feat(mcp): first-class Streamable HTTP transport (proto, core, UI); Add Remote wiring with transportType/headers/timeout; graceful session termination; regenerate protos

2026-09-01 23:19:18 +08:00 · 2025-08-24 16:43:03 -07:00
331 changed files with 7675 additions and 26538 deletions
@@ -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)
@@ -1,5 +0,0 @@
---
-"claude-dev": patch
---
-
-Fix issue on Account view where balance is fetched twice that cause janky UI
@@ -1,5 +0,0 @@
---
-"claude-dev": patch
---
-
-Fixes an issue where thinking text from litellm was not being passed through to Cline thinking UI
@@ -1,5 +0,0 @@
---
-"claude-dev": patch
---
-
-Fix Ollama connection issue to default endpoint at port 11434
@@ -1,5 +0,0 @@
---
-"claude-dev": patch
---
-
-Optimized Cline for GPT-5 model family with an aligned system prompt
@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+fix issue with gpt-5 not using auto-compact even when toggled on
@@ -1,5 +0,0 @@
---
-"claude-dev": patch
---
-
-REfactoring Tool Executor
@@ -1,5 +0,0 @@
---
-"claude-dev": patch
---
-
-Add search functionality to API provider dropdown
@@ -1,5 +0,0 @@
---
-"claude-dev": patch
---
-
-Remove disabled approve / reject buttons from UI.
@@ -1,5 +0,0 @@
---
-"claude-dev": patch
---
-
-Add "Use custom prompt" option to Ollama provider
@@ -1,5 +0,0 @@
---
-"claude-dev": patch
---
-
-Fix AutoApproveModal overflowing issue
@@ -1,5 +0,0 @@
---
-"claude-dev": patch
---
-
-Dify.ai api integration
@@ -1,5 +0,0 @@
---
-"claude-dev": minor
---
-
-support orchestration mode for sap provider
@@ -1,5 +0,0 @@
---
-"claude-dev": patch
---
-
-Improve Gemini Rate Limit handling
@@ -1,5 +0,0 @@
---
-"claude-dev": patch
---
-
-fix: Support Anthropic Caching when using LiteLLM
@@ -1,5 +0,0 @@
---
-"claude-dev": patch
---
-
-Prompt changes for deep-planning in windows/powershell
@@ -3,13 +3,13 @@
 		"ts"
 	],
 	"spec": [
-		"src/**/__tests__/*.ts"
+		"src/**/__tests__/*.ts",
+		"eslint-rules/__tests__/**/*.test.ts"
 	],
 	"require": [
 		"ts-node/register",
 		"source-map-support/register",
 		"./src/test/requires.ts"
 	],
-	"recursive": true,
-	"exit": true
+	"recursive": true
 }
@@ -1,21 +1,5 @@
 # Changelog

-## [3.27.0]
-
- Fix `grok-code-fast-1` model information
- Add call to action for trying free `grok-code-fast-1` in Announcement banner
-
-## [3.26.7]
-
- Add 200k context window variant for Claude Sonnet 4 to OpenRouter and Cline providers
-
-## [3.26.6]
-
- Add free Grok Coder model to Cline provider for users looking for a fast, free coding model option
- Fix GPT-5 models not respecting auto-compact setting when enabled, improving context window management
- Fix provider retry attempts not showing proper user feedback during rate limiting scenarios
- Improve markdown and code block styling to automatically adapt when switching VS Code themes
-
 ## [3.26.5]

 - fix (provider/vercel-ai-gateway): reduce model list load frequency in settings view
@@ -30,9 +30,9 @@ English | <a href="https://github.com/cline/cline/blob/main/locales/es/README.md
 </table>
 </div>

-Meet Cline, an AI assistant that can use your **CLI** a**N**d **E**ditor.
+Meet Cline (pronounced /klaɪn/, like "Klein"), an AI assistant that can use your **CLI** a**N**d **E**ditor.

-Thanks to [Claude Sonnet's agentic coding capabilities](https://www.anthropic.com/claude/sonnet), Cline can handle complex software development tasks step-by-step. With tools that let him create & edit files, explore large projects, use the browser, and execute terminal commands (after you grant permission), he can assist you in ways that go beyond code completion or tech support. Cline can even use the Model Context Protocol (MCP) to create new tools and extend his own capabilities. While autonomous AI scripts traditionally run in sandboxed environments, this extension provides a human-in-the-loop GUI to approve every file change and terminal command, providing a safe and accessible way to explore the potential of agentic AI.
+Thanks to [Claude 3.7 Sonnet's agentic coding capabilities](https://www.anthropic.com/claude/sonnet), Cline can handle complex software development tasks step-by-step. With tools that let him create & edit files, explore large projects, use the browser, and execute terminal commands (after you grant permission), he can assist you in ways that go beyond code completion or tech support. Cline can even use the Model Context Protocol (MCP) to create new tools and extend his own capabilities. While autonomous AI scripts traditionally run in sandboxed environments, this extension provides a human-in-the-loop GUI to approve every file change and terminal command, providing a safe and accessible way to explore the potential of agentic AI.

 1. Enter your task and add images to convert mockups into functional apps or fix bugs with screenshots.
 2. Cline starts by analyzing your file structure & source code ASTs, running regex searches, and reading relevant files to get up to speed in existing projects. By carefully managing what information is added to context, Cline can provide valuable assistance even for large, complex projects without overwhelming the context window.
@@ -87,7 +87,7 @@ All changes made by Cline are recorded in your file's Timeline, providing an eas

 ### Use the Browser

-With Claude Sonnet's new [Computer Use](https://www.anthropic.com/news/3-5-models-and-computer-use) capability, Cline can launch a browser, click elements, type text, and scroll, capturing screenshots and console logs at each step. This allows for interactive debugging, end-to-end testing, and even general web use! This gives him autonomy to fixing visual bugs and runtime issues without you needing to handhold and copy-pasting error logs yourself.
+With Claude 3.5 Sonnet's new [Computer Use](https://www.anthropic.com/news/3-5-models-and-computer-use) capability, Cline can launch a browser, click elements, type text, and scroll, capturing screenshots and console logs at each step. This allows for interactive debugging, end-to-end testing, and even general web use! This gives him autonomy to fixing visual bugs and runtime issues without you needing to handhold and copy-pasting error logs yourself.

 Try asking Cline to "test the app", and watch as he runs a command like `npm run dev`, launches your locally running dev server in a browser, and performs a series of tests to confirm that everything works. [See a demo here.](https://x.com/sdrzn/status/1850880547825823989)

@@ -37,8 +37,7 @@
 				"useYield": "off",
 				"noConstructorReturn": "off",
 				"noInvalidPositionAtImportRule": "off",
-				"noSwitchDeclarations": "off",
-				"noUnusedImports": "error"
+				"noSwitchDeclarations": "off"
 			},
 			"a11y": "off",
 			"style": {
@@ -60,7 +60,6 @@
 					"getting-started/what-is-cline",
 					"getting-started/model-selection-guide",
 					"getting-started/installing-cline",
-					"getting-started/installing-cline-jetbrains",
 					"getting-started/task-management",
 					"getting-started/understanding-context-management",
 					{
@@ -1,135 +0,0 @@
---
-title: "Installing Cline for JetBrains"
-description: "Get Cline running in your favorite JetBrains IDE with the same powerful AI assistance you know from VSCode."
---
-
-<Frame>
-	<img
-		src="https://storage.googleapis.com/cline_public_images/docs/assets/jetbrains-logo.svg"
-		alt="JetBrains logo"
-		style={{ width: "200px", height: "auto", margin: "0 auto 20px auto", display: "block" }}
-	/>
-</Frame>
-
-Cline for JetBrains works almost identically to Cline in VSCode. All the core features work properly: diff editing, using tools, logging in with different providers, MCP servers, Cline rules and workflows, and more.
-
-<Frame>
-	<img
-		src="https://storage.googleapis.com/cline_public_images/docs/assets/jetbrains-demo-hifi.gif"
-		alt="Cline running in JetBrains IDE showing AI assistance"
-	/>
-</Frame>
-
-<Note>Cline for JetBrains is currently in alpha. While all core features are functional, you may encounter occasional issues.</Note>
-
-## Installation
-
-Since Cline for JetBrains is currently in alpha, it's not yet available on the JetBrains Marketplace. You'll need to install it manually from a downloaded file:
-
-### Manual Installation from Disk
-
-1. **Download the Plugin:**
-   - Go to [https://plugins.jetbrains.com/plugin/28247-cline/versions/stable](https://plugins.jetbrains.com/plugin/28247-cline/versions/stable)
-   - Click **Download** to get the `.zip` file
-
-<Frame>
-	<img
-		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-marketplace-download.png"
-		alt="JetBrains plugin marketplace showing Cline download page"
-	/>
-</Frame>
-
-2. **Install from Disk:**
-   - Open your JetBrains IDE
-   - Go to **IntelliJ IDEA** (or whichever IDE you are in) → **Settings**
-
-<Frame>
-	<img
-		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-settings.png"
-		alt="JetBrains IDE settings dialog"
-	/>
-</Frame>
-
-   - Select **Plugins** from the left sidebar
-   - Click the gear icon ⚙️ and select **Install Plugin from Disk...**
-
-<Frame>
-	<img
-		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-install-disk.png"
-		alt="JetBrains IDE settings showing Install Plugin from Disk option"
-	/>
-</Frame>
-
-   - Select the downloaded `.zip` file
-
-<Frame>
-	<img
-		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-zip-file.png"
-		alt="File selection dialog showing Cline plugin zip file"
-	/>
-</Frame>
-
-   - Restart your IDE when prompted
-
-## Getting Started with Cline
-
-After installation, you'll find Cline in your IDE:
-
-1. **Open Cline:**
-   - Look for the Cline tool window (usually on the right side)
-   - Or go to **View** → **Tool Windows** → **Cline**
-
-2. **Sign In (optional, BYOK is also available):**
-   - Click **Sign In** in the Cline panel
-   - You'll be taken to [app.cline.bot](https://app.cline.bot) to create your account
-   - No credit card needed to get started with free credits
-
-3. **Start Coding:**
-   - Try this first prompt: "Hey Cline! Can you help me create a simple Hello World program in this project?"
-
-## Key Differences from VSCode
-
-While Cline for JetBrains includes all the same powerful features, there's one important difference to be aware of:
-
-**Terminal Integration:** The terminal inside JetBrains isn't integrated with Cline the same way it is in VSCode. Cline can execute commands, but the output will only appear in the webview if you expand the **Command Output** section.
-
-This means:
- Commands still run successfully
- You can see the output by clicking to expand Command Output in the chat
- Terminal commands work the same way, just with a different display
-
-## What Works
-
-Everything else works exactly like VSCode:
-
- **Diff Editing:** Cline can read, write, and edit files with the same precision
- **Tool Usage:** All of Cline's tools (file operations, web browsing, etc.) work identically  
- **API Providers:** Connect to Anthropic, OpenAI, local models, and more
- **MCP Servers:** Full support for Model Context Protocol servers
- **Cline Rules:** Custom instructions and workflows work the same way
- **@ Mentions:** Reference files, folders, problems, and more
- **Drag & Drop:** Add files and images to conversations
-
-## Tips for JetBrains Users
-
- **Project Context:** Cline automatically understands your project structure, just like in VSCode
- **Language Support:** Cline works with any language your JetBrains IDE supports
- **Debugging Help:** Share error messages and stack traces directly in the chat
- **Code Review:** Ask Cline to review your code changes before committing
-
-## Troubleshooting
-
-If you don't see the Cline tool window after installation:
- Restart your IDE completely
- Check **View** → **Tool Windows** → **Cline**
- Ensure the plugin is enabled in **Settings** → **Plugins**
-
-Having other issues? Join our [Discord community](https://discord.gg/cline) for help from the team and other users.
-
-## Next Steps
-
-Now that you have Cline installed, you might want to:
- Learn about [model selection](/getting-started/model-selection-guide) to choose the best AI provider
- Explore [@ mentions](/features/at-mentions/overview) to reference files and context efficiently  
- Set up [Cline rules](/features/cline-rules) for your specific workflow
- Try [MCP servers](/mcp/mcp-overview) to extend Cline's capabilities
@@ -7,13 +7,12 @@ SAP AI Core and the generative AI hub help you to integrate LLMs and AI into new

 **Website:** [SAP Help Portal](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/what-is-sap-ai-core)

+### Getting a Service Binding

 > 💡 **Information**
 >
 > SAP AI Core, and Generative AI Hub, are offerings from SAP BTP.
-> You need an active SAP BTP contract and a existing subaccount with a SAP AI Core instance with the `extended` service plan (For more details about SAP AI Core service plans and their capabilities, see the [Service Plans documentation](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/service-plans)) to perform these steps.
-
-### Getting a Service Binding
+> You need an active SAP BTP contract and a existing subaccount with a SAP AI Core instance to perform these steps.

 1. **Access:** Go to your subaccount via [BTP Cloud Cockpit](cockpit.btp.cloud.sap/cockpit)
 2. **Create a Service Binding:** Go to "Instances and Subscriptions", select your SAP AI Core service instance and click on Service Bindings > Create.
@@ -33,30 +32,14 @@ Refer to the [Generative AI Hub Supported Models page](https://me.sap.com/notes/
 5.  **Enter Base URL:** Add the `.serviceurls.AI_API_URL` field from the service binding into the "AI Core Base URL" field.
 6.  **Enter Auth URL:** Add the `.url` field from the service binding into the "AI Core Auth URL" field.
 7.  **Enter Resource Group:** Add the resource group where you have your model deployments. See [Create a Deployment for a Generative AI Model](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-deployment-for-generative-ai-model-in-sap-ai-core).
-8.  **Configure Orchestration Mode:** If you have an `extended` service plan, the "Orchestration Mode" checkbox will automatically appear.
-9.  **Select Model:** Choose your desired model from the "Model" dropdown.
-
-### Orchestration Mode vs Native API
-
-**Orchestration Mode:**
- **Simplified usage:** Provides access to all available models without requiring individual deployments using the [Harmonized API](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/harmonized-api)
-
-**Native API Mode:**
- **Manual deployments:** Requires manual model deployment and management in your SAP AI Core service instance
+8.  **Select Model:** Choose your desired model from the "Model" dropdown.

 ### Tips and Notes

- **Service Plan Requirement:** You must have the SAP AI Core `extended` service plan to use LLMs with Cline. Other service plans do not provide access to Generative AI Hub.
-
- **Orchestration Mode (Recommended):** Keep Orchestration Mode enabled for the simplest setup. It provides automatic access to all available models without requiring manual deployments.
-
- **Native API Mode:** Only disable Orchestration Mode if you have specific requirements that necessitate direct AI Core API access or need features not supported by the orchestration mode.
-
- **When using Native API Mode:**
-    -   **Model Selection:** The model dropdown displays models in two separate lists:
-        -   **Deployed Models:** These models are already deployed in your specified resource group and are ready to use immediately.
-        -   **Not Deployed Models:** These models don't have active deployments in your specified resource group. You won't be able to use these models until you create deployments for them in SAP AI Core.
-    -   **Creating Deployments:** To use a model that has not been deployed yet, you'll need to create a deployment in your SAP AI Core service instance. See [Create a Deployment for a Generative AI Model](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-deployment-for-generative-ai-model-in-sap-ai-core) for instructions.
+-   **Model Selection:** The model dropdown displays models in two separate lists:
+    -   **Deployed Models:** These models are already deployed in your specified resource group and are ready to use immediately.
+    -   **Not Deployed Models:** These models don't have active deployments in your specified resource group. You won't be able to use these models until you create deployments for them in SAP AI Core.
+-   **Creating Deployments:** To use a not deployed model, you'll need to create a deployment in your resource group in sap ai core service instance. See [Create a Deployment for a Generative AI Model](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-deployment-for-generative-ai-model-in-sap-ai-core) for instructions.

