excluded

Add a method to the host bridge to open and focus the terminal panel.

.changeset/breezy-shrimps-begin.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-fix showing the ai core exisiting models when resource group field is empty (using the default resource group)

.changeset/calm-mirrors-switch.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Add orchestrator script and improve standalone service for local testing

.changeset/chilly-zebras-repeat.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Reset account view on sign out

.changeset/cuddly-dingos-tap.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Fix issue on Account view where balance is fetched twice that cause janky UI

.changeset/cyan-bottles-battle.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Fixes an issue where thinking text from litellm was not being passed through to Cline thinking UI

.changeset/famous-bags-warn.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Add gRPC recorder request filtering logic to make it more generic and configurable

.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/healthy-waves-eat.md

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

.changeset/heavy-dolls-cry.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Add search functionality to API provider dropdown

.changeset/heavy-insects-retire.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-Add optional middleware for recording gRPC calls in the view.

.changeset/hip-chairs-wash.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Adding telemetry for terminal command issue

.changeset/hot-turtles-flash.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Remove disabled approve / reject buttons from UI.

.changeset/khaki-donuts-sneeze.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-Sync taskHistory across Cline instances so that it will update for all Cline instances when one instance creates, adds to, or deletes a task.

.changeset/late-fans-grow.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Adding a grpc recording class with its builder

.changeset/late-wasps-agree.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Fixed minor bug where entering slash commands would result in the following word being removed from the chat text area

.changeset/lucky-keys-visit.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Fix issue where editor panel gets reset to chat view on each chat input focus event

.changeset/orange-bees-itch.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Exclude dependency folders for deep-planning prompt

.changeset/pretty-apricots-help.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Sambanova provider: add DeepSeek-V3.1

.changeset/rare-oranges-flash.md

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

.changeset/rare-suns-report.md

@@ -1,5 +0,0 @@
----
-"claude-dev": minor
----
-
-fetch deployment id in design-time instead of runtime

.changeset/real-ads-glow.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-add free grok-coder-free model to cline provider

.changeset/rich-berries-applaud.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Adding a new standalone core api server script for local and integration testing purposes

.changeset/serious-dots-doubt.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-correctly passes extended thinking tokens when max output is set to -1 default, unset temp for anthropic models when extended thinking is on

.changeset/sixty-panthers-trade.md

@@ -2,4 +2,4 @@
 "claude-dev": patch
 ---
 
-Dify.ai api integration
+Add /task deep link handler

.changeset/slimy-eels-yell.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+fix: Return the updated token

.changeset/slimy-kids-sip.md

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

.changeset/small-lions-train.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Setup Raw Structure for implementing multi-workspace support with WorkspaceRoot

.changeset/small-pumpkins-tease.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Adds a CLI testing framework for the Cline Core extension, providing gRPC-based integration clients and utilities for automated scenarios

.changeset/stale-balloons-scream.md

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

.changeset/swift-ravens-lay.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Improve Gemini Rate Limit handling

.changeset/weak-years-sin.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-fix: Support Anthropic Caching when using LiteLLM

.changeset/wise-seas-shave.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Reasoning Effort Minimal on OpenAI

.changeset/witty-rivers-knock.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Adding basic multi root algorithm

.changeset/yellow-bags-prove.md

@@ -1,5 +0,0 @@
----
-"claude-dev": patch
----
-
-Adding hooks to record getlateststate for testing

.changeset/yellow-cycles-join.md

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

.github/CODEOWNERS

@@ -1,3 +1,3 @@
 /docs/
-/.github/   @saoudrizwan @dcbartlett
-/README.md  @saoudrizwan @nickbaumann98
+/.github/   @saoudrizwan
+/README.md  @saoudrizwan @nickbaumann98

.github/workflows/publish-nightly.yml

@@ -69,5 +69,7 @@ jobs:
               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"

.github/workflows/test.yml

@@ -90,10 +90,14 @@ jobs:
             - name: Build Tests and Extension
               run: npm run pretest
 
-            - name: Unit Tests
+            - name: Unit Tests (with coverage on Linux)
               run: |
-                npm install --no-save nyc
-                npx nyc --nycrc-path .nycrc.unit.json --reporter=lcov npm run test:unit
+                if [ "${{ runner.os }}" = "Linux" ]; then
+                  npm install --no-save nyc
+                  npx nyc --nycrc-path .nycrc.unit.json --reporter=lcov npm run test:unit
+                else
+                  npm run test:unit
+                fi
 
             # Run extension tests with coverage
             - name: Extension Integration Tests with Coverage
@@ -127,6 +131,8 @@ jobs:
                   path: |
                       extension_coverage.txt
                       webview-ui/webview_coverage.txt
+                      coverage-unit/lcov.info
+                      webview-ui/coverage/lcov.info
 
             # Set the check as failed if any of the tests failed
             - name: Check for test failures
@@ -143,6 +149,69 @@ jobs:
                       exit 1
                   fi
 
+    test-platform-integration:
+        runs-on: ubuntu-latest
+        steps:
+            - name: Checkout code
+              uses: actions/checkout@v4
+
+            - name: Setup Node.js environment
+              uses: actions/setup-node@v4
+              with:
+                  node-version: 22
+
+            - name: Cache root dependencies
+              uses: actions/cache@v4
+              id: root-cache
+              with:
+                  path: node_modules
+                  key: ${{ runner.os }}-npm-${{ hashFiles('package-lock.json') }}
+
+            - 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') }}
+
+            # Cache testing-platform dependencies
+            - name: Cache testing-platform dependencies
+              uses: actions/cache@v4
+              id: testing-platform-cache
+              with:
+                path: testing-platform/node_modules
+                key: ${{ runner.os }}-npm-testing-platform-${{ hashFiles('testing-platform/package-lock.json') }}
+
+            - name: Install root dependencies
+              if: steps.root-cache.outputs.cache-hit != 'true'
+              run: npm ci
+
+            - name: Install webview-ui dependencies
+              if: steps.webview-cache.outputs.cache-hit != 'true'
+              run: cd webview-ui && npm ci
+
+            - name: Compile standalone
+              run: npm run compile-standalone
+
+            - name: Install testing platform dependencies
+              if: steps.testing-platform-cache.outputs.cache-hit != 'true'
+              run: cd testing-platform && npm ci
+
+            - name: Running testing platform integration spec tests
+              continue-on-error: true
+              timeout-minutes: 7
+              # Temporarily wrapping the test command to always return a neutral exit code.
+              # This prevents the job from showing as failed and avoids distracting developers
+              # until the integration tests are ready to be enforced.
+              run: |
+                npm run test:tp-orchestrator -- tests/specs/ --count=1 --coverage || true
+
+            - name: Save Coverage Reports
+              uses: actions/upload-artifact@v4
+              with:
+                name: test-platform-integration-core-coverage
+                path: coverage/**/lcov.info
+
     coverage:
         needs: test
         runs-on: ubuntu-latest
@@ -221,3 +290,51 @@ jobs:
                     --verbose
               env:
                   GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+    qlty:
+        needs: [test, test-platform-integration]
+        runs-on: ubuntu-latest
+        # Run on PRs to main, pushes to main, and manual dispatches
+        steps:
+            - name: Checkout code
+              uses: actions/checkout@v4
+              with:
+                  fetch-depth: 0 # Fetch all history for accurate comparison
+
+            - name: Download unit tests coverage reports
+              uses: actions/download-artifact@v4
+              with:
+                  name: pr-coverage-reports
+                  path: .
+
+            - name: Upload core unit tests coverage to Qlty
+              uses: qltysh/qlty-action/coverage@v2
+              with:
+                  token: ${{ secrets.QLTY_COVERAGE_TOKEN }}
+                  # we can merge multiple files if necessary
+                  files: |
+                    coverage-unit/lcov.info
+                  tag: unit:core
+
+            - name: Upload webview-ui unit tests coverage to Qlty
+              uses: qltysh/qlty-action/coverage@v2
+              with:
+                  token: ${{ secrets.QLTY_COVERAGE_TOKEN }}
+                  # we can merge multiple files if necessary
+                  files: |
+                    webview-ui/coverage/lcov.info
+                  tag: unit:webview-ui
+                  add-prefix: webview-ui/
+
+            - name: Download test platform integration core coverage artifact
+              uses: actions/download-artifact@v4
+              with:
+                name: test-platform-integration-core-coverage
+                path: integration-core-coverage-reports
+
+            - name: Upload core integration tests coverage to Qlty
+              uses: qltysh/qlty-action/coverage@v2
+              with:
+                token: ${{ secrets.QLTY_COVERAGE_TOKEN }}
+                files: integration-core-coverage-reports/**/lcov.info
+                tag: integration:core

.github/workflows/trigger-jetbrains-tests.yml

@@ -0,0 +1,53 @@
+name: Trigger Jetbrains Plugin <-> Cline Tests
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+permissions:
+  contents: read
+concurrency:
+  group: jetbrains-trigger-${{ github.event.number }}
+  cancel-in-progress: true
+
+jobs:
+  trigger-integration-test:
+    name: Run Tests
+    runs-on: ubuntu-latest
+    steps:
+      - name: Generate GitHub App Token
+        id: app-token
+        uses: actions/create-github-app-token@v1
+        with:
+          app-id: 1998650
+          private-key: ${{ secrets.CLINE_JETBRAINS_WORKFLOW_KEY }}
+          owner: cline
+          repositories: intellij-plugin
+
+      - name: Trigger IntelliJ Plugin Integration Test
+        run: |
+          curl -X POST \
+            -H "Authorization: Bearer ${{ steps.app-token.outputs.token }}" \
+            -H "Accept: application/vnd.github.v3+json" \
+            -H "User-Agent: cline-pr-trigger" \
+            -H "Content-Type: application/json" \
+            https://api.github.com/repos/cline/intellij-plugin/dispatches \
+            -d @- <<EOF
+          {
+            "event_type": "cline-pr-check",
+            "client_payload": {
+              "pr_number": "${{ github.event.number }}",
+              "branch_name": "${{ github.head_ref }}",
+              "action": "${{ github.event.action }}",
+              "sha": "${{ github.event.pull_request.head.sha }}",
+              "pr_title": ${{ toJSON(github.event.pull_request.title) }},
+              "pr_url": "${{ github.event.pull_request.html_url }}"
+            }
+          }
+          EOF
+
+      - name: Log trigger details
+        run: |
+          echo "Triggered IntelliJ Plugin integration test for:"
+          echo "  PR #${{ github.event.number }}: ${{ github.event.pull_request.title }}"
+          echo "  Branch: ${{ github.head_ref }}"
+          echo "  Action: ${{ github.event.action }}"
+          echo "  SHA: ${{ github.event.pull_request.head.sha }}"

.gitignore

@@ -21,7 +21,7 @@ webview-ui/src/**/*.js.map
 # Ignore coverage directories and files
 coverage
 coverage-unit
-coverage-integration
+.nyc_output
 # But don't ignore the coverage scripts in .github/scripts/
 !.github/scripts/coverage/
 
@@ -37,6 +37,3 @@ test-results
 
 ## CLI pre-release  ##
 /cli 
-
-.nyc_output/
-coverage-integration/

.husky/pre-commit

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

.mocharc.json

@@ -3,12 +3,7 @@
 		"ts"
 	],
 	"spec": [
-		"src/**/__tests__/*.ts",
-		"src/**/*.test.ts"
-	],
-	"ignore": [
-		"src/test/**/*.test.ts",
-		"src/test/e2e/**/*.test.ts"
+		"src/**/__tests__/*.ts"
 	],
 	"require": [
 		"ts-node/register",

.nycrc.unit.json

@@ -6,23 +6,36 @@
 		"lcov"
 	],
 	"include": [
-		"src/**/*.ts",
-		"src/**/*.js"
+		"src/**/*.ts"
 	],
 	"exclude": [
 		"**/*.d.ts",
-		"**/*.test.ts",
-		"**/*.test.js",
-		"**/*.spec.ts",
-		"**/*.spec.js",
+
+		"**/*.{test,spec}.{js,jsx,ts,tsx,mjs,cjs}",
+		"**/__tests__/**",
 		"**/test/**",
 		"**/tests/**",
+		"**/.nyc_output/**",
+		"**/.vscode-test/**",
+		"**/tests-results/**",
+		"src/test/**",
+
+		"src/generated/**",
+
 		"**/node_modules/**",
 		"**/dist/**",
 		"**/out/**",
+		"**/build/**",
 		"**/coverage/**",
-		"src/test/**",
-		"src/generated/**"
+		"**/coverage-unit/**",
+		"**/proto/**",
+
+		"**/*.{config,setup}.{js,ts,mjs,cjs}",
+		"**/vite-env.d.ts",
+
+		"**/*.{css,scss,sass,less,styl}",
+		"**/*.{svg,png,jpg,jpeg,gif,ico}",
+		"**/*.{json,yaml,yml}"
 	],
 	"extension": [
 		".ts",

.vscode-test.mjs

@@ -2,22 +2,17 @@ import { defineConfig } from "@vscode/test-cli"
 import path from "path"
 
 export default defineConfig({
-	files: "src/test/*.test.ts",
+	files: "{out/**/*.test.js,src/**/*.test.js,!src/test/e2e/**/*.test.js,!out/src/test/e2e/**/*.test.js}",
 	mocha: {
 		ui: "bdd",
-		timeout: 20000,
-		require: ["ts-node/register/transpile-only", "./test-setup-integration.js"],
+		timeout: 20000, // Maximum time (in ms) that a test can run before failing
+		/** Set up alias path resolution during tests
+		 * @See {@link file://./test-setup.js}
+		 */
+		require: ["./test-setup.js"],
 	},
 	workspaceFolder: "test-workspace",
 	version: "stable",
 	extensionDevelopmentPath: path.resolve("./"),
 	launchArgs: ["--disable-extensions"],
-	env: {
-		TS_NODE_PROJECT: "./tsconfig.test.json",
-	},
-	coverage: {
-		reporter: ["lcov", "text"],
-		include: ["src/**/*.ts"],
-		exclude: ["**/*.d.ts", "**/*.test.ts", "**/*.spec.ts", "**/test/**", "**/tests/**", "src/test/**", "src/generated/**"],
-	},
 })

