thinkingBudgetTokens: 1600,
 	}
 
 	const mockModelInfo = {

src/core/api/providers/__tests__/claude-code.test.ts

@@ -0,0 +1,248 @@
+import { Anthropic } from "@anthropic-ai/sdk"
+import { afterEach, beforeEach, describe, it } from "mocha"
+import sinon from "sinon"
+import "should"
+import { ClaudeCodeHandler } from "@core/api/providers/claude-code"
+
+describe("ClaudeCodeHandler", () => {
+	let handler: ClaudeCodeHandler
+	let sandbox: sinon.SinonSandbox
+
+	beforeEach(() => {
+		sandbox = sinon.createSandbox()
+		handler = new ClaudeCodeHandler({
+			claudeCodePath: "/mock/path",
+			apiModelId: "claude-3-5-sonnet-20241022",
+		})
+	})
+
+	afterEach(() => {
+		sandbox.restore()
+	})
+
+	describe("token counting", () => {
+		it("should correctly handle token usage from assistant messages", async () => {
+			// The 'input_tokens' field represents the TOTAL number of input tokens used.
+			// See https://docs.anthropic.com/en/api/messages#usage-object
+
+			// Mock the runClaudeCode function
+			const runClaudeCodeModule = await import("@/integrations/claude-code/run")
+			const runClaudeCodeStub = sandbox.stub(runClaudeCodeModule, "runClaudeCode")
+
+			// Create a proper async generator mock for the Claude Code response
+			async function* mockGenerator() {
+				// First yield the system init
+				yield {
+					type: "system",
+					subtype: "init",
+					apiKeySource: "api",
+				}
+
+				// Yield assistant message with usage data
+				// Example: If base input is 70 tokens, cache read is 20, and cache creation is 10,
+				// then input_tokens from Anthropic API will be 100 (70 + 20 + 10)
+				yield {
+					type: "assistant",
+					message: {
+						content: [
+							{
+								type: "text",
+								text: "Test response",
+							},
+						],
+						usage: {
+							input_tokens: 100, // Total including cache (per Anthropic docs)
+							output_tokens: 50,
+							cache_read_input_tokens: 20, // Already included in input_tokens
+							cache_creation_input_tokens: 10, // Already included in input_tokens
+						},
+						stop_reason: "end_turn",
+					},
+				}
+
+				// Yield result with cost
+				yield {
+					type: "result",
+					result: {},
+					total_cost_usd: 0.005,
+				}
+			}
+
+			runClaudeCodeStub.returns(mockGenerator() as any)
+
+			const systemPrompt = "You are a helpful assistant."
+			const messages: Anthropic.Messages.MessageParam[] = [{ role: "user", content: "Hello" }]
+
+			const usageData: any[] = []
+
+			// Collect the results
+			for await (const chunk of handler.createMessage(systemPrompt, messages)) {
+				if (chunk.type === "usage") {
+					usageData.push({
+						inputTokens: chunk.inputTokens,
+						outputTokens: chunk.outputTokens,
+						cacheReadTokens: chunk.cacheReadTokens,
+						cacheWriteTokens: chunk.cacheWriteTokens,
+						totalCost: chunk.totalCost,
+					})
+				}
+			}
+
+			// Verify token counting follows Anthropic API specification
+			usageData.should.have.length(1)
+			usageData[0].should.deepEqual({
+				inputTokens: 100, // Total including cache tokens (per Anthropic API docs)
+				outputTokens: 50,
+				cacheReadTokens: 20, // Tracked separately for reporting
+				cacheWriteTokens: 10, // Tracked separately for reporting
+				totalCost: 0.005,
+			})
+
+			// CRITICAL ASSERTION: Verify that input_tokens is NOT inflated by re-adding cache tokens
+			// The bug would have caused inputTokens to be incorrectly calculated as 130 (100 + 20 + 10)
+			// The fix ensures it remains 100, as per Anthropic's specification
+			usageData[0].inputTokens.should.equal(100) // Correct: matches API response
+			usageData[0].inputTokens.should.not.equal(130) // Would be wrong: double-counting cache tokens
+		})
+
+		it("should handle missing usage fields with nullish coalescing", async () => {
+			// Mock the runClaudeCode function
+			const runClaudeCodeModule = await import("@/integrations/claude-code/run")
+			const runClaudeCodeStub = sandbox.stub(runClaudeCodeModule, "runClaudeCode")
+
+			// Create a proper async generator mock with missing/undefined usage fields
+			async function* mockGenerator() {
+				yield {
+					type: "assistant",
+					message: {
+						content: [
+							{
+								type: "text",
+								text: "Test response",
+							},
+						],
+						usage: {
+							input_tokens: 100,
+							output_tokens: 50,
+							// cache fields are undefined/missing
+						},
+						stop_reason: "end_turn",
+					},
+				}
+
+				yield {
+					type: "result",
+					result: {},
+					total_cost_usd: 0.005,
+				}
+			}
+
+			runClaudeCodeStub.returns(mockGenerator() as any)
+
+			const systemPrompt = "You are a helpful assistant."
+			const messages: Anthropic.Messages.MessageParam[] = [{ role: "user", content: "Hello" }]
+
+			const usageData: any[] = []
+
+			// Collect the results
+			for await (const chunk of handler.createMessage(systemPrompt, messages)) {
+				if (chunk.type === "usage") {
+					usageData.push({
+						inputTokens: chunk.inputTokens,
+						outputTokens: chunk.outputTokens,
+						cacheReadTokens: chunk.cacheReadTokens,
+						cacheWriteTokens: chunk.cacheWriteTokens,
+					})
+				}
+			}
+
+			// Verify that undefined cache tokens default to 0
+			usageData.should.have.length(1)
+			usageData[0].should.deepEqual({
+				inputTokens: 100,
+				outputTokens: 50,
+				cacheReadTokens: 0, // Should default to 0
+				cacheWriteTokens: 0, // Should default to 0
+			})
+		})
+
+		it("should handle completely missing usage object", async () => {
+			// Mock the runClaudeCode function
+			const runClaudeCodeModule = await import("@/integrations/claude-code/run")
+			const runClaudeCodeStub = sandbox.stub(runClaudeCodeModule, "runClaudeCode")
+
+			// Create a proper async generator mock with missing usage object
+			async function* mockGenerator() {
+				yield {
+					type: "assistant",
+					message: {
+						content: [
+							{
+								type: "text",
+								text: "Test response",
+							},
+						],
+						// usage is undefined
+						usage: undefined,
+						stop_reason: "end_turn",
+					},
+				}
+
+				// Need to yield a result chunk to trigger usage data emission
+				yield {
+					type: "result",
+					result: {},
+					total_cost_usd: 0,
+				}
+			}
+
+			runClaudeCodeStub.returns(mockGenerator() as any)
+
+			const systemPrompt = "You are a helpful assistant."
+			const messages: Anthropic.Messages.MessageParam[] = [{ role: "user", content: "Hello" }]
+
+			const usageData: any[] = []
+
+			// Collect the results
+			for await (const chunk of handler.createMessage(systemPrompt, messages)) {
+				if (chunk.type === "usage") {
+					usageData.push({
+						inputTokens: chunk.inputTokens,
+						outputTokens: chunk.outputTokens,
+						cacheReadTokens: chunk.cacheReadTokens,
+						cacheWriteTokens: chunk.cacheWriteTokens,
+					})
+				}
+			}
+
+			// All token counts should default to 0 when usage is undefined
+			usageData.should.have.length(1)
+			usageData[0].should.deepEqual({
+				inputTokens: 0,
+				outputTokens: 0,
+				cacheReadTokens: 0,
+				cacheWriteTokens: 0,
+			})
+		})
+	})
+
+	describe("getModel", () => {
+		it("should return the correct model when specified", () => {
+			const handler = new ClaudeCodeHandler({
+				apiModelId: "claude-3-5-sonnet-20241022",
+			})
+
+			const model = handler.getModel()
+			model.id.should.equal("claude-3-5-sonnet-20241022")
+		})
+
+		it("should return default model when not specified", () => {
+			const handler = new ClaudeCodeHandler({})
+
+			const model = handler.getModel()
+			// The default model should be set
+			model.id.should.be.type("string")
+			model.info.should.be.type("object")
+		})
+	})
+})