 #### Configuring Reasoning Effort for OpenAI Models

@@ -1,12 +1,12 @@
 {
 	"name": "claude-dev",
-	"version": "3.27.0",
+	"version": "3.26.3",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "claude-dev",
-			"version": "3.27.0",
+			"version": "3.26.3",
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@anthropic-ai/sdk": "^0.37.0",
@@ -16,7 +16,7 @@
 				"@bufbuild/protobuf": "^2.2.5",
 				"@cerebras/cerebras_cloud_sdk": "^1.35.0",
 				"@google-cloud/vertexai": "^1.9.3",
-				"@google/genai": "^1.11.0",
+				"@google/genai": "1.0.0",
 				"@grpc/grpc-js": "^1.9.15",
 				"@grpc/reflection": "^1.0.4",
 				"@mistralai/mistralai": "^1.5.0",
@@ -28,8 +28,6 @@
 				"@opentelemetry/sdk-trace-node": "^1.30.1",
 				"@opentelemetry/semantic-conventions": "^1.30.0",
 				"@playwright/test": "^1.53.2",
-				"@sap-ai-sdk/ai-api": "^1.17.0",
-				"@sap-ai-sdk/orchestration": "^1.17.0",
 				"@sentry/browser": "^9.12.0",
 				"@streamparser/json": "^0.0.22",
 				"@types/uuid": "^10.0.0",
@@ -57,6 +55,7 @@
 				"jschardet": "^3.1.4",
 				"jwt-decode": "^4.0.0",
 				"mammoth": "^1.8.0",
+				"monaco-vscode-textmate-theme-converter": "^0.1.7",
 				"nice-grpc": "^2.1.12",
 				"ollama": "^0.5.13",
 				"open": "^10.1.2",
@@ -66,7 +65,7 @@
 				"p-timeout": "^6.1.4",
 				"p-wait-for": "^5.0.2",
 				"pdf-parse": "^1.1.1",
-				"posthog-node": "^5.8.0",
+				"posthog-node": "^4.8.1",
 				"puppeteer-chromium-resolver": "^23.0.0",
 				"puppeteer-core": "^23.4.0",
 				"reconnecting-eventsource": "^1.6.4",
@@ -1802,13 +1801,6 @@
 				"url": "https://github.com/prettier/prettier?sponsor=1"
 			}
 		},
-		"node_modules/@colors/colors": {
-			"version": "1.6.0",
-			"license": "MIT",
-			"engines": {
-				"node": ">=0.1.90"
-			}
-		},
 		"node_modules/@cspotcode/source-map-support": {
 			"version": "0.8.1",
 			"dev": true,
@@ -1829,15 +1821,6 @@
 				"@jridgewell/sourcemap-codec": "^1.4.10"
 			}
 		},
-		"node_modules/@dabh/diagnostics": {
-			"version": "2.0.3",
-			"license": "MIT",
-			"dependencies": {
-				"colorspace": "1.1.x",
-				"enabled": "2.0.x",
-				"kuler": "^2.0.0"
-			}
-		},
 		"node_modules/@esbuild/darwin-arm64": {
 			"version": "0.25.0",
 			"cpu": [
@@ -2531,24 +2514,19 @@
 			}
 		},
 		"node_modules/@google/genai": {
-			"version": "1.15.0",
-			"resolved": "https://registry.npmjs.org/@google/genai/-/genai-1.15.0.tgz",
-			"integrity": "sha512-4CSW+hRTESWl3xVtde7pkQ3E+dDFhDq+m4ztmccRctZfx1gKy3v0M9STIMGk6Nq0s6O2uKMXupOZQ1JGorXVwQ==",
+			"version": "1.0.0",
 			"license": "Apache-2.0",
 			"dependencies": {
 				"google-auth-library": "^9.14.2",
-				"ws": "^8.18.0"
+				"ws": "^8.18.0",
+				"zod": "^3.22.4",
+				"zod-to-json-schema": "^3.22.4"
 			},
 			"engines": {
-				"node": ">=20.0.0"
+				"node": ">=18.0.0"
 			},
 			"peerDependencies": {
 				"@modelcontextprotocol/sdk": "^1.11.0"
-			},
-			"peerDependenciesMeta": {
-				"@modelcontextprotocol/sdk": {
-					"optional": true
-				}
 			}
 		},
 		"node_modules/@grpc/grpc-js": {
@@ -3690,12 +3668,6 @@
 				"node": ">=18"
 			}
 		},
-		"node_modules/@posthog/core": {
-			"version": "1.0.1",
-			"resolved": "https://registry.npmjs.org/@posthog/core/-/core-1.0.1.tgz",
-			"integrity": "sha512-bwXUeHe+MLgENm8+/FxEbiNocOw1Vjewmm+HEUaYQe6frq8OhZnrvtnzZU3Q3DF6N0UbAmD/q+iNfNgyx8mozg==",
-			"license": "MIT"
-		},
 		"node_modules/@protobufjs/aspromise": {
 			"version": "1.1.2",
 			"license": "BSD-3-Clause"
@@ -3760,162 +3732,6 @@
 				"node": ">=18"
 			}
 		},
-		"node_modules/@sap-ai-sdk/ai-api": {
-			"version": "1.17.0",
-			"license": "Apache-2.0",
-			"dependencies": {
-				"@sap-ai-sdk/core": "^1.17.0",
-				"@sap-cloud-sdk/connectivity": "^4.1.1",
-				"@sap-cloud-sdk/util": "^4.1.1"
-			}
-		},
-		"node_modules/@sap-ai-sdk/core": {
-			"version": "1.17.0",
-			"license": "Apache-2.0",
-			"dependencies": {
-				"@sap-cloud-sdk/connectivity": "^4.1.0",
-				"@sap-cloud-sdk/http-client": "^4.1.0",
-				"@sap-cloud-sdk/openapi": "^4.1.0",
-				"@sap-cloud-sdk/util": "^4.1.0"
-			}
-		},
-		"node_modules/@sap-ai-sdk/orchestration": {
-			"version": "1.17.0",
-			"license": "Apache-2.0",
-			"dependencies": {
-				"@sap-ai-sdk/ai-api": "^1.17.0",
-				"@sap-ai-sdk/core": "^1.17.0",
-				"@sap-ai-sdk/prompt-registry": "^1.17.0",
-				"@sap-cloud-sdk/util": "^4.1.1",
-				"yaml": "^2.8.1"
-			}
-		},
-		"node_modules/@sap-ai-sdk/prompt-registry": {
-			"version": "1.17.0",
-			"license": "Apache-2.0",
-			"dependencies": {
-				"@sap-ai-sdk/core": "^1.17.0",
-				"zod": "^3.25.76"
-			}
-		},
-		"node_modules/@sap-cloud-sdk/connectivity": {
-			"version": "4.1.1",
-			"license": "Apache-2.0",
-			"dependencies": {
-				"@sap-cloud-sdk/resilience": "^4.1.1",
-				"@sap-cloud-sdk/util": "^4.1.1",
-				"@sap/xsenv": "^5.6.1",
-				"@sap/xssec": "^4.9.0",
-				"async-retry": "^1.3.3",
-				"axios": "^1.11.0",
-				"jsonwebtoken": "^9.0.2"
-			}
-		},
-		"node_modules/@sap-cloud-sdk/http-client": {
-			"version": "4.1.1",
-			"license": "Apache-2.0",
-			"dependencies": {
-				"@sap-cloud-sdk/connectivity": "^4.1.1",
-				"@sap-cloud-sdk/resilience": "^4.1.1",
-				"@sap-cloud-sdk/util": "^4.1.1",
-				"axios": "^1.11.0"
-			}
-		},
-		"node_modules/@sap-cloud-sdk/openapi": {
-			"version": "4.1.1",
-			"license": "Apache-2.0",
-			"dependencies": {
-				"@sap-cloud-sdk/connectivity": "^4.1.1",
-				"@sap-cloud-sdk/http-client": "^4.1.1",
-				"@sap-cloud-sdk/resilience": "^4.1.1",
-				"@sap-cloud-sdk/util": "^4.1.1",
-				"axios": "^1.11.0"
-			}
-		},
-		"node_modules/@sap-cloud-sdk/resilience": {
-			"version": "4.1.1",
-			"license": "Apache-2.0",
-			"dependencies": {
-				"@sap-cloud-sdk/util": "^4.1.1",
-				"async-retry": "^1.3.3",
-				"axios": "^1.11.0",
-				"opossum": "^9.0.0"
-			}
-		},
-		"node_modules/@sap-cloud-sdk/util": {
-			"version": "4.1.1",
-			"license": "Apache-2.0",
-			"dependencies": {
-				"axios": "^1.11.0",
-				"chalk": "^4.1.0",
-				"logform": "^2.7.0",
-				"voca": "^1.4.1",
-				"winston": "^3.17.0",
-				"winston-transport": "^4.9.0"
-			}
-		},
-		"node_modules/@sap-cloud-sdk/util/node_modules/chalk": {
-			"version": "4.1.2",
-			"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/@sap-cloud-sdk/util/node_modules/supports-color": {
-			"version": "7.2.0",
-			"license": "MIT",
-			"dependencies": {
-				"has-flag": "^4.0.0"
-			},
-			"engines": {
-				"node": ">=8"
-			}
-		},
-		"node_modules/@sap/xsenv": {
-			"version": "5.6.1",
-			"license": "SEE LICENSE IN LICENSE file",
-			"dependencies": {
-				"debug": "4.4.0",
-				"node-cache": "^5.1.2",
-				"verror": "1.10.1"
-			},
-			"engines": {
-				"node": "^18.0.0 || ^20.0.0  || ^22.0.0"
-			}
-		},
-		"node_modules/@sap/xsenv/node_modules/debug": {
-			"version": "4.4.0",
-			"license": "MIT",
-			"dependencies": {
-				"ms": "^2.1.3"
-			},
-			"engines": {
-				"node": ">=6.0"
-			},
-			"peerDependenciesMeta": {
-				"supports-color": {
-					"optional": true
-				}
-			}
-		},
-		"node_modules/@sap/xssec": {
-			"version": "4.9.0",
-			"license": "SAP DEVELOPER LICENSE AGREEMENT",
-			"dependencies": {
-				"debug": "^4.3.4",
-				"jwt-decode": "^4"
-			},
-			"engines": {
-				"node": ">=18"
-			}
-		},
 		"node_modules/@sec-ant/readable-stream": {
 			"version": "0.4.1",
 			"license": "MIT"
@@ -5184,10 +5000,6 @@
 			"dev": true,
 			"license": "MIT"
 		},
-		"node_modules/@types/triple-beam": {
-			"version": "1.3.5",
-			"license": "MIT"
-		},
 		"node_modules/@types/turndown": {
 			"version": "5.0.5",
 			"dev": true,
@@ -5195,6 +5007,8 @@
 		},
 		"node_modules/@types/uuid": {
 			"version": "10.0.0",
+			"resolved": "https://registry.npmjs.org/@types/uuid/-/uuid-10.0.0.tgz",
+			"integrity": "sha512-7gqG38EyHgyP1S+7+xomFtL+ZNHcKv6DwNaCZmJmo1vgMugyF3TCnXVg4t1uk89mLNwnLtnY3TpOpCOyp1/xHQ==",
 			"license": "MIT"
 		},
 		"node_modules/@types/vscode": {
@@ -5927,13 +5741,6 @@
 				"url": "https://github.com/sponsors/ljharb"
 			}
 		},
-		"node_modules/assert-plus": {
-			"version": "1.0.0",
-			"license": "MIT",
-			"engines": {
-				"node": ">=0.8"
-			}
-		},
 		"node_modules/assertion-error": {
 			"version": "1.1.0",
 			"dev": true,
@@ -5976,13 +5783,6 @@
 				"node": ">= 0.4"
 			}
 		},
-		"node_modules/async-retry": {
-			"version": "1.3.3",
-			"license": "MIT",
-			"dependencies": {
-				"retry": "0.13.1"
-			}
-		},
 		"node_modules/asynckit": {
 			"version": "0.4.0",
 			"license": "MIT"
@@ -6002,11 +5802,11 @@
 			}
 		},
 		"node_modules/axios": {
-			"version": "1.11.0",
+			"version": "1.10.0",
 			"license": "MIT",
 			"dependencies": {
 				"follow-redirects": "^1.15.6",
-				"form-data": "^4.0.4",
+				"form-data": "^4.0.0",
 				"proxy-from-env": "^1.1.0"
 			}
 		},
@@ -6677,13 +6477,6 @@
 				"url": "https://github.com/chalk/wrap-ansi?sponsor=1"
 			}
 		},
-		"node_modules/clone": {
-			"version": "2.1.2",
-			"license": "MIT",
-			"engines": {
-				"node": ">=0.8"
-			}
-		},
 		"node_modules/clone-deep": {
 			"version": "4.0.1",
 			"license": "MIT",
@@ -6708,14 +6501,6 @@
 			"version": "13.0.3",
 			"license": "MIT"
 		},
-		"node_modules/color": {
-			"version": "3.2.1",
-			"license": "MIT",
-			"dependencies": {
-				"color-convert": "^1.9.3",
-				"color-string": "^1.6.0"
-			}
-		},
 		"node_modules/color-convert": {
 			"version": "2.0.1",
 			"license": "MIT",
@@ -6730,14 +6515,6 @@
 			"version": "1.1.4",
 			"license": "MIT"
 		},
-		"node_modules/color-string": {
-			"version": "1.9.1",
-			"license": "MIT",
-			"dependencies": {
-				"color-name": "^1.0.0",
-				"simple-swizzle": "^0.2.2"
-			}
-		},
 		"node_modules/color-support": {
 			"version": "1.1.3",
 			"license": "ISC",
@@ -6745,30 +6522,11 @@
 				"color-support": "bin.js"
 			}
 		},
-		"node_modules/color/node_modules/color-convert": {
-			"version": "1.9.3",
-			"license": "MIT",
-			"dependencies": {
-				"color-name": "1.1.3"
-			}
-		},
-		"node_modules/color/node_modules/color-name": {
-			"version": "1.1.3",
-			"license": "MIT"
-		},
 		"node_modules/colorette": {
 			"version": "2.0.20",
 			"dev": true,
 			"license": "MIT"
 		},
-		"node_modules/colorspace": {
-			"version": "1.1.4",
-			"license": "MIT",
-			"dependencies": {
-				"color": "^3.1.3",
-				"text-hex": "1.0.x"
-			}
-		},
 		"node_modules/combined-stream": {
 			"version": "1.0.8",
 			"license": "MIT",
@@ -6779,6 +6537,13 @@
 				"node": ">= 0.8"
 			}
 		},
+		"node_modules/commander": {
+			"version": "8.3.0",
+			"license": "MIT",
+			"engines": {
+				"node": ">= 12"
+			}
+		},
 		"node_modules/compress-commons": {
 			"version": "6.0.2",
 			"license": "MIT",
@@ -7442,10 +7207,6 @@
 			"version": "9.2.2",
 			"license": "MIT"
 		},
-		"node_modules/enabled": {
-			"version": "2.0.0",
-			"license": "MIT"
-		},
 		"node_modules/encodeurl": {
 			"version": "2.0.0",
 			"license": "MIT",
@@ -7635,6 +7396,7 @@
 		},
 		"node_modules/es-set-tostringtag": {
 			"version": "2.1.0",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"es-errors": "^1.3.0",
@@ -8269,13 +8031,6 @@
 				"@types/yauzl": "^2.9.1"
 			}
 		},
-		"node_modules/extsprintf": {
-			"version": "1.4.1",
-			"engines": [
-				"node >=0.6.0"
-			],
-			"license": "MIT"
-		},
 		"node_modules/fast-csv": {
 			"version": "4.3.6",
 			"license": "MIT",
@@ -8368,10 +8123,6 @@
 				"pend": "~1.2.0"
 			}
 		},
-		"node_modules/fecha": {
-			"version": "4.2.3",
-			"license": "MIT"
-		},
 		"node_modules/figures": {
 			"version": "6.1.0",
 			"license": "MIT",
@@ -8497,10 +8248,6 @@
 				"flat": "cli.js"
 			}
 		},
-		"node_modules/fn.name": {
-			"version": "1.1.0",
-			"license": "MIT"
-		},
 		"node_modules/follow-redirects": {
 			"version": "1.15.6",
 			"funding": [
@@ -8548,13 +8295,11 @@
 			}
 		},
 		"node_modules/form-data": {
-			"version": "4.0.4",
+			"version": "4.0.0",
 			"license": "MIT",
 			"dependencies": {
 				"asynckit": "^0.4.0",
 				"combined-stream": "^1.0.8",
-				"es-set-tostringtag": "^2.1.0",
-				"hasown": "^2.0.2",
 				"mime-types": "^2.1.12"
 			},
 			"engines": {
@@ -8603,7 +8348,6 @@
 		},
 		"node_modules/fs-extra": {
 			"version": "7.0.1",
-			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"graceful-fs": "^4.1.2",
@@ -9125,6 +8869,7 @@
 		},
 		"node_modules/has-flag": {
 			"version": "4.0.0",
+			"dev": true,
 			"license": "MIT",
 			"engines": {
 				"node": ">=8"
@@ -9167,6 +8912,7 @@
 		},
 		"node_modules/has-tostringtag": {
 			"version": "1.0.2",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"has-symbols": "^1.0.3"
@@ -10099,7 +9845,6 @@
 		},
 		"node_modules/jsonfile": {
 			"version": "4.0.0",
-			"dev": true,
 			"license": "MIT",
 			"optionalDependencies": {
 				"graceful-fs": "^4.1.6"
@@ -10107,6 +9852,7 @@
 		},
 		"node_modules/jsonwebtoken": {
 			"version": "9.0.2",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"jws": "^3.2.2",
@@ -10127,6 +9873,7 @@
 		},
 		"node_modules/jsonwebtoken/node_modules/jwa": {
 			"version": "1.4.2",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"buffer-equal-constant-time": "^1.0.1",
@@ -10136,6 +9883,7 @@
 		},
 		"node_modules/jsonwebtoken/node_modules/jws": {
 			"version": "3.2.2",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"jwa": "^1.4.1",
@@ -10199,10 +9947,6 @@
 				"node": ">=0.10.0"
 			}
 		},
-		"node_modules/kuler": {
-			"version": "2.0.0",
-			"license": "MIT"
-		},
 		"node_modules/lazystream": {
 			"version": "1.0.1",
 			"license": "MIT",
@@ -10434,6 +10178,7 @@
 		},
 		"node_modules/lodash.includes": {
 			"version": "4.3.0",
+			"dev": true,
 			"license": "MIT"
 		},
 		"node_modules/lodash.isboolean": {
@@ -10450,6 +10195,7 @@
 		},
 		"node_modules/lodash.isinteger": {
 			"version": "4.0.4",
+			"dev": true,
 			"license": "MIT"
 		},
 		"node_modules/lodash.isnil": {
@@ -10458,6 +10204,7 @@
 		},
 		"node_modules/lodash.isnumber": {
 			"version": "3.0.3",
+			"dev": true,
 			"license": "MIT"
 		},
 		"node_modules/lodash.isplainobject": {
@@ -10466,6 +10213,7 @@
 		},
 		"node_modules/lodash.isstring": {
 			"version": "4.0.1",
+			"dev": true,
 			"license": "MIT"
 		},
 		"node_modules/lodash.isundefined": {
@@ -10478,6 +10226,7 @@
 		},
 		"node_modules/lodash.once": {
 			"version": "4.1.1",
+			"dev": true,
 			"license": "MIT"
 		},
 		"node_modules/lodash.startcase": {
@@ -10677,21 +10426,6 @@
 				"url": "https://github.com/chalk/wrap-ansi?sponsor=1"
 			}
 		},
-		"node_modules/logform": {
-			"version": "2.7.0",
-			"license": "MIT",
-			"dependencies": {
-				"@colors/colors": "1.6.0",
-				"@types/triple-beam": "^1.3.2",
-				"fecha": "^4.2.0",
-				"ms": "^2.1.1",
-				"safe-stable-stringify": "^2.3.1",
-				"triple-beam": "^1.3.0"
-			},
-			"engines": {
-				"node": ">= 12.0.0"
-			}
-		},
 		"node_modules/long": {
 			"version": "5.2.4",
 			"license": "Apache-2.0"
@@ -11178,6 +10912,25 @@
 			"dev": true,
 			"license": "MIT"
 		},
+		"node_modules/monaco-vscode-textmate-theme-converter": {
+			"version": "0.1.7",
+			"license": "MIT",
+			"dependencies": {
+				"commander": "^8.1.0",
+				"fs-extra": "^7.0.1",
+				"tslib": "^2.3.0"
+			},
+			"bin": {
+				"mvttc": "lib/cjs/npx-script.js"
+			},
+			"peerDependencies": {
+				"tslib": "^2.0.1"
+			}
+		},
+		"node_modules/monaco-vscode-textmate-theme-converter/node_modules/tslib": {
+			"version": "2.7.0",
+			"license": "0BSD"
+		},
 		"node_modules/mri": {
 			"version": "1.2.0",
 			"dev": true,
@@ -11232,6 +10985,8 @@
 		},
 		"node_modules/nice-grpc-common": {
 			"version": "2.0.2",
+			"resolved": "https://registry.npmjs.org/nice-grpc-common/-/nice-grpc-common-2.0.2.tgz",
+			"integrity": "sha512-7RNWbls5kAL1QVUOXvBsv1uO0wPQK3lHv+cY1gwkTzirnG1Nop4cBJZubpgziNbaVc/bl9QJcyvsf/NQxa3rjQ==",
 			"license": "MIT",
 			"dependencies": {
 				"ts-error": "^1.0.6"
@@ -11283,16 +11038,6 @@
 			"license": "MIT",
 			"optional": true
 		},
-		"node_modules/node-cache": {
-			"version": "5.1.2",
-			"license": "MIT",
-			"dependencies": {
-				"clone": "2.x"
-			},
-			"engines": {
-				"node": ">= 8.0.0"
-			}
-		},
 		"node_modules/node-domexception": {
 			"version": "1.0.0",
 			"funding": [
@@ -11734,13 +11479,6 @@
 				"wrappy": "1"
 			}
 		},
-		"node_modules/one-time": {
-			"version": "1.0.0",
-			"license": "MIT",
-			"dependencies": {
-				"fn.name": "1.x.x"
-			}
-		},
 		"node_modules/open": {
 			"version": "10.1.2",
 			"license": "MIT",
@@ -11829,13 +11567,6 @@
 				"node": ">=0.10"
 			}
 		},
-		"node_modules/opossum": {
-			"version": "9.0.0",
-			"license": "Apache-2.0",
-			"engines": {
-				"node": "^24 || ^22 || ^20"
-			}
-		},
 		"node_modules/option": {
 			"version": "0.2.4",
 			"license": "BSD-2-Clause"
@@ -12398,15 +12129,13 @@
 			}
 		},
 		"node_modules/posthog-node": {
-			"version": "5.8.0",
-			"resolved": "https://registry.npmjs.org/posthog-node/-/posthog-node-5.8.0.tgz",
-			"integrity": "sha512-Idj6TgjYN0POXvrGK97ZKTLbLEY7sUjsaeMaquKt9UlK3Z9ps0nj0wRkFYKEYvfQ8OMwTwgKaze+5hXgmudwdw==",
+			"version": "4.8.1",
 			"license": "MIT",
 			"dependencies": {
-				"@posthog/core": "1.0.1"
+				"axios": "^1.7.4"
 			},
 			"engines": {
-				"node": ">=20"
+				"node": ">=15.0.0"
 			}
 		},
 		"node_modules/prebuild-install": {
@@ -12993,13 +12722,6 @@
 				"url": "https://github.com/sponsors/ljharb"
 			}
 		},
-		"node_modules/retry": {
-			"version": "0.13.1",
-			"license": "MIT",
-			"engines": {
-				"node": ">= 4"
-			}
-		},
 		"node_modules/reusify": {
 			"version": "1.0.4",
 			"license": "MIT",
@@ -13210,13 +12932,6 @@
 				"url": "https://github.com/sponsors/ljharb"
 			}
 		},
-		"node_modules/safe-stable-stringify": {
-			"version": "2.5.0",
-			"license": "MIT",
-			"engines": {
-				"node": ">=10"
-			}
-		},
 		"node_modules/safer-buffer": {
 			"version": "2.1.2",
 			"license": "MIT"
@@ -13693,17 +13408,6 @@
 				"url": "https://github.com/steveukx/git-js?sponsor=1"
 			}
 		},
-		"node_modules/simple-swizzle": {
-			"version": "0.2.2",
-			"license": "MIT",
-			"dependencies": {
-				"is-arrayish": "^0.3.1"
-			}
-		},
-		"node_modules/simple-swizzle/node_modules/is-arrayish": {
-			"version": "0.3.2",
-			"license": "MIT"
-		},
 		"node_modules/sinon": {
 			"version": "19.0.2",
 			"dev": true,
@@ -13868,13 +13572,6 @@
 			"version": "1.0.3",
 			"license": "BSD-3-Clause"
 		},
-		"node_modules/stack-trace": {
-			"version": "0.0.10",
-			"license": "MIT",
-			"engines": {
-				"node": "*"
-			}
-		},
 		"node_modules/statuses": {
 			"version": "2.0.1",
 			"license": "MIT",
@@ -14355,10 +14052,6 @@
 				"b4a": "^1.6.4"
 			}
 		},
-		"node_modules/text-hex": {
-			"version": "1.0.0",
-			"license": "MIT"
-		},
 		"node_modules/text-table": {
 			"version": "0.2.0",
 			"dev": true,
@@ -14443,13 +14136,6 @@
 			"version": "0.1.11",
 			"license": "Unlicense"
 		},
-		"node_modules/triple-beam": {
-			"version": "1.4.1",
-			"license": "MIT",
-			"engines": {
-				"node": ">= 14.0.0"
-			}
-		},
 		"node_modules/ts-error": {
 			"version": "1.0.6",
 			"license": "MIT"
@@ -14722,6 +14408,8 @@
 		},
 		"node_modules/ulid": {
 			"version": "2.4.0",
+			"resolved": "https://registry.npmjs.org/ulid/-/ulid-2.4.0.tgz",
+			"integrity": "sha512-fIRiVTJNcSRmXKPZtGzFQv9WRrZ3M9eoptl/teFJvjOzmpU+/K/JH6HZ8deBfb5vMEpicJcLn7JmvdknlMq7Zg==",
 			"license": "MIT",
 			"bin": {
 				"ulid": "bin/cli.js"
@@ -14801,7 +14489,6 @@
 		},
 		"node_modules/universalify": {
 			"version": "0.1.2",
-			"dev": true,
 			"license": "MIT",
 			"engines": {
 				"node": ">= 4.0.0"
@@ -14852,6 +14539,8 @@
 		},
 		"node_modules/uuid": {
 			"version": "11.1.0",
+			"resolved": "https://registry.npmjs.org/uuid/-/uuid-11.1.0.tgz",
+			"integrity": "sha512-0/A9rDy9P7cJ+8w1c9WD9V//9Wj15Ce2MPz8Ri6032usz+NfePxx5AcN3bN+r6ZL6jEo066/yNYB3tn4pQEx+A==",
 			"funding": [
 				"https://github.com/sponsors/broofa",
 				"https://github.com/sponsors/ctavan"
@@ -14895,22 +14584,6 @@
 				"node": ">= 0.8"
 			}
 		},
-		"node_modules/verror": {
-			"version": "1.10.1",
-			"license": "MIT",
-			"dependencies": {
-				"assert-plus": "^1.0.0",
-				"core-util-is": "1.0.2",
-				"extsprintf": "^1.2.0"
-			},
-			"engines": {
-				"node": ">=0.6.0"
-			}
-		},
-		"node_modules/verror/node_modules/core-util-is": {
-			"version": "1.0.2",
-			"license": "MIT"
-		},
 		"node_modules/version-range": {
 			"version": "4.14.0",
 			"dev": true,
@@ -14922,10 +14595,6 @@
 				"url": "https://bevry.me/fund"
 			}
 		},
-		"node_modules/voca": {
-			"version": "1.4.1",
-			"license": "MIT"
-		},
 		"node_modules/vscode-uri": {
 			"version": "3.1.0",
 			"license": "MIT"
@@ -15212,62 +14881,6 @@
 				"url": "https://github.com/sponsors/sindresorhus"
 			}
 		},
-		"node_modules/winston": {
-			"version": "3.17.0",
-			"license": "MIT",
-			"dependencies": {
-				"@colors/colors": "^1.6.0",
-				"@dabh/diagnostics": "^2.0.2",
-				"async": "^3.2.3",
-				"is-stream": "^2.0.0",
-				"logform": "^2.7.0",
-				"one-time": "^1.0.0",
-				"readable-stream": "^3.4.0",
-				"safe-stable-stringify": "^2.3.1",
-				"stack-trace": "0.0.x",
-				"triple-beam": "^1.3.0",
-				"winston-transport": "^4.9.0"
-			},
-			"engines": {
-				"node": ">= 12.0.0"
-			}
-		},
-		"node_modules/winston-transport": {
-			"version": "4.9.0",
-			"license": "MIT",
-			"dependencies": {
-				"logform": "^2.7.0",
-				"readable-stream": "^3.6.2",
-				"triple-beam": "^1.3.0"
-			},
-			"engines": {
-				"node": ">= 12.0.0"
-			}
-		},
-		"node_modules/winston-transport/node_modules/readable-stream": {
-			"version": "3.6.2",
-			"license": "MIT",
-			"dependencies": {
-				"inherits": "^2.0.3",
-				"string_decoder": "^1.1.1",
-				"util-deprecate": "^1.0.1"
-			},
-			"engines": {
-				"node": ">= 6"
-			}
-		},
-		"node_modules/winston/node_modules/readable-stream": {
-			"version": "3.6.2",
-			"license": "MIT",
-			"dependencies": {
-				"inherits": "^2.0.3",
-				"string_decoder": "^1.1.1",
-				"util-deprecate": "^1.0.1"
-			},
-			"engines": {
-				"node": ">= 6"
-			}
-		},
 		"node_modules/workerpool": {
 			"version": "6.5.1",
 			"dev": true,
@@ -15398,7 +15011,8 @@
 			"license": "ISC"
 		},
 		"node_modules/yaml": {
-			"version": "2.8.1",
+			"version": "2.8.0",
+			"dev": true,
 			"license": "ISC",
 			"bin": {
 				"yaml": "bin.mjs"
@@ -15574,7 +15188,7 @@
 			}
 		},
 		"node_modules/zod": {
-			"version": "3.25.76",
+			"version": "3.24.2",
 			"license": "MIT",
 			"funding": {
 				"url": "https://github.com/sponsors/colinhacks"
@@ -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": "3.27.0",
+	"version": "3.26.5",
 	"icon": "assets/icons/icon.png",
 	"engines": {
 		"vscode": "^1.84.0"
@@ -102,8 +102,15 @@
 			"activitybar": [
 				{
 					"id": "claude-dev-ActivityBar",
-					"title": "Cline",
-					"icon": "assets/icons/icon.svg"
+					"title": "Cline (⌘+')",
+					"icon": "assets/icons/icon.svg",
+					"when": "isMac"
+				},
+				{
+					"id": "claude-dev-ActivityBar",
+					"title": "Cline (Ctrl+')",
+					"icon": "assets/icons/icon.svg",
+					"when": "!isMac"
 				}
 			]
 		},
@@ -419,12 +426,10 @@
 		"@anthropic-ai/vertex-sdk": "^0.6.4",
 		"@aws-sdk/client-bedrock-runtime": "^3.840.0",
 		"@aws-sdk/credential-providers": "^3.840.0",
-		"@sap-ai-sdk/ai-api": "^1.17.0",
-		"@sap-ai-sdk/orchestration": "^1.17.0",
 		"@bufbuild/protobuf": "^2.2.5",
 		"@cerebras/cerebras_cloud_sdk": "^1.35.0",
 		"@google-cloud/vertexai": "^1.9.3",
-		"@google/genai": "^1.11.0",
+		"@google/genai": "1.0.0",
 		"@grpc/grpc-js": "^1.9.15",
 		"@grpc/reflection": "^1.0.4",
 		"@mistralai/mistralai": "^1.5.0",
@@ -463,6 +468,7 @@
 		"jschardet": "^3.1.4",
 		"jwt-decode": "^4.0.0",
 		"mammoth": "^1.8.0",
+		"monaco-vscode-textmate-theme-converter": "^0.1.7",
 		"nice-grpc": "^2.1.12",
 		"ollama": "^0.5.13",
 		"open": "^10.1.2",
@@ -472,7 +478,7 @@
 		"p-timeout": "^6.1.4",
 		"p-wait-for": "^5.0.2",
 		"pdf-parse": "^1.1.1",
-		"posthog-node": "^5.8.0",
+		"posthog-node": "^4.8.1",
 		"puppeteer-chromium-resolver": "^23.0.0",
 		"puppeteer-core": "^23.4.0",
 		"reconnecting-eventsource": "^1.6.4",
@@ -40,6 +40,10 @@ message AddRemoteMcpServerRequest {
  Metadata metadata = 1;
  string server_name = 2;
  string server_url = 3;
+  // New fields for first-class transport setup
+  string transport_type = 4; // "streamableHttp" | "sse" | "stdio" (clients may default to "streamableHttp")
+  map<string, string> headers = 5; // optional headers (e.g., Authorization)
+  int32 timeout = 6; // optional per-server timeout in seconds
 }