.vscode/launch.json

@@ -12,8 +12,7 @@
 			"args": [
 				"--extensionDevelopmentPath=${workspaceFolder}",
 				"--disable-workspace-trust",
-				// Avoid conflicts with the nightly extension
-				"--disable-extension=saoudrizwan.cline-nightly",
+				"--disable-extensions", // Avoid conflicts with installed extensions
 				"${workspaceFolder}"
 			],
 			"outFiles": [
@@ -33,7 +32,7 @@
 			"args": [
 				"--extensionDevelopmentPath=${workspaceFolder}",
 				"--disable-workspace-trust",
-				"--disable-extension=saoudrizwan.cline-nightly",
+				"--disable-extensions", // Avoid conflicts with installed extensions
 				"${workspaceFolder}"
 			],
 			"outFiles": [
@@ -53,7 +52,7 @@
 			"args": [
 				"--extensionDevelopmentPath=${workspaceFolder}",
 				"--disable-workspace-trust",
-				"--disable-extension=saoudrizwan.cline-nightly",
+				"--disable-extensions", // Avoid conflicts with installed extensions
 				"${workspaceFolder}"
 			],
 			"outFiles": [
@@ -75,9 +74,8 @@
 				"--user-data-dir=${workspaceFolder}/dist/tmp/user",
 				"--profile-temp",
 				"--sync=off",
-				"--disable-extensions",
+				"--disable-extensions", // Avoid conflicts with installed extensions
 				"--extensionDevelopmentPath=${workspaceFolder}",
-				"--disable-extension=saoudrizwan.cline-nightly",
 				"${workspaceFolder}"
 			],
 			"outFiles": [

.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 +1,102 @@
 # Changelog
 
+## [3.32.1]
+
+- Preserve reasoning traces for Cline/OpenRouter/Anthropic providers to maintain conversation integrity
+- Add automatically retry on rate limit errors with SAP AI Core provider
+- Fix Cline accounts using stale id token at refresh response
+- Minor UI improvements to Settings and Task Header
+
+## [3.32.0]
+
+- Added the new code-supernova-1-million stealth model, available for free and delivering a 1 million token context window
+- Changes to inform Cline about commands that are available on your system
+
+## [3.31.1]
+
+- Version bump
+
+## [3.31.0]
+
+- UI Improvements: New task header and focus chain design to take up less space for a cleaner experience
+- Voice Mode: Experimental feature that must be enabled in settings for hands-free coding
+- YOLO Mode: Enable in settings to let Cline approve all actions and automatically switch between plan/act mode
+- Fix Oracle Code Assist provider issues
+
+## [3.30.3]
+
+- Add Oracle Code Assist provider
+
+## [3.30.2]
+
+- Fix UI tests
+
+## [3.30.1]
+
+- Fix model list not being updated in time for user to use shortcut button to update model to stealth model
+- Fix flicker issue when switching modes
+- Fix Sticky header in settings view overlaping with content on scroll
+- Add experimental yolo mode feature that disables all user approvals and automatically executes a task and navigates through plan to act mode until the task is complete
+
+## [3.30.0]
+
+- Add code-supernova stealth model
+
+## [3.29.2]
+
+- Fix: Reverted change that caused formatting issues
+- Fix: Moonshot - Pass max_tokens value to provider
+
+## [3.29.1]
+
+- Changeset bump + Announcement banner update
+
+## [3.29.0]
+
+- Updated Baseten provider to fetch models from server
+- Fix: Updated insufficient balance URL for easy Cline balance top-ups
+- Accessibility: Improvements to screen readers in MCP, Cline Rules, workflows, and history views.
+
+## [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

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`

biome.jsonc

@@ -1,5 +1,5 @@
 {
-	"$schema": "https://biomejs.dev/schemas/2.1.4/schema.json",
+	"$schema": "https://biomejs.dev/schemas/2.2.4/schema.json",
 	"vcs": {
 		"enabled": true,
 		"clientKind": "git",
@@ -58,7 +58,17 @@
 				"useNumberNamespace": "off",
 				"noInferrableTypes": "off",
 				"useTemplate": "off",
-				"noUselessElse": "off"
+				"noUselessElse": "off",
+				"noRestrictedImports": {
+					"level": "error",
+					"options": {
+						"paths": {
+							"vscode": {
+								"message": "Use appropriate HostProvider methods or abstraction layer instead."
+							}
+						}
+					}
+				}
 			},
 			"suspicious": {
 				"noDoubleEquals": "warn",
@@ -114,16 +124,17 @@
 	"files": {
 		"includes": [
 			"**",
-			"!**/dist/**",
-			"!**/dist-*/**",
-			"!**/out/**",
-			"!**/evals/**",
-			"!**/playwright/**",
-			"!**/test-results/**",
-			"!**/node_modules/**",
-			"!**/webview-ui/build/**",
-			"!**/generated/**",
-			"!**/proto/**"
+			"!**/dist",
+			"!**/dist-*",
+			"!**/out",
+			"!**/evals",
+			"!**/playwright",
+			"!**/test-results",
+			"!**/node_modules",
+			"!**/webview-ui/build",
+			"!**/generated",
+			"!**/proto",
+			"!**/tests/specs"
 		]
 	},
 	"plugins": [
@@ -133,9 +144,9 @@
 		{
 			"includes": [
 				"**",
-				"!**/hosts/vscode/**",
 				"!**/test/**",
 				"!**/*.test.ts",
+				"!src/hosts/vscode/**",
 				"!src/dev/**",
 				"!src/extension.ts",
 				"!src/integrations/git/commit-message-generator.ts",
@@ -146,20 +157,90 @@
 				"src/dev/grit/vscode-api.grit"
 			]
 		},
+		// Only ExtensionContext is allowed to be imported from 'vscode' in the files below.
 		{
 			"includes": [
-				"**",
-				"!src/core/storage/state-migrations.ts",
-				"!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"
+				"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/core/storage/StateManager.ts"
 			],
-			"plugins": [
-				"src/dev/grit/use-cache-service.grit"
-			]
+			"linter": {
+				"rules": {
+					"style": {
+						"noRestrictedImports": {
+							"level": "error",
+							"options": {
+								"paths": {
+									"vscode": {
+										"message": "Use appropriate HostProvider methods or abstraction layer instead.",
+										"allowImportNames": [
+											"ExtensionContext"
+										]
+									}
+								}
+							}
+						}
+					}
+				}
+			}
+		},
+		// Only workspace is allowed to be imported from 'vscode' in the files below.
+		{
+			"includes": [
+				"src/core/storage/state-migrations.ts"
+			],
+			"linter": {
+				"rules": {
+					"style": {
+						"noRestrictedImports": {
+							"level": "error",
+							"options": {
+								"paths": {
+									"message": "Use appropriate HostProvider methods or abstraction layer instead.",
+									"vscode": {
+										"allowImportNames": [
+											"ExtensionContext",
+											"workspace"
+										]
+									}
+								},
+								"patterns": [
+									{
+										"message": "Use appropriate HostProvider methods or abstraction layer instead.",
+										"group": [
+											"!vscode/*",
+											"vscode/ExtensionContext/globalState/*",
+											"vscode/ExtensionContext/workspaceState/*",
+											"vscode/ExtensionContext/secrets/*",
+											"vscode/workspace/getConfiguration/*"
+										]
+									}
+								]
+							}
+						}
+					}
+				}
+			}
+		},
+		// Extension.ts allows to use vscode imports directly as it's the main entry point for VS Code extension.
+		{
+			"includes": [
+				"src/extension.ts",
+				"src/hosts/vscode/**",
+				"**/test/**",
+				"**/*.test.ts",
+				"src/dev/**"
+			],
+			"linter": {
+				"rules": {
+					"style": {
+						"noRestrictedImports": "off"
+					}
+				}
+			}
 		}
 	]
 }

docs/docs.json

@@ -91,6 +91,7 @@
 					"features/focus-chain",
 					"features/auto-compact",
 					"features/editing-messages",
+					"features/dictation",
 					{
 						"group": "@ Mentions",
 						"pages": [
@@ -121,6 +122,13 @@
 							"features/commands-and-shortcuts/git-integration",
 							"features/commands-and-shortcuts/keyboard-shortcuts"
 						]
+					},
+					{
+						"group": "Customization",
+						"pages": [
+							"features/customization/opening-cline-in-sidebar",
+							"features/customization/disable-terminal-pagers"
+						]
 					}
 				]
 			},
@@ -183,7 +191,8 @@
 					"provider-config/openrouter",
 					"provider-config/sap-aicore",
 					"provider-config/vercel-ai-gateway",
-					"provider-config/requesty"
+					"provider-config/requesty",
+					"provider-config/baseten"
 				]
 			},
 			{

docs/features/customization/disable-terminal-pagers.mdx

@@ -0,0 +1,79 @@
+---
+title: "Disable Terminal Pagers During Cline Sessions"
+description: "Make CLI output non-interactive when Cline runs commands by detecting the CLINE_ACTIVE environment variable and disabling pagers like less."
+---
+
+Many CLI tools (like Git) use a pager such as `less` for interactive, scrollable output. When Cline runs commands in your terminal, that interactivity gets in the way — the pager can pause on the first page and block progress. You can configure your shell so that when a terminal is spawned by Cline, pagers are disabled and output streams through normally.
+
+## How it works
+
+Cline sets an environment variable for terminals it opens to run commands:
+
+- `CLINE_ACTIVE` — non-empty when the shell is running under Cline
+
+You can detect this variable in your shell startup file and adjust environment variables or aliases only for Cline-run sessions. This keeps your normal interactive terminals unchanged.
+
+## Quick setup (Zsh/Bash)
+
+Add the following to your `~/.zshrc`, `~/.bashrc`, or `~/.bash_profile`:
+
+```bash
+# Disable pagers when the terminal is launched by Cline
+if [[ -n "$CLINE_ACTIVE" ]]; then
+  export PAGER=cat
+  export GIT_PAGER=cat
+  export SYSTEMD_PAGER=cat
+  export LESS="-FRX"
+fi
+```
+
+<Note>
+- `PAGER=cat` ensures generic pager-aware tools print directly to stdout
+- `GIT_PAGER=cat` prevents Git from invoking `less`
+- `SYSTEMD_PAGER=cat` disables paging in systemd tools (if present)
+- `LESS="-FRX"` makes `less` behave more like streaming output if a tool still calls it
+</Note>
+
+This configuration only applies when `CLINE_ACTIVE` is set, so your normal terminals keep their usual interactive behavior.
+
+## Verify
+
+- Open a task in Cline that runs terminal commands and check:
+  - `echo "$CLINE_ACTIVE"` prints a non-empty value
+  - `git log` or other long outputs should stream without pausing
+- If changes don't take effect:
+  - Make sure you updated the correct startup file for your shell
+  - Restart VS Code/Cursor so integrated terminals reload your shell config
+  - Confirm your terminal profile sources your `~/.zshrc` or `~/.bashrc`
+
+## Optional tweaks
+
+- Prefer command-line options when you don't want to rely on env vars:
+
+```bash
+# One-off usage (no aliases)
+git --no-pager log -n 50 --decorate --oneline
+systemctl --no-pager status nginx
+journalctl --no-pager -u nginx -n 200
+less -FRX README.md
+```
+
+- You can also override paging via shell aliases scoped to Cline sessions using options rather than env vars:
+
+```bash
+if [[ -n "$CLINE_ACTIVE" ]]; then
+  # Make 'less' non-interactive by default
+  alias less='less -FRX'
+  # Disable paging for common tools via CLI flags
+  alias git='command git --no-pager'
+  alias systemctl='command systemctl --no-pager'
+  alias journalctl='command journalctl --no-pager'
+fi
+```
+
+- If you prefer environment variables, many CLIs also respect a generic or tool-specific pager variable:
+  - Git: `GIT_PAGER=cat`
+  - Systemd: `SYSTEMD_PAGER=cat`
+  - Man pages: `MANPAGER=cat` (not typically needed for Cline-driven commands)
+
+- Aliases affect the current interactive shell, while environment variables propagate to child processes. Choose the approach that best fits your workflow.