src/core/api/providers/__tests__/litellm.test.ts

@@ -0,0 +1,243 @@
+import Anthropic from "@anthropic-ai/sdk"
+import { LiteLlmHandler, type LiteLlmModelInfoResponse } from "@core/api/providers/litellm"
+import { convertToOpenAiMessages } from "@core/api/transform/openai-format"
+import { expect } from "chai"
+import sinon from "sinon"
+
+const fakeClient = {
+	chat: {
+		completions: {
+			create: sinon.stub(),
+		},
+	},
+	baseURL: "fake",
+}
+
+describe("LiteLlmHandler", () => {
+	const originalFetch = global.fetch
+	const mockFetch = sinon.stub()
+
+	const mockModelFetch = (modelInfo: LiteLlmModelInfoResponse["data"][number]) => {
+		mockFetch.resolves({
+			ok: true,
+			json: () =>
+				Promise.resolve({
+					data: [modelInfo],
+				}),
+		})
+	}
+
+	let handler: LiteLlmHandler
+
+	const mockHandlerChat = () => {
+		sinon.stub(handler, "ensureClient" as any).returns(fakeClient)
+	}
+
+	const initializeHandler = (model: string) => {
+		handler = new LiteLlmHandler({
+			liteLlmApiKey: "test-api-key",
+			liteLlmBaseUrl: "http://localhost:4000",
+			liteLlmUsePromptCache: true,
+			liteLlmModelId: model,
+		})
+
+		mockHandlerChat()
+	}
+
+	beforeEach(() => {
+		global.fetch = mockFetch
+
+		// Configure the stub to return a stream that closes immediately with usage data
+		fakeClient.chat.completions.create.resolves(
+			createAsyncIterable([
+				{
+					choices: [{ delta: { content: "test response" } }],
+				},
+				{
+					choices: [{}],
+					usage: {
+						prompt_tokens: 100,
+						completion_tokens: 50,
+						cache_creation_input_tokens: 20,
+						cache_read_input_tokens: 10,
+					},
+				},
+			]),
+		)
+	})
+
+	afterEach(() => {
+		sinon.reset()
+
+		global.fetch = originalFetch
+	})
+
+	const createAsyncIterable = (data: any[] = []) => {
+		return {
+			[Symbol.asyncIterator]: async function* () {
+				yield* data
+			},
+		}
+	}
+
+	describe("prompt cache", () => {
+		const setModelData = (model: string, supportsPromptCaching: boolean) => {
+			mockModelFetch({
+				model_name: model,
+				litellm_params: {
+					model,
+				},
+				model_info: {
+					supports_prompt_caching: supportsPromptCaching,
+					input_cost_per_token: 0.01,
+					output_cost_per_token: 0.02,
+				},
+			})
+		}
+
+		describe("when the model doesn't support prompt caching", () => {
+			const model = "openai/gpt-5"
+
+			beforeEach(() => {
+				initializeHandler(model)
+				setModelData(model, false)
+			})
+
+			it("sends the system prompt and messages with the openai format", async () => {
+				const systemPrompt = "Test System Prompt"
+				const messages: Anthropic.Messages.MessageParam[] = [
+					{
+						role: "user",
+						content: "first message",
+					},
+					{
+						role: "assistant",
+						content: "first response",
+					},
+					{
+						role: "user",
+						content: [
+							{
+								type: "text",
+								text: "test",
+							},
+							{
+								type: "text",
+								text: "second message",
+							},
+						],
+					},
+				]
+
+				for await (const _ of handler.createMessage(systemPrompt, messages)) {
+				}
+
+				sinon.assert.calledOnce(fakeClient.chat.completions.create)
+
+				const callArgs = fakeClient.chat.completions.create.getCall(0).args[0]
+
+				const systemPromptMessage = callArgs.messages.shift()
+				expect(systemPromptMessage).to.deep.equal({
+					role: "system",
+					content: systemPrompt,
+				})
+
+				expect(callArgs.messages).to.deep.equal(convertToOpenAiMessages(messages))
+			})
+		})
+
+		describe("when the model supports prompt caching", () => {
+			const model = "anthropic/claude-sonnet-4-20250514"
+
+			beforeEach(() => {
+				initializeHandler(model)
+
+				setModelData(model, true)
+			})
+
+			it("inserts the cache control in the system prompt and the last two user messages", async () => {
+				const systemPrompt = "Test System Prompt"
+				const messages: Anthropic.Messages.MessageParam[] = [
+					{
+						role: "user",
+						content: "first message",
+					},
+					{
+						role: "assistant",
+						content: "first response",
+					},
+					{
+						role: "user",
+						content: [
+							{
+								type: "text",
+								text: "test",
+							},
+							{
+								type: "text",
+								text: "second message",
+							},
+						],
+					},
+				]
+
+				for await (const _ of handler.createMessage(systemPrompt, messages)) {
+				}
+
+				sinon.assert.calledOnce(fakeClient.chat.completions.create)
+
+				const callArgs = fakeClient.chat.completions.create.getCall(0).args[0]
+
+				expect(callArgs.messages[0]).to.deep.equal({
+					role: "system",
+					content: [
+						{
+							text: systemPrompt,
+							type: "text",
+							cache_control: {
+								type: "ephemeral",
+							},
+						},
+					],
+				})
+
+				const sentMessages = callArgs.messages
+				expect(sentMessages.length).to.equal(4)
+
+				const firstUserMessage = sentMessages[1]
+
+				expect(firstUserMessage).to.deep.equal({
+					role: "user",
+					content: [
+						{
+							type: "text",
+							text: "first message",
+							cache_control: {
+								type: "ephemeral",
+							},
+						},
+					],
+				})
+
+				const lastUserMessage = sentMessages[3]
+				expect(lastUserMessage.content[0]).to.deep.equal({
+					type: "text",
+					text: "test",
+				})
+
+				const lastContentBlock = lastUserMessage.content[lastUserMessage.content.length - 1]
+				expect(lastContentBlock).to.deep.equal({
+					type: "text",
+					text: "second message",
+					cache_control: {
+						type: "ephemeral",
+					},
+				})
+
+				expect(callArgs.model).to.be.a("string")
+				expect(callArgs.stream).to.equal(true)
+				expect(callArgs.stream_options).to.deep.equal({ include_usage: true })
+			})
+		})
+	})
+})

src/core/api/providers/baseten.ts

@@ -2,12 +2,12 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { BasetenModelId, basetenDefaultModelId, basetenModels, ModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "@utils/cost"
 import OpenAI from "openai"
-import { ApiHandler } from "../"
+import { ApiHandler, CommonApiHandlerOptions } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 
-interface BasetenHandlerOptions {
+interface BasetenHandlerOptions extends CommonApiHandlerOptions {
 	basetenApiKey?: string
 	basetenModelId?: string
 	basetenModelInfo?: ModelInfo
@@ -146,20 +146,15 @@ export class BasetenHandler implements ApiHandler {
 		}
 	}
 
-	/**
-	 * Checks if the current model supports vision/images
-	 */
-	supportsImages(): boolean {
-		const model = this.getModel()
-		return model.info.supportsImages === true
-	}
-
 	/**
 	 * Checks if the current model supports tools
 	 */
 	supportsTools(): boolean {
-		const _model = this.getModel()
-		// Baseten models support tools via OpenAI-compatible API
-		return true
+		const model = this.getModel()
+		const modelInfo = model.info as any
+
+		// Use dynamic API data when available, fallback to true since all current Baseten models support tools
+		// (as of 2025-09-16 - could change if Baseten add non-tool models in future, currently no plans to do so)
+		return modelInfo.supportedFeatures ? modelInfo.supportedFeatures.includes("tools") : true
 	}
 }

src/core/api/providers/bedrock.ts

@@ -16,7 +16,7 @@ import { withRetry } from "../retry"
 import { convertToR1Format } from "../transform/r1-format"
 import { ApiStream } from "../transform/stream"
 
-interface AwsBedrockHandlerOptions extends CommonApiHandlerOptions {
+export interface AwsBedrockHandlerOptions extends CommonApiHandlerOptions {
 	apiModelId?: string
 	awsAccessKey?: string
 	awsSecretKey?: string
@@ -30,7 +30,7 @@ interface AwsBedrockHandlerOptions extends CommonApiHandlerOptions {
 	awsProfile?: string
 	awsBedrockEndpoint?: string
 	awsBedrockCustomSelected?: boolean
-	awsBedrockCustomModelBaseId?: BedrockModelId
+	awsBedrockCustomModelBaseId?: string
 	thinkingBudgetTokens?: number
 }
 
@@ -170,7 +170,7 @@ export class AwsBedrockHandler implements ApiHandler {
 			if (baseModel && baseModel in bedrockModels) {
 				return {
 					id: modelId,
-					info: bedrockModels[baseModel],
+					info: bedrockModels[baseModel as BedrockModelId],
 				}
 			}
 			// For custom models without valid base model in bedrock model list, use default model's capabilities

src/core/api/providers/claude-code.ts

@@ -118,10 +118,14 @@ export class ClaudeCodeHandler implements ApiHandler {
 					}
 				}
 
-				usage.inputTokens += message.usage.input_tokens
-				usage.outputTokens += message.usage.output_tokens
-				usage.cacheReadTokens = (usage.cacheReadTokens || 0) + (message.usage.cache_read_input_tokens || 0)
-				usage.cacheWriteTokens = (usage.cacheWriteTokens || 0) + (message.usage.cache_creation_input_tokens || 0)
+				// According to Anthropic's API documentation:
+				// https://docs.anthropic.com/en/api/messages#usage-object
+				// The `input_tokens` field already includes both `cache_read_input_tokens` and `cache_creation_input_tokens`.
+				// Therefore, we should not add cache tokens to the input_tokens count again, as this would result in double-counting.
+				usage.inputTokens = message.usage?.input_tokens ?? 0
+				usage.outputTokens = message.usage?.output_tokens ?? 0
+				usage.cacheReadTokens = message.usage?.cache_read_input_tokens ?? 0
+				usage.cacheWriteTokens = message.usage?.cache_creation_input_tokens ?? 0
 
 				continue
 			}

src/core/api/providers/cline.ts

@@ -32,6 +32,7 @@ export class ClineHandler implements ApiHandler {
 	private client: OpenAI | undefined
 	private readonly _baseUrl = clineEnvConfig.apiBaseUrl
 	lastGenerationId?: string
+	private lastRequestId?: string
 
 	constructor(options: ClineHandlerOptions) {
 		this.options = options
@@ -54,6 +55,31 @@ export class ClineHandler implements ApiHandler {
 						"X-Task-ID": this.options.ulid || "",
 						"X-Cline-Version": extensionVersion,
 					},
+					// Capture real HTTP request ID from initial streaming response headers
+					fetch: async (...args: Parameters<typeof fetch>): Promise<Awaited<ReturnType<typeof fetch>>> => {
+						const [input, init] = args
+						const resp = await fetch(input, init)
+						try {
+							let urlStr = ""
+							if (typeof input === "string") {
+								urlStr = input
+							} else if (input instanceof URL) {
+								urlStr = input.toString()
+							} else if (typeof (input as { url?: unknown }).url === "string") {
+								urlStr = (input as { url: string }).url
+							}
+							// Only record for chat completions (the primary streaming request)
+							if (urlStr.includes("/chat/completions")) {
+								const rid = resp.headers.get("x-request-id") || resp.headers.get("request-id")
+								if (rid) {
+									this.lastRequestId = rid
+								}
+							}
+						} catch {
+							// ignore header capture errors
+						}
+						return resp
+					},
 				})
 			} catch (error: any) {
 				throw new Error(`Error creating Cline client: ${error.message}`)
@@ -70,6 +96,7 @@ export class ClineHandler implements ApiHandler {
 			const client = await this.ensureClient()
 
 			this.lastGenerationId = undefined
+			this.lastRequestId = undefined
 
 			let didOutputUsage: boolean = false
 
@@ -92,6 +119,7 @@ export class ClineHandler implements ApiHandler {
 					const metadataStr = error.metadata ? `\nMetadata: ${JSON.stringify(error.metadata, null, 2)}` : ""
 					throw new Error(`Cline API Error ${error.code}: ${error.message}${metadataStr}`)
 				}
+
 				if (!this.lastGenerationId && chunk.id) {
 					this.lastGenerationId = chunk.id
 				}
@@ -136,9 +164,9 @@ export class ClineHandler implements ApiHandler {
 
 					if (this.getModel().id === "cline/sonic") {
 						totalCost = 0
-					} 
+					}
 