 message ToggleToolAutoApproveRequest {
@@ -32,7 +32,7 @@ service ModelsService {
  // Refreshes and returns Baseten models
  rpc refreshBasetenModels(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
  // Fetches available models from SAP AI Core
-  rpc getSapAiCoreModels(SapAiCoreModelsRequest) returns (SapAiCoreModelsResponse);
+  rpc getSapAiCoreModels(SapAiCoreModelsRequest) returns (StringArray);
 }

 // List of VS Code LM models
@@ -50,20 +50,20 @@ message LanguageModelChatSelector {

 // Price tier for tiered pricing models
 message PriceTier {
-  int64 token_limit = 1;  // Upper limit (inclusive) of input tokens for this price
+  int32 token_limit = 1;  // Upper limit (inclusive) of input tokens for this price
  double price = 2;       // Price per million tokens for this tier
 }

 // Thinking configuration for models that support thinking/reasoning
 message ThinkingConfig {
-  optional int64 max_budget = 1;                    // Max allowed thinking budget tokens
+  optional int32 max_budget = 1;                    // Max allowed thinking budget tokens
  optional double output_price = 2;                 // Output price per million tokens when budget > 0
  repeated PriceTier output_price_tiers = 3;        // Optional: Tiered output price when budget > 0
 }

 // Model tier for tiered pricing structures
 message ModelTier {
-  int64 context_window = 1;
+  int32 context_window = 1;
  optional double input_price = 2;
  optional double output_price = 3;
  optional double cache_writes_price = 4;
@@ -108,12 +108,6 @@ message SapAiCoreModelsRequest {
  string resource_group = 6;
 }

-// Response for SAP AI Core models with orchestration availability
-message SapAiCoreModelsResponse {
-  repeated string model_names = 1;
-  bool orchestration_available = 2;
-}
-
 // Request for updating API configuration
 message UpdateApiConfigurationRequest {
  Metadata metadata = 1;
@@ -155,14 +149,12 @@ enum ApiProvider {
  BASETEN = 30;
  ZAI = 31;
  VERCEL_AI_GATEWAY = 32;
-  QWEN_CODE = 33;
-  DIFY = 34;
 }

 // Model info for OpenAI-compatible models
 message OpenAiCompatibleModelInfo {
-  optional int64 max_tokens = 1;
-  optional int64 context_window = 2;
+  optional int32 max_tokens = 1;
+  optional int32 context_window = 2;
  optional bool supports_images = 3;
  bool supports_prompt_cache = 4;
  optional double input_price = 5;
@@ -179,8 +171,8 @@ message OpenAiCompatibleModelInfo {

 // Model info for LiteLLM models
 message LiteLLMModelInfo {
-  optional int64 max_tokens = 1;
-  optional int64 context_window = 2;
+  optional int32 max_tokens = 1;
+  optional int32 context_window = 2;
  optional bool supports_images = 3;
  bool supports_prompt_cache = 4;
  optional double input_price = 5;
@@ -232,8 +224,8 @@ message ModelsApiConfiguration {
  optional string requesty_base_url = 33;
  optional string together_api_key = 34;
  optional string fireworks_api_key = 35;
-  optional int64 fireworks_model_max_completion_tokens = 36;
-  optional int64 fireworks_model_max_tokens = 37;
+  optional int32 fireworks_model_max_completion_tokens = 36;
+  optional int32 fireworks_model_max_tokens = 37;
  optional string qwen_api_key = 38;
  optional string doubao_api_key = 39;
  optional string mistral_api_key = 40;
@@ -245,35 +237,31 @@ message ModelsApiConfiguration {
  optional string xai_api_key = 46;
  optional string sambanova_api_key = 47;
  optional string cerebras_api_key = 48;
-  optional int64 request_timeout_ms = 49;
+  optional int32 request_timeout_ms = 49;
  optional string sap_ai_core_client_id = 50;
  optional string sap_ai_core_client_secret = 51;
  optional string sap_ai_resource_group = 52;
  optional string sap_ai_core_token_url = 53;
  optional string sap_ai_core_base_url = 54;
-  optional bool sap_ai_core_use_orchestration_mode = 55;
-  optional string moonshot_api_key = 56;
-  optional string moonshot_api_line = 57;
-  optional string aws_authentication = 58;
-  optional string aws_bedrock_api_key = 59;
-  optional string cline_account_id = 60;
-  optional string groq_api_key = 61;
-  optional string hugging_face_api_key = 62;
-  optional string huawei_cloud_maas_api_key = 63;
-  optional string baseten_api_key = 64;
-  optional string ollama_api_key = 65;
-  optional string zai_api_key = 66;
-  optional string zai_api_line = 67;
-  optional string lm_studio_max_tokens = 68;
-  optional string vercel_ai_gateway_api_key = 69;
-  optional string qwen_code_oauth_path = 70;
-  optional string dify_api_key = 71;
-  optional string dify_base_url = 72;
+  optional string moonshot_api_key = 55;
+  optional string moonshot_api_line = 56;
+  optional string aws_authentication = 57;
+  optional string aws_bedrock_api_key = 58;
+  optional string cline_account_id = 59;
+  optional string groq_api_key = 60;
+  optional string hugging_face_api_key = 61;
+  optional string huawei_cloud_maas_api_key = 62;
+  optional string baseten_api_key = 63;
+  optional string ollama_api_key = 64;
+  optional string zai_api_key = 65;
+  optional string zai_api_line = 66;
+  optional string lm_studio_max_tokens = 67;
+  optional string vercel_ai_gateway_api_key = 68;

  // Plan mode configurations
  optional ApiProvider plan_mode_api_provider = 100;
  optional string plan_mode_api_model_id = 101;
-  optional int64 plan_mode_thinking_budget_tokens = 102;
+  optional int32 plan_mode_thinking_budget_tokens = 102;
  optional string plan_mode_reasoning_effort = 103;
  optional LanguageModelChatSelector plan_mode_vs_code_lm_model_selector = 104;
  optional bool plan_mode_aws_bedrock_custom_selected = 105;
@@ -305,7 +293,7 @@ message ModelsApiConfiguration {
  // Act mode configurations
  optional ApiProvider act_mode_api_provider = 200;
  optional string act_mode_api_model_id = 201;
-  optional int64 act_mode_thinking_budget_tokens = 202;
+  optional int32 act_mode_thinking_budget_tokens = 202;
  optional string act_mode_reasoning_effort = 203;
  optional LanguageModelChatSelector act_mode_vs_code_lm_model_selector = 204;
  optional bool act_mode_aws_bedrock_custom_selected = 205;
@@ -193,9 +193,6 @@ message ApiConfiguration {
  optional string zai_api_line = 60;
  optional string lm_studio_max_tokens = 61;
  optional string vercel_ai_gateway_api_key = 62;
-  optional string qwen_code_oauth_path = 63;
-  optional string dify_api_key = 64;
-  optional string dify_base_url = 65;
  
  // Plan mode configurations
  optional string plan_mode_api_provider = 100;
@@ -249,6 +249,9 @@ service UiService {
  // Subscribe to partial message updates (streaming Cline messages as they're built)
  rpc subscribeToPartialMessage(EmptyRequest) returns (stream ClineMessage);
  
+  // Subscribe to theme change events
+  rpc subscribeToTheme(EmptyRequest) returns (stream String);
+  
  // Initialize webview when it launches
  rpc initializeWebview(EmptyRequest) returns (Empty);
  
@@ -26,9 +26,6 @@ service WorkspaceService {

  // Opens the IDE file explorer panel and selects a file or directory.
  rpc openInFileExplorerPanel(OpenInFileExplorerPanelRequest) returns (OpenInFileExplorerPanelResponse); 
-
-  // Opens and focuses the Cline sidebar panel in the host IDE.
-  rpc openClineSidebarPanel(OpenClineSidebarPanelRequest) returns (OpenClineSidebarPanelResponse);
 }

 message GetWorkspacePathsRequest {
@@ -89,7 +86,3 @@ message OpenInFileExplorerPanelRequest {
  string path = 1;
 }
 message OpenInFileExplorerPanelResponse {}
-
-// Request/response for opening the Cline sidebar
-message OpenClineSidebarPanelRequest {}
-message OpenClineSidebarPanelResponse {}
@@ -1,288 +0,0 @@
-import { Anthropic } from "@anthropic-ai/sdk"
-import { ApiHandlerOptions, ModelInfo } from "@shared/api"
-import { ApiHandler } from "../../core/api/index"
-import { ApiStream } from "../../core/api/transform/stream"
-
-export class DifyHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private baseUrl: string
-	private apiKey: string
-	private conversationId: string | null = null
-
-	constructor(options: ApiHandlerOptions) {
-		this.options = options
-		this.apiKey = options.difyApiKey || ""
-		this.baseUrl = options.difyBaseUrl || ""
-
-		console.log("[DIFY DEBUG] Constructor called with:", {
-			hasApiKey: !!this.apiKey,
-			baseUrl: this.baseUrl,
-		})
-
-		if (!this.apiKey) {
-			throw new Error("Dify API key is required")
-		}
-		if (!this.baseUrl) {
-			throw new Error("Dify base URL is required")
-		}
-	}
-
-	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
-		console.log("[DIFY DEBUG] createMessage called with:", {
-			systemPromptLength: systemPrompt?.length || 0,
-			messagesCount: messages?.length || 0,
-		})
-
-		// Convert messages to Dify format
-		const query = this.convertMessagesToQuery(systemPrompt, messages)
-		const requestBody = {
-			inputs: {},
-			query: query,
-			response_mode: "streaming",
-			conversation_id: this.conversationId || "",
-			user: "cline-user", // A unique user identifier
-			files: [],
-		}
-
-		const fullUrl = `${this.baseUrl}/chat-messages`
-		console.log("[DIFY DEBUG] Making request to:", fullUrl)
-		console.log("[DIFY DEBUG] Request body:", JSON.stringify(requestBody, null, 2))
-		console.log("[DIFY DEBUG] Current process environment variables (for proxy debugging):", process.env)
-
-		let response: Response
-		try {
-			response = await fetch(fullUrl, {
-				method: "POST",
-				headers: {
-					Authorization: `Bearer ${this.apiKey}`,
-					"Content-Type": "application/json",
-				},
-				body: JSON.stringify(requestBody),
-			})
-		} catch (error: any) {
-			console.error("[DIFY DEBUG] Network error during fetch:", error)
-			// Log more detailed error information if available (e.g., from undici)
-			const cause = error.cause ? ` | Cause: ${error.cause}` : ""
-			throw new Error(`Dify API network error: ${error.message}${cause}`)
-		}
-
-		console.log("[DIFY DEBUG] Response status:", response.status)
-		const headersObj: Record<string, string> = {}
-		response.headers.forEach((value, key) => {
-			headersObj[key] = value
-		})
-		console.log("[DIFY DEBUG] Response headers:", headersObj)
-
-		if (!response.ok) {
-			const errorText = await response.text()
-			console.error("[DIFY DEBUG] Error response:", errorText)
-			throw new Error(`Dify API error: ${response.status} ${response.statusText} - ${errorText}`)
-		}
-
-		if (!response.body) {
-			throw new Error("No response body from Dify API")
-		}
-
-		const reader = response.body.getReader()
-		const decoder = new TextDecoder()
-		let buffer = ""
-		let fullText = ""
-
-		console.log("[DIFY DEBUG] Starting to read streaming response...")
-
-		try {
-			while (true) {
-				const { done, value } = await reader.read()
-				if (done) {
-					console.log("[DIFY DEBUG] Stream ended naturally")
-					break
-				}
-
-				const chunk = decoder.decode(value, { stream: true })
-				console.log("[DIFY DEBUG] Raw chunk received:", JSON.stringify(chunk))
-
-				buffer += chunk
-				const lines = buffer.split("\n")
-
-				// Keep the last incomplete line in the buffer
-				buffer = lines.pop() || ""
-
-				for (const line of lines) {
-					console.log("[DIFY DEBUG] Processing line:", JSON.stringify(line))
-
-					if (line.startsWith("data: ")) {
-						const data = line.slice(6).trim()
-						console.log("[DIFY DEBUG] Extracted data:", JSON.stringify(data))
-
-						if (data === "[DONE]") {
-							console.log("[DIFY DEBUG] Received [DONE] signal")
-							return // Explicitly return on [DONE]
-						}
-
-						if (data === "") {
-							console.log("[DIFY DEBUG] Empty data line, skipping")
-							continue
-						}
-
-						try {
-							const parsed = JSON.parse(data)
-							console.log("[DIFY DEBUG] Parsed JSON:", parsed)
-
-							// Capture conversation_id as soon as it's available
-							if (parsed.conversation_id && !this.conversationId) {
-								this.conversationId = parsed.conversation_id
-								console.log("[DIFY DEBUG] Captured conversation_id:", this.conversationId)
-							}
-
-							// Handle different Dify event types based on actual Dify API
-							if (parsed.event === "message") {
-								console.log("[DIFY DEBUG] Message event, answer:", parsed.answer)
-								// Dify sends the full text in each "answer" chunk, so we replace.
-								if (typeof parsed.answer === "string") {
-									fullText = parsed.answer
-									console.log("[DIFY DEBUG] Updated fullText length:", fullText.length)
-									yield {
-										type: "text",
-										text: fullText,
-									}
-								}
-							} else if (parsed.event === "message_replace") {
-								console.log("[DIFY DEBUG] Replace message event:", parsed)
-								if (parsed.answer) {
-									fullText = parsed.answer // Replace instead of append
-									console.log("[DIFY DEBUG] Replaced fullText length:", fullText.length)
-									yield {
-										type: "text",
-										text: fullText,
-									}
-								}
-							} else if (parsed.event === "message_end") {
-								console.log("[DIFY DEBUG] Message end event", parsed)
-								// Message completed. Yield final text if we have any.
-								if (fullText) {
-									yield {
-										type: "text",
-										text: fullText,
-									}
-								}
-								// Yield usage data if available
-								if (parsed.usage) {
-									yield {
-										type: "usage",
-										inputTokens: parsed.usage.prompt_tokens || 0,
-										outputTokens: parsed.usage.completion_tokens || parsed.usage.total_tokens || 0,
-										totalCost: parsed.usage.total_price || 0,
-									}
-								}
-								return // End of stream
-							} else if (parsed.event === "error") {
-								console.error("[DIFY DEBUG] Error event:", parsed)
-								throw new Error(`Dify API error: ${parsed.message || "Unknown error"}`)
-							} else if (parsed.event === "workflow_started" || parsed.event === "workflow_finished") {
-								console.log("[DIFY DEBUG] Workflow event:", parsed.event)
-								// These are informational events, continue processing
-							} else if (parsed.event === "node_started" || parsed.event === "node_finished") {
-								console.log("[DIFY DEBUG] Node event:", parsed.event, parsed.data)
-								// These are informational events, continue processing
-							} else if (parsed.event === "ping") {
-								console.log("[DIFY DEBUG] Ping event received, keeping connection alive.")
-								// Ping event, do nothing
-							} else {
-								console.log("[DIFY DEBUG] Unknown event type:", parsed.event, "Full object:", parsed)
-								// Try to extract text from other possible fields
-								if (parsed.text) {
-									fullText += parsed.text
-									yield {
-										type: "text",
-										text: fullText,
-									}
-								} else if (parsed.content) {
-									fullText += parsed.content
-									yield {
-										type: "text",
-										text: fullText,
-									}
-								}
-							}
-						} catch (e) {
-							console.warn("[DIFY DEBUG] Failed to parse JSON:", data, "Error:", e)
-						}
-					} else if (line.trim() !== "") {
-						console.log(
-							"[DIFY DEBUG] Non-data line (not starting with 'data:'), trying to parse as direct JSON:",
-							JSON.stringify(line),
-						)
-						// Try to parse as direct JSON (fallback for non-SSE responses, though Dify uses SSE)
-						try {
-							const parsed = JSON.parse(line.trim())
-							console.log("[DIFY DEBUG] Parsed direct JSON:", parsed)
-
-							// Handle the same event types as above
-							if (parsed.event === "message" && parsed.answer) {
-								fullText += parsed.answer
-								yield {
-									type: "text",
-									text: fullText,
-								}
-							} else if (parsed.event === "message_end") {
-								if (fullText) {
-									yield {
-										type: "text",
-										text: fullText,
-									}
-								}
-								return
-							} else if (parsed.event === "error") {
-								console.error("[DIFY DEBUG] Direct JSON Error event:", parsed)
-								throw new Error(`Dify API error: ${parsed.message || "Unknown error"}`)
-							}
-						} catch (e) {
-							// Not JSON, continue
-							console.log("[DIFY DEBUG] Line is not direct JSON, continuing")
-						}
-					}
-				}
-			}
-		} finally {
-			reader.releaseLock()
-			console.log("[DIFY DEBUG] Stream reader released")
-		}
-	}
-
-	private convertMessagesToQuery(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): string {
-		// Dify's context is managed by `conversation_id`. The `query` should be the last user message.
-		// The system prompt is typically configured in the Dify App itself.
-		const lastUserMessage = messages.filter((m) => m.role === "user").pop()
-
-		if (!lastUserMessage) {
-			return "" // Should not happen in normal flow
-		}
-
-		const userQuery = Array.isArray(lastUserMessage.content)
-			? lastUserMessage.content.map((c) => ("text" in c ? c.text : "")).join("\n")
-			: (lastUserMessage.content as string)
-
-		// Only prepend the system prompt if it's the very first message of a new conversation.
-		if (!this.conversationId && systemPrompt) {
-			console.log("[DIFY DEBUG] Prepending system prompt for new conversation.")
-			return `${systemPrompt}\n\n---\n\n${userQuery}`
-		}
-
-		return userQuery
-	}
-
-	getModel(): { id: string; info: ModelInfo } {
-		return {
-			id: "dify-workflow",
-			info: {
-				maxTokens: 8192,
-				contextWindow: 128000,
-				supportsImages: true,
-				supportsPromptCache: false,
-				inputPrice: 0,
-				outputPrice: 0,
-				description: "Dify workflow - model selection is configured in your Dify application",
-			},
-		}
-	}
-}
@@ -1,22 +1,19 @@
 import * as vscode from "vscode"
 import {
 	migrateCustomInstructionsToGlobalRules,
-	migrateTaskHistoryToFile,
 	migrateWelcomeViewCompleted,
 	migrateWorkspaceToGlobalStorage,
 } from "./core/storage/state-migrations"
 import { WebviewProvider } from "./core/webview"
 import { Logger } from "./services/logging/Logger"
+import { PostHogClientProvider } from "./services/posthog/PostHogClientProvider"
+import { EmptyRequest } from "./shared/proto/cline/common"
 import { WebviewProviderType } from "./shared/webview/types"
 import "./utils/path" // necessary to have access to String.prototype.toPosix

 import { HostProvider } from "@/hosts/host-provider"
 import { FileContextTracker } from "./core/context/context-tracking/FileContextTracker"
-import { errorService } from "./services/error"
-import { featureFlagsService } from "./services/feature-flags"
-import { initializeDistinctId } from "./services/logging/distinctId"
-import { PostHogClientProvider } from "./services/posthog/PostHogClientProvider"
-import { telemetryService } from "./services/telemetry"
+import { telemetryService } from "./services/posthog/PostHogClientProvider"
 import { ShowMessageType } from "./shared/proto/host/window"
 import { getLatestAnnouncementId } from "./utils/announcements"
 /**
@@ -26,11 +23,18 @@ import { getLatestAnnouncementId } from "./utils/announcements"
 * @returns The webview provider
 */
 export async function initialize(context: vscode.ExtensionContext): Promise<WebviewProvider> {
-	// Set the distinct ID for logging and telemetry
-	await initializeDistinctId(context)
-
 	// Initialize PostHog client provider
-	PostHogClientProvider.getInstance()
+	let distinctId = context.globalState.get<string>("cline.distinctId")
+	if (!distinctId) {
+		try {
+			const response = await HostProvider.env.getMachineId(EmptyRequest.create({}))
+			distinctId = response.value
+		} catch (e) {
+			Logger.warn(`Failed to get machine ID: ${e instanceof Error ? e.message : String(e)}`)
+			// PostHogProvider will fall back to uuid
+		}
+	}
+	PostHogClientProvider.getInstance(distinctId)