docs/features/customization/opening-cline-in-sidebar.mdx

@@ -0,0 +1,60 @@
+---
+title: "Opening Cline in the Right Sidebar"
+description: "Learn how to open Cline in the right sidebar in VS Code and Cursor"
+---
+
+By default, when you first install Cline, it appears in VS Code's left sidebar alongside your file explorer and other extensions. However, for a better coding experience, we recommend moving Cline to the right sidebar. This allows you to keep your project files visible in the left sidebar while chatting with Cline on the right, giving you full visibility of your codebase as Cline works on your project.
+
+## VS Code
+
+To open Cline in the right sidebar:
+
+<Steps>
+  <Step title="Align Extension View">
+    Make sure your extension view is aligned vertically to the left
+  </Step>
+  <Step title="Open Right Side View">
+    Click the button that opens the right side panel in VS Code (typically used to open GitHub Copilot chat). Optionally use the `Option + CMD/Ctrl + B` shortcut.
+  </Step>
+  <Step title="Drag Cline Icon">
+    Drag the Cline icon over to the nav panel at the top of that right view
+  </Step>
+</Steps>
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/vscode_right_view.gif"
+		alt="VS Code Right Sidebar Setup"
+	/>
+</Frame>
+
+## Cursor
+
+To open Cline in the right sidebar:
+
+<Steps>
+  <Step title="Align Extensions">
+    Cursor uses a horizontal activity bar by default to optimize space for the AI chat interface ([see here for details](https://cursor.com/docs/configuration/migrations/vscode#activity-bar-orientation)). To switch to vertical:
+    
+    1. Open the Command Palette (`CMD/Ctrl + Shift + P`)
+    2. Search for "Preferences: Open Settings (UI)"
+    3. Search for `workbench.activityBar.orientation`
+    4. Set the value to `vertical`
+    5. Restart Cursor for the changes to take effect
+  </Step>
+  <Step title="Open Agent Panel">
+    Click the Cursor cube icon button that opens Cursor's agent (right side view panel)
+  </Step>
+  <Step title="Drag to Three Dots">
+    Drag the Cline icon directly onto the three dots button - it doesn't work if you just drag it to the top, it has to be the three dots
+  </Step>
+</Steps>
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/cursor-side-bar.gif"
+		alt="Cursor Right Sidebar Setup"
+	/>
+</Frame>
+
+Once set up, Cline will load on the right side and you can use it as normal.

docs/features/dictation.mdx

@@ -0,0 +1,60 @@
+---
+title: Dictation
+description:
+---
+
+Cline lets you transcribe speech to text in an easy, built-in service
+
+## Get Started
+
+1. **Enable Dictation** in Feature Settings.
+2. **Click the microphone** in the chat input area.
+3. **Speak** - the button turns red while recording.
+4. **Click Stop Recording** when done.
+5. **Wait for transcription** - "[Transcribing...]" will appear and then the finished transcription will appear.
+
+## Settings
+
+Enable or disable dictation in Feature Settings by toggling "Enable Dictation." You can also change the transcription language to one of the supported languages.
+
+## Requirements
+
+Cline uses FFmpeg to capture your voice across all platforms:
+
+-   **macOS**: FFmpeg (via Homebrew: `brew install ffmpeg`)
+-   **Linux**: FFmpeg (via apt: `sudo apt-get install ffmpeg`)
+-   **Windows**: FFmpeg (via winget: `winget install Gyan.FFmpeg`)
+
+If you don't have FFmpeg installed, Cline will automatically detect this and prompt you to install it with a single click.
+
+## Technical Details
+
+### Independent from Chat Provider
+
+The voice transcription feature works completely independently from whatever chat provider you're using. You can use Claude, GPT-4, or any other model for your conversations, and voice transcription will always use Cline's own transcription service. As long as you have a valid Cline account with enough credits, dictation will work regardless of your chat model choice.
+
+### Audio Format
+
+Voice recordings are captured in WebM format using the Opus codec for optimal compression. The system records in mono (single channel) at a 16kHz sample rate, which is specifically optimized for voice recognition. The bitrate is set to 32kbps to keep file sizes efficient while maintaining good audio quality.
+
+### Privacy & Security
+
+Your audio is recorded locally on your machine and only the audio file itself is sent to Cline's transcription service for processing. No audio is stored anywhere after transcription is complete, and all temporary files are automatically cleaned up to protect your privacy.
+
+## Troubleshooting
+
+`Failed to start recording` - Audio recording tools aren't installed. Cline will prompt you to install FFmpeg - just follow the chat instructions.
+
+`Invalid audio format or request data` - Usually an audio recording issue. Make sure FFmpeg is properly installed and working.
+
+`Authentication failed` - You need to reauthenticate your Cline account. Sign out and back in, then check your internet connection.
+
+`Insufficient credits for transcription service` - Your Cline account doesn't have enough credits. Check your balance and purchase more if needed.
+
+`Cannot connect to transcription service` - Connection issue. Check your internet connection and firewall settings aren't blocking Cline's servers.
+
+## API Usage
+
+Voice transcription uses Cline's transcription service, which requires credits from your Cline account. Currently, voice transcription is billed at $0.006 per minute of audio.
+
+**Note:** We are still experimenting with this feature and pricing may change in the future.

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

@@ -1,6 +1,6 @@
 ---
-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."
+title: "Installing Cline for JetBrains"
+description: "Install Cline in your favorite JetBrains IDE with the same powerful AI assistance you know from VSCode."
 ---
 
 <Frame>
@@ -20,109 +20,103 @@ Cline for JetBrains works almost identically to Cline in VSCode. All the core fe
 	/>
 </Frame>
 
-<Note>Cline for JetBrains is in early access. All core features are functional, with ongoing improvements based on user feedback.</Note>
+Cline is now available on the [JetBrains Marketplace](https://plugins.jetbrains.com/plugin/28247-cline). Works in IntelliJ IDEA, PyCharm, WebStorm, DataSpell, PhpStorm, and all other JetBrains IDEs.
 
 ## 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:
+**Method 1: Direct from your IDE**
 
-### 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
+1. Open your JetBrains IDE
+2. Press `Ctrl+Alt+S` (Windows/Linux) or `Cmd+,` (macOS) 
+3. Go to Plugins → Marketplace tab
+4. Search "Cline" and click Install
+5. Restart your IDE
 
 <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"
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-marketplace-search.png"
+		alt="JetBrains marketplace showing Cline plugin search results"
 	/>
 </Frame>
 
-2. **Install from Disk:**
-   - Open your JetBrains IDE
-   - Go to **IntelliJ IDEA** (or whichever IDE you are in) → **Settings**
+**Method 2: Browser install**
 
-<Frame>
-	<img
-		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-settings.png"
-		alt="JetBrains IDE settings dialog"
-	/>
-</Frame>
+Visit [plugins.jetbrains.com/plugin/28247-cline](https://plugins.jetbrains.com/plugin/28247-cline) and click the "Install to IDE" button. Your IDE will open and prompt you to install.
 
-   - Select **Plugins** from the left sidebar
-   - Click the gear icon ⚙️ and select **Install Plugin from Disk...**
+<details>
+<summary>Method 3: Manual installation</summary>
 
-<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>
+Download the plugin from the [marketplace page](https://plugins.jetbrains.com/plugin/28247-cline), then:
 
-   - Select the downloaded `.zip` file
+1. Go to Settings → Plugins
+2. Click the gear icon → Install Plugin from Disk
+3. Select the downloaded `.zip` file
+4. Restart your IDE
 
-<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
+</details>
 
 ## Getting Started with Cline
 
-After installation, you'll find Cline in your IDE:
+After installation, you'll find Cline in your IDE. Look for the Cline tool window (usually on the right side) or go to **View** → **Tool Windows** → **Cline**.
 
-1. **Open Cline:**
-   - Look for the Cline tool window (usually on the right side)
-   - Or go to **View** → **Tool Windows** → **Cline**
+Sign in is optional - you can also bring your own API key. If you want to sign in, 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.
 
-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?"
+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
+The terminal integration works differently in JetBrains. Unlike VSCode where terminal output streams directly to the chat, JetBrains shows command output in a collapsible section. Commands still execute successfully - you just need to expand the **Command Output** section to see results.
 
 ## What Works
 
-Everything else works exactly like VSCode:
+Everything else works exactly like VSCode. Cline can read, write, and edit files with the same precision. All his tools work identically - file operations, web browsing, you name it. 
 
-- **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
+You get full support for:
+- API providers (Anthropic, OpenAI, local models)
+- MCP servers and custom tools
+- Cline rules and workflows
+- @ mentions for files, folders, and problems
+- Drag & drop for files and images
 
 ## 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
+Cline automatically understands your project structure, just like in VSCode. He works with any language your JetBrains IDE supports - Java, Python, JavaScript, Go, whatever you're building.
+
+I find it helpful to share error messages and stack traces directly in the chat when debugging. You can also ask him to review your code changes before committing.
 
 ## Troubleshooting
 
+### Plugin Installation Issues
+
+If you can't find Cline in the marketplace:
+- Make sure you're searching in the **Marketplace** tab (not Installed)
+- Try searching for "Cline AI" or just "Cline"
+- Check that your IDE version is compatible (2023.1 or later recommended)
+
+If installation fails:
+- Restart your IDE and try again
+- Check your internet connection
+- Try installing from disk as an alternative
+
+### Plugin Not Appearing
+
 If you don't see the Cline tool window after installation:
-- Restart your IDE completely
+- Restart your IDE completely (File → Exit and reopen)
 - Check **View** → **Tool Windows** → **Cline**
-- Ensure the plugin is enabled in **Settings** → **Plugins**
+- Verify the plugin is enabled in **Settings** → **Plugins** → **Installed** tab
+- Look for the Cline icon in your IDE's tool window bar (usually on the right side)
+
+### Common Issues
+
+**Plugin appears to be installed but doesn't work:**
+- Ensure you've restarted your IDE after installation
+- Check if there are any error messages in the IDE's event log
+- Try disabling and re-enabling the plugin in Settings
+
+**Performance or compatibility issues:**
+- Make sure you're using a supported JetBrains IDE version
+- Check for IDE updates that might improve compatibility
+- Consider allocating more memory to your IDE if needed
 
 Having other issues? Join our [Discord community](https://discord.gg/cline) for help from the team and other users.
 

docs/getting-started/installing-cline.mdx

@@ -1,13 +1,17 @@
 ---
 title: "Installing Cline"
-description: "Cline is a VS Code extension that brings AI-powered coding assistance directly
-    to your editor. Install using one of these methods:"
+description: "Cline brings AI-powered coding assistance to your editor. Available for VS Code and JetBrains IDEs."
 ---
 
-### Installation Options
+## Choose Your Editor
 
--   **VS Code Marketplace (Recommended):** Fastest method for standard VS Code and Cursor users.
--   **Open VSX Registry:** For VS Code-compatible editors like VSCodium.
+Cline works across multiple development environments:
+
+-   **VS Code/Cursor:** Install from VS Code Marketplace (most popular)
+-   **JetBrains IDEs:** Install from JetBrains Marketplace - works in IntelliJ IDEA, PyCharm, WebStorm, and more
+-   **VSCodium/Windsurf:** Install from Open VSX Registry
+
+## VS Code Installation
 
 ### VS Code Marketplace: Step-by-Step Setup
 
@@ -46,6 +50,18 @@ For VS Code-compatible editors without Marketplace access (like VSCodium and Win
 4. Select "Cline" by saoudrizwan and click **Install**.
 5. Reload if prompted.
 
+## JetBrains Installation
+
+For IntelliJ IDEA, PyCharm, WebStorm, DataSpell, and other JetBrains IDEs:
+
+1. Open your JetBrains IDE
+2. Press `Ctrl+Alt+S` (Windows/Linux) or `Cmd+,` (macOS) to open Settings
+3. Go to Plugins → Marketplace tab
+4. Search "Cline" and click Install
+5. Restart your IDE
+
+**Need more help?** See our [complete JetBrains installation guide](/getting-started/installing-cline-jetbrains) for screenshots and troubleshooting.
+
 ### Creating Your Cline Account
 
 Now that you have Cline installed, let's get you set up with your account:

docs/mcp/configuring-mcp-servers.mdx

@@ -7,7 +7,7 @@ title: "Configuring MCP Servers"
 Utilizing MCP servers will increase your token usage. Cline offers the ability to restrict or disable MCP server functionality as desired.
 
 1. Click the "MCP Servers" icon in the top navigation bar of the Cline extension.
-2. Select the "Installed" tab, and then Click the "Advanced MCP Settings" link at the bottom of that pane.
+2. Select the "Configure" tab, and then Click the "Advanced MCP Settings" link at the bottom of that pane.
 3. Cline will open a new settings window. find `Cline>Mcp:Mode` and make your selection from the dropdown menu.
 
 <Frame>
@@ -56,7 +56,7 @@ To set the maximum time to wait for a response after a tool call to the MCP serv
 Settings for all installed MCP servers are located in the `cline_mcp_settings.json` file:
 
 1. Click the MCP Servers icon at the top navigation bar of the Cline pane.
-2. Select the "Installed" tab.
+2. Select the "Configure" tab.
 3. Click the "Configure MCP Servers" button at the bottom of the pane.
 