-					if  (this.getModel().id === "x-ai/grok-code-fast-1") {
+					if (this.getModel().id === "x-ai/grok-code-fast-1") {
 						totalCost = 0
 					}
 
@@ -203,6 +231,11 @@ export class ClineHandler implements ApiHandler {
 		return undefined
 	}
 
+	// Expose the last HTTP request ID captured from response headers (X-Request-ID)
+	getLastRequestId(): string | undefined {
+		return this.lastRequestId
+	}
+
 	getModel(): { id: string; info: ModelInfo } {
 		const modelId = this.options.openRouterModelId
 		const modelInfo = this.options.openRouterModelInfo

src/core/api/providers/dify.ts

@@ -1,8 +1,13 @@
 import { Anthropic } from "@anthropic-ai/sdk"
-import { ApiHandlerOptions, ModelInfo } from "../../../shared/api"
+import { ModelInfo } from "../../../shared/api"
 import { ApiHandler } from "../index"
 import { ApiStream } from "../transform/stream"
 
+interface DifyHandlerOptions {
+	difyApiKey?: string
+	difyBaseUrl?: string
+}
+
 // Dify API Response Types
 export interface DifyFileResponse {
 	id: string
@@ -66,14 +71,14 @@ interface DifyConversationResponse {
 }
 
 export class DifyHandler implements ApiHandler {
-	private options: ApiHandlerOptions
+	private options: DifyHandlerOptions
 	private baseUrl: string
 	private apiKey: string
 	private conversationId: string | null = null
 	private currentTaskId: string | null = null
 	private abortController: AbortController | null = null
 
-	constructor(options: ApiHandlerOptions) {
+	constructor(options: DifyHandlerOptions) {
 		this.options = options
 		this.apiKey = options.difyApiKey || ""
 		this.baseUrl = options.difyBaseUrl || ""

src/core/api/providers/gemini.ts

@@ -1,16 +1,18 @@
 import type { Anthropic } from "@anthropic-ai/sdk"
 // Restore GenerateContentConfig import and add GenerateContentResponseUsageMetadata
-import { type GenerateContentConfig, type GenerateContentResponseUsageMetadata, GoogleGenAI, Part } from "@google/genai"
-import { telemetryService } from "@services/posthog/PostHogClientProvider"
+import { ApiError, type GenerateContentConfig, type GenerateContentResponseUsageMetadata, GoogleGenAI, Part } from "@google/genai"
 import { GeminiModelId, geminiDefaultModelId, geminiModels, ModelInfo } from "@shared/api"
+import { telemetryService } from "@/services/telemetry"
 import { ApiHandler, CommonApiHandlerOptions } from "../"
-import { withRetry } from "../retry"
+import { RetriableError, withRetry } from "../retry"
 import { convertAnthropicMessageToGemini } from "../transform/gemini-format"
 import { ApiStream } from "../transform/stream"
 
 // Define a default TTL for the cache (e.g., 15 minutes in seconds)
 const _DEFAULT_CACHE_TTL_SECONDS = 900
 
+const rateLimitPatterns = [/got status: 429/i, /429 Too Many Requests/i, /rate limit exceeded/i, /too many requests/i]
+
 interface GeminiHandlerOptions extends CommonApiHandlerOptions {
 	isVertex?: boolean
 	vertexProjectId?: string
@@ -222,24 +224,40 @@ export class GeminiHandler implements ApiHandler {
 			if (error instanceof Error) {
 				apiError = error.message
 
-				// Gemini doesn't include status codes in their errors
-				// https://github.com/googleapis/js-genai/blob/61f7f27b866c74333ca6331883882489bcb708b9/src/_api_client.ts#L569
-				const rateLimitPatterns = [
-					/got status: 429/i,
-					/429 Too Many Requests/i,
-					/rate limit exceeded/i,
-					/too many requests/i,
-				]
+				if (error instanceof ApiError) {
+					if (error.status === 429) {
+						// The API includes more details in the message
+						// https://github.com/googleapis/js-genai/blob/v1.11.0/src/_api_client.ts#L758
+						const response = this.attemptParse(error.message)
 
-				const isRateLimit =
-					error.name === "ClientError" && rateLimitPatterns.some((pattern) => pattern.test(error.message))
+						if (response && response.error) {
+							const responseBody = this.attemptParse(response.error.message)
 
-				if (isRateLimit) {
-					const rateLimitError = Object.assign(new Error(error.message), {
-						...error,
-						status: 429,
-					})
-					throw rateLimitError
+							if (responseBody.error) {
+								const detail = responseBody.error.details?.find(
+									(d: any) => d["@type"] === "type.googleapis.com/google.rpc.RetryInfo",
+								)
+
+								const detailedError = new RetriableError(
+									apiError,
+									this.parseRetryDelay(detail?.retryDelay) || undefined,
+									{
+										cause: error,
+									},
+								)
+								throw detailedError
+							}
+						}
+
+						throw new RetriableError(apiError, undefined, { cause: error })
+					}
+
+					// Fallback in case Gemini throws a rate limit error without a 429 status code
+					// https://github.com/cline/cline/pull/5205#discussion_r2311761559
+					const isRateLimit = rateLimitPatterns.some((pattern) => pattern.test(error.message))
+					if (isRateLimit) {
+						throw new RetriableError(apiError, undefined, { cause: error })
+					}
 				}
 			} else {
 				apiError = String(error)
@@ -420,4 +438,35 @@ export class GeminiHandler implements ApiHandler {
 
 		return Math.ceil(totalChars / 4)
 	}
+
+	private parseRetryDelay(retryAfter?: string): number {
+		if (!retryAfter) {
+			return 0
+		}
+
+		const unit = retryAfter.at(-1)
+		const value = parseInt(retryAfter, 10)
+
+		if (Number.isNaN(value)) {
+			return 0
+		}
+
+		if (unit === "s") {
+			return value
+		} else if (unit === "m") {
+			return value * 60 // Convert minutes to seconds
+		} else if (unit === "h") {
+			return value * 60 * 60 // Convert hours to seconds
+		}
+
+		return value
+	}
+
+	private attemptParse(str: string) {
+		try {
+			return JSON.parse(str)
+		} catch (_) {
+			return null
+		}
+	}
 }

src/core/api/providers/huawei-cloud-maas.ts

@@ -1,12 +1,12 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { HuaweiCloudMaasModelId, huaweiCloudMaasDefaultModelId, huaweiCloudMaasModels, ModelInfo } from "@shared/api"
 import OpenAI from "openai"
-import { ApiHandler } from ".."
+import { ApiHandler, CommonApiHandlerOptions } from ".."
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 
-interface HuaweiCloudMaaSHandlerOptions {
+interface HuaweiCloudMaaSHandlerOptions extends CommonApiHandlerOptions {
 	huaweiCloudMaasApiKey?: string
 	huaweiCloudMaasModelId?: string
 	huaweiCloudMaasModelInfo?: ModelInfo

src/core/api/providers/litellm.ts

@@ -1,6 +1,7 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { LiteLLMModelInfo, liteLlmDefaultModelId, liteLlmModelInfoSaneDefaults } from "@shared/api"
 import OpenAI from "openai"
+import { isAnthropicModelId } from "@/utils/model-utils"
 import { ApiHandler, CommonApiHandlerOptions } from ".."
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
@@ -16,7 +17,7 @@ interface LiteLlmHandlerOptions extends CommonApiHandlerOptions {
 	ulid?: string
 }
 
-interface LiteLlmModelInfoResponse {
+export interface LiteLlmModelInfoResponse {
 	data: Array<{
 		model_name: string
 		litellm_params: {
@@ -28,6 +29,7 @@ interface LiteLlmModelInfoResponse {
 			output_cost_per_token: number
 			cache_creation_input_token_cost?: number
 			cache_read_input_token_cost?: number
+			supports_prompt_caching?: boolean
 			[key: string]: any
 		}
 	}>
@@ -61,7 +63,17 @@ export class LiteLlmHandler implements ApiHandler {
 		return this.client
 	}
 
-	private async fetchModelInfo(): Promise<LiteLlmModelInfoResponse | undefined> {
+	private async modelInfo(publicModelName: string): Promise<LiteLlmModelInfoResponse["data"][number] | undefined> {
+		const modelInfo = await this.fetchModelsInfo()
+
+		if (!modelInfo?.data) {
+			return undefined
+		}
+
+		return modelInfo.data.find((model) => model.model_name === publicModelName)
+	}
+
+	private async fetchModelsInfo(): Promise<LiteLlmModelInfoResponse | undefined> {
 		// Check if cache is still valid
 		const now = Date.now()
 		if (this.modelInfoCache && now - this.modelInfoCacheTimestamp < this.modelInfoCacheTTL) {
@@ -121,19 +133,14 @@ export class LiteLlmHandler implements ApiHandler {
 		cacheReadCostPerToken?: number
 	}> {
 		try {
-			const modelInfo = await this.fetchModelInfo()
+			const matchingModel = await this.modelInfo(publicModelName)
 