 	// Migrate custom instructions to global Cline rules (one-time cleanup)
 	await migrateCustomInstructionsToGlobalRules(context)
@@ -41,9 +45,6 @@ export async function initialize(context: vscode.ExtensionContext): Promise<Webv
 	// Migrate workspace storage values back to global storage (reverting previous migration)
 	await migrateWorkspaceToGlobalStorage(context)

-	// Ensure taskHistory.json exists and migrate legacy state (runs once)
-	await migrateTaskHistoryToFile(context)
-
 	// Clean up orphaned file context warnings (startup cleanup)
 	await FileContextTracker.cleanupOrphanedWarnings(context)

@@ -74,7 +75,7 @@ async function showVersionUpdateAnnouncement(context: vscode.ExtensionContext) {
 				const message = previousVersion
 					? `Cline has been updated to v${currentVersion}`
 					: `Welcome to Cline v${currentVersion}`
-				await HostProvider.workspace.openClineSidebarPanel({})
+				await vscode.commands.executeCommand("claude-dev.SidebarProvider.focus")
 				await new Promise((resolve) => setTimeout(resolve, 200))
 				HostProvider.window.showMessage({
 					type: ShowMessageType.INFORMATION,
@@ -95,9 +96,7 @@ async function showVersionUpdateAnnouncement(context: vscode.ExtensionContext) {
 */
 export async function tearDown(): Promise<void> {
 	PostHogClientProvider.getInstance().dispose()
-	telemetryService.dispose()
-	errorService.dispose()
-	featureFlagsService.dispose()
+
 	// Dispose all webview instances
 	await WebviewProvider.disposeAllInstances()
 }
@@ -9,7 +9,6 @@ import { CerebrasHandler } from "./providers/cerebras"
 import { ClaudeCodeHandler } from "./providers/claude-code"
 import { ClineHandler } from "./providers/cline"
 import { DeepSeekHandler } from "./providers/deepseek"
-import { DifyHandler } from "./providers/dify"
 import { DoubaoHandler } from "./providers/doubao"
 import { FireworksHandler } from "./providers/fireworks"
 import { GeminiHandler } from "./providers/gemini"
@@ -26,7 +25,6 @@ import { OpenAiHandler } from "./providers/openai"
 import { OpenAiNativeHandler } from "./providers/openai-native"
 import { OpenRouterHandler } from "./providers/openrouter"
 import { QwenHandler } from "./providers/qwen"
-import { QwenCodeHandler } from "./providers/qwen-code"
 import { RequestyHandler } from "./providers/requesty"
 import { SambanovaHandler } from "./providers/sambanova"
 import { SapAiCoreHandler } from "./providers/sapaicore"
@@ -38,10 +36,6 @@ import { XAIHandler } from "./providers/xai"
 import { ZAiHandler } from "./providers/zai"
 import { ApiStream, ApiStreamUsageChunk } from "./transform/stream"

-export type CommonApiHandlerOptions = {
-	onRetryAttempt?: ApiConfiguration["onRetryAttempt"]
-}
-
 export interface ApiHandler {
 	createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream
 	getModel(): ApiHandlerModel
@@ -54,9 +48,9 @@ export interface ApiHandlerModel {
 }

 export interface ApiProviderInfo {
+	modelId: string
 	providerId: string
-	model: ApiHandlerModel
-	customPrompt?: string // "compact"
+	customPrompt?: string
 }

 export interface SingleCompletionHandler {
@@ -71,7 +65,6 @@ function createHandlerForProvider(
 	switch (apiProvider) {
 		case "anthropic":
 			return new AnthropicHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				apiKey: options.apiKey,
 				anthropicBaseUrl: options.anthropicBaseUrl,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
@@ -80,7 +73,6 @@ function createHandlerForProvider(
 			})
 		case "openrouter":
 			return new OpenRouterHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				openRouterApiKey: options.openRouterApiKey,
 				openRouterModelId: mode === "plan" ? options.planModeOpenRouterModelId : options.actModeOpenRouterModelId,
 				openRouterModelInfo: mode === "plan" ? options.planModeOpenRouterModelInfo : options.actModeOpenRouterModelInfo,
@@ -91,7 +83,6 @@ function createHandlerForProvider(
 			})
 		case "bedrock":
 			return new AwsBedrockHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 				awsAccessKey: options.awsAccessKey,
 				awsSecretKey: options.awsSecretKey,
@@ -113,7 +104,6 @@ function createHandlerForProvider(
 			})
 		case "vertex":
 			return new VertexHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				vertexProjectId: options.vertexProjectId,
 				vertexRegion: options.vertexRegion,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
@@ -125,7 +115,6 @@ function createHandlerForProvider(
 			})
 		case "openai":
 			return new OpenAiHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				openAiApiKey: options.openAiApiKey,
 				openAiBaseUrl: options.openAiBaseUrl,
 				azureApiVersion: options.azureApiVersion,
@@ -136,7 +125,6 @@ function createHandlerForProvider(
 			})
 		case "ollama":
 			return new OllamaHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				ollamaBaseUrl: options.ollamaBaseUrl,
 				ollamaApiKey: options.ollamaApiKey,
 				ollamaModelId: mode === "plan" ? options.planModeOllamaModelId : options.actModeOllamaModelId,
@@ -145,14 +133,12 @@ function createHandlerForProvider(
 			})
 		case "lmstudio":
 			return new LmStudioHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				lmStudioBaseUrl: options.lmStudioBaseUrl,
 				lmStudioModelId: mode === "plan" ? options.planModeLmStudioModelId : options.actModeLmStudioModelId,
 				lmStudioMaxTokens: options.lmStudioMaxTokens,
 			})
 		case "gemini":
 			return new GeminiHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				vertexProjectId: options.vertexProjectId,
 				vertexRegion: options.vertexRegion,
 				geminiApiKey: options.geminiApiKey,
@@ -164,20 +150,17 @@ function createHandlerForProvider(
 			})
 		case "openai-native":
 			return new OpenAiNativeHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				openAiNativeApiKey: options.openAiNativeApiKey,
 				reasoningEffort: mode === "plan" ? options.planModeReasoningEffort : options.actModeReasoningEffort,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "deepseek":
 			return new DeepSeekHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				deepSeekApiKey: options.deepSeekApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "requesty":
 			return new RequestyHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				requestyBaseUrl: options.requestyBaseUrl,
 				requestyApiKey: options.requestyApiKey,
 				reasoningEffort: mode === "plan" ? options.planModeReasoningEffort : options.actModeReasoningEffort,
@@ -188,19 +171,16 @@ function createHandlerForProvider(
 			})
 		case "fireworks":
 			return new FireworksHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				fireworksApiKey: options.fireworksApiKey,
 				fireworksModelId: mode === "plan" ? options.planModeFireworksModelId : options.actModeFireworksModelId,
 			})
 		case "together":
 			return new TogetherHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				togetherApiKey: options.togetherApiKey,
 				togetherModelId: mode === "plan" ? options.planModeTogetherModelId : options.actModeTogetherModelId,
 			})
 		case "qwen":
 			return new QwenHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				qwenApiKey: options.qwenApiKey,
 				qwenApiLine:
 					options.qwenApiLine === QwenApiRegions.INTERNATIONAL ? QwenApiRegions.INTERNATIONAL : QwenApiRegions.CHINA,
@@ -208,33 +188,23 @@ function createHandlerForProvider(
 				thinkingBudgetTokens:
 					mode === "plan" ? options.planModeThinkingBudgetTokens : options.actModeThinkingBudgetTokens,
 			})
-		case "qwen-code":
-			return new QwenCodeHandler({
-				onRetryAttempt: options.onRetryAttempt,
-				qwenCodeOauthPath: options.qwenCodeOauthPath,
-				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
-			})
 		case "doubao":
 			return new DoubaoHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				doubaoApiKey: options.doubaoApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "mistral":
 			return new MistralHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				mistralApiKey: options.mistralApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "vscode-lm":
 			return new VsCodeLmHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				vsCodeLmModelSelector:
 					mode === "plan" ? options.planModeVsCodeLmModelSelector : options.actModeVsCodeLmModelSelector,
 			})
 		case "cline":
 			return new ClineHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				clineAccountId: options.clineAccountId,
 				ulid: options.ulid,
 				reasoningEffort: mode === "plan" ? options.planModeReasoningEffort : options.actModeReasoningEffort,
@@ -246,7 +216,6 @@ function createHandlerForProvider(
 			})
 		case "litellm":
 			return new LiteLlmHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				liteLlmApiKey: options.liteLlmApiKey,
 				liteLlmBaseUrl: options.liteLlmBaseUrl,
 				liteLlmModelId: mode === "plan" ? options.planModeLiteLlmModelId : options.actModeLiteLlmModelId,
@@ -258,14 +227,12 @@ function createHandlerForProvider(
 			})
 		case "moonshot":
 			return new MoonshotHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				moonshotApiKey: options.moonshotApiKey,
 				moonshotApiLine: options.moonshotApiLine,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "huggingface":
 			return new HuggingFaceHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				huggingFaceApiKey: options.huggingFaceApiKey,
 				huggingFaceModelId: mode === "plan" ? options.planModeHuggingFaceModelId : options.actModeHuggingFaceModelId,
 				huggingFaceModelInfo:
@@ -273,39 +240,33 @@ function createHandlerForProvider(
 			})
 		case "nebius":
 			return new NebiusHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				nebiusApiKey: options.nebiusApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "asksage":
 			return new AskSageHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				asksageApiKey: options.asksageApiKey,
 				asksageApiUrl: options.asksageApiUrl,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "xai":
 			return new XAIHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				xaiApiKey: options.xaiApiKey,
 				reasoningEffort: mode === "plan" ? options.planModeReasoningEffort : options.actModeReasoningEffort,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "sambanova":
 			return new SambanovaHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				sambanovaApiKey: options.sambanovaApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "cerebras":
 			return new CerebrasHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				cerebrasApiKey: options.cerebrasApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "groq":
 			return new GroqHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				groqApiKey: options.groqApiKey,
 				groqModelId: mode === "plan" ? options.planModeGroqModelId : options.actModeGroqModelId,
 				groqModelInfo: mode === "plan" ? options.planModeGroqModelInfo : options.actModeGroqModelInfo,
@@ -313,7 +274,6 @@ function createHandlerForProvider(
 			})
 		case "baseten":
 			return new BasetenHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				basetenApiKey: options.basetenApiKey,
 				basetenModelId: mode === "plan" ? options.planModeBasetenModelId : options.actModeBasetenModelId,
 				basetenModelInfo: mode === "plan" ? options.planModeBasetenModelInfo : options.actModeBasetenModelInfo,
@@ -321,7 +281,6 @@ function createHandlerForProvider(
 			})
 		case "sapaicore":
 			return new SapAiCoreHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				sapAiCoreClientId: options.sapAiCoreClientId,
 				sapAiCoreClientSecret: options.sapAiCoreClientSecret,
 				sapAiCoreTokenUrl: options.sapAiCoreTokenUrl,
@@ -331,11 +290,9 @@ function createHandlerForProvider(
 				thinkingBudgetTokens:
 					mode === "plan" ? options.planModeThinkingBudgetTokens : options.actModeThinkingBudgetTokens,
 				reasoningEffort: mode === "plan" ? options.planModeReasoningEffort : options.actModeReasoningEffort,
-				sapAiCoreUseOrchestrationMode: options.sapAiCoreUseOrchestrationMode,
 			})
 		case "claude-code":
 			return new ClaudeCodeHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				claudeCodePath: options.claudeCodePath,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 				thinkingBudgetTokens:
@@ -343,25 +300,14 @@ function createHandlerForProvider(
 			})
 		case "huawei-cloud-maas":
 			return new HuaweiCloudMaaSHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				huaweiCloudMaasApiKey: options.huaweiCloudMaasApiKey,
 				huaweiCloudMaasModelId:
 					mode === "plan" ? options.planModeHuaweiCloudMaasModelId : options.actModeHuaweiCloudMaasModelId,
 				huaweiCloudMaasModelInfo:
 					mode === "plan" ? options.planModeHuaweiCloudMaasModelInfo : options.actModeHuaweiCloudMaasModelInfo,
 			})
-		case "dify": // Add Dify.ai handler
-			console.log("[DIFY DEBUG] Instantiating DifyHandler with options:", {
-				difyApiKeyPresent: !!options.difyApiKey,
-				difyBaseUrl: options.difyBaseUrl,
-			})
-			return new DifyHandler({
-				difyApiKey: options.difyApiKey,
-				difyBaseUrl: options.difyBaseUrl,
-			})
 		case "vercel-ai-gateway":
 			return new VercelAIGatewayHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				vercelAiGatewayApiKey: options.vercelAiGatewayApiKey,
 				vercelAiGatewayModelId:
 					mode === "plan" ? options.planModeVercelAiGatewayModelId : options.actModeVercelAiGatewayModelId,
@@ -370,14 +316,12 @@ function createHandlerForProvider(
 			})
 		case "zai":
 			return new ZAiHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				zaiApiLine: options.zaiApiLine,
 				zaiApiKey: options.zaiApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		default:
 			return new AnthropicHandler({
-				onRetryAttempt: options.onRetryAttempt,
 				apiKey: options.apiKey,
 				anthropicBaseUrl: options.anthropicBaseUrl,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
@@ -1,248 +0,0 @@
-import { Anthropic } from "@anthropic-ai/sdk"
-import { afterEach, beforeEach, describe, it } from "mocha"
-import sinon from "sinon"
-import "should"
-import { ClaudeCodeHandler } from "@core/api/providers/claude-code"
-
-describe("ClaudeCodeHandler", () => {
-	let handler: ClaudeCodeHandler
-	let sandbox: sinon.SinonSandbox
-
-	beforeEach(() => {
-		sandbox = sinon.createSandbox()
-		handler = new ClaudeCodeHandler({
-			claudeCodePath: "/mock/path",
-			apiModelId: "claude-3-5-sonnet-20241022",
-		})
-	})
-
-	afterEach(() => {
-		sandbox.restore()
-	})
-
-	describe("token counting", () => {
-		it("should correctly handle token usage from assistant messages", async () => {
-			// The 'input_tokens' field represents the TOTAL number of input tokens used.
-			// See https://docs.anthropic.com/en/api/messages#usage-object
-
-			// Mock the runClaudeCode function
-			const runClaudeCodeModule = await import("@/integrations/claude-code/run")
-			const runClaudeCodeStub = sandbox.stub(runClaudeCodeModule, "runClaudeCode")
-
-			// Create a proper async generator mock for the Claude Code response
-			async function* mockGenerator() {
-				// First yield the system init
-				yield {
-					type: "system",
-					subtype: "init",
-					apiKeySource: "api",
-				}
-
-				// Yield assistant message with usage data
-				// Example: If base input is 70 tokens, cache read is 20, and cache creation is 10,
-				// then input_tokens from Anthropic API will be 100 (70 + 20 + 10)
-				yield {
-					type: "assistant",
-					message: {
-						content: [
-							{
-								type: "text",
-								text: "Test response",
-							},
-						],
-						usage: {
-							input_tokens: 100, // Total including cache (per Anthropic docs)
-							output_tokens: 50,
-							cache_read_input_tokens: 20, // Already included in input_tokens
-							cache_creation_input_tokens: 10, // Already included in input_tokens
-						},
-						stop_reason: "end_turn",
-					},
-				}
-
-				// Yield result with cost
-				yield {
-					type: "result",
-					result: {},
-					total_cost_usd: 0.005,
-				}
-			}
-
-			runClaudeCodeStub.returns(mockGenerator() as any)
-
-			const systemPrompt = "You are a helpful assistant."
-			const messages: Anthropic.Messages.MessageParam[] = [{ role: "user", content: "Hello" }]
-
-			const usageData: any[] = []
-
-			// Collect the results
-			for await (const chunk of handler.createMessage(systemPrompt, messages)) {
-				if (chunk.type === "usage") {
-					usageData.push({
-						inputTokens: chunk.inputTokens,
-						outputTokens: chunk.outputTokens,
-						cacheReadTokens: chunk.cacheReadTokens,
-						cacheWriteTokens: chunk.cacheWriteTokens,
-						totalCost: chunk.totalCost,
-					})
-				}
-			}
-
-			// Verify token counting follows Anthropic API specification
-			usageData.should.have.length(1)
-			usageData[0].should.deepEqual({
-				inputTokens: 100, // Total including cache tokens (per Anthropic API docs)
-				outputTokens: 50,
-				cacheReadTokens: 20, // Tracked separately for reporting
-				cacheWriteTokens: 10, // Tracked separately for reporting
-				totalCost: 0.005,
-			})
-
-			// CRITICAL ASSERTION: Verify that input_tokens is NOT inflated by re-adding cache tokens
-			// The bug would have caused inputTokens to be incorrectly calculated as 130 (100 + 20 + 10)
-			// The fix ensures it remains 100, as per Anthropic's specification
-			usageData[0].inputTokens.should.equal(100) // Correct: matches API response
-			usageData[0].inputTokens.should.not.equal(130) // Would be wrong: double-counting cache tokens
-		})
-
-		it("should handle missing usage fields with nullish coalescing", async () => {
-			// Mock the runClaudeCode function
-			const runClaudeCodeModule = await import("@/integrations/claude-code/run")
-			const runClaudeCodeStub = sandbox.stub(runClaudeCodeModule, "runClaudeCode")
-
-			// Create a proper async generator mock with missing/undefined usage fields
-			async function* mockGenerator() {
-				yield {
-					type: "assistant",
-					message: {
-						content: [
-							{
-								type: "text",
-								text: "Test response",
-							},
-						],
-						usage: {
-							input_tokens: 100,
-							output_tokens: 50,
-							// cache fields are undefined/missing
-						},
-						stop_reason: "end_turn",
-					},
-				}
-
-				yield {
-					type: "result",
-					result: {},
-					total_cost_usd: 0.005,
-				}
-			}
-
-			runClaudeCodeStub.returns(mockGenerator() as any)
-
-			const systemPrompt = "You are a helpful assistant."
-			const messages: Anthropic.Messages.MessageParam[] = [{ role: "user", content: "Hello" }]
-
-			const usageData: any[] = []
-
-			// Collect the results
-			for await (const chunk of handler.createMessage(systemPrompt, messages)) {
-				if (chunk.type === "usage") {
-					usageData.push({
-						inputTokens: chunk.inputTokens,
-						outputTokens: chunk.outputTokens,
-						cacheReadTokens: chunk.cacheReadTokens,
-						cacheWriteTokens: chunk.cacheWriteTokens,
-					})
-				}
-			}
-
-			// Verify that undefined cache tokens default to 0
-			usageData.should.have.length(1)
-			usageData[0].should.deepEqual({
-				inputTokens: 100,
-				outputTokens: 50,
-				cacheReadTokens: 0, // Should default to 0
-				cacheWriteTokens: 0, // Should default to 0
-			})
-		})
-
-		it("should handle completely missing usage object", async () => {
-			// Mock the runClaudeCode function
-			const runClaudeCodeModule = await import("@/integrations/claude-code/run")
-			const runClaudeCodeStub = sandbox.stub(runClaudeCodeModule, "runClaudeCode")
-
-			// Create a proper async generator mock with missing usage object
-			async function* mockGenerator() {
-				yield {
-					type: "assistant",
-					message: {
-						content: [
-							{
-								type: "text",
-								text: "Test response",
-							},
-						],
-						// usage is undefined
-						usage: undefined,
-						stop_reason: "end_turn",
-					},
-				}
-
-				// Need to yield a result chunk to trigger usage data emission
-				yield {
-					type: "result",
-					result: {},
-					total_cost_usd: 0,
-				}
-			}
-
-			runClaudeCodeStub.returns(mockGenerator() as any)
-
-			const systemPrompt = "You are a helpful assistant."
-			const messages: Anthropic.Messages.MessageParam[] = [{ role: "user", content: "Hello" }]
-
-			const usageData: any[] = []
-
-			// Collect the results
-			for await (const chunk of handler.createMessage(systemPrompt, messages)) {
-				if (chunk.type === "usage") {
-					usageData.push({
-						inputTokens: chunk.inputTokens,
-						outputTokens: chunk.outputTokens,
-						cacheReadTokens: chunk.cacheReadTokens,
-						cacheWriteTokens: chunk.cacheWriteTokens,
-					})
-				}
-			}
-
-			// All token counts should default to 0 when usage is undefined
-			usageData.should.have.length(1)
-			usageData[0].should.deepEqual({
-				inputTokens: 0,
-				outputTokens: 0,
-				cacheReadTokens: 0,
-				cacheWriteTokens: 0,
-			})
-		})
-	})
-
-	describe("getModel", () => {
-		it("should return the correct model when specified", () => {
-			const handler = new ClaudeCodeHandler({
-				apiModelId: "claude-3-5-sonnet-20241022",
-			})
-
-			const model = handler.getModel()
-			model.id.should.equal("claude-3-5-sonnet-20241022")
-		})
-
-		it("should return default model when not specified", () => {
-			const handler = new ClaudeCodeHandler({})
-
-			const model = handler.getModel()
-			// The default model should be set
-			model.id.should.be.type("string")
-			model.info.should.be.type("object")
-		})
-	})
-})
@@ -1,243 +0,0 @@
-import Anthropic from "@anthropic-ai/sdk"
-import { LiteLlmHandler, type LiteLlmModelInfoResponse } from "@core/api/providers/litellm"
-import { convertToOpenAiMessages } from "@core/api/transform/openai-format"
-import { expect } from "chai"
-import sinon from "sinon"
-
-const fakeClient = {
-	chat: {
-		completions: {
-			create: sinon.stub(),
-		},
-	},
-	baseURL: "fake",
-}
-
-describe("LiteLlmHandler", () => {
-	const originalFetch = global.fetch
-	const mockFetch = sinon.stub()
-
-	const mockModelFetch = (modelInfo: LiteLlmModelInfoResponse["data"][number]) => {
-		mockFetch.resolves({
-			ok: true,
-			json: () =>
-				Promise.resolve({
-					data: [modelInfo],
-				}),
-		})
-	}
-
-	let handler: LiteLlmHandler
-
-	const mockHandlerChat = () => {
-		sinon.stub(handler, "ensureClient" as any).returns(fakeClient)
-	}
-
-	const initializeHandler = (model: string) => {
-		handler = new LiteLlmHandler({
-			liteLlmApiKey: "test-api-key",
-			liteLlmBaseUrl: "http://localhost:4000",
-			liteLlmUsePromptCache: true,
-			liteLlmModelId: model,
-		})
-
-		mockHandlerChat()
-	}
-
-	beforeEach(() => {
-		global.fetch = mockFetch
-
-		// Configure the stub to return a stream that closes immediately with usage data
-		fakeClient.chat.completions.create.resolves(
-			createAsyncIterable([
-				{
-					choices: [{ delta: { content: "test response" } }],
-				},
-				{
-					choices: [{}],
-					usage: {
-						prompt_tokens: 100,
-						completion_tokens: 50,
-						cache_creation_input_tokens: 20,
-						cache_read_input_tokens: 10,
-					},
-				},
-			]),
-		)
-	})
-
-	afterEach(() => {
-		sinon.reset()
-
-		global.fetch = originalFetch
-	})
-
-	const createAsyncIterable = (data: any[] = []) => {
-		return {
-			[Symbol.asyncIterator]: async function* () {
-				yield* data
-			},
-		}
-	}
-
-	describe("prompt cache", () => {
-		const setModelData = (model: string, supportsPromptCaching: boolean) => {
-			mockModelFetch({
-				model_name: model,
-				litellm_params: {
-					model,
-				},
-				model_info: {
-					supports_prompt_caching: supportsPromptCaching,
-					input_cost_per_token: 0.01,
-					output_cost_per_token: 0.02,
-				},
-			})
-		}
-
-		describe("when the model doesn't support prompt caching", () => {
-			const model = "openai/gpt-5"
-
-			beforeEach(() => {
-				initializeHandler(model)
-				setModelData(model, false)
-			})
-
-			it("sends the system prompt and messages with the openai format", async () => {
-				const systemPrompt = "Test System Prompt"
-				const messages: Anthropic.Messages.MessageParam[] = [
-					{
-						role: "user",
-						content: "first message",
-					},
-					{
-						role: "assistant",
-						content: "first response",
-					},
-					{
-						role: "user",
-						content: [
-							{
-								type: "text",
-								text: "test",
-							},
-							{
-								type: "text",
-								text: "second message",
-							},
-						],
-					},
-				]
-
-				for await (const _ of handler.createMessage(systemPrompt, messages)) {
-				}
-
-				sinon.assert.calledOnce(fakeClient.chat.completions.create)
-
-				const callArgs = fakeClient.chat.completions.create.getCall(0).args[0]
-
-				const systemPromptMessage = callArgs.messages.shift()
-				expect(systemPromptMessage).to.deep.equal({
-					role: "system",
-					content: systemPrompt,
-				})
-
-				expect(callArgs.messages).to.deep.equal(convertToOpenAiMessages(messages))
-			})
-		})
-
-		describe("when the model supports prompt caching", () => {
-			const model = "anthropic/claude-sonnet-4-20250514"
-
-			beforeEach(() => {
-				initializeHandler(model)
-
-				setModelData(model, true)
-			})
-
-			it("inserts the cache control in the system prompt and the last two user messages", async () => {
-				const systemPrompt = "Test System Prompt"
-				const messages: Anthropic.Messages.MessageParam[] = [
-					{
-						role: "user",
-						content: "first message",
-					},
-					{
-						role: "assistant",
-						content: "first response",
-					},
-					{
-						role: "user",
-						content: [
-							{
-								type: "text",
-								text: "test",
-							},
-							{
-								type: "text",
-								text: "second message",
-							},
-						],
-					},
-				]
-
-				for await (const _ of handler.createMessage(systemPrompt, messages)) {
-				}
-
-				sinon.assert.calledOnce(fakeClient.chat.completions.create)
-
-				const callArgs = fakeClient.chat.completions.create.getCall(0).args[0]
-
-				expect(callArgs.messages[0]).to.deep.equal({
-					role: "system",
-					content: [
-						{
-							text: systemPrompt,
-							type: "text",
-							cache_control: {
-								type: "ephemeral",
-							},
-						},
-					],
-				})
-
-				const sentMessages = callArgs.messages
-				expect(sentMessages.length).to.equal(4)
-
-				const firstUserMessage = sentMessages[1]
-
-				expect(firstUserMessage).to.deep.equal({
-					role: "user",
-					content: [
-						{
-							type: "text",
-							text: "first message",
-							cache_control: {
-								type: "ephemeral",
-							},
-						},
-					],
-				})
-
-				const lastUserMessage = sentMessages[3]
-				expect(lastUserMessage.content[0]).to.deep.equal({
-					type: "text",
-					text: "test",
-				})
-
-				const lastContentBlock = lastUserMessage.content[lastUserMessage.content.length - 1]
-				expect(lastContentBlock).to.deep.equal({
-					type: "text",
-					text: "second message",
-					cache_control: {
-						type: "ephemeral",
-					},
-				})
-
-				expect(callArgs.model).to.be.a("string")
-				expect(callArgs.stream).to.equal(true)
-				expect(callArgs.stream_options).to.deep.equal({ include_usage: true })
-			})
-		})
-	})
-})
@@ -1,11 +1,11 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { Stream as AnthropicStream } from "@anthropic-ai/sdk/streaming"
 import { AnthropicModelId, anthropicDefaultModelId, anthropicModels, CLAUDE_SONNET_4_1M_SUFFIX, ModelInfo } from "@shared/api"
-import { ApiHandler, CommonApiHandlerOptions } from "../index"
+import { ApiHandler } from "../index"
 import { withRetry } from "../retry"
 import { ApiStream } from "../transform/stream"