 The file uses a JSON format with a `mcpServers` object containing named server configurations:

docs/mcp/connecting-to-a-remote-server.mdx

@@ -54,7 +54,7 @@ Please note: Smithery is maintained independently and is not affiliated with our
 
 ### Managing Installed MCP Servers
 
-Once added, your MCP servers appear in the "Installed" tab where you can:
+Once added, your MCP servers appear in the "Configure" tab where you can:
 
 #### View Server Status
 
@@ -98,7 +98,7 @@ If a server fails to connect:
 
 For advanced users, Cline stores MCP server configurations in a JSON file that can be modified:
 
-1. In the "Installed" tab, click "Configure MCP Servers" to access the settings file
+1. In the "Configure" tab, click "Configure MCP Servers" to access the settings file
 2. The configuration for each server follows this format:
 
 ```json

docs/package-lock.json

@@ -1386,7 +1386,7 @@
 			"integrity": "sha512-/uR4hAwpcJW9+zbmZL48kKFnWLkOxhIqoGWvZzjg0CniVhR4emtQJAps80WqLAhz0iJgCQxg/axtA7leaznDzQ==",
 			"license": "Elastic-2.0",
 			"dependencies": {
-				"axios": "^1.8.3",
+				"axios": "^1.12.0",
 				"openapi-types": "^12.0.0"
 			},
 			"engines": {
@@ -2688,9 +2688,9 @@
 			}
 		},
 		"node_modules/axios": {
-			"version": "1.11.0",
-			"resolved": "https://registry.npmjs.org/axios/-/axios-1.11.0.tgz",
-			"integrity": "sha512-1Lx3WLFQWm3ooKDYZD1eXmoGO9fxYQjrycfHFC8P0sCfQVXyROp0p9PFWBehewBOdCwHc+f/b8I0fMto5eSfwA==",
+			"version": "1.12.2",
+			"resolved": "https://registry.npmjs.org/axios/-/axios-1.12.2.tgz",
+			"integrity": "sha512-vMJzPewAlRyOgxV2dU0Cuz2O8zzzx9VYtbJOaBgXFeLc4IV/Eg50n4LowmehOOR61S8ZMpc2K5Sa7g6A4jfkUw==",
 			"license": "MIT",
 			"dependencies": {
 				"follow-redirects": "^1.15.6",

docs/provider-config/baseten.mdx

@@ -0,0 +1,115 @@
+---
+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:
+For the most updated pricing, please visit: https://www.baseten.co/products/model-apis/
+
+**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`- Advanced coding and reasoning (262K context) - \$0.38/\$1.53 per 1M tokens
+-   `Qwen/Qwen3-235B-A22B-Instruct-2507` - 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.

esbuild.mjs

@@ -6,7 +6,7 @@ import * as esbuild from "esbuild"
 const __filename = fileURLToPath(import.meta.url)
 const __dirname = path.dirname(__filename)
 
-const production = process.argv.includes("--production")
+const production = process.argv.includes("--production") || process.env["IS_DEBUG_BUILD"] === "false"
 const watch = process.argv.includes("--watch")
 const standalone = process.argv.includes("--standalone")
 const e2eBuild = process.argv.includes("--e2e-build")
@@ -123,15 +123,29 @@ const copyWasmFiles = {
 	},
 }
 
+const buildEnvVars = { "import.meta.url": "_importMetaUrl" }
+if (production) {
+	// IS_DEV is always disable in production builds.
+	buildEnvVars["process.env.IS_DEV"] = "false"
+}
+// Set the environment and telemetry env vars. The API key env vars need to be populated in the GitHub
+// workflows from the secrets.
+if (process.env.CLINE_ENVIRONMENT) {
+	buildEnvVars["process.env.CLINE_ENVIRONMENT"] = JSON.stringify(process.env.CLINE_ENVIRONMENT)
+}
+if (process.env.TELEMETRY_SERVICE_API_KEY) {
+	buildEnvVars["process.env.TELEMETRY_SERVICE_API_KEY"] = JSON.stringify(process.env.TELEMETRY_SERVICE_API_KEY)
+}
+if (process.env.ERROR_SERVICE_API_KEY) {
+	buildEnvVars["process.env.ERROR_SERVICE_API_KEY"] = JSON.stringify(process.env.ERROR_SERVICE_API_KEY)
+}
 // Base configuration shared between extension and standalone builds
 const baseConfig = {
 	bundle: true,
 	minify: production,
 	sourcemap: !production,
 	logLevel: "silent",
-	define: production
-		? { "import.meta.url": "_importMetaUrl", "process.env.IS_DEV": JSON.stringify(!production) }
-		: { "import.meta.url": "_importMetaUrl" },
+	define: buildEnvVars,
 	tsconfig: path.resolve(__dirname, "tsconfig.json"),
 	plugins: [
 		copyWasmFiles,

evals/package-lock.json

@@ -9,9 +9,9 @@
       "version": "0.1.0",
       "license": "MIT",
       "dependencies": {
-        "axios": "^1.8.2",
+        "axios": "^1.12.0",
         "better-sqlite3": "^11.10.0",
-        "chalk": "^4.1.2",
+        "chalk": "5.6.2",
         "commander": "^9.4.1",
         "dotenv": "^16.5.0",
         "execa": "^5.1.1",
@@ -200,12 +200,13 @@
       "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q=="
     },
     "node_modules/axios": {
-      "version": "1.10.0",
-      "resolved": "https://registry.npmjs.org/axios/-/axios-1.10.0.tgz",
-      "integrity": "sha512-/1xYAC4MP/HEG+3duIhFr4ZQXR4sQXOIe+o6sdqzeykGLx6Upp/1p8MHqhINOvGeP7xyNHe7tsiJByc4SSVUxw==",
+      "version": "1.12.2",
+      "resolved": "https://registry.npmjs.org/axios/-/axios-1.12.2.tgz",
+      "integrity": "sha512-vMJzPewAlRyOgxV2dU0Cuz2O8zzzx9VYtbJOaBgXFeLc4IV/Eg50n4LowmehOOR61S8ZMpc2K5Sa7g6A4jfkUw==",
+      "license": "MIT",
       "dependencies": {
         "follow-redirects": "^1.15.6",
-        "form-data": "^4.0.0",
+        "form-data": "^4.0.4",
         "proxy-from-env": "^1.1.0"
       }
     },
@@ -292,15 +293,12 @@
       }
     },
     "node_modules/chalk": {
-      "version": "4.1.2",
-      "resolved": "https://registry.npmjs.org/chalk/-/chalk-4.1.2.tgz",
-      "integrity": "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA==",
-      "dependencies": {
-        "ansi-styles": "^4.1.0",
-        "supports-color": "^7.1.0"
-      },
+      "version": "5.6.2",
+      "resolved": "https://registry.npmjs.org/chalk/-/chalk-5.6.2.tgz",
+      "integrity": "sha512-7NzBL0rN6fMUW+f7A6Io4h40qQlG+xGmtMxfbnH/K7TAtt8JQWVQK+6g0UXKMeVJoyV5EkkNsErQ8pVD3bLHbA==",
+      "license": "MIT",
       "engines": {
-        "node": ">=10"
+        "node": "^12.17.0 || ^14.13 || >=16.0.0"
       },
       "funding": {
         "url": "https://github.com/chalk/chalk?sponsor=1"
@@ -607,9 +605,10 @@
       }
     },
     "node_modules/form-data": {
-      "version": "4.0.3",
-      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.3.tgz",
-      "integrity": "sha512-qsITQPfmvMOSAdeyZ+12I1c+CKSstAFAwu+97zrnWAbIr5u8wfsExUzCesVLC8NgHuRUqNN4Zy6UPWUTRGslcA==",
+      "version": "4.0.4",
+      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.4.tgz",
+      "integrity": "sha512-KrGhL9Q4zjj0kiUt5OO4Mr/A/jlI2jDYs5eHBpYHPcBEVSiipAvn2Ko2HnPe20rmcuuvMHNdZFp+4IlGTMF0Ow==",
+      "license": "MIT",
       "dependencies": {
         "asynckit": "^0.4.0",
         "combined-stream": "^1.0.8",
@@ -708,6 +707,7 @@
       "version": "4.0.0",
       "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-4.0.0.tgz",
       "integrity": "sha512-EykJT/Q1KjTWctppgIAgfSO0tKVuZUjhgMr17kqTumMl6Afv3EISleU7qZUzoXDFTAHTDC4NOoG/ZxU3EvlMPQ==",
+      "license": "MIT",
       "engines": {
         "node": ">=8"
       }
@@ -843,6 +843,22 @@
         "url": "https://github.com/sponsors/sindresorhus"
       }
     },
+    "node_modules/log-symbols/node_modules/chalk": {
+      "version": "4.1.2",
+      "resolved": "https://registry.npmjs.org/chalk/-/chalk-4.1.2.tgz",
+      "integrity": "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA==",
+      "license": "MIT",
+      "dependencies": {
+        "ansi-styles": "^4.1.0",
+        "supports-color": "^7.1.0"
+      },
+      "engines": {
+        "node": ">=10"
+      },
+      "funding": {
+        "url": "https://github.com/chalk/chalk?sponsor=1"
+      }
+    },
     "node_modules/make-error": {
       "version": "1.3.6",
       "resolved": "https://registry.npmjs.org/make-error/-/make-error-1.3.6.tgz",
@@ -1003,6 +1019,22 @@
         "url": "https://github.com/sponsors/sindresorhus"
       }
     },
+    "node_modules/ora/node_modules/chalk": {
+      "version": "4.1.2",
+      "resolved": "https://registry.npmjs.org/chalk/-/chalk-4.1.2.tgz",
+      "integrity": "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA==",
+      "license": "MIT",
+      "dependencies": {
+        "ansi-styles": "^4.1.0",
+        "supports-color": "^7.1.0"
+      },
+      "engines": {
+        "node": ">=10"
+      },
+      "funding": {
+        "url": "https://github.com/chalk/chalk?sponsor=1"
+      }
+    },
     "node_modules/path-key": {
       "version": "3.1.1",
       "resolved": "https://registry.npmjs.org/path-key/-/path-key-3.1.1.tgz",
@@ -1251,6 +1283,7 @@
       "version": "7.2.0",
       "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-7.2.0.tgz",
       "integrity": "sha512-qpCAvRl9stuOHveKsn7HncJRvv501qIacKzQlO/+Lwxc9+0q2wLyv4Dfvt80/DPn2pqOBsJdDiogXGR9+OvwRw==",
+      "license": "MIT",
       "dependencies": {
         "has-flag": "^4.0.0"
       },
@@ -1635,12 +1668,12 @@
       "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q=="
     },
     "axios": {
-      "version": "1.10.0",
-      "resolved": "https://registry.npmjs.org/axios/-/axios-1.10.0.tgz",
-      "integrity": "sha512-/1xYAC4MP/HEG+3duIhFr4ZQXR4sQXOIe+o6sdqzeykGLx6Upp/1p8MHqhINOvGeP7xyNHe7tsiJByc4SSVUxw==",
+      "version": "1.12.2",
+      "resolved": "https://registry.npmjs.org/axios/-/axios-1.12.2.tgz",
+      "integrity": "sha512-vMJzPewAlRyOgxV2dU0Cuz2O8zzzx9VYtbJOaBgXFeLc4IV/Eg50n4LowmehOOR61S8ZMpc2K5Sa7g6A4jfkUw==",
       "requires": {
         "follow-redirects": "^1.15.6",
-        "form-data": "^4.0.0",
+        "form-data": "^4.0.4",
         "proxy-from-env": "^1.1.0"
       }
     },
@@ -1695,13 +1728,9 @@
       }
     },
     "chalk": {
-      "version": "4.1.2",
-      "resolved": "https://registry.npmjs.org/chalk/-/chalk-4.1.2.tgz",
-      "integrity": "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA==",
-      "requires": {
-        "ansi-styles": "^4.1.0",
-        "supports-color": "^7.1.0"
-      }
+      "version": "5.6.2",
+      "resolved": "https://registry.npmjs.org/chalk/-/chalk-5.6.2.tgz",
+      "integrity": "sha512-7NzBL0rN6fMUW+f7A6Io4h40qQlG+xGmtMxfbnH/K7TAtt8JQWVQK+6g0UXKMeVJoyV5EkkNsErQ8pVD3bLHbA=="
     },
     "chownr": {
       "version": "1.1.4",
@@ -1909,9 +1938,9 @@
       "integrity": "sha512-gew4GsXizNgdoRyqmyfMHyAmXsZDk6mHkSxZFCzW9gwlbtOW44CDtYavM+y+72qD/Vq2l550kMF52DT8fOLJqQ=="
     },
     "form-data": {
-      "version": "4.0.3",
-      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.3.tgz",
-      "integrity": "sha512-qsITQPfmvMOSAdeyZ+12I1c+CKSstAFAwu+97zrnWAbIr5u8wfsExUzCesVLC8NgHuRUqNN4Zy6UPWUTRGslcA==",
+      "version": "4.0.4",
+      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.4.tgz",
+      "integrity": "sha512-KrGhL9Q4zjj0kiUt5OO4Mr/A/jlI2jDYs5eHBpYHPcBEVSiipAvn2Ko2HnPe20rmcuuvMHNdZFp+4IlGTMF0Ow==",
       "requires": {
         "asynckit": "^0.4.0",
         "combined-stream": "^1.0.8",
@@ -2054,6 +2083,17 @@
       "requires": {
         "chalk": "^4.1.0",
         "is-unicode-supported": "^0.1.0"
+      },
+      "dependencies": {
+        "chalk": {
+          "version": "4.1.2",
+          "resolved": "https://registry.npmjs.org/chalk/-/chalk-4.1.2.tgz",
+          "integrity": "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA==",
+          "requires": {
+            "ansi-styles": "^4.1.0",
+            "supports-color": "^7.1.0"
+          }
+        }
       }
     },
     "make-error": {
@@ -2164,6 +2204,17 @@
         "log-symbols": "^4.1.0",
         "strip-ansi": "^6.0.0",
         "wcwidth": "^1.0.1"
+      },
+      "dependencies": {
+        "chalk": {
+          "version": "4.1.2",
+          "resolved": "https://registry.npmjs.org/chalk/-/chalk-4.1.2.tgz",
+          "integrity": "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA==",
+          "requires": {
+            "ansi-styles": "^4.1.0",
+            "supports-color": "^7.1.0"
+          }
+        }
       }
     },
     "path-key": {

evals/package.json

@@ -19,9 +19,9 @@
   "author": "",
   "license": "MIT",
   "dependencies": {
-    "axios": "^1.8.2",
+    "axios": "^1.12.0",
     "better-sqlite3": "^11.10.0",
-    "chalk": "^4.1.2",
+    "chalk": "5.6.2",
     "dotenv": "^16.5.0",
     "commander": "^9.4.1",
     "execa": "^5.1.1",

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": "3.27.2",
+	"version": "3.32.1",
 	"icon": "assets/icons/icon.png",
 	"engines": {
 		"vscode": "^1.84.0"
@@ -200,6 +200,11 @@
 				"command": "cline.openWalkthrough",
 				"title": "Open Walkthrough",
 				"category": "Cline"
+			},
+			{