-			if (modelInfo?.data) {
-				// Find the model by public name
-				const matchingModel = modelInfo.data.find((model) => model.model_name === publicModelName)
-
-				if (matchingModel?.model_info) {
-					return {
-						inputCostPerToken: matchingModel.model_info.input_cost_per_token || 0,
-						outputCostPerToken: matchingModel.model_info.output_cost_per_token || 0,
-						cacheCreationCostPerToken: matchingModel.model_info.cache_creation_input_token_cost,
-						cacheReadCostPerToken: matchingModel.model_info.cache_read_input_token_cost,
-					}
+			if (matchingModel) {
+				return {
+					inputCostPerToken: matchingModel.model_info.input_cost_per_token || 0,
+					outputCostPerToken: matchingModel.model_info.output_cost_per_token || 0,
+					cacheCreationCostPerToken: matchingModel.model_info.cache_creation_input_token_cost,
+					cacheReadCostPerToken: matchingModel.model_info.cache_read_input_token_cost,
 				}
 			}
 		} catch (error) {
@@ -177,7 +184,7 @@ export class LiteLlmHandler implements ApiHandler {
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
 		const client = this.ensureClient()
 		const formattedMessages = convertToOpenAiMessages(messages)
-		const systemMessage: OpenAI.Chat.ChatCompletionSystemMessageParam = {
+		const systemMessage: OpenAI.Chat.ChatCompletionSystemMessageParam | Anthropic.Messages.TextBlockParam = {
 			role: "system",
 			content: systemPrompt,
 		}
@@ -191,17 +198,26 @@ export class LiteLlmHandler implements ApiHandler {
 
 		let temperature: number | undefined = this.options.liteLlmModelInfo?.temperature ?? 0
 
-		if (isOminiModel && reasoningOn) {
-			temperature = undefined // Thinking mode doesn't support temperature
+		if ((isOminiModel || isAnthropicModelId(modelId)) && reasoningOn) {
+			temperature = undefined // OAI omni and Anthropic extended thinking mode doesn't support temperature
 		}
 
-		// Define cache control object if prompt caching is enabled
-		const cacheControl = this.options.liteLlmUsePromptCache ? { cache_control: { type: "ephemeral" } } : undefined
+		const modelInfo = await this.modelInfo(modelId)
+		const cacheControl =
+			this.options.liteLlmUsePromptCache && Boolean(modelInfo?.model_info.supports_prompt_caching)
+				? { cache_control: { type: "ephemeral" } }
+				: undefined
 
-		// Add cache_control to system message if enabled
-		const enhancedSystemMessage = {
-			...systemMessage,
-			...(cacheControl && cacheControl),
+		if (cacheControl) {
+			// Add cache_control to system message if enabled
+			// https://docs.litellm.ai/docs/providers/anthropic#caching---large-context-caching
+			systemMessage.content = [
+				{
+					text: systemPrompt,
+					type: "text",
+					...cacheControl,
+				},
+			] as Anthropic.Messages.TextBlockParam[]
 		}
 
 		// Find the last two user messages to apply caching
@@ -213,19 +229,49 @@ export class LiteLlmHandler implements ApiHandler {
 		const secondLastUserMsgIndex = userMsgIndices[userMsgIndices.length - 2] ?? -1
 
 		// Apply cache_control to the last two user messages if enabled
-		const enhancedMessages = formattedMessages.map((message, index) => {
-			if ((index === lastUserMsgIndex || index === secondLastUserMsgIndex) && cacheControl) {
-				return {
-					...message,
-					...cacheControl,
+		// https://docs.litellm.ai/docs/providers/anthropic#caching---large-context-caching
+		const enhancedMessages: OpenAI.Chat.ChatCompletionMessageParam[] = formattedMessages.map(
+			(message, index): OpenAI.Chat.ChatCompletionMessageParam => {
+				if ((index === lastUserMsgIndex || index === secondLastUserMsgIndex) && cacheControl) {
+					// Handle both string and array content types
+					if (typeof message.content === "string") {
+						return {
+							...message,
+							content: [
+								{
+									type: "text",
+									text: message.content,
+									...cacheControl,
+								},
+							] as any,
+						}
+					} else if (Array.isArray(message.content)) {
+						// Apply cache control to the last content item in the array
+						return {
+							...message,
+							content: message.content.map((item, contentIndex) =>
+								contentIndex === (message.content?.length || 0) - 1
+									? {
+											...item,
+											...cacheControl,
+										}
+									: item,
+							) as any,
+						}
+					}
+
+					return {
+						...message,
+						...cacheControl,
+					}
 				}
-			}
-			return message
-		})
+				return message
+			},
+		)
 
 		const stream = await client.chat.completions.create({
 			model: this.options.liteLlmModelId || liteLlmDefaultModelId,
-			messages: [enhancedSystemMessage, ...enhancedMessages],
+			messages: [systemMessage, ...enhancedMessages],
 			temperature,
 			stream: true,
 			stream_options: { include_usage: true },
@@ -244,16 +290,16 @@ export class LiteLlmHandler implements ApiHandler {
 				}
 			}
 
-			// Handle reasoning events (thinking)
-			// Thinking is not in the standard types but may be in the response
+			// Handle reasoning events
+			// This is not in the standard types but may be in the response
 			interface ThinkingDelta {
-				thinking?: string
+				reasoning_content?: string
 			}
 
-			if ((delta as ThinkingDelta)?.thinking) {
+			if ((delta as ThinkingDelta)?.reasoning_content) {
 				yield {
 					type: "reasoning",
-					reasoning: (delta as ThinkingDelta).thinking || "",
+					reasoning: (delta as ThinkingDelta).reasoning_content || "",
 				}
 			}
 

src/core/api/providers/qwen-code.ts

@@ -4,7 +4,7 @@ import { ModelInfo, QwenCodeModelId, qwenCodeDefaultModelId, qwenCodeModels } fr
 import OpenAI from "openai"
 import * as os from "os"
 import * as path from "path"
-import { ApiHandler } from "../"
+import { ApiHandler, CommonApiHandlerOptions } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
@@ -24,7 +24,7 @@ interface QwenOAuthCredentials {
 	resource_url?: string
 }
 
-interface QwenCodeHandlerOptions {
+interface QwenCodeHandlerOptions extends CommonApiHandlerOptions {
 	qwenCodeOauthPath?: string
 	apiModelId?: string
 }

src/core/api/providers/requesty.ts

@@ -2,6 +2,7 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { ModelInfo, requestyDefaultModelId, requestyDefaultModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "@utils/cost"
 import OpenAI from "openai"
+import { toRequestyServiceStringUrl } from "@/shared/providers/requesty"
 import { ApiHandler, CommonApiHandlerOptions } from "../index"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
@@ -41,7 +42,7 @@ export class RequestyHandler implements ApiHandler {
 			}
 			try {
 				this.client = new OpenAI({
-					baseURL: this.options.requestyBaseUrl || "https://router.requesty.ai/v1",
+					baseURL: toRequestyServiceStringUrl(this.options.requestyBaseUrl),
 					apiKey: this.options.requestyApiKey,
 					defaultHeaders: {
 						"HTTP-Referer": "https://cline.bot",
@@ -82,7 +83,6 @@ export class RequestyHandler implements ApiHandler {
 				? thinking
 				: {}
 
-		// @ts-ignore-next-line
 		const stream = await client.chat.completions.create({
 			model: model.id,
 			max_tokens: model.info.maxTokens || undefined,

src/core/api/providers/sapaicore.ts

@@ -21,6 +21,7 @@ interface SapAiCoreHandlerOptions extends CommonApiHandlerOptions {
 	apiModelId?: string
 	sapAiCoreUseOrchestrationMode?: boolean
 	thinkingBudgetTokens?: number
+	deploymentId?: string
 	reasoningEffort?: string
 }
 
@@ -28,6 +29,7 @@ interface Deployment {
 	id: string
 	name: string
 }
+
 interface Token {
 	access_token: string
 	expires_in: number
@@ -394,11 +396,8 @@ export class SapAiCoreHandler implements ApiHandler {
 		return this.token.access_token
 	}
 
+	// TODO: these fallback fetching deployment id methods can be removed in future version if decided that users migration to fetching deployment id in design-time (open SAP AI Core provider UI) considered as completed.
 	private async getAiCoreDeployments(): Promise<Deployment[]> {
-		if (this.options.sapAiCoreClientSecret === "") {
-			return [{ id: "notconfigured", name: "ai-core-not-configured" }]
-		}
-
 		const token = await this.getToken()
 		const headers = {
 			Authorization: `Bearer ${token}`,
@@ -456,7 +455,7 @@ export class SapAiCoreHandler implements ApiHandler {
 	}
 