-interface AnthropicHandlerOptions extends CommonApiHandlerOptions {
+interface AnthropicHandlerOptions {
 	apiKey?: string
 	anthropicBaseUrl?: string
 	apiModelId?: string
@@ -1,10 +1,10 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { AskSageModelId, askSageDefaultModelId, askSageDefaultURL, askSageModels, ModelInfo } from "@shared/api"
-import { ApiHandler, CommonApiHandlerOptions } from ".."
+import { ApiHandler } from ".."
 import { withRetry } from "../retry"
 import { ApiStream } from "../transform/stream"

-interface AskSageHandlerOptions extends CommonApiHandlerOptions {
+interface AskSageHandlerOptions {
 	asksageApiKey?: string
 	asksageApiUrl?: string
 	apiModelId?: string
@@ -2,12 +2,12 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { BasetenModelId, basetenDefaultModelId, basetenModels, ModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "@utils/cost"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"

-interface BasetenHandlerOptions extends CommonApiHandlerOptions {
+interface BasetenHandlerOptions {
 	basetenApiKey?: string
 	basetenModelId?: string
 	basetenModelInfo?: ModelInfo
@@ -11,12 +11,12 @@ import {
 import { fromNodeProviderChain } from "@aws-sdk/credential-providers"
 import { BedrockModelId, bedrockDefaultModelId, bedrockModels, CLAUDE_SONNET_4_1M_SUFFIX, ModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "@utils/cost"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { convertToR1Format } from "../transform/r1-format"
 import { ApiStream } from "../transform/stream"

-interface AwsBedrockHandlerOptions extends CommonApiHandlerOptions {
+interface AwsBedrockHandlerOptions {
 	apiModelId?: string
 	awsAccessKey?: string
 	awsSecretKey?: string
@@ -1,11 +1,11 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import Cerebras from "@cerebras/cerebras_cloud_sdk"
 import { CerebrasModelId, cerebrasDefaultModelId, cerebrasModels, ModelInfo } from "@shared/api"
-import { ApiHandler, CommonApiHandlerOptions } from "../index"
+import { ApiHandler } from "../index"
 import { withRetry } from "../retry"
 import { ApiStream } from "../transform/stream"

-interface CerebrasHandlerOptions extends CommonApiHandlerOptions {
+interface CerebrasHandlerOptions {
 	cerebrasApiKey?: string
 	apiModelId?: string
 }
@@ -2,11 +2,11 @@ import type { Anthropic } from "@anthropic-ai/sdk"
 import { filterMessagesForClaudeCode } from "@/integrations/claude-code/message-filter"
 import { runClaudeCode } from "@/integrations/claude-code/run"
 import { ClaudeCodeModelId, claudeCodeDefaultModelId, claudeCodeModels } from "@/shared/api"
-import { type ApiHandler, CommonApiHandlerOptions } from ".."
+import { type ApiHandler } from ".."
 import { withRetry } from "../retry"
 import { type ApiStream, ApiStreamUsageChunk } from "../transform/stream"

-interface ClaudeCodeHandlerOptions extends CommonApiHandlerOptions {
+interface ClaudeCodeHandlerOptions {
 	claudeCodePath?: string
 	apiModelId?: string
 	thinkingBudgetTokens?: number
@@ -118,14 +118,10 @@ export class ClaudeCodeHandler implements ApiHandler {
 					}
 				}

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

 				continue
 			}
@@ -8,15 +8,14 @@ import { ClineAccountService } from "@/services/account/ClineAccountService"
 import { AuthService } from "@/services/auth/AuthService"
 import { CLINE_ACCOUNT_AUTH_ERROR_MESSAGE } from "@/shared/ClineAccount"
 import { version as extensionVersion } from "../../../../package.json"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { createOpenRouterStream } from "../transform/openrouter-stream"
 import { ApiStream, ApiStreamUsageChunk } from "../transform/stream"
 import { OpenRouterErrorResponse } from "./types"

-interface ClineHandlerOptions extends CommonApiHandlerOptions {
+interface ClineHandlerOptions {
 	ulid?: string
-	taskId?: string
 	reasoningEffort?: string
 	thinkingBudgetTokens?: number
 	openRouterProviderSorting?: string
@@ -138,10 +137,6 @@ export class ClineHandler implements ApiHandler {
 						totalCost = 0
 					}

-					if (this.getModel().id === "x-ai/grok-code-fast-1") {
-						totalCost = 0
-					}
-
 					yield {
 						type: "usage",
 						cacheWriteTokens: 0,
@@ -2,13 +2,13 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { DeepSeekModelId, deepSeekDefaultModelId, deepSeekModels, ModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "@utils/cost"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { convertToR1Format } from "../transform/r1-format"
 import { ApiStream } from "../transform/stream"