+				"command": "cline.reconstructTaskHistory",
+				"title": "Reconstruct Task History",
+				"category": "Cline"
 			}
 		],
 		"keybindings": [
@@ -356,11 +361,14 @@
 		"test:ci": "node scripts/test-ci.js",
 		"test:integration": "vscode-test",
 		"test:unit": "TS_NODE_PROJECT='./tsconfig.unit-test.json' mocha",
-		"test:coverage": "vscode-test --coverage && mv coverage coverage-integration",
+		"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 --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",
+		"test:e2e:build": "vsce package --allow-package-secrets sendgrid --out dist/e2e.vsix",
+		"test:e2e": "playwright install && npm run test:e2e:build && node src/test/e2e/utils/build.mjs && playwright test",
+		"test:e2e:optimal": "npm run test:e2e:build && node src/test/e2e/utils/build.mjs && playwright test",
+		"test:e2e:ui": "npx tsx scripts/interactive-playwright.ts",
 		"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",
@@ -382,7 +390,7 @@
 		]
 	},
 	"devDependencies": {
-		"@biomejs/biome": "^2.1.4",
+		"@biomejs/biome": "^2.2.0",
 		"@bufbuild/buf": "^1.54.0",
 		"@changesets/cli": "^2.27.12",
 		"@types/better-sqlite3": "^7.6.13",
@@ -401,8 +409,9 @@
 		"@vscode/test-cli": "^0.0.10",
 		"@vscode/test-electron": "^2.5.2",
 		"@vscode/vsce": "^3.6.0",
+		"c8": "^10.1.3",
 		"chai": "^4.3.10",
-		"chalk": "^5.3.0",
+		"chalk": "5.6.2",
 		"esbuild": "^0.25.0",
 		"grpc-tools": "^1.13.0",
 		"husky": "^9.1.7",
@@ -415,6 +424,7 @@
 		"rimraf": "^6.0.1",
 		"should": "^13.2.3",
 		"sinon": "^19.0.2",
+		"tree-kill": "^1.2.2",
 		"ts-node": "^10.9.2",
 		"ts-proto": "^2.6.1",
 		"tsconfig-paths": "^4.2.0",
@@ -447,7 +457,7 @@
 		"@types/uuid": "^10.0.0",
 		"@vscode/codicons": "^0.0.36",
 		"archiver": "^7.0.1",
-		"axios": "^1.8.2",
+		"axios": "^1.12.0",
 		"cheerio": "^1.0.0",
 		"chokidar": "^4.0.1",
 		"chrome-launcher": "^1.1.2",
@@ -462,6 +472,7 @@
 		"get-folder-size": "^5.0.0",
 		"globby": "^14.0.2",
 		"grpc-health-check": "^2.0.2",
+		"https-proxy-agent": "^7.0.6",
 		"iconv-lite": "^0.6.3",
 		"ignore": "^7.0.3",
 		"image-size": "^2.0.2",
@@ -484,7 +495,7 @@
 		"reconnecting-eventsource": "^1.6.4",
 		"serialize-error": "^11.0.3",
 		"simple-git": "^3.27.0",
-		"strip-ansi": "^7.1.0",
+		"strip-ansi": "^7.1.2",
 		"tree-sitter-wasms": "^0.1.11",
 		"ts-morph": "^25.0.1",
 		"turndown": "^7.2.0",
@@ -493,5 +504,40 @@
 		"vscode-uri": "^3.1.0",
 		"web-tree-sitter": "^0.22.6",
 		"zod": "^3.24.2"
+	},
+	"c8": {
+		"reporter": [
+			"lcov",
+			"html"
+		],
+		"exclude": [
+			"**/testing-platform/**",
+			"**/webview-ui/**",
+			"**/.vscode-test/**",
+			"**/node_modules/**",
+			"node_modules",
+			"**/dist-standalone/src/**",
+			"**/dist-standalone/vsce-extension/https:/**",
+			"**/dist-standalone/vsce-extension/**",
+			"**/dist-standalone/https:/**",
+			"**/dist-standalone/LIB/src/**",
+			"**/dist-standalone/pdfjs-dist/**",
+			"**/*.d.ts",
+			"**/*.{test,spec}.{js,jsx,ts,tsx,mjs,cjs}",
+			"**/__tests__/**",
+			"**/test/**",
+			"**/tests/**",
+			"**/.nyc_output/**",
+			"**/tests-results/**",
+			"src/test/**",
+			"**/src/xml/**",
+			"**/standalone/**",
+			"**/src/generated/**",
+			"**/evals/cli/dist/**",
+			"**/evals/cli/src/**",
+			"dist"
+		],
+		"all": true,
+		"exclude-after-remap": true
 	}
 }

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/dictation.proto

@@ -0,0 +1,41 @@
+syntax = "proto3";
+
+package cline;
+import "cline/common.proto";
+option java_package = "bot.cline.proto";
+option java_multiple_files = true;
+
+service DictationService {
+  rpc startRecording(EmptyRequest) returns (RecordingResult);
+  rpc stopRecording(EmptyRequest) returns (RecordedAudio);
+  rpc cancelRecording(EmptyRequest) returns (RecordingResult);
+  rpc getRecordingStatus(EmptyRequest) returns (RecordingStatus);
+  rpc transcribeAudio(TranscribeAudioRequest) returns (Transcription);
+}
+
+message TranscribeAudioRequest {
+  string audio_base64 = 2;
+  string language = 3;
+}
+
+message RecordingResult {
+  bool success = 1;
+  string error = 2;
+}
+
+message RecordedAudio {
+  bool success = 1;
+  string audio_base64 = 2;
+  string error = 3;
+}
+
+message RecordingStatus {
+  bool is_recording = 1;
+  double duration_seconds = 2;
+  string error = 3;
+}
+
+message Transcription {
+  string text = 1;
+  string error = 2;
+}

proto/cline/file.proto

@@ -50,7 +50,7 @@ service FileService {
   rpc refreshRules(EmptyRequest) returns (RefreshedRules);
 
   // Opens a task's conversation history file on disk
-  rpc openTaskHistory(StringRequest) returns (Empty);
+  rpc openDiskConversationHistory(StringRequest) returns (Empty);
   
   // Toggles a workflow on or off
   rpc toggleWorkflow(ToggleWorkflowRequest) returns (ClineRulesToggles);

proto/cline/models.proto

@@ -33,6 +33,8 @@ service ModelsService {
   rpc refreshBasetenModels(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
   // Fetches available models from SAP AI Core
   rpc getSapAiCoreModels(SapAiCoreModelsRequest) returns (SapAiCoreModelsResponse);
+  // Fetches available models from OCA
+  rpc refreshOcaModels(StringRequest) returns (OcaCompatibleModelInfo);
 }
 
 // List of VS Code LM models
@@ -127,6 +129,48 @@ message UpdateApiConfigurationRequest {
   ModelsApiConfiguration api_configuration = 2;
 }
 
+ // Model info for OCA (OpenAI-compatible) models exposed by the OCA provider
+message OcaModelInfo {
+  // Maximum completion tokens per request supported by this model
+  optional int64 max_tokens = 1;
+  // Total context window in tokens (input + output)
+  optional int64 context_window = 2;
+  // Whether the model supports image inputs
+  optional bool supports_images = 3;
+  // Whether prompt caching is supported for this model
+  bool supports_prompt_cache = 4;
+  // Price per million input tokens (USD unless otherwise specified by provider)
+  optional double input_price = 5;
+  // Price per million output tokens (USD unless otherwise specified by provider)
+  optional double output_price = 6;
+  // Thinking/reasoning configuration if the model supports it
+  optional ThinkingConfig thinking_config = 7;
+  // Price per million tokens for prompt cache writes
+  optional double cache_writes_price = 9;
+  // Price per million tokens for prompt cache reads
+  optional double cache_reads_price = 10;
+  // Human-readable model description
+  optional string description = 11;
+  // Recommended default temperature for this model
+  optional double temperature = 13;
+  // Optional survey content to display in the UI
+  optional string survey_content = 14;
+  // Identifier for the survey associated with this model
+  optional string survey_id = 15;
+  // Optional banner content (e.g., deprecation or promotion notes)
+  optional string banner = 16;
+  // Canonical model identifier as reported by OCA
+  string model_name = 17;
+}
+
+ // Aggregated OCA model catalog keyed by model identifier
+message OcaCompatibleModelInfo {
+  // key: canonical model id as reported by OCA (e.g., "openai/gpt-4o-mini")
+  // value: OcaModelInfo describing that model
+  map<string, OcaModelInfo> models = 1;
+  optional string error = 2;
+}
+
 // API Provider enumeration
 enum ApiProvider {
   ANTHROPIC = 0;
@@ -164,6 +208,7 @@ enum ApiProvider {
   VERCEL_AI_GATEWAY = 32;
   QWEN_CODE = 33;
   DIFY = 34;
+  OCA = 35;
 }
 
 // Model info for OpenAI-compatible models
@@ -276,6 +321,9 @@ message ModelsApiConfiguration {
   optional string qwen_code_oauth_path = 70;
   optional string dify_api_key = 71;
   optional string dify_base_url = 72;
+  optional string oca_base_url = 73;
+  optional string oca_api_key = 74;
+  optional string oca_refresh_token = 75;
 
   // Plan mode configurations
   optional ApiProvider plan_mode_api_provider = 100;
@@ -309,6 +357,8 @@ message ModelsApiConfiguration {
   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;
+  optional string plan_mode_oca_model_id = 131;
+  optional OcaModelInfo plan_mode_oca_model_info = 132;
 
 
   // Act mode configurations
@@ -343,7 +393,6 @@ message ModelsApiConfiguration {
   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;
-
-
-  repeated string favorited_model_ids = 300;
+  optional string act_mode_oca_model_id = 231;
+  optional OcaModelInfo act_mode_oca_model_info = 232;
 }

proto/cline/oca_account.proto

@@ -0,0 +1,36 @@
+syntax = "proto3";
+
+package cline;
+import "cline/common.proto";
+option java_package = "bot.cline.proto";
+option java_multiple_files = true;
+
+// Service for account-related operations
+service OcaAccountService {
+  // Handles the user clicking the login link in the UI.
+  // Generates a secure nonce for state validation, stores it in secrets,
+  // and opens the authentication URL in the external browser.
+  rpc ocaAccountLoginClicked(EmptyRequest) returns (String);
+    
+  // Handles the user clicking the logout button in the UI.
+  // Clears API keys and user state.
+  rpc ocaAccountLogoutClicked(EmptyRequest) returns (Empty);
+
+  // Subscribe to auth status update events (when authentication state changes)
+  rpc ocaSubscribeToAuthStatusUpdate(EmptyRequest) 
+      returns (stream OcaAuthState);
+
+}
+
+
+message OcaAuthState {
+  optional OcaUserInfo user = 1;
+  optional string api_key = 2;
+}
+
+// User's information
+message OcaUserInfo {
+  string uid = 1;
+  optional string display_name = 2;
+  optional string email = 3;
+}

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;
 
@@ -17,8 +18,13 @@ service StateService {
   rpc updateSettings(UpdateSettingsRequest) returns (Empty);
   rpc updateTelemetrySetting(TelemetrySettingRequest) returns (Empty);
   rpc setWelcomeViewCompleted(BooleanRequest) returns (Empty);
+  rpc updateInfoBannerVersion(Int64Request) returns (Empty);
+}
+message DictationSettings {
+  bool feature_enabled = 1;
+  bool dictation_enabled = 2;
+  string dictation_language = 3;
 }
-
 message State {
   string state_json = 1;
 }
@@ -138,6 +144,10 @@ message UpdateSettingsRequest {
   optional string custom_prompt = 19;
   optional BrowserSettingsUpdate browser_settings = 20;
   optional string default_terminal_profile = 21;
+  optional bool yolo_mode_toggled = 22;
+  optional DictationSettings dictation_settings = 23;
+  optional int32 auto_condense_threshold = 24;
+  optional bool multi_root_enabled = 25;
 }
 
 // Complete API Configuration message
@@ -149,10 +159,10 @@ 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;
@@ -165,14 +175,14 @@ 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;
@@ -208,61 +218,65 @@ message ApiConfiguration {
   optional string qwen_code_oauth_path = 63;
   optional string dify_api_key = 64;
   optional string dify_base_url = 65;
+  optional string oca_base_url = 66;
+  optional string oca_api_key = 67;
+  optional string oca_refresh_token = 68;
   
   // 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;
+  optional string plan_mode_oca_model_id = 124;
+  optional OcaModelInfo plan_mode_oca_model_info = 125;
   
   // 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;
+  optional string act_mode_oca_model_id = 224;
+  optional OcaModelInfo act_mode_oca_model_info = 225;
 
   // Extension fields for Bedrock Api Keys
   optional string aws_authentication = 301;

proto/host/env.proto

@@ -17,10 +17,19 @@ 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);
 }
 
@@ -42,4 +51,4 @@ message GetTelemetrySettingsResponse {
 
 message TelemetrySettingsEvent {
   Setting is_enabled = 1; 
-}
+}

proto/host/workspace.proto

@@ -27,6 +27,9 @@ service WorkspaceService {
 
   // Opens and focuses the Cline sidebar panel in the host IDE.
   rpc openClineSidebarPanel(OpenClineSidebarPanelRequest) returns (OpenClineSidebarPanelResponse);
+
+  // Opens and focuses the terminal panel.
+  rpc openTerminalPanel(OpenTerminalRequest) returns (OpenTerminalResponse);
 }
 
 message GetWorkspacePathsRequest {
@@ -82,12 +85,11 @@ message SearchWorkspaceItemsResponse {
 
 message OpenProblemsPanelRequest {}
 message OpenProblemsPanelResponse {}
-
 message OpenInFileExplorerPanelRequest {
   string path = 1;
 }
 message OpenInFileExplorerPanelResponse {}
-
-// Request/response for opening the Cline sidebar
 message OpenClineSidebarPanelRequest {}
 message OpenClineSidebarPanelResponse {}
+message OpenTerminalRequest {}
+message OpenTerminalResponse {}

scripts/interactive-playwright.ts