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
-		if (this.options.sapAiCoreUseOrchestrationMode ?? true) {
+		if (this.options.sapAiCoreUseOrchestrationMode) {
 			yield* this.createMessageWithOrchestration(systemPrompt, messages)
 		} else {
 			yield* this.createMessageWithDeployments(systemPrompt, messages)
@@ -496,7 +495,6 @@ export class SapAiCoreHandler implements ApiHandler {
 			// Define the LLM to be used by the Orchestration pipeline
 			const llm: LlmModuleConfig = {
 				model_name: model.id,
-				model_params: { max_tokens: model.info.maxTokens },
 			}
 
 			const templating: TemplatingModuleConfig = {
@@ -546,7 +544,13 @@ export class SapAiCoreHandler implements ApiHandler {
 		}
 
 		const model = this.getModel()
-		const deploymentId = await this.getDeploymentForModel(model.id)
+		let deploymentId = this.options.deploymentId
+
+		if (!deploymentId) {
+			// Fallback to runtime deployment id fetching for users who haven't opened the SAP provider UI
+			console.log(`No pre-configured deployment ID found for model ${model.id}, falling back to runtime fetching`)
+			deploymentId = await this.getDeploymentForModel(model.id)
+		}
 
 		const anthropicModels = [
 			"anthropic--claude-4-sonnet",

src/core/api/providers/vercel-ai-gateway.ts

@@ -1,12 +1,12 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { ModelInfo, vercelAiGatewayDefaultModelId, vercelAiGatewayDefaultModelInfo } from "@shared/api"
 import OpenAI from "openai"
-import { ApiHandler } from "../index"
+import { ApiHandler, CommonApiHandlerOptions } from "../index"
 import { withRetry } from "../retry"
 import { ApiStream } from "../transform/stream"
 import { createVercelAIGatewayStream } from "../transform/vercel-ai-gateway-stream"
 
-interface VercelAIGatewayHandlerOptions {
+interface VercelAIGatewayHandlerOptions extends CommonApiHandlerOptions {
 	vercelAiGatewayApiKey?: string
 	vercelAiGatewayModelId?: string
 	vercelAiGatewayModelInfo?: ModelInfo

src/core/api/providers/zai.ts

@@ -10,12 +10,12 @@ import {
 } from "@shared/api"
 import OpenAI from "openai"
 import { version as extensionVersion } from "../../../../package.json"
-import { ApiHandler } from ".."
+import { ApiHandler, CommonApiHandlerOptions } from ".."
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 
-interface ZAiHandlerOptions {
+interface ZAiHandlerOptions extends CommonApiHandlerOptions {
 	zaiApiLine?: string
 	zaiApiKey?: string
 	apiModelId?: string
@@ -39,7 +39,9 @@ export class ZAiHandler implements ApiHandler {
 			}
 			try {
 				this.client = new OpenAI({
-					baseURL: this.useChinaApi() ? "https://open.bigmodel.cn/api/paas/v4" : "https://api.z.ai/api/paas/v4",
+					baseURL: this.useChinaApi()
+						? "https://open.bigmodel.cn/api/coding/paas/v4"
+						: "https://api.z.ai/api/coding/paas/v4",
 					apiKey: this.options.zaiApiKey,
 					defaultHeaders: {
 						"HTTP-Referer": "https://cline.bot",

src/core/api/retry.ts

@@ -12,6 +12,18 @@ const DEFAULT_OPTIONS: Required<RetryOptions> = {
 	retryAllErrors: false,
 }
 
+export class RetriableError extends Error {
+	status: number = 429
+	retryAfter?: number
+
+	constructor(message: string, retryAfter?: number, options?: ErrorOptions) {
+		super(message, options)
+		this.name = "RetriableError"
+
+		this.retryAfter = retryAfter
+	}
+}
+
 export function withRetry(options: RetryOptions = {}) {
 	const { maxRetries, baseDelay, maxDelay, retryAllErrors } = { ...DEFAULT_OPTIONS, ...options }
 
@@ -24,7 +36,7 @@ export function withRetry(options: RetryOptions = {}) {
 					yield* originalMethod.apply(this, args)
 					return
 				} catch (error: any) {
-					const isRateLimit = error?.status === 429
+					const isRateLimit = error?.status === 429 || error instanceof RetriableError
 					const isLastAttempt = attempt === maxRetries - 1
 
 					if ((!isRateLimit && !retryAllErrors) || isLastAttempt) {
@@ -36,7 +48,8 @@ export function withRetry(options: RetryOptions = {}) {
 					const retryAfter =
 						error.headers?.["retry-after"] ||
 						error.headers?.["x-ratelimit-reset"] ||
-						error.headers?.["ratelimit-reset"]
+						error.headers?.["ratelimit-reset"] ||
+						error.retryAfter
 
 					let delay: number
 					if (retryAfter) {

src/core/api/transform/openrouter-stream.ts

@@ -1,7 +1,6 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { CLAUDE_SONNET_4_1M_SUFFIX, ModelInfo, openRouterClaudeSonnet41mModelId } from "@shared/api"
 import OpenAI from "openai"
-import { isGPT5ModelFamily } from "../../prompts/system-prompt/utils"
 import { convertToOpenAiMessages } from "./openai-format"
 import { convertToR1Format } from "./r1-format"
 

src/core/assistant-message/index.ts

@@ -1,3 +1,4 @@
+import { ClineDefaultTool } from "@shared/tools"
 export type AssistantMessageContent = TextContent | ToolUse
 
 export { parseAssistantMessageV2 } from "./parse-assistant-message"
@@ -8,32 +9,6 @@ export interface TextContent {
 	partial: boolean
 }
 
-export const toolUseNames = [
-	"execute_command",
-	"read_file",
-	"write_to_file",
-	"replace_in_file",
-	"search_files",
-	"list_files",
-	"list_code_definition_names",
-	"browser_action",
-	"use_mcp_tool",
-	"access_mcp_resource",
-	"ask_followup_question",
-	"plan_mode_respond",
-	"load_mcp_documentation",
-	"attempt_completion",
-	"new_task",
-	"condense",
-	"summarize_task",
-	"report_bug",
-	"new_rule",
-	"web_fetch",
-] as const
-
-// Converts array of tool call names into a union type ("execute_command" | "read_file" | ...)
-export type ToolUseName = (typeof toolUseNames)[number]
-
 export const toolParamNames = [
 	"command",
 	"requires_approval",
@@ -63,13 +38,14 @@ export const toolParamNames = [
 	"additional_context",
 	"needs_more_exploration",
 	"task_progress",
+	"timeout",
 ] as const
 
 export type ToolParamName = (typeof toolParamNames)[number]
 
 export interface ToolUse {
 	type: "tool_use"
-	name: ToolUseName
+	name: ClineDefaultTool // id of the tool being used
 	// params is a partial record, allowing only some or none of the possible parameters to be used
 	params: Partial<Record<ToolParamName, string>>
 	partial: boolean

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

@@ -1,4 +1,5 @@
-import { AssistantMessageContent, TextContent, ToolParamName, ToolUse, ToolUseName, toolParamNames, toolUseNames } from "." // Assuming types are defined in index.ts or a similar file
+import { ClineDefaultTool, toolUseNames } from "@shared/tools"
+import { AssistantMessageContent, TextContent, ToolParamName, ToolUse, toolParamNames } from "." // Assuming types are defined in index.ts or a similar file
 
 // parseAssistantmessageV1 removed in https://github.com/cline/cline/pull/5425
 
@@ -33,7 +34,7 @@ export function parseAssistantMessageV2(assistantMessage: string): AssistantMess
 	let currentParamName: ToolParamName | undefined
 
 	// Precompute tags for faster lookups
-	const toolUseOpenTags = new Map<string, ToolUseName>()
+	const toolUseOpenTags = new Map<string, ClineDefaultTool>()
 	const toolParamOpenTags = new Map<string, ToolParamName>()
 	for (const name of toolUseNames) {
 		toolUseOpenTags.set(`<${name}>`, name)

src/core/context/context-management/ContextManager.ts

@@ -291,7 +291,7 @@ export class ContextManager {
 
 		// Make sure that the last message being removed is a assistant message, so the next message after the initial user-assistant pair is an assistant message. This preserves the user-assistant-user-assistant structure.
 		// NOTE: anthropic format messages are always user-assistant-user-assistant, while openai format messages can have multiple user messages in a row (we use anthropic format throughout cline)
-		if (apiMessages[rangeEndIndex].role !== "assistant") {
+		if (apiMessages[rangeEndIndex] && apiMessages[rangeEndIndex].role !== "assistant") {
 			rangeEndIndex -= 1
 		}
 

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

@@ -1,10 +1,9 @@
-import { getTaskMetadata, saveTaskMetadata } from "@core/storage/disk"
+import { getTaskMetadata, readTaskHistoryFromState, saveTaskMetadata } from "@core/storage/disk"
 import type { ClineMessage } from "@shared/ExtensionMessage"
 import chokidar, { FSWatcher } from "chokidar"
 import * as path from "path"
 import * as vscode from "vscode"
 import { Controller } from "@/core/controller"
-import { HistoryItem } from "@/shared/HistoryItem"
 import { getCwd } from "@/utils/path"
 import type { FileMetadataEntry } from "./ContextTrackerTypes"
 
@@ -286,8 +285,7 @@ export class FileContextTracker {
 	static async cleanupOrphanedWarnings(context: vscode.ExtensionContext): Promise<void> {
 		const startTime = Date.now()
 		try {
-			// eslint-disable-next-line eslint-rules/no-direct-vscode-state-api
-			const taskHistory = (context.globalState.get("taskHistory") as HistoryItem[]) || []
+			const taskHistory = await readTaskHistoryFromState(context)
 			const existingTaskIds = new Set(taskHistory.map((task) => task.id))
 			const allStateKeys = context.workspaceState.keys()
 			const pendingWarningKeys = allStateKeys.filter((key) => key.startsWith("pendingFileContextWarning_"))
@@ -312,7 +310,7 @@ export class FileContextTracker {
 				`FileContextTracker: Processed ${existingTaskIds.size} tasks, found ${pendingWarningKeys.length} pending warnings, ${orphanedPendingContextTasks.length} orphaned, deleted ${orphanedPendingContextTasks.length}, took ${duration}ms`,
 			)
 		} catch (error) {
-			console.error("Error cleaning up orphaned file context warnings:", error)
+			console.error("[FileContextTracker] Error cleaning up orphaned file context warnings:", error)
 		}
 	}
 }

src/core/controller/account/getRedirectUrl.ts

@@ -0,0 +1,11 @@
+import { EmptyRequest, String } from "@shared/proto/cline/common"
+import { HostProvider } from "@/hosts/host-provider"
+import { Controller } from "../index"
+
+/**
+ * Constructs and returns a URL that will redirect to the user's IDE.
+ */
+export async function getRedirectUrl(_controller: Controller, _: EmptyRequest): Promise<String> {
+	const url = (await HostProvider.env.getIdeRedirectUri({})).value
+	return { value: url }
+}

src/core/controller/account/openrouterAuthClicked.ts

@@ -7,10 +7,10 @@ import { Controller } from ".."
  * Initiates OpenRouter auth
  */
 export async function openrouterAuthClicked(_: Controller, __: EmptyRequest): Promise<Empty> {
-	const callbackUri = await HostProvider.get().getCallbackUri()
-	const authUri = `https://openrouter.ai/auth?callback_url=${callbackUri}/openrouter`
+	const callbackUrl = await HostProvider.get().getCallbackUrl()
+	const authUrl = `https://openrouter.ai/auth?callback_url=${callbackUrl}/openrouter`
 