-interface DeepSeekHandlerOptions extends CommonApiHandlerOptions {
+interface DeepSeekHandlerOptions {
 	deepSeekApiKey?: string
 	apiModelId?: string
 }
@@ -1,655 +0,0 @@
-import { Anthropic } from "@anthropic-ai/sdk"
-import { ApiHandlerOptions, ModelInfo } from "../../../shared/api"
-import { ApiHandler } from "../index"
-import { ApiStream } from "../transform/stream"
-
-// Dify API Response Types
-export interface DifyFileResponse {
-	id: string
-	name: string
-	size: number
-	extension: string
-	mime_type: string
-	created_by: string
-	created_at: number
-}
-
-export interface DifyMessage {
-	id: string
-	conversation_id: string
-	inputs: Record<string, any>
-	query: string
-	message_files: Array<{
-		id: string
-		type: string
-		url: string
-		belongs_to: string
-	}>
-	answer: string
-	created_at: number
-	feedback?: {
-		rating: string
-	}
-	retriever_resources?: any[]
-}
-
-interface DifyHistoryResponse {
-	data: DifyMessage[]
-	has_more: boolean
-	limit: number
-}
-
-interface DifyConversation {
-	id: string
-	name: string
-	inputs: Record<string, any>
-	status: string
-	introduction: string
-	created_at: number
-	updated_at: number
-}
-
-interface DifyConversationsResponse {
-	data: DifyConversation[]
-	has_more: boolean
-	limit: number
-}
-
-interface DifyConversationResponse {
-	id: string
-	name: string
-	inputs: Record<string, any>
-	status: string
-	introduction: string
-	created_at: number
-	updated_at: number
-}
-
-export class DifyHandler implements ApiHandler {
-	private options: ApiHandlerOptions
-	private baseUrl: string
-	private apiKey: string
-	private conversationId: string | null = null
-	private currentTaskId: string | null = null
-	private abortController: AbortController | null = null
-
-	constructor(options: ApiHandlerOptions) {
-		this.options = options
-		this.apiKey = options.difyApiKey || ""
-		this.baseUrl = options.difyBaseUrl || ""
-
-		console.log("[DIFY DEBUG] Constructor called with:", {
-			hasApiKey: !!this.apiKey,
-			baseUrl: this.baseUrl,
-		})
-
-		if (!this.apiKey) {
-			throw new Error("Dify API key is required")
-		}
-		if (!this.baseUrl) {
-			throw new Error("Dify base URL is required")
-		}
-	}
-
-	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
-		console.log("[DIFY DEBUG] createMessage called with:", {
-			systemPromptLength: systemPrompt?.length || 0,
-			messagesCount: messages?.length || 0,
-		})
-
-		// Convert messages to Dify format
-		const query = this.convertMessagesToQuery(systemPrompt, messages)
-		const requestBody = {
-			inputs: {},
-			query: query,
-			response_mode: "streaming",
-			conversation_id: this.conversationId || "",
-			user: "cline-user", // A unique user identifier
-			files: [],
-		}
-
-		const fullUrl = `${this.baseUrl}/chat-messages`
-		console.log("[DIFY DEBUG] Making request to:", fullUrl)
-		console.log("[DIFY DEBUG] Request body:", JSON.stringify(requestBody, null, 2))
-
-		let response: Response
-		try {
-			response = await fetch(fullUrl, {
-				method: "POST",
-				headers: {
-					Authorization: `Bearer ${this.apiKey}`,
-					"Content-Type": "application/json",
-				},
-				body: JSON.stringify(requestBody),
-			})
-		} catch (error: any) {
-			console.error("[DIFY DEBUG] Network error during fetch:", error)
-			const cause = error.cause ? ` | Cause: ${error.cause}` : ""
-			throw new Error(`Dify API network error: ${error.message}${cause}`)
-		}
-
-		console.log("[DIFY DEBUG] Response status:", response.status)
-		const headersObj: Record<string, string> = {}
-		response.headers.forEach((value, key) => {
-			headersObj[key] = value
-		})
-		console.log("[DIFY DEBUG] Response headers:", headersObj)
-
-		if (!response.ok) {
-			const errorText = await response.text()
-			console.error("[DIFY DEBUG] Error response:", errorText)
-			throw new Error(`Dify API error: ${response.status} ${response.statusText} - ${errorText}`)
-		}
-
-		if (!response.body) {
-			throw new Error("No response body from Dify API")
-		}
-
-		const reader = response.body.getReader()
-		const decoder = new TextDecoder()
-		let buffer = ""
-		let fullText = ""
-		let hasYieldedContent = false
-		const processedEvents: string[] = []
-		let lastEventTime = Date.now()
-
-		console.log("[DIFY DEBUG] Starting to read streaming response...")
-
-		try {
-			while (true) {
-				const { done, value } = await reader.read()
-				if (done) {
-					console.log("[DIFY DEBUG] Stream ended naturally")
-					console.log(
-						"[DIFY DEBUG] Final state - hasYieldedContent:",
-						hasYieldedContent,
-						"fullText length:",
-						fullText.length,
-						"processedEvents:",
-						processedEvents,
-					)
-					break
-				}
-
-				const chunk = decoder.decode(value, { stream: true })
-				console.log("[DIFY DEBUG] Raw chunk received:", JSON.stringify(chunk))
-
-				buffer += chunk
-				const lines = buffer.split("\n")
-
-				// Keep the last incomplete line in the buffer
-				buffer = lines.pop() || ""
-
-				for (const line of lines) {
-					console.log("[DIFY DEBUG] Processing line:", JSON.stringify(line))
-
-					if (line.startsWith("data: ")) {
-						const data = line.slice(6).trim()
-						console.log("[DIFY DEBUG] Extracted data:", JSON.stringify(data))
-
-						if (data === "[DONE]") {
-							console.log("[DIFY DEBUG] Received [DONE] signal")
-							break
-						}
-
-						if (data === "") {
-							console.log("[DIFY DEBUG] Empty data line, skipping")
-							continue
-						}
-
-						try {
-							const parsed = JSON.parse(data)
-							console.log("[DIFY DEBUG] Parsed JSON:", parsed)
-							processedEvents.push(parsed.event || "unknown")
-							lastEventTime = Date.now()
-
-							// Capture conversation_id as soon as it's available
-							if (parsed.conversation_id && !this.conversationId) {
-								this.conversationId = parsed.conversation_id
-								console.log("[DIFY DEBUG] Captured conversation_id:", this.conversationId)
-							}
-
-							// Handle different Dify event types based on actual Dify API
-							if (parsed.event === "message") {
-								console.log("[DIFY DEBUG] Message event, answer:", parsed.answer)
-								// Dify sends the full text in each "answer" chunk, so we replace.
-								if (typeof parsed.answer === "string") {
-									fullText = parsed.answer
-									console.log("[DIFY DEBUG] Updated fullText length:", fullText.length)
-									yield {
-										type: "text",
-										text: fullText,
-									}
-									hasYieldedContent = true
-								}
-							} else if (parsed.event === "message_replace") {
-								console.log("[DIFY DEBUG] Replace message event:", parsed)
-								if (parsed.answer) {
-									fullText = parsed.answer // Replace instead of append
-									console.log("[DIFY DEBUG] Replaced fullText length:", fullText.length)
-									yield {
-										type: "text",
-										text: fullText,
-									}
-									hasYieldedContent = true
-								}
-							} else if (parsed.event === "message_end") {
-								console.log("[DIFY DEBUG] Message end event", parsed)
-								// Message completed. Yield final text if we have any.
-								if (fullText) {
-									yield {
-										type: "text",
-										text: fullText,
-									}
-									hasYieldedContent = true
-								}
-								// Yield usage data if available
-								if (parsed.usage) {
-									yield {
-										type: "usage",
-										inputTokens: parsed.usage.prompt_tokens || 0,
-										outputTokens: parsed.usage.completion_tokens || parsed.usage.total_tokens || 0,
-										totalCost: parsed.usage.total_price || 0,
-									}
-								}
-								return // End of stream
-							} else if (parsed.event === "error") {
-								console.error("[DIFY DEBUG] Error event:", parsed)
-								throw new Error(`Dify API error: ${parsed.message || "Unknown error"}`)
-							} else if (parsed.event === "workflow_started" || parsed.event === "workflow_finished") {
-								console.log("[DIFY DEBUG] Workflow event:", parsed.event)
-								// These are informational events, continue processing
-							} else if (parsed.event === "node_started" || parsed.event === "node_finished") {
-								console.log("[DIFY DEBUG] Node event:", parsed.event, parsed.data)
-								// These are informational events, continue processing
-							} else if (parsed.event === "ping") {
-								console.log("[DIFY DEBUG] Ping event received, keeping connection alive.")
-								// Ping event, do nothing
-							} else {
-								console.log("[DIFY DEBUG] Unknown event type:", parsed.event, "Full object:", parsed)
-								// Try to extract text from other possible fields
-								if (parsed.text) {
-									fullText += parsed.text
-									yield {
-										type: "text",
-										text: fullText,
-									}
-									hasYieldedContent = true
-								} else if (parsed.content) {
-									fullText += parsed.content
-									yield {
-										type: "text",
-										text: fullText,
-									}
-									hasYieldedContent = true
-								} else if (parsed.answer) {
-									// Fallback: some events might have answer field even if not "message" type
-									fullText += parsed.answer
-									yield {
-										type: "text",
-										text: fullText,
-									}
-									hasYieldedContent = true
-								}
-							}
-						} catch (e) {
-							console.warn("[DIFY DEBUG] Failed to parse JSON:", data, "Error:", e)
-						}
-					} else if (line.trim() !== "") {
-						console.log(
-							"[DIFY DEBUG] Non-data line (not starting with 'data:'), trying to parse as direct JSON:",
-							JSON.stringify(line),
-						)
-						// Try to parse as direct JSON (fallback for non-SSE responses, though Dify uses SSE)
-						try {
-							const parsed = JSON.parse(line.trim())
-							console.log("[DIFY DEBUG] Parsed direct JSON:", parsed)
-							processedEvents.push(parsed.event || "direct-json")
-
-							// Handle the same event types as above
-							if (parsed.event === "message" && parsed.answer) {
-								fullText += parsed.answer
-								yield {
-									type: "text",
-									text: fullText,
-								}
-								hasYieldedContent = true
-							} else if (parsed.event === "message_end") {
-								if (fullText) {
-									yield {
-										type: "text",
-										text: fullText,
-									}
-									hasYieldedContent = true
-								}
-								return
-							} else if (parsed.event === "error") {
-								console.error("[DIFY DEBUG] Direct JSON Error event:", parsed)
-								throw new Error(`Dify API error: ${parsed.message || "Unknown error"}`)
-							} else if (parsed.answer || parsed.text || parsed.content) {
-								// Fallback for any content in direct JSON
-								const content = parsed.answer || parsed.text || parsed.content
-								fullText += content
-								yield {
-									type: "text",
-									text: fullText,
-								}
-								hasYieldedContent = true
-							}
-						} catch (e) {
-							// Not JSON, continue
-							console.log("[DIFY DEBUG] Line is not direct JSON, continuing")
-						}
-					}
-				}
-			}
-
-			// Final check - if we haven't yielded any content, provide diagnostic information
-			if (!hasYieldedContent) {
-				const diagnosticInfo = {
-					processedEvents,
-					finalFullTextLength: fullText.length,
-					finalFullText: fullText,
-					streamDuration: Date.now() - lastEventTime,
-					conversationId: this.conversationId,
-				}
-				console.error("[DIFY DEBUG] No content was yielded! Diagnostic info:", diagnosticInfo)
-
-				// If we have any accumulated text at all, yield it as a fallback
-				if (fullText.trim()) {
-					console.log("[DIFY DEBUG] Yielding accumulated text as fallback:", fullText)
-					yield {
-						type: "text",
-						text: fullText,
-					}
-				} else {
-					// Provide a more informative error
-					throw new Error(
-						`Dify API did not provide any assistant messages. ` +
-							`Events processed: [${processedEvents.join(", ")}]. ` +
-							`Check your Dify application configuration and ensure it's properly set up to return responses. ` +
-							`API URL: ${fullUrl}. Conversation ID: ${this.conversationId || "none"}.`,
-					)
-				}
-			}
-		} finally {
-			reader.releaseLock()
-			console.log("[DIFY DEBUG] Stream reader released")
-		}
-	}
-
-	private convertMessagesToQuery(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): string {
-		// Dify's context is managed by `conversation_id`. The `query` should be the last user message.
-		// The system prompt is typically configured in the Dify App itself.
-		const lastUserMessage = messages.filter((m) => m.role === "user").pop()
-
-		if (!lastUserMessage) {
-			return "" // Should not happen in normal flow
-		}
-
-		const userQuery = Array.isArray(lastUserMessage.content)
-			? lastUserMessage.content.map((c) => ("text" in c ? c.text : "")).join("\n")
-			: (lastUserMessage.content as string)
-
-		// Only prepend the system prompt if it's the very first message of a new conversation.
-		if (!this.conversationId && systemPrompt) {
-			console.log("[DIFY DEBUG] Prepending system prompt for new conversation.")
-			return `${systemPrompt}\n\n---\n\n${userQuery}`
-		}
-
-		return userQuery
-	}
-
-	getModel(): { id: string; info: ModelInfo } {
-		return {
-			id: "dify-workflow",
-			info: {
-				maxTokens: 8192,
-				contextWindow: 128000,
-				supportsImages: true,
-				supportsPromptCache: false,
-				inputPrice: 0,
-				outputPrice: 0,
-				description: "Dify workflow - model selection is configured in your Dify application",
-			},
-		}
-	}
-
-	// Additional Dify API Methods
-
-	/**
-	 * Upload a file for use in conversations
-	 * @param file File buffer to upload
-	 * @param filename Name of the file
-	 * @param user User identifier (defaults to "cline-user")
-	 * @returns Promise with file upload response
-	 */
-	async uploadFile(file: Buffer, filename: string, user: string = "cline-user"): Promise<DifyFileResponse> {
-		const formData = new FormData()
-		formData.append("file", new Blob([new Uint8Array(file)]), filename)
-		formData.append("user", user)
-
-		const response = await fetch(`${this.baseUrl}/files/upload`, {
-			method: "POST",
-			headers: {
-				Authorization: `Bearer ${this.apiKey}`,
-			},
-			body: formData,
-		})
-
-		if (!response.ok) {
-			const errorText = await response.text()
-			throw new Error(`Dify file upload error: ${response.status} ${response.statusText} - ${errorText}`)
-		}
-
-		return response.json()
-	}
-
-	/**
-	 * Stop generation for a specific task
-	 * @param taskId Task ID from streaming response
-	 * @param user User identifier (defaults to "cline-user")
-	 * @returns Promise that resolves when generation is stopped
-	 */
-	async stopGeneration(taskId: string, user: string = "cline-user"): Promise<void> {
-		const response = await fetch(`${this.baseUrl}/chat-messages/${taskId}/stop`, {
-			method: "POST",
-			headers: {
-				Authorization: `Bearer ${this.apiKey}`,
-				"Content-Type": "application/json",
-			},
-			body: JSON.stringify({ user }),
-		})
-
-		if (!response.ok) {
-			const errorText = await response.text()
-			throw new Error(`Dify stop generation error: ${response.status} ${response.statusText} - ${errorText}`)
-		}
-	}
-
-	/**
-	 * Get conversation history messages with pagination
-	 * @param conversationId Conversation ID
-	 * @param user User identifier (defaults to "cline-user")
-	 * @param firstId First message ID for pagination (optional)
-	 * @param limit Number of messages to return (default: 20)
-	 * @returns Promise with conversation history
-	 */
-	async getConversationHistory(
-		conversationId: string,
-		user: string = "cline-user",
-		firstId?: string,
-		limit: number = 20,
-	): Promise<DifyHistoryResponse> {
-		const params = new URLSearchParams({ user, limit: limit.toString() })
-		if (firstId) {
-			params.append("first_id", firstId)
-		}
-
-		const response = await fetch(`${this.baseUrl}/conversations/${conversationId}/messages?${params}`, {
-			headers: {
-				Authorization: `Bearer ${this.apiKey}`,
-			},
-		})
-
-		if (!response.ok) {
-			const errorText = await response.text()
-			throw new Error(`Dify get conversation history error: ${response.status} ${response.statusText} - ${errorText}`)
-		}
-
-		return response.json()
-	}
-
-	/**
-	 * Get list of conversations for a user
-	 * @param user User identifier (defaults to "cline-user")
-	 * @param lastId Last conversation ID for pagination (optional)
-	 * @param limit Number of conversations to return (default: 20)
-	 * @param sortBy Sort field (default: "-updated_at")
-	 * @returns Promise with conversations list
-	 */
-	async getConversations(
-		user: string = "cline-user",
-		lastId?: string,
-		limit: number = 20,
-		sortBy: string = "-updated_at",
-	): Promise<DifyConversationsResponse> {
-		const params = new URLSearchParams({
-			user,
-			limit: limit.toString(),
-			sort_by: sortBy,
-		})
-		if (lastId) {
-			params.append("last_id", lastId)
-		}
-
-		const response = await fetch(`${this.baseUrl}/conversations?${params}`, {
-			headers: {
-				Authorization: `Bearer ${this.apiKey}`,
-			},
-		})
-
-		if (!response.ok) {
-			const errorText = await response.text()
-			throw new Error(`Dify get conversations error: ${response.status} ${response.statusText} - ${errorText}`)
-		}
-
-		return response.json()
-	}
-
-	/**
-	 * Delete a conversation
-	 * @param conversationId Conversation ID to delete
-	 * @param user User identifier (defaults to "cline-user")
-	 * @returns Promise that resolves when conversation is deleted
-	 */
-	async deleteConversation(conversationId: string, user: string = "cline-user"): Promise<void> {
-		const response = await fetch(`${this.baseUrl}/conversations/${conversationId}`, {
-			method: "DELETE",
-			headers: {
-				Authorization: `Bearer ${this.apiKey}`,
-				"Content-Type": "application/json",
-			},
-			body: JSON.stringify({ user }),
-		})
-
-		if (!response.ok) {
-			const errorText = await response.text()
-			throw new Error(`Dify delete conversation error: ${response.status} ${response.statusText} - ${errorText}`)
-		}
-	}
-
-	/**
-	 * Rename a conversation
-	 * @param conversationId Conversation ID to rename
-	 * @param user User identifier (defaults to "cline-user")
-	 * @param name New conversation name (optional if auto_generate is true)
-	 * @param autoGenerate Whether to auto-generate the name (default: false)
-	 * @returns Promise with updated conversation details
-	 */
-	async renameConversation(
-		conversationId: string,
-		user: string = "cline-user",
-		name?: string,
-		autoGenerate: boolean = false,
-	): Promise<DifyConversationResponse> {
-		const body: any = { user, auto_generate: autoGenerate }
-		if (name) {
-			body.name = name
-		}
-
-		const response = await fetch(`${this.baseUrl}/conversations/${conversationId}/name`, {
-			method: "POST",
-			headers: {
-				Authorization: `Bearer ${this.apiKey}`,
-				"Content-Type": "application/json",
-			},
-			body: JSON.stringify(body),
-		})
-
-		if (!response.ok) {
-			const errorText = await response.text()
-			throw new Error(`Dify rename conversation error: ${response.status} ${response.statusText} - ${errorText}`)
-		}
-
-		return response.json()
-	}
-
-	/**
-	 * Submit feedback for a message
-	 * @param messageId Message ID to provide feedback for
-	 * @param rating Rating: "like" or "dislike"
-	 * @param content Optional feedback content
-	 * @param user User identifier (defaults to "cline-user")
-	 * @returns Promise that resolves when feedback is submitted
-	 */
-	async submitMessageFeedback(
-		messageId: string,
-		rating: "like" | "dislike",
-		content?: string,
-		user: string = "cline-user",
-	): Promise<void> {
-		const body: any = { rating, user }
-		if (content) {
-			body.content = content
-		}
-
-		const response = await fetch(`${this.baseUrl}/messages/${messageId}/feedbacks`, {
-			method: "POST",
-			headers: {
-				Authorization: `Bearer ${this.apiKey}`,
-				"Content-Type": "application/json",
-			},
-			body: JSON.stringify(body),
-		})
-
-		if (!response.ok) {
-			const errorText = await response.text()
-			throw new Error(`Dify submit feedback error: ${response.status} ${response.statusText} - ${errorText}`)
-		}
-	}
-
-	/**
-	 * Get current conversation ID
-	 * @returns Current conversation ID or null
-	 */
-	getCurrentConversationId(): string | null {
-		return this.conversationId
-	}
-
-	/**
-	 * Set conversation ID for continuing existing conversations
-	 * @param conversationId Conversation ID to set
-	 */
-	setConversationId(conversationId: string): void {
-		this.conversationId = conversationId
-	}
-
-	/**
-	 * Reset conversation ID to start a new conversation
-	 */
-	resetConversation(): void {
-		this.conversationId = null
-		this.currentTaskId = null
-	}
-}
@@ -1,12 +1,12 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { DoubaoModelId, doubaoDefaultModelId, doubaoModels, ModelInfo } from "@shared/api"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from ".."
+import { ApiHandler } from ".."
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"

-interface DoubaoHandlerOptions extends CommonApiHandlerOptions {
+interface DoubaoHandlerOptions {
 	doubaoApiKey?: string
 	apiModelId?: string
 }
@@ -1,12 +1,12 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { FireworksModelId, fireworksDefaultModelId, fireworksModels, ModelInfo } from "@shared/api"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from ".."
+import { ApiHandler } from ".."
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"

-interface FireworksHandlerOptions extends CommonApiHandlerOptions {
+interface FireworksHandlerOptions {
 	fireworksApiKey?: string
 	fireworksModelId?: string
 	fireworksModelMaxCompletionTokens?: number
@@ -1,19 +1,17 @@
 import type { Anthropic } from "@anthropic-ai/sdk"
 // Restore GenerateContentConfig import and add GenerateContentResponseUsageMetadata
-import { ApiError, type GenerateContentConfig, type GenerateContentResponseUsageMetadata, GoogleGenAI, Part } from "@google/genai"
+import { type GenerateContentConfig, type GenerateContentResponseUsageMetadata, GoogleGenAI, Part } from "@google/genai"
+import { telemetryService } from "@services/posthog/PostHogClientProvider"
 import { GeminiModelId, geminiDefaultModelId, geminiModels, ModelInfo } from "@shared/api"
-import { telemetryService } from "@/services/telemetry"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
-import { RetriableError, withRetry } from "../retry"
+import { ApiHandler } from "../"
+import { withRetry } from "../retry"
 import { convertAnthropicMessageToGemini } from "../transform/gemini-format"
 import { ApiStream } from "../transform/stream"

 // Define a default TTL for the cache (e.g., 15 minutes in seconds)
 const _DEFAULT_CACHE_TTL_SECONDS = 900

-const rateLimitPatterns = [/got status: 429/i, /429 Too Many Requests/i, /rate limit exceeded/i, /too many requests/i]
-
-interface GeminiHandlerOptions extends CommonApiHandlerOptions {
+interface GeminiHandlerOptions {
 	isVertex?: boolean
 	vertexProjectId?: string
 	vertexRegion?: string
@@ -224,40 +222,24 @@ export class GeminiHandler implements ApiHandler {
 			if (error instanceof Error) {
 				apiError = error.message

-				if (error instanceof ApiError) {
-					if (error.status === 429) {
-						// The API includes more details in the message
-						// https://github.com/googleapis/js-genai/blob/v1.11.0/src/_api_client.ts#L758
-						const response = this.attemptParse(error.message)
+				// Gemini doesn't include status codes in their errors
+				// https://github.com/googleapis/js-genai/blob/61f7f27b866c74333ca6331883882489bcb708b9/src/_api_client.ts#L569
+				const rateLimitPatterns = [
+					/got status: 429/i,
+					/429 Too Many Requests/i,
+					/rate limit exceeded/i,
+					/too many requests/i,
+				]

-						if (response && response.error) {
-							const responseBody = this.attemptParse(response.error.message)
+				const isRateLimit =
+					error.name === "ClientError" && rateLimitPatterns.some((pattern) => pattern.test(error.message))

-							if (responseBody.error) {
-								const detail = responseBody.error.details?.find(
-									(d: any) => d["@type"] === "type.googleapis.com/google.rpc.RetryInfo",
-								)
-
-								const detailedError = new RetriableError(
-									apiError,
-									this.parseRetryDelay(detail?.retryDelay) || undefined,
-									{
-										cause: error,
-									},
-								)
-								throw detailedError
-							}
-						}
-
-						throw new RetriableError(apiError, undefined, { cause: error })
-					}
-
-					// Fallback in case Gemini throws a rate limit error without a 429 status code
-					// https://github.com/cline/cline/pull/5205#discussion_r2311761559
-					const isRateLimit = rateLimitPatterns.some((pattern) => pattern.test(error.message))
-					if (isRateLimit) {
-						throw new RetriableError(apiError, undefined, { cause: error })
-					}
+				if (isRateLimit) {
+					const rateLimitError = Object.assign(new Error(error.message), {
+						...error,
+						status: 429,
+					})
+					throw rateLimitError
 				}
 			} else {
 				apiError = String(error)
@@ -438,35 +420,4 @@ export class GeminiHandler implements ApiHandler {

 		return Math.ceil(totalChars / 4)
 	}
-
-	private parseRetryDelay(retryAfter?: string): number {
-		if (!retryAfter) {
-			return 0
-		}
-
-		const unit = retryAfter.at(-1)
-		const value = parseInt(retryAfter, 10)
-
-		if (Number.isNaN(value)) {
-			return 0
-		}
-
-		if (unit === "s") {
-			return value
-		} else if (unit === "m") {
-			return value * 60 // Convert minutes to seconds
-		} else if (unit === "h") {
-			return value * 60 * 60 // Convert hours to seconds
-		}
-
-		return value
-	}
-
-	private attemptParse(str: string) {
-		try {
-			return JSON.parse(str)
-		} catch (_) {
-			return null
-		}
-	}
 }
@@ -2,12 +2,12 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { GroqModelId, groqDefaultModelId, groqModels, ModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "@utils/cost"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"

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

-interface HuaweiCloudMaaSHandlerOptions extends CommonApiHandlerOptions {
+interface HuaweiCloudMaaSHandlerOptions {
 	huaweiCloudMaasApiKey?: string
 	huaweiCloudMaasModelId?: string
 	huaweiCloudMaasModelInfo?: ModelInfo
@@ -2,12 +2,12 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { HuggingFaceModelId, huggingFaceDefaultModelId, huggingFaceModels, ModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "@utils/cost"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"

-interface HuggingFaceHandlerOptions extends CommonApiHandlerOptions {
+interface HuggingFaceHandlerOptions {
 	huggingFaceApiKey?: string
 	huggingFaceModelId?: string
 	huggingFaceModelInfo?: ModelInfo
@@ -1,12 +1,12 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { LiteLLMModelInfo, liteLlmDefaultModelId, liteLlmModelInfoSaneDefaults } from "@shared/api"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from ".."
+import { ApiHandler } from ".."
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"

-interface LiteLlmHandlerOptions extends CommonApiHandlerOptions {
+interface LiteLlmHandlerOptions {
 	liteLlmApiKey?: string
 	liteLlmBaseUrl?: string
 	liteLlmModelId?: string
@@ -16,7 +16,7 @@ interface LiteLlmHandlerOptions extends CommonApiHandlerOptions {
 	ulid?: string
 }

-export interface LiteLlmModelInfoResponse {
+interface LiteLlmModelInfoResponse {
 	data: Array<{
 		model_name: string
 		litellm_params: {
@@ -28,7 +28,6 @@ export interface LiteLlmModelInfoResponse {
 			output_cost_per_token: number
 			cache_creation_input_token_cost?: number
 			cache_read_input_token_cost?: number
-			supports_prompt_caching?: boolean
 			[key: string]: any
 		}
 	}>
@@ -62,17 +61,7 @@ export class LiteLlmHandler implements ApiHandler {
 		return this.client
 	}

-	private async modelInfo(publicModelName: string): Promise<LiteLlmModelInfoResponse["data"][number] | undefined> {
-		const modelInfo = await this.fetchModelsInfo()
-
-		if (!modelInfo?.data) {
-			return undefined
-		}
-
-		return modelInfo.data.find((model) => model.model_name === publicModelName)
-	}
-
-	private async fetchModelsInfo(): Promise<LiteLlmModelInfoResponse | undefined> {
+	private async fetchModelInfo(): Promise<LiteLlmModelInfoResponse | undefined> {
 		// Check if cache is still valid
 		const now = Date.now()
 		if (this.modelInfoCache && now - this.modelInfoCacheTimestamp < this.modelInfoCacheTTL) {
@@ -132,14 +121,19 @@ export class LiteLlmHandler implements ApiHandler {
 		cacheReadCostPerToken?: number
 	}> {
 		try {
-			const matchingModel = await this.modelInfo(publicModelName)
+			const modelInfo = await this.fetchModelInfo()

-			if (matchingModel) {
-				return {
-					inputCostPerToken: matchingModel.model_info.input_cost_per_token || 0,
-					outputCostPerToken: matchingModel.model_info.output_cost_per_token || 0,
-					cacheCreationCostPerToken: matchingModel.model_info.cache_creation_input_token_cost,
-					cacheReadCostPerToken: matchingModel.model_info.cache_read_input_token_cost,
+			if (modelInfo?.data) {
+				// Find the model by public name
+				const matchingModel = modelInfo.data.find((model) => model.model_name === publicModelName)
+
+				if (matchingModel?.model_info) {
+					return {
+						inputCostPerToken: matchingModel.model_info.input_cost_per_token || 0,
+						outputCostPerToken: matchingModel.model_info.output_cost_per_token || 0,
+						cacheCreationCostPerToken: matchingModel.model_info.cache_creation_input_token_cost,
+						cacheReadCostPerToken: matchingModel.model_info.cache_read_input_token_cost,
+					}
 				}
 			}
 		} catch (error) {
@@ -183,7 +177,7 @@ export class LiteLlmHandler implements ApiHandler {
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
 		const client = this.ensureClient()
 		const formattedMessages = convertToOpenAiMessages(messages)
-		const systemMessage: OpenAI.Chat.ChatCompletionSystemMessageParam | Anthropic.Messages.TextBlockParam = {
+		const systemMessage: OpenAI.Chat.ChatCompletionSystemMessageParam = {
 			role: "system",
 			content: systemPrompt,
 		}
@@ -201,22 +195,13 @@ export class LiteLlmHandler implements ApiHandler {
 			temperature = undefined // Thinking mode doesn't support temperature
 		}

-		const modelInfo = await this.modelInfo(modelId)
-		const cacheControl =
-			this.options.liteLlmUsePromptCache && Boolean(modelInfo?.model_info.supports_prompt_caching)
-				? { cache_control: { type: "ephemeral" } }
-				: undefined
+		// Define cache control object if prompt caching is enabled
+		const cacheControl = this.options.liteLlmUsePromptCache ? { cache_control: { type: "ephemeral" } } : undefined