@@ -0,0 +1,112 @@
+#!/usr/bin/env npx tsx
+
+/**
+ * Interactive Playwright launcher for the Cline VS Code extension.
+ *
+ * Overview:
+ *  - Starts the mock Cline API server (from the e2e test fixtures).
+ *  - Downloads a stable build of VS Code (via @vscode/test-electron).
+ *  - Creates a temporary VS Code user profile directory.
+ *  - Installs and links the Cline extension (from dist/e2e.vsix and the dev path).
+ *  - Opens a test workspace and automatically reveals the Cline sidebar.
+ *  - Records **all gRPC calls** during the session for later inspection.
+ *  - Keeps VS Code running for manual interactive testing until the window is closed or Ctrl+C is pressed.
+ *  - Cleans up all resources (mock server, temp profile, Electron process) on exit.
+ *
+ * Usage:
+ *   1. (Optional) Build and install the e2e extension:
+ *        npm run test:e2e:build
+ *
+ *   2. From the repo root, start the interactive session:
+ *        npm run test:playwright:interactive
+ *
+ *   3. VS Code will launch with the Cline extension loaded and gRPC recording enabled.
+ *
+ *   4. Interact with the extension manually.
+ *
+ *   5. Close the VS Code window or press Ctrl+C to end the session and trigger cleanup.
+ */
+
+import { downloadAndUnzipVSCode, SilentReporter } from "@vscode/test-electron"
+import { mkdtempSync } from "fs"
+import os from "os"
+import path from "path"
+import { _electron } from "playwright"
+import { ClineApiServerMock } from "../src/test/e2e/fixtures/server"
+import { E2ETestHelper } from "../src/test/e2e/utils/helpers"
+
+async function main() {
+	await ClineApiServerMock.startGlobalServer()
+
+	const userDataDir = mkdtempSync(path.join(os.tmpdir(), "vsce-interactive"))
+	const executablePath = await downloadAndUnzipVSCode("stable", undefined, new SilentReporter())
+
+	// launch VSCode
+	const app = await _electron.launch({
+		executablePath,
+		env: {
+			...process.env,
+			TEMP_PROFILE: "true",
+			E2E_TEST: "true",
+			CLINE_ENVIRONMENT: "local",
+			GRPC_RECORDER_ENABLED: "true",
+			GRPC_RECORDER_TESTS_FILTERS_ENABLED: "true",
+		},
+		args: [
+			"--no-sandbox",
+			"--disable-updates",
+			"--disable-workspace-trust",
+			"--disable-extensions",
+			"--skip-welcome",
+			"--skip-release-notes",
+			`--user-data-dir=${userDataDir}`,
+			`--install-extension=${path.join(E2ETestHelper.CODEBASE_ROOT_DIR, "dist", "e2e.vsix")}`,
+			`--extensionDevelopmentPath=${E2ETestHelper.CODEBASE_ROOT_DIR}`,
+			path.join(E2ETestHelper.E2E_TESTS_DIR, "fixtures", "workspace"),
+		],
+	})
+
+	const page = await app.firstWindow()
+
+	await E2ETestHelper.openClineSidebar(page)
+
+	console.log("VSCode with Cline extension is now running!")
+	console.log(`Temporary data directory on: ${userDataDir}`)
+	console.log("You can manually interact with the extension.")
+	console.log("Press Ctrl+C to close when done.")
+
+	async function teardown() {
+		console.log("Cleaning up resources...")
+		try {
+			await app?.close()
+			await ClineApiServerMock.stopGlobalServer?.()
+			await E2ETestHelper.rmForRetries(userDataDir, { recursive: true })
+		} catch (e) {
+			console.log(`We could teardown interactive playwright properly, error:${e}`)
+		}
+		console.log("Finished cleaning up resources...")
+	}
+
+	process.on("SIGINT", async () => {
+		await teardown()
+		process.exit(0)
+	})
+
+	process.on("SIGTERM", async () => {
+		await teardown()
+		process.exit(0)
+	})
+
+	const win = await app.firstWindow()
+	win.on("close", async () => {
+		console.log("VS Code window closed.")
+		await teardown()
+		process.exit(0)
+	})
+	process.stdin.resume()
+}
+
+main().catch((err) => {
+	console.error("Failed to start:", err)
+	process.exit(1)
+})

scripts/runclinecore.sh

@@ -9,7 +9,7 @@ if [[ "${1:-}" == "-h" ]]; then
 fi
 
 CORE_DIR=~/.cline/core
-INSTALL_DIR=$CORE_DIR/0.0.1
+INSTALL_DIR=$CORE_DIR/dev-instance/
 LOG_FILE=~/.cline/cline-core-service.log
 
 ZIP_FILE=standalone.zip
@@ -25,4 +25,6 @@ unp $ZIP_FILE > /dev/null
 
 pkill -f cline-core.js || true
 
+echo pwd: $(pwd)
+set -x
 NODE_PATH=./node_modules DEV_WORKSPACE_FOLDER=/tmp/ node cline-core.js 2>&1 | tee $LOG_FILE

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

@@ -28,19 +28,19 @@
  * Ideal for local development, testing, or lightweight E2E scenarios.
  */
 
+import * as fs from "node:fs"
 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"
+const USE_C8 = process.env.USE_C8 === "true"
 
 // Locate the standalone build directory and core file with flexible path resolution
 const projectRoot = process.env.PROJECT_ROOT || path.resolve(__dirname, "..")
@@ -48,8 +48,11 @@ const distDir = process.env.CLINE_DIST_DIR || path.join(projectRoot, "dist-stand
 const clineCoreFile = process.env.CLINE_CORE_FILE || "cline-core.js"
 const coreFile = path.join(distDir, clineCoreFile)
 
+const childProcesses: ChildProcess[] = []
+
 async function main(): Promise<void> {
 	console.log("Starting Simple Cline gRPC Server...")
+	console.log(`Project Root: ${projectRoot}`)
 	console.log(`Workspace: ${WORKSPACE_DIR}`)
 	console.log(`ProtoBus Port: ${PROTOBUS_PORT}`)
 	console.log(`HostBridge Port: ${HOSTBRIDGE_PORT}`)
@@ -75,27 +78,24 @@ async function main(): Promise<void> {
 		process.exit(1)
 	}
 
-	// Create temporary directories like e2e tests
+	const extensionsDir = path.join(distDir, "vsce-extension")
 	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,
+			HOST_BRIDGE_ADDRESS: `127.0.0.1:${HOSTBRIDGE_PORT}`,
 		},
 	})
+	childProcesses.push(hostbridge)
 
 	console.log(`Temp user data dir: ${userDataDir}`)
 	console.log(`Temp extensions dir: ${extensionsDir}`)
-
-	// Extract standalone.zip to the extensions directory
+	// Extract standalone.zip if needed
 	const standaloneZipPath = path.join(distDir, "standalone.zip")
 	if (!fs.existsSync(standaloneZipPath)) {
 		console.error(`standalone.zip not found at: ${standaloneZipPath}`)
@@ -104,47 +104,56 @@ async function main(): Promise<void> {
 
 	console.log("Extracting standalone.zip to extensions directory...")
 	try {
-		execSync(`unzip -q "${standaloneZipPath}" -d "${extensionsDir}"`, { stdio: "inherit" })
+		if (!fs.existsSync(extensionsDir)) {
+			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,
+	const covDir = path.join(projectRoot, `coverage/coverage-core-${PROTOBUS_PORT}`)
+
+	const baseArgs = ["--enable-source-maps", path.join(distDir, "cline-core.js")]
+
+	const spawnArgs = USE_C8 ? ["c8", "--report-dir", covDir, "node", ...baseArgs] : ["node", ...baseArgs]
+
+	console.log(`Starting Cline Core Service... (useC8=${USE_C8})`)
+
+	const coreService: ChildProcess = spawn("npx", spawnArgs, {
+		cwd: projectRoot,
 		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,
+			E2E_TEST,
+			CLINE_ENVIRONMENT,
 			CLINE_DIR: userDataDir,
 			INSTALL_DIR: extensionsDir,
 		},
 		stdio: "inherit",
 	})
+	childProcesses.push(coreService)
+
+	const shutdown = async () => {
+		console.log("\nShutting down services...")
+
+		while (childProcesses.length > 0) {
+			const child = childProcesses.pop()
+			if (child && !child.killed) child.kill("SIGINT")
+		}
 
-	// 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)
+		} catch (err) {
+			console.warn("Failed to cleanup temp directories:", err)
 		}
 
 		process.exit(0)
@@ -155,24 +164,20 @@ async function main(): Promise<void> {
 
 	coreService.on("exit", (code) => {
 		console.log(`Core service exited with code ${code}`)
-		hostbridge.kill()
-		process.exit(code || 0)
+		shutdown()
 	})
-
 	hostbridge.on("exit", (code) => {
 		console.log(`HostBridge exited with code ${code}`)
-		coreService.kill()
-		process.exit(code || 0)
+		shutdown()
 	})
 
-	console.log("Cline gRPC Server is running!")
-	console.log(`Connect to: 127.0.0.1:${PROTOBUS_PORT}`)
+	console.log(`Cline gRPC Server is running on 127.0.0.1:${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)
+	main().catch((err) => {
+		console.error("Failed to start simple Cline server:", err)
 		process.exit(1)
 	})
 }

scripts/testing-platform-orchestrator.ts

@@ -14,61 +14,124 @@
  * Flags:
  *   --server-logs        Show server logs (hidden by default)
  *   --count=<number>     Repeat execution N times (default: 1)
+ *   --fix     			  Automatically update spec files with actual responses
+ *   --coverage     	  Generate integration test coverage information
  *
- * 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 net from "net"
 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
+import kill from "tree-kill"
 
 let showServerLogs = false
+let fix = false
+let coverage = false
+const WAIT_SERVER_DEFAULT_TIMEOUT = 15000
+const usedPorts = new Set<number>()
 
-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)
+/**
+ * Find an available TCP port within the given range [min, max].
+ *
+ * - Ports are allocated sequentially (starting at `min`) rather than randomly,
+ *   which avoids accidental reuse when running hundreds of tests in a row.
+ * - Each successfully allocated port is tracked in `usedPorts` to guarantee
+ *   it is never handed out again within the lifetime of this orchestrator.
+ * - Before returning, the function binds a temporary server to the port to
+ *   verify that the OS really considers it available, then immediately closes it.
+ *
+ * This approach makes the orchestrator much more robust on CI (e.g. GitHub Actions),
+ * where a just-terminated server may leave its socket in TIME_WAIT and cause
+ * flakiness if the same port is reallocated too soon.
+ */
+async function getAvailablePort(min = 20000, max = 49151): Promise<number> {
+	return new Promise((resolve, _) => {
+		const tryPort = (candidate?: number) => {
+			const port = candidate ?? Math.floor(Math.random() * (max - min + 1)) + min
+			if (usedPorts.has(port)) {
+				// already allocated in this run
+				return tryPort()
 			}
-		}, SERVER_BOOT_DELAY)
+			const server = net.createServer()
+			server.once("error", () => tryPort())
+			server.once("listening", () => {
+				server.close(() => {
+					usedPorts.add(port) // mark reserved
+					resolve(port)
+				})
+			})
+			server.listen(port, "127.0.0.1")
+		}
+		tryPort()
 	})
 }
 
+// Poll until a given TCP port on a host is accepting connections.
+async function waitForPort(port: number, host = "127.0.0.1", timeout = 10000): Promise<void> {
+	const start = Date.now()
+	const waitForPortSleepMs = 100
+	while (Date.now() - start < timeout) {
+		await new Promise((res) => setTimeout(res, waitForPortSleepMs))
+		try {
+			await new Promise<void>((resolve, reject) => {
+				const socket = net.connect(port, host, () => {
+					socket.destroy()
+					resolve()
+				})
+				socket.on("error", reject)
+			})
+			return
+		} catch {
+			// try again
+		}
+	}
+	throw new Error(`Timeout waiting for ${host}:${port}`)
+}
+
+async function startServer(): Promise<{ server: ChildProcess; grpcPort: string }> {
+	const grpcPort = (await getAvailablePort()).toString()
+	const hostbridgePort = (await getAvailablePort()).toString()
+
+	const server = spawn("npx", ["tsx", "scripts/test-standalone-core-api-server.ts"], {
+		stdio: showServerLogs ? "inherit" : "pipe",
+		env: {
+			...process.env,
+			PROTOBUS_PORT: grpcPort,
+			HOSTBRIDGE_PORT: hostbridgePort,
+			USE_C8: coverage ? "true" : "false",
+		},
+	})
+
+	// Wait for either the server to become ready or fail on spawn error
+	await Promise.race([
+		waitForPort(Number(grpcPort), "127.0.0.1", WAIT_SERVER_DEFAULT_TIMEOUT),
+		new Promise((_, reject) => server.once("error", reject)),
+	])
+
+	return { server, grpcPort }
+}
+
 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)
+		if (!server.pid) return resolve()
+
+		kill(server.pid, "SIGINT", (err) => {
+			if (err) console.warn("Failed to kill server process:", err)
+			server.once("exit", () => resolve())
+		})
 	})
 }
 
-function runTestingPlatform(specFile: string): Promise<void> {
+function runTestingPlatform(specFile: string, grpcPort: string): Promise<void> {
 	return new Promise((resolve, reject) => {
-		const testProcess = spawn("npx", ["ts-node", "index.ts", specFile], {
+		const testProcess = spawn("npx", ["ts-node", "index.ts", specFile, ...(fix ? ["--fix"] : [])], {
 			cwd: path.join(process.cwd(), "testing-platform"),
 			stdio: "inherit",
 			env: {
 				...process.env,
-				HOSTBRIDGE_PORT: STANDALONE_GRPC_SERVER_PORT,