-	await openExternal(authUri)
+	await openExternal(authUrl)
 
 	return {}
 }

src/core/controller/browser/updateBrowserSettings.ts

@@ -1,62 +0,0 @@
-import { UpdateBrowserSettingsRequest } from "@shared/proto/cline/browser"
-import { Boolean } from "@shared/proto/cline/common"
-import { DEFAULT_BROWSER_SETTINGS, BrowserSettings as SharedBrowserSettings } from "../../../shared/BrowserSettings"
-import { Controller } from "../index"
-
-/**
- * Update browser settings
- * @param controller The controller instance
- * @param request The browser settings request message
- * @returns Success response
- */
-export async function updateBrowserSettings(controller: Controller, request: UpdateBrowserSettingsRequest): Promise<Boolean> {
-	try {
-		// Get current browser settings to preserve fields not in the request
-		const currentSettings = controller.stateManager.getGlobalStateKey("browserSettings")
-		const mergedWithDefaults = { ...DEFAULT_BROWSER_SETTINGS, ...currentSettings }
-
-		// Convert from protobuf format to shared format, merging with existing settings
-		const newBrowserSettings: SharedBrowserSettings = {
-			...mergedWithDefaults, // Start with existing settings (and defaults)
-			viewport: {
-				// Apply updates from request
-				width: request.viewport?.width || mergedWithDefaults.viewport.width,
-				height: request.viewport?.height || mergedWithDefaults.viewport.height,
-			},
-			// Explicitly handle optional boolean and string fields from the request
-			remoteBrowserEnabled:
-				request.remoteBrowserEnabled === undefined
-					? mergedWithDefaults.remoteBrowserEnabled
-					: request.remoteBrowserEnabled,
-			remoteBrowserHost:
-				request.remoteBrowserHost === undefined ? mergedWithDefaults.remoteBrowserHost : request.remoteBrowserHost,
-			chromeExecutablePath:
-				// If chromeExecutablePath is explicitly in the request (even as ""), use it.
-				// Otherwise, fall back to mergedWithDefaults.
-				"chromeExecutablePath" in request ? request.chromeExecutablePath : mergedWithDefaults.chromeExecutablePath,
-			disableToolUse: request.disableToolUse === undefined ? mergedWithDefaults.disableToolUse : request.disableToolUse,
-			customArgs: "customArgs" in request ? request.customArgs : mergedWithDefaults.customArgs,
-		}
-
-		// Update global state with new settings
-		controller.stateManager.setGlobalState("browserSettings", newBrowserSettings)
-
-		// Update task browser settings if task exists
-		if (controller.task) {
-			controller.task.browserSettings = newBrowserSettings
-			controller.task.browserSession.browserSettings = newBrowserSettings
-		}
-
-		// Post updated state to webview
-		await controller.postStateToWebview()
-
-		return Boolean.create({
-			value: true,
-		})
-	} catch (error) {
-		console.error("Error updating browser settings:", error)
-		return Boolean.create({
-			value: false,
-		})
-	}
-}

src/core/controller/checkpoints/checkpointDiff.ts

@@ -3,7 +3,7 @@ import { Controller } from ".."
 
 export async function checkpointDiff(controller: Controller, request: Int64Request): Promise<Empty> {
 	if (request.value) {
-		await controller.task?.presentMultifileDiff(request.value, false)
+		await controller.task?.checkpointManager?.presentMultifileDiff?.(request.value, false)
 	}
-	return Empty
+	return Empty.create()
 }

src/core/controller/checkpoints/checkpointRestore.ts

@@ -23,7 +23,11 @@ export async function checkpointRestore(controller: Controller, request: Checkpo
 		})
 
 		// NOTE: cancelTask awaits abortTask, which awaits diffViewProvider.revertChanges, which reverts any edited files, allowing us to reset to a checkpoint rather than running into a state where the revertChanges function is called alongside or after the checkpoint reset
-		await controller.task?.restoreCheckpoint(request.number, request.restoreType as ClineCheckpointRestore, request.offset)
+		await controller.task?.checkpointManager?.restoreCheckpoint(
+			request.number,
+			request.restoreType as ClineCheckpointRestore,
+			request.offset,
+		)
 	}
 	return Empty.create({})
 }

src/core/controller/commands/addToCline.ts

@@ -1,7 +1,7 @@
 import { getFileMentionFromPath } from "@/core/mentions"
 import { WebviewProvider } from "@/core/webview"
 import { singleFileDiagnosticsToProblemsString } from "@/integrations/diagnostics"
-import { telemetryService } from "@/services/posthog/PostHogClientProvider"
+import { telemetryService } from "@/services/telemetry"
 import { CommandContext, Empty } from "@/shared/proto/index.cline"
 import { Controller } from "../index"
 import { sendAddToInputEventToClient } from "../ui/subscribeToAddToInput"

src/core/controller/commands/explainWithCline.ts

@@ -1,6 +1,6 @@
 import { getFileMentionFromPath } from "@/core/mentions"
 import { HostProvider } from "@/hosts/host-provider"
-import { telemetryService } from "@/services/posthog/PostHogClientProvider"
+import { telemetryService } from "@/services/telemetry"
 import { CommandContext, Empty } from "@/shared/proto/index.cline"
 import { ShowMessageType } from "@/shared/proto/index.host"
 import { Controller } from "../index"

src/core/controller/commands/fixWithCline.ts

@@ -1,6 +1,6 @@
 import { getFileMentionFromPath } from "@/core/mentions"
 import { singleFileDiagnosticsToProblemsString } from "@/integrations/diagnostics"
-import { telemetryService } from "@/services/posthog/PostHogClientProvider"
+import { telemetryService } from "@/services/telemetry"
 import { CommandContext, Empty } from "@/shared/proto/index.cline"
 import { Controller } from "../index"
 

src/core/controller/commands/improveWithCline.ts

@@ -1,6 +1,6 @@
 import { getFileMentionFromPath } from "@/core/mentions"
 import { HostProvider } from "@/hosts/host-provider"
-import { telemetryService } from "@/services/posthog/PostHogClientProvider"
+import { telemetryService } from "@/services/telemetry"
 import { CommandContext, Empty } from "@/shared/proto/index.cline"
 import { ShowMessageType } from "@/shared/proto/index.host"
 import { Controller } from "../index"

src/core/controller/file/createRuleFile.ts

@@ -1,7 +1,7 @@
 import { refreshClineRulesToggles } from "@core/context/instructions/user-instructions/cline-rules"
 import { createRuleFile as createRuleFileImpl } from "@core/context/instructions/user-instructions/rule-helpers"
+import { getWorkspaceBasename } from "@core/workspace"
 import { RuleFile, RuleFileRequest } from "@shared/proto/cline/file"
-import * as path from "path"
 import { refreshWorkflowToggles } from "@/core/context/instructions/user-instructions/workflows"
 import { HostProvider } from "@/hosts/host-provider"
 import { ShowMessageType } from "@/shared/proto/host/window"
@@ -68,7 +68,7 @@ export async function createRuleFile(controller: Controller, request: RuleFileRe
 
 	return RuleFile.create({
 		filePath: filePath,
-		displayName: path.basename(filePath),
+		displayName: getWorkspaceBasename(filePath, "Controller.createRuleFile"),
 		alreadyExists: fileExists,
 	})
 }

src/core/controller/file/deleteRuleFile.ts

@@ -1,6 +1,6 @@
 import { deleteRuleFile as deleteRuleFileImpl } from "@core/context/instructions/user-instructions/rule-helpers"
+import { getWorkspaceBasename } from "@core/workspace"
 import { RuleFile, RuleFileRequest } from "@shared/proto/cline/file"
-import * as path from "path"
 import { HostProvider } from "@/hosts/host-provider"
 import { ShowMessageType } from "@/shared/proto/host/window"
 import { Controller } from ".."
@@ -40,7 +40,7 @@ export async function deleteRuleFile(controller: Controller, request: RuleFileRe
 	//await refreshWorkflowToggles(controller.context, cwd)
 	await controller.postStateToWebview()
 
-	const fileName = path.basename(request.rulePath)
+	const fileName = getWorkspaceBasename(request.rulePath, "Controller.deleteRuleFile")
 
 	const fileTypeName = request.type === "workflow" ? "workflow" : "rule"
 

src/core/controller/file/ifFileExistsRelativePath.ts

@@ -1,7 +1,7 @@
+import { workspaceResolver } from "@core/workspace"
 import { BooleanResponse, StringRequest } from "@shared/proto/cline/common"
 import { getWorkspacePath } from "@utils/path"
 import * as fs from "fs"
-import * as path from "path"
 import { Controller } from ".."
 