-		if (cacheControl) {
-			// Add cache_control to system message if enabled
-			// https://docs.litellm.ai/docs/providers/anthropic#caching---large-context-caching
-			systemMessage.content = [
-				{
-					text: systemPrompt,
-					type: "text",
-					...cacheControl,
-				},
-			] as Anthropic.Messages.TextBlockParam[]
+		// Add cache_control to system message if enabled
+		const enhancedSystemMessage = {
+			...systemMessage,
+			...(cacheControl && cacheControl),
 		}

 		// Find the last two user messages to apply caching
@@ -228,49 +213,19 @@ export class LiteLlmHandler implements ApiHandler {
 		const secondLastUserMsgIndex = userMsgIndices[userMsgIndices.length - 2] ?? -1

 		// Apply cache_control to the last two user messages if enabled
-		// https://docs.litellm.ai/docs/providers/anthropic#caching---large-context-caching
-		const enhancedMessages: OpenAI.Chat.ChatCompletionMessageParam[] = formattedMessages.map(
-			(message, index): OpenAI.Chat.ChatCompletionMessageParam => {
-				if ((index === lastUserMsgIndex || index === secondLastUserMsgIndex) && cacheControl) {
-					// Handle both string and array content types
-					if (typeof message.content === "string") {
-						return {
-							...message,
-							content: [
-								{
-									type: "text",
-									text: message.content,
-									...cacheControl,
-								},
-							] as any,
-						}
-					} else if (Array.isArray(message.content)) {
-						// Apply cache control to the last content item in the array
-						return {
-							...message,
-							content: message.content.map((item, contentIndex) =>
-								contentIndex === (message.content?.length || 0) - 1
-									? {
-											...item,
-											...cacheControl,
-										}
-									: item,
-							) as any,
-						}
-					}
-
-					return {
-						...message,
-						...cacheControl,
-					}
+		const enhancedMessages = formattedMessages.map((message, index) => {
+			if ((index === lastUserMsgIndex || index === secondLastUserMsgIndex) && cacheControl) {
+				return {
+					...message,
+					...cacheControl,
 				}
-				return message
-			},
-		)
+			}
+			return message
+		})

 		const stream = await client.chat.completions.create({
 			model: this.options.liteLlmModelId || liteLlmDefaultModelId,
-			messages: [systemMessage, ...enhancedMessages],
+			messages: [enhancedSystemMessage, ...enhancedMessages],
 			temperature,
 			stream: true,
 			stream_options: { include_usage: true },
@@ -289,16 +244,16 @@ export class LiteLlmHandler implements ApiHandler {
 				}
 			}

-			// Handle reasoning events
-			// This is not in the standard types but may be in the response
+			// Handle reasoning events (thinking)
+			// Thinking is not in the standard types but may be in the response
 			interface ThinkingDelta {
-				reasoning_content?: string
+				thinking?: string
 			}

-			if ((delta as ThinkingDelta)?.reasoning_content) {
+			if ((delta as ThinkingDelta)?.thinking) {
 				yield {
 					type: "reasoning",
-					reasoning: (delta as ThinkingDelta).reasoning_content || "",
+					reasoning: (delta as ThinkingDelta).thinking || "",
 				}
 			}

@@ -1,12 +1,12 @@
 import type { Anthropic } from "@anthropic-ai/sdk"
 import { type ModelInfo, openAiModelInfoSaneDefaults } from "@shared/api"
 import OpenAI from "openai"
-import type { ApiHandler, CommonApiHandlerOptions } from "../"
+import type { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import type { ApiStream } from "../transform/stream"

-interface LmStudioHandlerOptions extends CommonApiHandlerOptions {
+interface LmStudioHandlerOptions {
 	lmStudioBaseUrl?: string
 	lmStudioModelId?: string
 	lmStudioMaxTokens?: string
@@ -1,12 +1,12 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { Mistral } from "@mistralai/mistralai"
 import { MistralModelId, ModelInfo, mistralDefaultModelId, mistralModels } from "@shared/api"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { convertToMistralMessages } from "../transform/mistral-format"
 import { ApiStream } from "../transform/stream"

-interface MistralHandlerOptions extends CommonApiHandlerOptions {
+interface MistralHandlerOptions {
 	mistralApiKey?: string
 	apiModelId?: string
 }
@@ -1,12 +1,12 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import OpenAI from "openai"
 import { ModelInfo, MoonshotModelId, moonshotDefaultModelId, moonshotModels } from "@/shared/api"
-import { ApiHandler, CommonApiHandlerOptions } from "../index"
+import { ApiHandler } from "../index"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"

-interface MoonshotHandlerOptions extends CommonApiHandlerOptions {
+interface MoonshotHandlerOptions {
 	moonshotApiKey?: string
 	moonshotApiLine?: string
 	apiModelId?: string
@@ -1,13 +1,13 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { type ModelInfo, type NebiusModelId, nebiusDefaultModelId, nebiusModels } from "@shared/api"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from "../index"
+import { ApiHandler } from "../index"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { convertToR1Format } from "../transform/r1-format"
 import { ApiStream } from "../transform/stream"

-interface NebiusHandlerOptions extends CommonApiHandlerOptions {
+interface NebiusHandlerOptions {
 	nebiusApiKey?: string
 	apiModelId?: string
 }
@@ -1,12 +1,12 @@
 import type { Anthropic } from "@anthropic-ai/sdk"
 import { type ModelInfo, openAiModelInfoSaneDefaults } from "@shared/api"
 import { type Config, type Message, Ollama } from "ollama"
-import type { ApiHandler, CommonApiHandlerOptions } from "../"
+import type { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { convertToOllamaMessages } from "../transform/ollama-format"
 import type { ApiStream } from "../transform/stream"

-interface OllamaHandlerOptions extends CommonApiHandlerOptions {
+interface OllamaHandlerOptions {
 	ollamaBaseUrl?: string
 	ollamaApiKey?: string
 	ollamaModelId?: string
@@ -29,7 +29,7 @@ export class OllamaHandler implements ApiHandler {
 		if (!this.client) {
 			try {
 				const clientOptions: Partial<Config> = {
-					host: this.options.ollamaBaseUrl,
+					host: this.options.ollamaBaseUrl || "http://localhost:11434",
 				}

 				// Add API key if provided (for Ollama cloud or authenticated instances)
@@ -3,12 +3,12 @@ import { ModelInfo, OpenAiNativeModelId, openAiNativeDefaultModelId, openAiNativ
 import { calculateApiCostOpenAI } from "@utils/cost"
 import OpenAI from "openai"
 import type { ChatCompletionReasoningEffort } from "openai/resources/chat/completions"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"

-interface OpenAiNativeHandlerOptions extends CommonApiHandlerOptions {
+interface OpenAiNativeHandlerOptions {
 	openAiNativeApiKey?: string
 	reasoningEffort?: string
 	apiModelId?: string
@@ -2,13 +2,13 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { azureOpenAiDefaultApiVersion, ModelInfo, OpenAiCompatibleModelInfo, openAiModelInfoSaneDefaults } from "@shared/api"
 import OpenAI, { AzureOpenAI } from "openai"
 import type { ChatCompletionReasoningEffort } from "openai/resources/chat/completions"
-import { ApiHandler, CommonApiHandlerOptions } from "../index"
+import { ApiHandler } from "../index"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { convertToR1Format } from "../transform/r1-format"
 import { ApiStream } from "../transform/stream"

-interface OpenAiHandlerOptions extends CommonApiHandlerOptions {
+interface OpenAiHandlerOptions {
 	openAiApiKey?: string
 	openAiBaseUrl?: string
 	azureApiVersion?: string
@@ -4,13 +4,22 @@ import { ModelInfo, openRouterDefaultModelId, openRouterDefaultModelInfo } from
 import { shouldSkipReasoningForModel } from "@utils/model-utils"
 import axios from "axios"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { createOpenRouterStream } from "../transform/openrouter-stream"
 import { ApiStream, ApiStreamUsageChunk } from "../transform/stream"
 import { OpenRouterErrorResponse } from "./types"

-interface OpenRouterHandlerOptions extends CommonApiHandlerOptions {
+interface OpenRouterHandlerOptions {
+	openRouterApiKey?: string
+	openRouterModelId?: string
+	openRouterModelInfo?: ModelInfo
+	openRouterProviderSorting?: string
+	reasoningEffort?: string
+	thinkingBudgetTokens?: number
+}
+
+interface OpenRouterHandlerOptions {
 	openRouterApiKey?: string
 	openRouterModelId?: string
 	openRouterModelInfo?: ModelInfo
@@ -1,272 +0,0 @@
-import { promises as fs } from "node:fs"
-import { Anthropic } from "@anthropic-ai/sdk"
-import { ModelInfo, QwenCodeModelId, qwenCodeDefaultModelId, qwenCodeModels } from "@shared/api"
-import OpenAI from "openai"
-import * as os from "os"
-import * as path from "path"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
-import { withRetry } from "../retry"
-import { convertToOpenAiMessages } from "../transform/openai-format"
-import { ApiStream } from "../transform/stream"
-
-// --- Constants for Qwen OAuth2 ---
-const QWEN_OAUTH_BASE_URL = "https://chat.qwen.ai"
-const QWEN_OAUTH_TOKEN_ENDPOINT = `${QWEN_OAUTH_BASE_URL}/api/v1/oauth2/token`
-const QWEN_OAUTH_CLIENT_ID = "f0304373b74a44d2b584a3fb70ca9e56"
-const QWEN_DIR = ".qwen"
-const QWEN_CREDENTIAL_FILENAME = "oauth_creds.json"
-
-interface QwenOAuthCredentials {
-	access_token: string
-	refresh_token: string
-	token_type: string
-	expiry_date: number
-	resource_url?: string
-}
-
-interface QwenCodeHandlerOptions extends CommonApiHandlerOptions {
-	qwenCodeOauthPath?: string
-	apiModelId?: string
-}
-
-function getQwenCachedCredentialPath(customPath?: string): string {
-	if (customPath) {
-		// Support custom path that starts with ~/ or is absolute
-		if (customPath.startsWith("~/")) {
-			return path.join(os.homedir(), customPath.slice(2))
-		}
-		return path.resolve(customPath)
-	}
-	return path.join(os.homedir(), QWEN_DIR, QWEN_CREDENTIAL_FILENAME)
-}
-
-function objectToUrlEncoded(data: Record<string, string>): string {
-	return Object.keys(data)
-		.map((key) => `${encodeURIComponent(key)}=${encodeURIComponent(data[key])}`)
-		.join("&")
-}
-
-export class QwenCodeHandler implements ApiHandler {
-	private options: QwenCodeHandlerOptions
-	private credentials: QwenOAuthCredentials | null = null
-	private client: OpenAI | undefined
-
-	constructor(options: QwenCodeHandlerOptions) {
-		this.options = options
-	}
-
-	private ensureClient(): OpenAI {
-		if (!this.client) {
-			// Create the client instance with dummy key initially
-			// The API key will be updated dynamically via ensureAuthenticated
-			this.client = new OpenAI({
-				apiKey: "dummy-key-will-be-replaced",
-				baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1",
-			})
-		}
-		return this.client
-	}
-
-	private async loadCachedQwenCredentials(): Promise<QwenOAuthCredentials> {
-		try {
-			const keyFile = getQwenCachedCredentialPath(this.options.qwenCodeOauthPath)
-			const credsStr = await fs.readFile(keyFile, "utf-8")
-			return JSON.parse(credsStr)
-		} catch (error) {
-			console.error(
-				`Error reading or parsing credentials file at ${getQwenCachedCredentialPath(this.options.qwenCodeOauthPath)}`,
-			)
-			throw new Error(`Failed to load Qwen OAuth credentials: ${error}`)
-		}
-	}
-
-	private async refreshAccessToken(credentials: QwenOAuthCredentials): Promise<QwenOAuthCredentials> {
-		if (!credentials.refresh_token) {
-			throw new Error("No refresh token available in credentials.")
-		}
-
-		const bodyData = {
-			grant_type: "refresh_token",
-			refresh_token: credentials.refresh_token,
-			client_id: QWEN_OAUTH_CLIENT_ID,
-		}
-
-		const response = await fetch(QWEN_OAUTH_TOKEN_ENDPOINT, {
-			method: "POST",
-			headers: {
-				"Content-Type": "application/x-www-form-urlencoded",
-				Accept: "application/json",
-			},
-			body: objectToUrlEncoded(bodyData),
-		})
-
-		if (!response.ok) {
-			const errorText = await response.text()
-			throw new Error(`Token refresh failed: ${response.status} ${response.statusText}. Response: ${errorText}`)
-		}
-
-		const tokenData = await response.json()
-
-		if (tokenData.error) {
-			throw new Error(`Token refresh failed: ${tokenData.error} - ${tokenData.error_description}`)
-		}
-
-		const newCredentials = {
-			...credentials,
-			access_token: tokenData.access_token,
-			token_type: tokenData.token_type,
-			refresh_token: tokenData.refresh_token || credentials.refresh_token,
-			expiry_date: Date.now() + tokenData.expires_in * 1000,
-		}
-
-		const filePath = getQwenCachedCredentialPath(this.options.qwenCodeOauthPath)
-		await fs.writeFile(filePath, JSON.stringify(newCredentials, null, 2))
-
-		return newCredentials
-	}
-
-	private isTokenValid(credentials: QwenOAuthCredentials): boolean {
-		const TOKEN_REFRESH_BUFFER_MS = 30 * 1000 // 30s buffer
-		if (!credentials.expiry_date) {
-			return false
-		}
-		return Date.now() < credentials.expiry_date - TOKEN_REFRESH_BUFFER_MS
-	}
-
-	private async ensureAuthenticated(): Promise<void> {
-		if (!this.credentials) {
-			this.credentials = await this.loadCachedQwenCredentials()
-		}
-
-		if (!this.isTokenValid(this.credentials)) {
-			this.credentials = await this.refreshAccessToken(this.credentials)
-		}
-
-		// After authentication, update the apiKey and baseURL on the existing client
-		const client = this.ensureClient()
-		client.apiKey = this.credentials.access_token
-		client.baseURL = this.getBaseUrl(this.credentials)
-	}
-
-	private getBaseUrl(creds: QwenOAuthCredentials): string {
-		let baseUrl = creds.resource_url || "https://dashscope.aliyuncs.com/compatible-mode/v1"
-		if (!baseUrl.startsWith("http://") && !baseUrl.startsWith("https://")) {
-			baseUrl = `https://${baseUrl}`
-		}
-		return baseUrl.endsWith("/v1") ? baseUrl : `${baseUrl}/v1`
-	}
-
-	private async callApiWithRetry<T>(apiCall: () => Promise<T>): Promise<T> {
-		try {
-			return await apiCall()
-		} catch (error: any) {
-			if (error.status === 401) {
-				// Token expired, refresh and retry
-				this.credentials = await this.refreshAccessToken(this.credentials!)
-				const client = this.ensureClient()
-				client.apiKey = this.credentials.access_token
-				client.baseURL = this.getBaseUrl(this.credentials)
-				return await apiCall()
-			} else {
-				throw error
-			}
-		}
-	}
-
-	@withRetry()
-	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
-		await this.ensureAuthenticated()
-		const client = this.ensureClient()
-		const model = this.getModel()
-
-		const systemMessage: OpenAI.Chat.ChatCompletionSystemMessageParam = {
-			role: "system",
-			content: systemPrompt,
-		}
-
-		const convertedMessages = [systemMessage, ...convertToOpenAiMessages(messages)]
-
-		const requestOptions: OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming = {
-			model: model.id,
-			temperature: 0,
-			messages: convertedMessages,
-			stream: true,
-			stream_options: { include_usage: true },
-			max_completion_tokens: model.info.maxTokens,
-		}
-
-		const stream = await this.callApiWithRetry(() => client.chat.completions.create(requestOptions))
-
-		let fullContent = ""
-
-		for await (const apiChunk of stream) {
-			const delta = apiChunk.choices[0]?.delta ?? {}
-
-			if (delta.content) {
-				let newText = delta.content
-				if (newText.startsWith(fullContent)) {
-					newText = newText.substring(fullContent.length)
-				}
-				fullContent = delta.content
-
-				if (newText) {
-					// Check for thinking blocks
-					if (newText.includes("<think>") || newText.includes("</think>")) {
-						// Simple parsing for thinking blocks
-						const parts = newText.split(/<\/?think>/g)
-						for (let i = 0; i < parts.length; i++) {
-							if (parts[i]) {
-								if (i % 2 === 0) {
-									// Outside thinking block
-									yield {
-										type: "text",
-										text: parts[i],
-									}
-								} else {
-									// Inside thinking block
-									yield {
-										type: "reasoning",
-										reasoning: parts[i],
-									}
-								}
-							}
-						}
-					} else {
-						yield {
-							type: "text",
-							text: newText,
-						}
-					}
-				}
-			}
-
-			// Handle reasoning content (o1-style)
-			if ("reasoning_content" in delta && delta.reasoning_content) {
-				yield {
-					type: "reasoning",
-					reasoning: (delta.reasoning_content as string | undefined) || "",
-				}
-			}
-
-			if (apiChunk.usage) {
-				yield {
-					type: "usage",
-					inputTokens: apiChunk.usage.prompt_tokens || 0,
-					outputTokens: apiChunk.usage.completion_tokens || 0,
-				}
-			}
-		}
-	}
-
-	getModel(): { id: QwenCodeModelId; info: ModelInfo } {
-		const modelId = this.options.apiModelId
-		if (modelId && modelId in qwenCodeModels) {
-			const id = modelId as QwenCodeModelId
-			return { id, info: qwenCodeModels[id] }
-		}
-		return {
-			id: qwenCodeDefaultModelId,
-			info: qwenCodeModels[qwenCodeDefaultModelId],
-		}
-	}
-}
@@ -10,13 +10,13 @@ import {
 	QwenApiRegions,
 } from "@shared/api"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { convertToR1Format } from "../transform/r1-format"
 import { ApiStream } from "../transform/stream"

-interface QwenHandlerOptions extends CommonApiHandlerOptions {
+interface QwenHandlerOptions {
 	qwenApiKey?: string
 	qwenApiLine?: QwenApiRegions
 	apiModelId?: string
@@ -2,12 +2,12 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { ModelInfo, requestyDefaultModelId, requestyDefaultModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "@utils/cost"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from "../index"
+import { ApiHandler } from "../index"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"

-interface RequestyHandlerOptions extends CommonApiHandlerOptions {
+interface RequestyHandlerOptions {
 	requestyBaseUrl?: string
 	requestyApiKey?: string
 	reasoningEffort?: string
@@ -1,13 +1,13 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { ModelInfo, SambanovaModelId, sambanovaDefaultModelId, sambanovaModels } from "@shared/api"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from "../index"
+import { ApiHandler } from "../index"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { convertToR1Format } from "../transform/r1-format"
 import { ApiStream } from "../transform/stream"

-interface SambanovaHandlerOptions extends CommonApiHandlerOptions {
+interface SambanovaHandlerOptions {
 	sambanovaApiKey?: string
 	apiModelId?: string
 }
@@ -4,22 +4,20 @@ import {
 	ConversationRole as BedrockConversationRole,
 	type Message as BedrockMessage,
 } from "@aws-sdk/client-bedrock-runtime"
-import { ChatMessages, LlmModuleConfig, OrchestrationClient, TemplatingModuleConfig } from "@sap-ai-sdk/orchestration"
 import { ModelInfo, SapAiCoreModelId, sapAiCoreDefaultModelId, sapAiCoreModels } from "@shared/api"
 import axios from "axios"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { ApiHandler } from "../"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"

-interface SapAiCoreHandlerOptions extends CommonApiHandlerOptions {
+interface SapAiCoreHandlerOptions {
 	sapAiCoreClientId?: string
 	sapAiCoreClientSecret?: string
 	sapAiCoreTokenUrl?: string
 	sapAiResourceGroup?: string
 	sapAiCoreBaseUrl?: string
 	apiModelId?: string
-	sapAiCoreUseOrchestrationMode?: boolean
 	thinkingBudgetTokens?: number
 	reasoningEffort?: string
 }
@@ -352,33 +350,19 @@ export class SapAiCoreHandler implements ApiHandler {
 	private options: SapAiCoreHandlerOptions
 	private token?: Token
 	private deployments?: Deployment[]
-	private isAiCoreEnvSetup: boolean = false

 	constructor(options: SapAiCoreHandlerOptions) {
 		this.options = options
 	}

-	private validateCredentials(): void {
-		if (
-			!this.options.sapAiCoreClientId ||
-			!this.options.sapAiCoreClientSecret ||
-			!this.options.sapAiCoreTokenUrl ||
-			!this.options.sapAiCoreBaseUrl
-		) {
-			throw new Error("Missing required SAP AI Core credentials. Please check your configuration.")
-		}
-	}
-
 	private async authenticate(): Promise<Token> {
-		this.validateCredentials()
-
 		const payload = {
 			grant_type: "client_credentials",
-			client_id: this.options.sapAiCoreClientId,
-			client_secret: this.options.sapAiCoreClientSecret,
+			client_id: this.options.sapAiCoreClientId || "",
+			client_secret: this.options.sapAiCoreClientSecret || "",
 		}

-		const tokenUrl = this.options.sapAiCoreTokenUrl!.replace(/\/+$/, "") + "/oauth/token"
+		const tokenUrl = (this.options.sapAiCoreTokenUrl || "").replace(/\/+$/, "") + "/oauth/token"
 		const response = await axios.post(tokenUrl, payload, {
 			headers: { "Content-Type": "application/x-www-form-urlencoded" },
 		})
@@ -456,87 +440,6 @@ export class SapAiCoreHandler implements ApiHandler {
 	}