+				STANDALONE_GRPC_SERVER_PORT: grpcPort,
 			},
 		})
 
@@ -80,9 +143,9 @@ function runTestingPlatform(specFile: string): Promise<void> {
 }
 
 async function runSpec(specFile: string): Promise<void> {
-	const server = await startServer()
+	const { server, grpcPort } = await startServer()
 	try {
-		await runTestingPlatform(specFile)
+		await runTestingPlatform(specFile, grpcPort)
 		console.log(`✅ ${path.basename(specFile)} passed`)
 	} finally {
 		await stopServer(server)
@@ -133,8 +196,7 @@ async function runAll(inputPath: string, count: number) {
 	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`)
+	console.log(`🏁 All runs completed in ${((Date.now() - totalStart) / 1000).toFixed(2)}s`)
 }
 
 async function main() {
@@ -142,9 +204,13 @@ async function main() {
 	const inputPath = args._[0]
 	const count = Number(args.count)
 	showServerLogs = Boolean(args["server-logs"])
+	fix = Boolean(args["fix"])
+	coverage = Boolean(args["coverage"])
 
 	if (!inputPath) {
-		console.error("Usage: npx tsx scripts/testing-platform-orchestrator.ts <spec-file-or-folder> [--count=N] [--server-logs]")
+		console.error(
+			"Usage: npx tsx scripts/testing-platform-orchestrator.ts <spec-file-or-folder> [--count=N] [--server-logs] [--fix] [--coverage]",
+		)
 		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

@@ -1,4 +1,4 @@
-import * as vscode from "vscode"
+import { ExtensionContext } from "vscode"
 import {
 	migrateCustomInstructionsToGlobalRules,
 	migrateTaskHistoryToFile,
@@ -12,6 +12,8 @@ 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 { ExtensionRegistryInfo } from "./registry"
+import { audioRecordingService } from "./services/dictation/AudioRecordingService"
 import { ErrorService } from "./services/error"
 import { featureFlagsService } from "./services/feature-flags"
 import { initializeDistinctId } from "./services/logging/distinctId"
@@ -25,15 +27,16 @@ import { getLatestAnnouncementId } from "./utils/announcements"
  * @param context
  * @returns The webview provider
  */
-export async function initialize(context: vscode.ExtensionContext): Promise<WebviewProvider> {
+export async function initialize(context: ExtensionContext): Promise<WebviewProvider> {
 	// Set the distinct ID for logging and telemetry
 	await initializeDistinctId(context)
 
 	// Initialize PostHog client provider
 	PostHogClientProvider.getInstance()
 
-	// Setup the ErrorService
+	// Setup the external services
 	await ErrorService.initialize()
+	await featureFlagsService.poll()
 
 	// Migrate custom instructions to global Cline rules (one-time cleanup)
 	await migrateCustomInstructionsToGlobalRules(context)
@@ -59,9 +62,9 @@ export async function initialize(context: vscode.ExtensionContext): Promise<Webv
 	return sidebarWebview
 }
 
-async function showVersionUpdateAnnouncement(context: vscode.ExtensionContext) {
+async function showVersionUpdateAnnouncement(context: 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 {
@@ -70,7 +73,7 @@ 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)
@@ -97,6 +100,9 @@ async function showVersionUpdateAnnouncement(context: vscode.ExtensionContext) {
  * Performs cleanup when Cline is deactivated that is common to all platforms.
  */
 export async function tearDown(): Promise<void> {
+	// Clean up audio recording service to ensure no orphaned processes
+	audioRecordingService.cleanup()
+
 	PostHogClientProvider.getInstance().dispose()
 	telemetryService.dispose()
 	ErrorService.get().dispose()

src/config.ts

@@ -4,7 +4,7 @@ export enum Environment {
 	local = "local",
 }
 
-interface EnvironmentConfig {
+export interface EnvironmentConfig {
 	appBaseUrl: string
 	apiBaseUrl: string
 	mcpBaseUrl: string

src/core/api/index.ts

@@ -21,6 +21,7 @@ import { LmStudioHandler } from "./providers/lmstudio"
 import { MistralHandler } from "./providers/mistral"
 import { MoonshotHandler } from "./providers/moonshot"
 import { NebiusHandler } from "./providers/nebius"
+import { OcaHandler } from "./providers/oca"
 import { OllamaHandler } from "./providers/ollama"
 import { OpenAiHandler } from "./providers/openai"
 import { OpenAiNativeHandler } from "./providers/openai-native"
@@ -57,6 +58,7 @@ export interface ApiProviderInfo {
 	providerId: string
 	model: ApiHandlerModel
 	customPrompt?: string // "compact"
+	autoCondenseThreshold?: number // 0-1 range
 }
 
 export interface SingleCompletionHandler {
@@ -352,10 +354,6 @@ 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,
@@ -376,6 +374,19 @@ function createHandlerForProvider(
 				zaiApiKey: options.zaiApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
+		case "oca":
+			return new OcaHandler({
+				ocaBaseUrl: options.ocaBaseUrl,
+				ocaModelId: mode === "plan" ? options.planModeOcaModelId : options.actModeOcaModelId,
+				ocaModelInfo: mode === "plan" ? options.planModeOcaModelInfo : options.actModeOcaModelInfo,
+				thinkingBudgetTokens:
+					mode === "plan" ? options.planModeThinkingBudgetTokens : options.actModeThinkingBudgetTokens,
+				ocaUsePromptCache:
+					mode === "plan"
+						? options.planModeOcaModelInfo?.supportsPromptCache
+						: options.actModeOcaModelInfo?.supportsPromptCache,
+				taskId: options.ulid,
+			})
 		default:
 			return new AnthropicHandler({
 				onRetryAttempt: options.onRetryAttempt,

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/anthropic.ts

@@ -150,6 +150,8 @@ export class AnthropicHandler implements ApiHandler {
 			}
 		}
 
+		let thinkingDeltaAccumulator = ""
+
 		for await (const chunk of stream) {
 			switch (chunk?.type) {
 				case "message_start":
@@ -182,14 +184,26 @@ export class AnthropicHandler implements ApiHandler {
 								type: "reasoning",
 								reasoning: chunk.content_block.thinking || "",
 							}
+							const thinking = chunk.content_block.thinking
+							const signature = chunk.content_block.signature
+							if (thinking && signature) {
+								yield {
+									type: "ant_thinking",
+									thinking,
+									signature,
+								}
+							}
 							break
 						case "redacted_thinking":
-							// Handle redacted thinking blocks - we still mark it as reasoning
-							// but note that the content is encrypted
+							// Content is encrypted, and we don't to pass placeholder text back to the API
 							yield {
 								type: "reasoning",
 								reasoning: "[Redacted thinking block]",
 							}
+							yield {
+								type: "ant_redacted_thinking",
+								data: chunk.content_block.data,
+							}
 							break
 						case "text":
 							// we may receive multiple text blocks, in which case just insert a line break between them
@@ -209,10 +223,23 @@ export class AnthropicHandler implements ApiHandler {
 				case "content_block_delta":
 					switch (chunk.delta.type) {
 						case "thinking_delta":
+							// 'reasoning' type just displays in the UI, but ant_thinking will be used to send the thinking traces back to the API
 							yield {
 								type: "reasoning",
 								reasoning: chunk.delta.thinking,
 							}
+							thinkingDeltaAccumulator += chunk.delta.thinking
+							break
+						case "signature_delta":
+							// It's used when sending the thinking block back to the API
+							// API expects this in completed form, not as array of deltas
+							if (thinkingDeltaAccumulator && chunk.delta.signature) {
+								yield {
+									type: "ant_thinking",
+									thinking: thinkingDeltaAccumulator,
+									signature: chunk.delta.signature,
+								}
+							}
 							break
 						case "text_delta":
 							yield {
@@ -220,10 +247,6 @@ export class AnthropicHandler implements ApiHandler {
 								text: chunk.delta.text,
 							}
 							break
-						case "signature_delta":
-							// We don't need to do anything with the signature in the client
-							// It's used when sending the thinking block back to the API
-							break
 					}
 					break
 				case "content_block_stop":

src/core/api/providers/baseten.ts

@@ -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/cline.ts

@@ -162,7 +162,7 @@ export class ClineHandler implements ApiHandler {
 					// @ts-ignore-next-line
 					let totalCost = (chunk.usage.cost || 0) + (chunk.usage.cost_details?.upstream_inference_cost || 0)
 
-					if (this.getModel().id === "cline/sonic") {
+					if (this.getModel().id === "cline/code-supernova-1-million") {
 						totalCost = 0
 					}
 
@@ -200,14 +200,13 @@ export class ClineHandler implements ApiHandler {
 	async getApiStreamUsage(): Promise<ApiStreamUsageChunk | undefined> {
 		if (this.lastGenerationId) {
 			try {
-				// TODO: replace this with firebase auth
-				// TODO: use global API Host
 				const clineAccountAuthToken = await this._authService.getAuthToken()
 				if (!clineAccountAuthToken) {
 					throw new Error(CLINE_ACCOUNT_AUTH_ERROR_MESSAGE)
 				}
 				const response = await axios.get(`${this.clineAccountService.baseUrl}/generation?id=${this.lastGenerationId}`, {
 					headers: {
+						// Align with backend auth expectations
 						Authorization: `Bearer ${clineAccountAuthToken}`,
 					},
 					timeout: 15_000, // this request hangs sometimes

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/moonshot.ts

@@ -49,6 +49,7 @@ export class MoonshotHandler implements ApiHandler {
 			model: model.id,
 			messages: openAiMessages,
 			temperature: 0,
+			max_tokens: model.info.maxTokens,
 			stream: true,
 			stream_options: { include_usage: true },
 		})

src/core/api/providers/oca.ts

@@ -0,0 +1,261 @@
+import { Anthropic } from "@anthropic-ai/sdk"
+import { LiteLLMModelInfo, liteLlmDefaultModelId, liteLlmModelInfoSaneDefaults } from "@shared/api"
+import OpenAI, { APIError, OpenAIError } from "openai"
+import type { FinalRequestOptions, Headers as OpenAIHeaders } from "openai/core"
+import { OcaAuthService } from "@/services/auth/oca/OcaAuthService"
+import { DEFAULT_OCA_BASE_URL, OCI_HEADER_OPC_REQUEST_ID } from "@/services/auth/oca/utils/constants"
+import { createOcaHeaders } from "@/services/auth/oca/utils/utils"
+import { Logger } from "@/services/logging/Logger"
+import { ApiHandler, type CommonApiHandlerOptions } from ".."
+import { withRetry } from "../retry"
+import { convertToOpenAiMessages } from "../transform/openai-format"
+import { ApiStream } from "../transform/stream"
+
+export interface OcaHandlerOptions extends CommonApiHandlerOptions {
+	ocaBaseUrl?: string
+	ocaModelId?: string
+	ocaModelInfo?: LiteLLMModelInfo
+	thinkingBudgetTokens?: number
+	ocaUsePromptCache?: boolean
+	taskId?: string
+}
+
+export class OcaHandler implements ApiHandler {
+	protected options: OcaHandlerOptions
+	protected client: OpenAI | undefined
+
+	constructor(options: OcaHandlerOptions) {
+		this.options = options
+	}
+
+	protected initializeClient(options: OcaHandlerOptions) {
+		return new (class OCIOpenAI extends OpenAI {
+			protected override async prepareOptions(opts: FinalRequestOptions<unknown>): Promise<void> {
+				const token = await OcaAuthService.getInstance().getAuthToken()
+				if (!token) {
+					throw new OpenAIError("Unable to handle auth, Oracle Code Assist (OCA) access token is not available")
+				}
+				opts.headers ??= {}
+				// OCA Headers
+				const ociHeaders = await createOcaHeaders(token, options.taskId!)
+				opts.headers = { ...opts.headers, ...ociHeaders }
+				Logger.log(`Making request with customer opc-request-id: ${opts.headers?.["opc-request-id"]}`)
+				return super.prepareOptions(opts)
+			}
+
+			protected override makeStatusError(
+				status: number | undefined,
+				error: Object | undefined,
+				message: string | undefined,
+				headers: OpenAIHeaders | undefined,
+			): APIError {
+				interface OciError {
+					code?: string
+					message?: string
+				}
+				let ociErrorMessage = message
+				if (typeof error === "object" && error !== null) {
+					try {
+						ociErrorMessage = JSON.stringify(error)
+						const ociErr = error as OciError
+						if (ociErr.code !== undefined && ociErr.message !== undefined) {
+							ociErrorMessage = `${ociErr.code}: ${ociErr.message}`
+						}
+					} catch {}
+				}
+				const opcRequestId = headers?.[OCI_HEADER_OPC_REQUEST_ID]
+				if (opcRequestId) {
+					ociErrorMessage += `\n(${OCI_HEADER_OPC_REQUEST_ID}: ${opcRequestId})`
+				}
+				return super.makeStatusError(status, error, ociErrorMessage, headers)