 /**
@@ -25,7 +25,12 @@ export async function ifFileExistsRelativePath(_controller: Controller, request:
 	}
 
 	// Resolve the relative path to absolute path
-	const absolutePath = path.resolve(workspacePath, request.value)
+	const resolvedPath = workspaceResolver.resolveWorkspacePath(
+		workspacePath,
+		request.value,
+		"Controller.ifFileExistsRelativePath",
+	)
+	const absolutePath = typeof resolvedPath === "string" ? resolvedPath : resolvedPath.absolutePath
 	// Check if the file exists
 	try {
 		return BooleanResponse.create({ value: fs.statSync(absolutePath).isFile() })

src/core/controller/file/openFileRelativePath.ts

@@ -1,7 +1,7 @@
+import { workspaceResolver } from "@core/workspace"
 import { openFile as openFileIntegration } from "@integrations/misc/open-file"
 import { Empty, StringRequest } from "@shared/proto/cline/common"
 import { getWorkspacePath } from "@utils/path"
-import * as path from "path"
 import { Controller } from ".."
 
 /**
@@ -20,7 +20,12 @@ export async function openFileRelativePath(_controller: Controller, request: Str
 
 	if (request.value) {
 		// Resolve the relative path to absolute path
-		const absolutePath = path.resolve(workspacePath, request.value)
+		const resolvedPath = workspaceResolver.resolveWorkspacePath(
+			workspacePath,
+			request.value,
+			"Controller.openFileRelativePath",
+		)
+		const absolutePath = typeof resolvedPath === "string" ? resolvedPath : resolvedPath.absolutePath
 
 		// Open the file using the existing integration
 		openFileIntegration(absolutePath)

src/core/controller/file/openFocusChainFile.ts

@@ -1,5 +1,5 @@
 import { openFile as openFileIntegration } from "@integrations/misc/open-file"
-import { telemetryService } from "../../../services/posthog/PostHogClientProvider"
+import { telemetryService } from "../../../services/telemetry"
 import { Empty, StringRequest } from "../../../shared/proto/cline/common"
 import { ensureFocusChainFile, extractFocusChainListFromText } from "../../task/focus-chain/file-utils"
 import { Controller } from ".."

src/core/controller/file/searchCommits.ts

@@ -1,6 +1,5 @@
 import { StringRequest } from "@shared/proto/cline/common"
 import { GitCommits } from "@shared/proto/cline/file"
-import { convertGitCommitsToProtoGitCommits } from "@shared/proto-conversions/file/git-commit-conversion"
 import { searchCommits as searchCommitsUtil } from "@utils/git"
 import { getWorkspacePath } from "@utils/path"
 import { Controller } from ".."
@@ -20,9 +19,7 @@ export async function searchCommits(_controller: Controller, request: StringRequ
 	try {
 		const commits = await searchCommitsUtil(request.value || "", cwd)
 
-		const protoCommits = convertGitCommitsToProtoGitCommits(commits)
-
-		return GitCommits.create({ commits: protoCommits })
+		return GitCommits.create({ commits })
 	} catch (error) {
 		console.error(`Error searching commits: ${JSON.stringify(error)}`)
 		return GitCommits.create({ commits: [] })

src/core/controller/file/searchFiles.ts

@@ -1,8 +1,7 @@
+import { searchWorkspaceFiles } from "@services/search/file-search"
 import { FileSearchRequest, FileSearchResults, FileSearchType } from "@shared/proto/cline/file"
-import { SearchWorkspaceItemsRequest_SearchItemType } from "@shared/proto/host/workspace"
 import { convertSearchResultsToProtoFileInfos } from "@shared/proto-conversions/file/search-result-conversion"
 import { getWorkspacePath } from "@utils/path"
-import { HostProvider } from "@/hosts/host-provider"
 import { Controller } from ".."
 
 /**
@@ -17,47 +16,36 @@ export async function searchFiles(_controller: Controller, request: FileSearchRe
 	if (!workspacePath) {
 		// Handle case where workspace path is not available
 		console.error("Error in searchFiles: No workspace path available")
-		return FileSearchResults.create({
-			results: [],
-			mentionsRequestId: request.mentionsRequestId,
-		})
+		return { results: [], mentionsRequestId: request.mentionsRequestId }
 	}
 
 	try {
-		// Map enum to host SearchItemType (0 = FILE, 1 = FOLDER)
-		const selectedTypeValue: SearchWorkspaceItemsRequest_SearchItemType | undefined =
-			request.selectedType === FileSearchType.FILE
-				? SearchWorkspaceItemsRequest_SearchItemType.FILE
-				: request.selectedType === FileSearchType.FOLDER
-					? SearchWorkspaceItemsRequest_SearchItemType.FOLDER
-					: undefined
+		// Map enum to string for the search service
+		let selectedTypeString: "file" | "folder" | undefined
+		if (request.selectedType === FileSearchType.FILE) {
+			selectedTypeString = "file"
+		} else if (request.selectedType === FileSearchType.FOLDER) {
+			selectedTypeString = "folder"
+		}
 
-		// Use host-provided search via hostbridge (no fallback)
-		const hostResponse = await HostProvider.workspace.searchWorkspaceItems({
-			query: request.query || "",
-			limit: request.limit || 20,
-			selectedType: selectedTypeValue,
-		})
-
-		const mapped: { path: string; type: "file" | "folder"; label?: string }[] = (hostResponse.items || []).map(
-			(item: { path?: string; type: SearchWorkspaceItemsRequest_SearchItemType; label?: string }) => ({
-				path: String(item.path || ""),
-				type: item.type === SearchWorkspaceItemsRequest_SearchItemType.FOLDER ? "folder" : "file",
-				label: item.label || undefined,
-			}),
+		// Call file search service with query from request
+		const searchResults = await searchWorkspaceFiles(
+			request.query || "",
+			workspacePath,
+			request.limit || 20, // Use default limit of 20 if not specified
+			selectedTypeString,
 		)
 
-		const protoResults = convertSearchResultsToProtoFileInfos(mapped)
+		// Convert search results to proto FileInfo objects using the conversion function
+		const protoResults = convertSearchResultsToProtoFileInfos(searchResults)
 
-		return FileSearchResults.create({
-			results: protoResults,
-			mentionsRequestId: request.mentionsRequestId,
-		})
+		// Return successful results
+		return { results: protoResults, mentionsRequestId: request.mentionsRequestId }
 	} catch (error) {
-		console.error("Error in host searchWorkspaceItems:", error instanceof Error ? error.message : String(error))
-		return FileSearchResults.create({
-			results: [],
-			mentionsRequestId: request.mentionsRequestId,
-		})
+		// Log the error but don't include it in the response, following the pattern in searchCommits
+		console.error("Error in searchFiles:", error)
+
+		// Return empty results without error message
+		return { results: [], mentionsRequestId: request.mentionsRequestId }
 	}
 }

src/core/controller/file/toggleClineRule.ts

@@ -1,7 +1,7 @@
-import path from "node:path"
-import { telemetryService } from "@services/posthog/PostHogClientProvider"
+import { getWorkspaceBasename } from "@core/workspace"
 import type { ToggleClineRuleRequest } from "@shared/proto/cline/file"
 import { ToggleClineRules } from "@shared/proto/cline/file"
+import { telemetryService } from "@/services/telemetry"
 import type { Controller } from "../index"
 
 /**
@@ -36,14 +36,7 @@ export async function toggleClineRule(controller: Controller, request: ToggleCli
 	// Track rule toggle telemetry with current task context
 	if (controller.task?.ulid) {
 		// Extract just the filename for privacy (no full paths)
-		const ruleFileName = path.basename(rulePath)
-		telemetryService.captureClineRuleToggled(controller.task.ulid, ruleFileName, enabled, isGlobal)
-	}
-
-	// Track rule toggle telemetry with current task context
-	if (controller.task?.ulid) {
-		// Extract just the filename for privacy (no full paths)
-		const ruleFileName = path.basename(rulePath)
+		const ruleFileName = getWorkspaceBasename(rulePath, "Controller.toggleClineRule")
 		telemetryService.captureClineRuleToggled(controller.task.ulid, ruleFileName, enabled, isGlobal)
 	}
 

src/core/controller/file/toggleWindsurfRule.ts

@@ -1,4 +1,3 @@
-import { ClineRulesToggles as AppClineRulesToggles } from "@shared/cline-rules"
 import type { ToggleWindsurfRuleRequest } from "@shared/proto/cline/file"
 import { ClineRulesToggles } from "@shared/proto/cline/file"
 import type { Controller } from "../index"

src/core/controller/grpc-handler.ts

@@ -1,8 +1,9 @@
+import { Controller } from "@core/controller/index"
 import { serviceHandlers } from "@generated/hosts/vscode/protobus-services"
+import { GrpcRecorderBuilder } from "@/core/controller/grpc-recorder/grpc-recorder.builder"
+import { GrpcRequestRegistry } from "@/core/controller/grpc-request-registry"
 import { ExtensionMessage } from "@/shared/ExtensionMessage"
 import { GrpcCancel, GrpcRequest } from "@/shared/WebviewMessage"
-import { GrpcRequestRegistry } from "./grpc-request-registry"
-import { Controller } from "./index"
 
 /**
  * Type definition for a streaming response handler
@@ -15,6 +16,36 @@ export type StreamingResponseHandler<TResponse> = (
 
 export type PostMessageToWebview = (message: ExtensionMessage) => Thenable<boolean | undefined>
 
+/**
+ * Creates a middleware wrapper for recording gRPC requests and responses
+ */
+function withRecordingMiddleware(postMessage: PostMessageToWebview, controller: Controller): PostMessageToWebview {
+	return async (response: ExtensionMessage) => {
+		if (response?.grpc_response) {
+			try {
+				GrpcRecorderBuilder.getRecorder(controller).recordResponse(
+					response.grpc_response.request_id,
+					response.grpc_response,
+				)
+			} catch (e) {
+				console.warn("Failed to record gRPC response:", e)
+			}
+		}
+		return postMessage(response)
+	}
+}
+
+/**
+ * Records gRPC request with error handling
+ */
+function recordRequest(request: GrpcRequest, controller: Controller): void {
+	try {
+		GrpcRecorderBuilder.getRecorder(controller).recordRequest(request)
+	} catch (e) {
+		console.warn("Failed to record gRPC request:", e)
+	}
+}
+
 /**
  * Handles a gRPC request from the webview.
  */
@@ -23,10 +54,15 @@ export async function handleGrpcRequest(
 	postMessageToWebview: PostMessageToWebview,
 	request: GrpcRequest,
 ): Promise<void> {
+	recordRequest(request, controller)
+
+	// Create recording middleware wrapper
+	const postMessageWithRecording = withRecordingMiddleware(postMessageToWebview, controller)
+
 	if (request.is_streaming) {
-		await handleStreamingRequest(controller, postMessageToWebview, request)
+		await handleStreamingRequest(controller, postMessageWithRecording, request)
 	} else {
-		await handleUnaryRequest(controller, postMessageToWebview, request)
+		await handleUnaryRequest(controller, postMessageWithRecording, request)
 	}
 }
 

src/core/controller/grpc-recorder/__tests__/grpc-recorder.builder.test.ts

@@ -0,0 +1,50 @@
+import { describe, it } from "mocha"
+import "should"
+import { GrpcRecorderNoops } from "@/core/controller/grpc-recorder/grpc-recorder"
+import { GrpcRecorderBuilder } from "@/core/controller/grpc-recorder/grpc-recorder.builder"
+import { LogFileHandler } from "@/core/controller/grpc-recorder/log-file-handler"
+
+describe("GrpcRecorderBuilder", () => {
+	describe("when not enabling", () => {
+		it("should return GrpcRecorderNoops when enableIf is false", () => {
+			const builder = new GrpcRecorderBuilder()
+			const recorder = builder.enableIf(false).build()
+
+			recorder.should.be.instanceOf(GrpcRecorderNoops)
+		})
+
+		it("should return GrpcRecorderNoops when enableIf is false even with log file handler", () => {
+			const builder = new GrpcRecorderBuilder()
+			const logFileHandler = new LogFileHandler()
+			const recorder = builder.withLogFileHandler(logFileHandler).enableIf(false).build()
+
+			recorder.should.be.instanceOf(GrpcRecorderNoops)
+		})
+	})
+
+	describe("GrpcRecorderNoops functionality", () => {
+		it("should have no-op methods that don't throw errors", () => {
+			const recorder = new GrpcRecorderNoops()
+
+			recorder.recordRequest({
+				request_id: "test-id",
+				service: "TestService",
+				method: "testMethod",
+				message: {},
+				is_streaming: false,
+			})
+
+			recorder.recordResponse("test-id", {
+				request_id: "test-id",
+				message: {},
+			})
+
+			recorder.recordError("test-id", "test error")
+
+			const sessionLog = recorder.getSessionLog()
+			sessionLog.should.have.property("startTime").which.is.a.String()
+			sessionLog.should.have.property("entries").which.is.an.Array()
+			sessionLog.entries.should.have.length(0)
+		})
+	})
+})

src/core/controller/grpc-recorder/__tests__/grpc-recorder.test.ts

@@ -0,0 +1,214 @@
+import { GrpcRecorder, IRecorder } from "@core/controller/grpc-recorder/grpc-recorder"
+import { expect } from "chai"
+import { ExtensionMessage } from "@/shared/ExtensionMessage"
+import { GrpcRequest } from "@/shared/WebviewMessage"
+
+describe("grpc-recorder", () => {
+	let recorder: IRecorder
+
+	before(async () => {
+		recorder = GrpcRecorder.builder()
+			.withFilters((req: GrpcRequest) => req.service === "the-unwanted-service")
+			.enableIf(true)
+			.build()
+	})
+
+	describe("GrpcRecorder", () => {
+		it("matches multiple request, response and stats", async () => {
+			interface UseCase {
+				request: GrpcRequest
+				response: ExtensionMessage["grpc_response"]
+				expectedStatus: string
+			}
+			const requestResponseUseCases: UseCase[] = [
+				{
+					request: {
+						service: "the-service",
+						method: "the-method",
+						message: "the-message",
+						request_id: "request-id-1",
+						is_streaming: false,
+					},
+					response: {
+						request_id: "request-id-1",
+						message: "the-message-response",
+						error: "",
+					},
+					expectedStatus: "completed",
+				},
+				{
+					request: {
+						service: "streaming-service",
+						method: "stream-method",
+						message: { data: "streaming-data", count: 42 },
+						request_id: "request-id-2",
+						is_streaming: true,
+					},
+					response: {
+						request_id: "request-id-2",
+						message: { streamData: "chunk-1" },
+						error: "",
+						is_streaming: true,
+						sequence_number: 1,
+					},
+					expectedStatus: "completed",
+				},
+				{
+					request: {
+						service: "another-service",
+						method: "another-method",
+						message: { complex: { nested: "object", array: [1, 2, 3] } },
+						request_id: "request-id-3",
+						is_streaming: false,
+					},
+					response: {
+						request_id: "request-id-3",
+						message: "",
+						error: "Something went wrong",
+					},
+					expectedStatus: "error",
+				},
+			]
+
+			const initialExpectedStatus = "pending"
+
+			requestResponseUseCases.forEach((us: UseCase, index: number) => {
+				recorder.recordRequest(us.request)
+
+				let sessionLog = recorder.getSessionLog()
+				expect(sessionLog.entries).length(index + 1, `unexpected request_id: ${us.request.request_id}`)
+
+				expect(sessionLog.entries[index]).to.include({
+					service: us.request.service,
+					method: us.request.method,
+					isStreaming: us.request.is_streaming,
+					requestId: us.request.request_id,
+					status: initialExpectedStatus,
+				})
+
+				if (us.response) {
+					recorder.recordResponse(us.request.request_id, us.response)
+				}
+				sessionLog = recorder.getSessionLog()
+
+				expect(sessionLog.entries[index].status).equal(us.expectedStatus)
+				expect(sessionLog.entries[index].response).to.deep.include({
+					error: us.response?.error,
+				})
+			})
+
+			const sessionLog = recorder.getSessionLog()
+			expect(sessionLog.stats).to.include({
+				totalRequests: 3,
+				pendingRequests: 0,
+				completedRequests: 2,
+				errorRequests: 1,
+			})
+
+			recorder.recordRequest({
+				service: "the-unwanted-service",
+				method: "the-method",
+				message: "the-message",
+				request_id: "request-id-1",
+				is_streaming: false,
+			})
+
+			expect(sessionLog.entries).length(3)
+		})
+
+		it("using default filtering should filter out unwanted requests", async () => {
+			const customRecorder = GrpcRecorder.builder()
+				.withFilters(
+					(req) => req.is_streaming,
+					(req) => ["cline.UiService", "cline.McpService", "cline.WebService"].includes(req.service),
+				)
+				.enableIf(true)
+				.build()
+			const unwantedServices = ["cline.UiService", "cline.McpService", "cline.WebService"]
+			unwantedServices.forEach((us) => {
+				customRecorder.recordRequest({
+					service: us,
+					method: "the-method",
+					message: "the-message",
+					request_id: "request-id-1",
+					is_streaming: false,
+				})
+			})
+			let sessionLog = customRecorder.getSessionLog()
+			expect(sessionLog.entries).length(0)
+			customRecorder.recordRequest({
+				service: "streaming-request",
+				method: "the-method",
+				message: "the-message",
+				request_id: "request-id-1",
+				is_streaming: true,
+			})
+			sessionLog = customRecorder.getSessionLog()
+			expect(sessionLog.entries).length(0)
+		})
+
+		it("cleanupSyntheticEntries removes synthetic entries from session log", async () => {
+			const testRecorder = GrpcRecorder.builder().enableIf(true).build()
+
+			// Add regular request
+			testRecorder.recordRequest({
+				service: "regular-service",
+				method: "regular-method",
+				message: "regular-message",
+				request_id: "regular-id",
+				is_streaming: false,
+			})
+
+			// Add synthetic request
+			testRecorder.recordRequest(
+				{
+					service: "synthetic-service",
+					method: "synthetic-method",
+					message: "synthetic-message",
+					request_id: "synthetic-id",
+					is_streaming: false,
+				},
+				true, // synthetic = true
+			)
+
+			let sessionLog = testRecorder.getSessionLog()
+			expect(sessionLog.entries).length(2)
+
+			testRecorder.cleanupSyntheticEntries()
+
+			sessionLog = testRecorder.getSessionLog()
+			expect(sessionLog.entries).length(1)
+			expect(sessionLog.entries[0].requestId).equal("regular-id")
+		})
+
+		it("recordResponse executes post-record hooks", async () => {
+			let hookExecuted = false
+			let hookEntry: any = null
+
+			const mockHook = async (entry: any) => {
+				hookExecuted = true
+				hookEntry = entry
+			}
+
+			const testRecorder = GrpcRecorder.builder().withPostRecordHooks(mockHook).enableIf(true).build()
+
+			testRecorder.recordRequest({
+				service: "test-service",
+				method: "test-method",
+				message: "test-message",
+				request_id: "test-id",
+				is_streaming: false,
+			})
+
+			testRecorder.recordResponse("test-id", {
+				request_id: "test-id",
+				message: "response-message",
+				error: "",
+			})
+
+			expect(hookExecuted).to.be.true
+			expect(hookEntry).to.not.be.null
+			expect(hookEntry.requestId).equal("test-id")
+		})
+	})
+})