+			}
+		})({
+			baseURL: options.ocaBaseUrl || DEFAULT_OCA_BASE_URL,
+			apiKey: "noop",
+		})
+	}
+
+	protected ensureClient(): OpenAI {
+		if (!this.client) {
+			if (!this.options.ocaModelId) {
+				throw new Error("Oracle Code Assist (OCA) model is not selected")
+			}
+			try {
+				this.client = this.initializeClient(this.options)
+			} catch (error) {
+				throw new Error(`Error creating Oracle Code Assist (OCA) client: ${error.message}`)
+			}
+		}
+		return this.client
+	}
+
+	async calculateCost(prompt_tokens: number, completion_tokens: number): Promise<number | undefined> {
+		// Reference: https://github.com/BerriAI/litellm/blob/122ee634f434014267af104814022af1d9a0882f/litellm/proxy/spend_tracking/spend_management_endpoints.py#L1473
+		const client = this.ensureClient()
+		const modelId = this.options.ocaModelId || liteLlmDefaultModelId
+		const token = await OcaAuthService.getInstance().getAuthToken()
+		if (!token) {
+			throw new OpenAIError("Unable to handle auth, Oracle Code Assist (OCA) access token is not available")
+		}
+		const ociHeaders = await createOcaHeaders(token, this.options.taskId!)
+		Logger.log(`Making calculate cost request with customer opc-request-id: ${ociHeaders["opc-request-id"]}`)
+		try {
+			const response = await fetch(`${client.baseURL}/spend/calculate`, {
+				method: "POST",
+				headers: ociHeaders,
+				body: JSON.stringify({
+					completion_response: {
+						model: modelId,
+						usage: {
+							prompt_tokens,
+							completion_tokens,
+						},
+					},
+				}),
+			})
+
+			if (response.ok) {
+				const data: { cost: number } = await response.json()
+				return data.cost
+			} else {
+				console.error("Error calculating spend:", response.statusText)
+				return undefined
+			}
+		} catch (error) {
+			console.error("Error calculating spend:", error)
+			return undefined
+		}
+	}
+
+	@withRetry()
+	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		const client = this.ensureClient()
+		const formattedMessages = convertToOpenAiMessages(messages)
+		const systemMessage: OpenAI.Chat.ChatCompletionSystemMessageParam = {
+			role: "system",
+			content: systemPrompt,
+		}
+		const modelId = this.options.ocaModelId || liteLlmDefaultModelId
+		const isOminiModel = modelId.includes("o1-mini") || modelId.includes("o3-mini") || modelId.includes("o4-mini")
+
+		// Configuration for extended thinking
+		const budgetTokens = this.options.thinkingBudgetTokens || 0
+		const reasoningOn = budgetTokens !== 0 ? true : false
+		const thinkingConfig = reasoningOn ? { type: "enabled", budget_tokens: budgetTokens } : undefined
+
+		let temperature: number | undefined = this.options.ocaModelInfo?.temperature ?? 0
+		const maxTokens: number | undefined = this.options.ocaModelInfo?.maxTokens
+
+		if (isOminiModel && reasoningOn) {
+			temperature = undefined // Thinking mode doesn't support temperature
+		}
+
+		// Define cache control object if prompt caching is enabled
+		const cacheControl = this.options.ocaUsePromptCache ? { cache_control: { type: "ephemeral" } } : undefined
+
+		// Add cache_control to system message if enabled
+		const enhancedSystemMessage = {
+			...systemMessage,
+			...(cacheControl && cacheControl),
+		}
+
+		// Find the last two user messages to apply caching
+		const userMsgIndices = formattedMessages.reduce((acc, msg, index) => {
+			if (msg.role === "user") {
+				acc.push(index)
+			}
+			return acc
+		}, [] as number[])
+		const lastUserMsgIndex = userMsgIndices[userMsgIndices.length - 1] ?? -1
+		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,
+				}
+			}
+			return message
+		})
+
+		const stream = await client.chat.completions.create({
+			model: this.options.ocaModelId || liteLlmDefaultModelId,
+			messages: [enhancedSystemMessage, ...enhancedMessages],
+			temperature,
+			stream: true,
+			max_completion_tokens: maxTokens,
+			max_tokens: maxTokens,
+			stream_options: { include_usage: true },
+			...(thinkingConfig && { thinking: thinkingConfig }), // Add thinking configuration when applicable
+			...(this.options.taskId && {
+				litellm_session_id: `cline-${this.options.taskId}`,
+			}), // Add session ID for LiteLLM tracking
+		})
+
+		const inputCost = (await this.calculateCost(1e6, 0)) || 0
+		const outputCost = (await this.calculateCost(0, 1e6)) || 0
+
+		for await (const chunk of stream) {
+			const delta = chunk.choices[0]?.delta
+
+			// Handle normal text content
+			if (delta?.content) {
+				yield {
+					type: "text",
+					text: delta.content,
+				}
+			}
+
+			// Handle reasoning events (thinking)
+			// Thinking is not in the standard types but may be in the response
+			interface ThinkingDelta {
+				thinking?: string
+			}
+
+			if ((delta as ThinkingDelta)?.thinking) {
+				yield {
+					type: "reasoning",
+					reasoning: (delta as ThinkingDelta).thinking || "",
+				}
+			}
+
+			// Handle token usage information
+			if (chunk.usage) {
+				const totalCost =
+					(inputCost * chunk.usage.prompt_tokens) / 1e6 + (outputCost * chunk.usage.completion_tokens) / 1e6
+
+				// Extract cache-related information if available
+				// Need to use type assertion since these properties are not in the standard OpenAI types
+				const usage = chunk.usage as {
+					prompt_tokens: number
+					completion_tokens: number
+					cache_creation_input_tokens?: number
+					prompt_cache_miss_tokens?: number
+					cache_read_input_tokens?: number
+					prompt_cache_hit_tokens?: number
+				}
+
+				const cacheWriteTokens = usage.cache_creation_input_tokens || usage.prompt_cache_miss_tokens || 0
+				const cacheReadTokens = usage.cache_read_input_tokens || usage.prompt_cache_hit_tokens || 0
+
+				yield {
+					type: "usage",
+					inputTokens: usage.prompt_tokens || 0,
+					outputTokens: usage.completion_tokens || 0,
+					cacheWriteTokens: cacheWriteTokens > 0 ? cacheWriteTokens : undefined,
+					cacheReadTokens: cacheReadTokens > 0 ? cacheReadTokens : undefined,
+					totalCost,
+				}
+			}
+		}
+	}
+
+	getModel() {
+		return {
+			id: this.options.ocaModelId || liteLlmDefaultModelId,
+			info: this.options.ocaModelInfo || liteLlmModelInfoSaneDefaults,
+		}
+	}
+}

src/core/api/providers/openrouter.ts

@@ -122,6 +122,21 @@ export class OpenRouterHandler implements ApiHandler {
 				}
 			}
 
+			// OpenRouter passes reasoning details that we can pass back unmodified in api requests to preserve reasoning traces for model
+			// See: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks
+			if (
+				"reasoning_details" in delta &&
+				delta.reasoning_details &&
+				// @ts-ignore-next-line
+				delta.reasoning_details.length && // exists and non-0
+				!shouldSkipReasoningForModel(this.options.openRouterModelId)
+			) {
+				yield {
+					type: "reasoning_details",
+					reasoning_details: delta.reasoning_details,
+				}
+			}
+
 			if (!didOutputUsage && chunk.usage) {
 				yield {
 					type: "usage",

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

@@ -9,6 +9,7 @@ import { ModelInfo, SapAiCoreModelId, sapAiCoreDefaultModelId, sapAiCoreModels }
 import axios from "axios"
 import OpenAI from "openai"
 import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 
@@ -454,8 +455,9 @@ export class SapAiCoreHandler implements ApiHandler {
 		return this.deployments?.some((d) => d.name.split(":")[0].toLowerCase() === modelId.split(":")[0].toLowerCase()) ?? false
 	}
 
+	@withRetry()
 	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)
@@ -495,7 +497,6 @@ 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 = {
@@ -824,16 +825,13 @@ export class SapAiCoreHandler implements ApiHandler {
 
 							// Handle metadata (token usage)
 							if (data.metadata?.usage) {
+								// inputTokens does not include cached write/read tokens
 								let inputTokens = data.metadata.usage.inputTokens || 0
 								const outputTokens = data.metadata.usage.outputTokens || 0
 
-								// calibrate input token
-								const totalTokens = data.metadata.usage.totalTokens || 0
 								const cacheReadInputTokens = data.metadata.usage.cacheReadInputTokens || 0
-								const cacheWriteOutputTokens = data.metadata.usage.cacheWriteOutputTokens || 0
-								if (inputTokens + outputTokens + cacheReadInputTokens + cacheWriteOutputTokens !== totalTokens) {
-									inputTokens = totalTokens - outputTokens - cacheReadInputTokens - cacheWriteOutputTokens
-								}
+								const cacheWriteInputTokens = data.metadata.usage.cacheWriteInputTokens || 0
+								inputTokens = inputTokens + cacheReadInputTokens + cacheWriteInputTokens
 
 								yield {
 									type: "usage",

src/core/api/providers/zai.ts

@@ -85,7 +85,6 @@ export class ZAiHandler implements ApiHandler {
 			messages: openAiMessages,
 			stream: true,
 			stream_options: { include_usage: true },
-			temperature: 0,
 		})
 
 		for await (const chunk of stream) {

src/core/api/transform/openai-format.ts

@@ -115,7 +115,15 @@ export function convertToOpenAiMessages(
 
 				// Process non-tool messages
 				let content: string | undefined
+				const reasoningDetails: any[] = []
 				if (nonToolMessages.length > 0) {
+					nonToolMessages.forEach((part) => {
+						// @ts-ignore-next-line
+						if (part.type === "text" && part.reasoning_details) {
+							// @ts-ignore-next-line
+							reasoningDetails.push(part.reasoning_details)
+						}
+					})
 					content = nonToolMessages
 						.map((part) => {
 							if (part.type === "image") {
@@ -142,6 +150,8 @@ export function convertToOpenAiMessages(
 					content,
 					// Cannot be an empty array. API expects an array with minimum length 1, and will respond with an error if it's empty
 					tool_calls: tool_calls.length > 0 ? tool_calls : undefined,
+					// @ts-ignore-next-line
+					reasoning_details: reasoningDetails,
 				})
 			}
 		}

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

@@ -139,10 +139,6 @@ export async function createOpenRouterStream(
 				reasoning = { max_tokens: budget_tokens }
 			}
 			break
-		case "cline/sonic":
-			temperature = 0.7
-			topP = 0.95
-			break
 		default:
 			if (thinkingBudgetTokens && model.info?.thinkingConfig && thinkingBudgetTokens > 0) {
 				temperature = undefined // extended thinking does not support non-1 temperature

src/core/api/transform/stream.ts

@@ -1,5 +1,11 @@
 export type ApiStream = AsyncGenerator<ApiStreamChunk>
-export type ApiStreamChunk = ApiStreamTextChunk | ApiStreamReasoningChunk | ApiStreamUsageChunk
+export type ApiStreamChunk =
+	| ApiStreamTextChunk
+	| ApiStreamReasoningChunk
+	| ApiStreamReasoningDetailsChunk
+	| ApiStreamAnthropicThinkingChunk
+	| ApiStreamAnthropicRedactedThinkingChunk
+	| ApiStreamUsageChunk
 
 export interface ApiStreamTextChunk {
 	type: "text"
@@ -11,6 +17,22 @@ export interface ApiStreamReasoningChunk {
 	reasoning: string
 }
 
+export interface ApiStreamReasoningDetailsChunk {
+	type: "reasoning_details"
+	reasoning_details: any // openrouter has various properties that we can pass back unmodified in api requests to preserve reasoning traces
+}
+
+export interface ApiStreamAnthropicThinkingChunk {
+	type: "ant_thinking"
+	thinking: string
+	signature: string
+}
+
+export interface ApiStreamAnthropicRedactedThinkingChunk {
+	type: "ant_redacted_thinking"
+	data: string
+}
+
 export interface ApiStreamUsageChunk {
 	type: "usage"
 	inputTokens: number

src/core/api/transform/vscode-lm-format.test.ts

@@ -1,15 +1,10 @@
 // This file contains `declare module "vscode"` so we must import it.
-import "../core/api/providers/vscode-lm"
+import "../providers/vscode-lm"
 import { describe, it } from "mocha"
 import "should"
 import { Anthropic } from "@anthropic-ai/sdk"
 import * as vscode from "vscode"
-import {
-	asObjectSafe,
-	convertToAnthropicMessage,
-	convertToAnthropicRole,
-	convertToVsCodeLmMessages,
-} from "../core/api/transform/vscode-lm-format"
+import { asObjectSafe, convertToAnthropicMessage, convertToAnthropicRole, convertToVsCodeLmMessages } from "./vscode-lm-format"
 
 describe("asObjectSafe", () => {
 	it("should handle falsy values", () => {

src/core/assistant-message/index.ts

@@ -38,6 +38,7 @@ export const toolParamNames = [
 	"additional_context",
 	"needs_more_exploration",
 	"task_progress",
+	"timeout",
 ] as const
 
 export type ToolParamName = (typeof toolParamNames)[number]