 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
-		if (this.options.sapAiCoreUseOrchestrationMode ?? true) {
-			yield* this.createMessageWithOrchestration(systemPrompt, messages)
-		} else {
-			yield* this.createMessageWithDeployments(systemPrompt, messages)
-		}
-	}
-
-	// TODO: support credentials changes after initial setup
-	private ensureAiCoreEnvSetup(): void {
-		// Only set up once to avoid redundant operations
-		if (this.isAiCoreEnvSetup) {
-			return
-		}
-
-		// Validate required credentials
-		this.validateCredentials()
-
-		const aiCoreServiceCredentials = {
-			clientid: this.options.sapAiCoreClientId!,
-			clientsecret: this.options.sapAiCoreClientSecret!,
-			url: this.options.sapAiCoreTokenUrl!,
-			serviceurls: {
-				AI_API_URL: this.options.sapAiCoreBaseUrl!,
-			},
-		}
-		process.env["AICORE_SERVICE_KEY"] = JSON.stringify(aiCoreServiceCredentials)
-
-		// Mark as set up to avoid redundant calls
-		this.isAiCoreEnvSetup = true
-	}
-
-	private async *createMessageWithOrchestration(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
-		try {
-			// Ensure AI Core environment variable is set up (only runs once)
-			this.ensureAiCoreEnvSetup()
-			const model = this.getModel()
-
-			// 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 = {
-				template: [
-					{
-						role: "system",
-						content: systemPrompt,
-					},
-				],
-			}
-			const orchestrationClient = new OrchestrationClient(
-				{ llm, templating },
-				{ resourceGroup: this.options.sapAiResourceGroup || "default" },
-			)
-
-			const sapMessages = this.convertMessageParamToSAPMessages(messages)
-
-			const response = await orchestrationClient.stream({
-				messages: sapMessages,
-			})
-
-			for await (const chunk of response.stream.toContentStream()) {
-				yield { type: "text", text: chunk }
-			}
-
-			const tokenUsage = response.getTokenUsage()
-			if (tokenUsage) {
-				yield {
-					type: "usage",
-					inputTokens: tokenUsage.prompt_tokens || 0,
-					outputTokens: tokenUsage.completion_tokens || 0,
-				}
-			}
-		} catch (error) {
-			console.error("Error in SAP orchestration mode:", error)
-			throw error
-		}
-	}
-
-	private async *createMessageWithDeployments(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
 		const token = await this.getToken()
 		const headers = {
 			Authorization: `Bearer ${token}`,
@@ -1031,8 +934,4 @@ export class SapAiCoreHandler implements ApiHandler {
 		}
 		return { id: sapAiCoreDefaultModelId, info: sapAiCoreModels[sapAiCoreDefaultModelId] }
 	}
-	private convertMessageParamToSAPMessages(messages: Anthropic.Messages.MessageParam[]): ChatMessages {
-		// Use the existing OpenAI converter since the logic is identical
-		return convertToOpenAiMessages(messages) as ChatMessages
-	}
 }
@@ -1,13 +1,13 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { ModelInfo, openAiModelInfoSaneDefaults } from "@shared/api"
 import OpenAI from "openai"
-import { ApiHandler, CommonApiHandlerOptions } from "../index"
+import { ApiHandler } from "../index"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { convertToR1Format } from "../transform/r1-format"
 import { ApiStream } from "../transform/stream"

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

-interface VercelAIGatewayHandlerOptions extends CommonApiHandlerOptions {
+interface VercelAIGatewayHandlerOptions {
 	vercelAiGatewayApiKey?: string
 	vercelAiGatewayModelId?: string
 	vercelAiGatewayModelInfo?: ModelInfo
@@ -1,12 +1,12 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { AnthropicVertex } from "@anthropic-ai/vertex-sdk"
 import { ModelInfo, VertexModelId, vertexDefaultModelId, vertexModels } from "@shared/api"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { ApiStream } from "../transform/stream"
 import { GeminiHandler } from "./gemini"

-interface VertexHandlerOptions extends CommonApiHandlerOptions {
+interface VertexHandlerOptions {
 	vertexProjectId?: string
 	vertexRegion?: string
 	apiModelId?: string
@@ -3,13 +3,13 @@ import { ModelInfo, openAiModelInfoSaneDefaults } from "@shared/api"
 import { SELECTOR_SEPARATOR, stringifyVsCodeLmModelSelector } from "@shared/vsCodeSelectorUtils"
 import { calculateApiCostAnthropic } from "@utils/cost"
 import * as vscode from "vscode"
-import { ApiHandler, CommonApiHandlerOptions, SingleCompletionHandler } from "../"
+import { ApiHandler, SingleCompletionHandler } from "../"
 import { withRetry } from "../retry"
 import { ApiStream } from "../transform/stream"
 import { convertToVsCodeLmMessages } from "../transform/vscode-lm-format"
 import type { LanguageModelChatSelector as LanguageModelChatSelectorFromTypes } from "./types"

-interface VsCodeLmHandlerOptions extends CommonApiHandlerOptions {
+interface VsCodeLmHandlerOptions {
 	vsCodeLmModelSelector?: any
 }

@@ -3,12 +3,18 @@ import { ModelInfo, XAIModelId, xaiDefaultModelId, xaiModels } from "@shared/api
 import { shouldSkipReasoningForModel } from "@utils/model-utils"
 import OpenAI from "openai"
 import { ChatCompletionReasoningEffort } from "openai/resources/chat/completions"
-import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { ApiHandler } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"

-interface XAIHandlerOptions extends CommonApiHandlerOptions {
+interface XAIHandlerOptions {
+	xaiApiKey?: string
+	reasoningEffort?: string
+	apiModelId?: string
+}
+
+interface XAIHandlerOptions {
 	xaiApiKey?: string
 	reasoningEffort?: string
 	apiModelId?: string
@@ -10,12 +10,12 @@ import {
 } from "@shared/api"
 import OpenAI from "openai"
 import { version as extensionVersion } from "../../../../package.json"
-import { ApiHandler, CommonApiHandlerOptions } from ".."
+import { ApiHandler } from ".."
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"

-interface ZAiHandlerOptions extends CommonApiHandlerOptions {
+interface ZAiHandlerOptions {
 	zaiApiLine?: string
 	zaiApiKey?: string
 	apiModelId?: string
@@ -12,18 +12,6 @@ const DEFAULT_OPTIONS: Required<RetryOptions> = {
 	retryAllErrors: false,
 }

-export class RetriableError extends Error {
-	status: number = 429
-	retryAfter?: number
-
-	constructor(message: string, retryAfter?: number, options?: ErrorOptions) {
-		super(message, options)
-		this.name = "RetriableError"
-
-		this.retryAfter = retryAfter
-	}
-}
-
 export function withRetry(options: RetryOptions = {}) {
 	const { maxRetries, baseDelay, maxDelay, retryAllErrors } = { ...DEFAULT_OPTIONS, ...options }

@@ -36,7 +24,7 @@ export function withRetry(options: RetryOptions = {}) {
 					yield* originalMethod.apply(this, args)
 					return
 				} catch (error: any) {
-					const isRateLimit = error?.status === 429 || error instanceof RetriableError
+					const isRateLimit = error?.status === 429
 					const isLastAttempt = attempt === maxRetries - 1

 					if ((!isRateLimit && !retryAllErrors) || isLastAttempt) {
@@ -48,8 +36,7 @@ export function withRetry(options: RetryOptions = {}) {
 					const retryAfter =
 						error.headers?.["retry-after"] ||
 						error.headers?.["x-ratelimit-reset"] ||
-						error.headers?.["ratelimit-reset"] ||
-						error.retryAfter
+						error.headers?.["ratelimit-reset"]

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

@@ -151,6 +152,17 @@ export async function createOpenRouterStream(
 			}
 	}

+	// Removes messages in the middle when close to context window limit. Should not be applied to models that support prompt caching since it would continuously break the cache.
+	let shouldApplyMiddleOutTransform = !model.info.supportsPromptCache
+	// except for deepseek (which we set supportsPromptCache to true for), where because the context window is so small our truncation algo might miss and we should use openrouter's middle-out transform as a fallback to ensure we don't exceed the context window (FIXME: once we have a more robust token estimator we should not rely on this)
+	if (model.id === "deepseek/deepseek-chat") {
+		shouldApplyMiddleOutTransform = true
+	}
+
+	if (isGPT5ModelFamily(model.id)) {
+		shouldApplyMiddleOutTransform = false
+	}
+
 	// hardcoded provider sorting for kimi-k2
 	const isKimiK2 = model.id === "moonshotai/kimi-k2"
 	openRouterProviderSorting = isKimiK2 ? undefined : openRouterProviderSorting
@@ -164,6 +176,7 @@ export async function createOpenRouterStream(
 		messages: openAiMessages,
 		stream: true,
 		stream_options: { include_usage: true },
+		transforms: shouldApplyMiddleOutTransform ? ["middle-out"] : undefined,
 		include_reasoning: true,
 		...(model.id.startsWith("openai/o") ? { reasoning_effort: reasoningEffort || "medium" } : {}),
 		...(reasoning ? { reasoning } : {}),
@@ -1,9 +1,10 @@
-import { getTaskMetadata, readTaskHistoryFromState, saveTaskMetadata } from "@core/storage/disk"
+import { getTaskMetadata, saveTaskMetadata } from "@core/storage/disk"
 import type { ClineMessage } from "@shared/ExtensionMessage"
 import chokidar, { FSWatcher } from "chokidar"
 import * as path from "path"
 import * as vscode from "vscode"
 import { Controller } from "@/core/controller"
+import { HistoryItem } from "@/shared/HistoryItem"
 import { getCwd } from "@/utils/path"
 import type { FileMetadataEntry } from "./ContextTrackerTypes"

@@ -242,7 +243,7 @@ export class FileContextTracker {
 			const key = `pendingFileContextWarning_${this.taskId}`
 			// NOTE: Using 'as any' because dynamic keys like pendingFileContextWarning_${taskId}
 			// are legitimate workspace state keys but don't fit the strict LocalStateKey type system
-			this.controller.stateManager.setWorkspaceState(key as any, files)
+			this.controller.cacheService.setWorkspaceState(key as any, files)
 		} catch (error) {
 			console.error("Error storing pending file context warning:", error)
 		}
@@ -254,7 +255,7 @@ export class FileContextTracker {
 	async retrievePendingFileContextWarning(): Promise<string[] | undefined> {
 		try {
 			const key = `pendingFileContextWarning_${this.taskId}`
-			const files = this.controller.stateManager.getWorkspaceStateKey(key as any) as string[]
+			const files = this.controller.cacheService.getWorkspaceStateKey(key as any) as string[]
 			return files
 		} catch (error) {
 			console.error("Error retrieving pending file context warning:", error)
@@ -269,7 +270,7 @@ export class FileContextTracker {
 		try {
 			const files = await this.retrievePendingFileContextWarning()
 			if (files) {
-				this.controller.stateManager.setWorkspaceState(`pendingFileContextWarning_${this.taskId}` as any, undefined)
+				this.controller.cacheService.setWorkspaceState(`pendingFileContextWarning_${this.taskId}` as any, undefined)
 				return files
 			}
 		} catch (error) {
@@ -285,7 +286,8 @@ export class FileContextTracker {
 	static async cleanupOrphanedWarnings(context: vscode.ExtensionContext): Promise<void> {
 		const startTime = Date.now()
 		try {
-			const taskHistory = await readTaskHistoryFromState(context)
+			// eslint-disable-next-line eslint-rules/no-direct-vscode-state-api
+			const taskHistory = (context.globalState.get("taskHistory") as HistoryItem[]) || []
 			const existingTaskIds = new Set(taskHistory.map((task) => task.id))
 			const allStateKeys = context.workspaceState.keys()
 			const pendingWarningKeys = allStateKeys.filter((key) => key.startsWith("pendingFileContextWarning_"))
@@ -310,7 +312,7 @@ export class FileContextTracker {
 				`FileContextTracker: Processed ${existingTaskIds.size} tasks, found ${pendingWarningKeys.length} pending warnings, ${orphanedPendingContextTasks.length} orphaned, deleted ${orphanedPendingContextTasks.length}, took ${duration}ms`,
 			)
 		} catch (error) {
-			console.error("[FileContextTracker] Error cleaning up orphaned file context warnings:", error)
+			console.error("Error cleaning up orphaned file context warnings:", error)
 		}
 	}
 }
@@ -74,18 +74,18 @@ export async function refreshClineRulesToggles(
 	localToggles: ClineRulesToggles
 }> {
 	// Global toggles
-	const globalClineRulesToggles = controller.stateManager.getGlobalStateKey("globalClineRulesToggles")
+	const globalClineRulesToggles = controller.cacheService.getGlobalStateKey("globalClineRulesToggles")
 	const globalClineRulesFilePath = await ensureRulesDirectoryExists()
 	const updatedGlobalToggles = await synchronizeRuleToggles(globalClineRulesFilePath, globalClineRulesToggles)
-	controller.stateManager.setGlobalState("globalClineRulesToggles", updatedGlobalToggles)
+	controller.cacheService.setGlobalState("globalClineRulesToggles", updatedGlobalToggles)

 	// Local toggles
-	const localClineRulesToggles = controller.stateManager.getWorkspaceStateKey("localClineRulesToggles")
+	const localClineRulesToggles = controller.cacheService.getWorkspaceStateKey("localClineRulesToggles")
 	const localClineRulesFilePath = path.resolve(workingDirectory, GlobalFileNames.clineRules)
 	const updatedLocalToggles = await synchronizeRuleToggles(localClineRulesFilePath, localClineRulesToggles, "", [
 		[".clinerules", "workflows"],
 	])
-	controller.stateManager.setWorkspaceState("localClineRulesToggles", updatedLocalToggles)
+	controller.cacheService.setWorkspaceState("localClineRulesToggles", updatedLocalToggles)

 	return {
 		globalToggles: updatedGlobalToggles,
@@ -23,13 +23,13 @@ export async function refreshExternalRulesToggles(
 	cursorLocalToggles: ClineRulesToggles
 }> {
 	// local windsurf toggles
-	const localWindsurfRulesToggles = controller.stateManager.getWorkspaceStateKey("localWindsurfRulesToggles")
+	const localWindsurfRulesToggles = controller.cacheService.getWorkspaceStateKey("localWindsurfRulesToggles")
 	const localWindsurfRulesFilePath = path.resolve(workingDirectory, GlobalFileNames.windsurfRules)
 	const updatedLocalWindsurfToggles = await synchronizeRuleToggles(localWindsurfRulesFilePath, localWindsurfRulesToggles)
-	controller.stateManager.setWorkspaceState("localWindsurfRulesToggles", updatedLocalWindsurfToggles)
+	controller.cacheService.setWorkspaceState("localWindsurfRulesToggles", updatedLocalWindsurfToggles)

 	// local cursor toggles
-	const localCursorRulesToggles = controller.stateManager.getWorkspaceStateKey("localCursorRulesToggles")
+	const localCursorRulesToggles = controller.cacheService.getWorkspaceStateKey("localCursorRulesToggles")

 	// cursor has two valid locations for rules files, so we need to check both and combine
 	// synchronizeRuleToggles will drop whichever rules files are not in each given path, but combining the results will result in no data loss
@@ -40,7 +40,7 @@ export async function refreshExternalRulesToggles(
 	const updatedLocalCursorToggles2 = await synchronizeRuleToggles(localCursorRulesFilePath, localCursorRulesToggles)

 	const updatedLocalCursorToggles = combineRuleToggles(updatedLocalCursorToggles1, updatedLocalCursorToggles2)
-	controller.stateManager.setWorkspaceState("localCursorRulesToggles", updatedLocalCursorToggles)
+	controller.cacheService.setWorkspaceState("localCursorRulesToggles", updatedLocalCursorToggles)

 	return {
 		windsurfLocalToggles: updatedLocalWindsurfToggles,
@@ -247,31 +247,31 @@ export async function deleteRuleFile(
 		// Update the appropriate toggles
 		if (isGlobal) {
 			if (type === "workflow") {
-				const toggles = controller.stateManager.getGlobalStateKey("globalWorkflowToggles")
+				const toggles = controller.cacheService.getGlobalStateKey("globalWorkflowToggles")
 				delete toggles[rulePath]
-				controller.stateManager.setGlobalState("globalWorkflowToggles", toggles)
+				controller.cacheService.setGlobalState("globalWorkflowToggles", toggles)
 			} else {
-				const toggles = controller.stateManager.getGlobalStateKey("globalClineRulesToggles")
+				const toggles = controller.cacheService.getGlobalStateKey("globalClineRulesToggles")
 				delete toggles[rulePath]
-				controller.stateManager.setGlobalState("globalClineRulesToggles", toggles)
+				controller.cacheService.setGlobalState("globalClineRulesToggles", toggles)
 			}
 		} else {
 			if (type === "workflow") {
-				const toggles = controller.stateManager.getWorkspaceStateKey("workflowToggles")
+				const toggles = controller.cacheService.getWorkspaceStateKey("workflowToggles")
 				delete toggles[rulePath]
-				controller.stateManager.setWorkspaceState("workflowToggles", toggles)
+				controller.cacheService.setWorkspaceState("workflowToggles", toggles)
 			} else if (type === "cursor") {
-				const toggles = controller.stateManager.getWorkspaceStateKey("localCursorRulesToggles")
+				const toggles = controller.cacheService.getWorkspaceStateKey("localCursorRulesToggles")
 				delete toggles[rulePath]
-				controller.stateManager.setWorkspaceState("localCursorRulesToggles", toggles)
+				controller.cacheService.setWorkspaceState("localCursorRulesToggles", toggles)
 			} else if (type === "windsurf") {
-				const toggles = controller.stateManager.getWorkspaceStateKey("localWindsurfRulesToggles")
+				const toggles = controller.cacheService.getWorkspaceStateKey("localWindsurfRulesToggles")
 				delete toggles[rulePath]
-				controller.stateManager.setWorkspaceState("localWindsurfRulesToggles", toggles)
+				controller.cacheService.setWorkspaceState("localWindsurfRulesToggles", toggles)
 			} else {
-				const toggles = controller.stateManager.getWorkspaceStateKey("localClineRulesToggles")
+				const toggles = controller.cacheService.getWorkspaceStateKey("localClineRulesToggles")
 				delete toggles[rulePath]
-				controller.stateManager.setWorkspaceState("localClineRulesToggles", toggles)
+				controller.cacheService.setWorkspaceState("localClineRulesToggles", toggles)
 			}
 		}

@@ -15,15 +15,15 @@ export async function refreshWorkflowToggles(
 	localWorkflowToggles: ClineRulesToggles
 }> {
 	// Global workflows
-	const globalWorkflowToggles = controller.stateManager.getGlobalStateKey("globalWorkflowToggles")
+	const globalWorkflowToggles = controller.cacheService.getGlobalStateKey("globalWorkflowToggles")
 	const globalClineWorkflowsFilePath = await ensureWorkflowsDirectoryExists()
 	const updatedGlobalWorkflowToggles = await synchronizeRuleToggles(globalClineWorkflowsFilePath, globalWorkflowToggles)
-	controller.stateManager.setGlobalState("globalWorkflowToggles", updatedGlobalWorkflowToggles)
+	controller.cacheService.setGlobalState("globalWorkflowToggles", updatedGlobalWorkflowToggles)

-	const workflowRulesToggles = controller.stateManager.getWorkspaceStateKey("workflowToggles")
+	const workflowRulesToggles = controller.cacheService.getWorkspaceStateKey("workflowToggles")
 	const workflowsDirPath = path.resolve(workingDirectory, GlobalFileNames.workflows)
 	const updatedWorkflowToggles = await synchronizeRuleToggles(workflowsDirPath, workflowRulesToggles)
-	controller.stateManager.setWorkspaceState("workflowToggles", updatedWorkflowToggles)
+	controller.cacheService.setWorkspaceState("workflowToggles", updatedWorkflowToggles)

 	return {
 		globalWorkflowToggles: updatedGlobalWorkflowToggles,
@@ -11,7 +11,7 @@ import type { Controller } from "../index"
 export async function authStateChanged(controller: Controller, request: AuthStateChangedRequest): Promise<AuthState> {
 	try {
 		// Store the user info directly in global state
-		controller.stateManager.setGlobalState("userInfo", request.user)
+		controller.cacheService.setGlobalState("userInfo", request.user)

 		// Return the same user info
 		return AuthState.create({ user: request.user })
@@ -19,7 +19,7 @@ export async function discoverBrowser(controller: Controller, _request: EmptyReq
 			// This way we don't override the user's preference

 			// Test the connection to get the endpoint
-			const browserSettings = controller.stateManager.getGlobalStateKey("browserSettings")
+			const browserSettings = controller.cacheService.getGlobalStateKey("browserSettings")
 			const browserSession = new BrowserSession(controller.context, browserSettings)
 			const result = await browserSession.testConnection(discoveredHost)

@@ -11,7 +11,7 @@ import { Controller } from "../index"
 export async function getBrowserConnectionInfo(controller: Controller, _: EmptyRequest): Promise<BrowserConnectionInfo> {
 	try {
 		// Get browser settings from extension state
-		const browserSettings = controller.stateManager.getGlobalStateKey("browserSettings")
+		const browserSettings = controller.cacheService.getGlobalStateKey("browserSettings")

 		// Check if there's an active browser session by using the controller's handleWebviewMessage approach
 		// This is similar to what's done in controller/index.ts for the "getBrowserConnectionInfo" message
@@ -11,7 +11,7 @@ import { Controller } from "../index"
 */
 export async function getDetectedChromePath(controller: Controller, _: EmptyRequest): Promise<ChromePath> {
 	try {
-		const browserSettings = controller.stateManager.getGlobalStateKey("browserSettings")
+		const browserSettings = controller.cacheService.getGlobalStateKey("browserSettings")
 		const browserSession = new BrowserSession(controller.context, browserSettings)
 		const result = await browserSession.getDetectedChromePath()

@@ -12,7 +12,7 @@ import { Controller } from "../index"
 */
 export async function testBrowserConnection(controller: Controller, request: StringRequest): Promise<BrowserConnection> {
 	try {
-		const browserSettings = controller.stateManager.getGlobalStateKey("browserSettings")
+		const browserSettings = controller.cacheService.getGlobalStateKey("browserSettings")
 		const browserSession = new BrowserSession(controller.context, browserSettings)
 		const text = request.value || ""

@@ -12,7 +12,7 @@ import { Controller } from "../index"
 export async function updateBrowserSettings(controller: Controller, request: UpdateBrowserSettingsRequest): Promise<Boolean> {
 	try {
 		// Get current browser settings to preserve fields not in the request
-		const currentSettings = controller.stateManager.getGlobalStateKey("browserSettings")
+		const currentSettings = controller.cacheService.getGlobalStateKey("browserSettings")
 		const mergedWithDefaults = { ...DEFAULT_BROWSER_SETTINGS, ...currentSettings }

 		// Convert from protobuf format to shared format, merging with existing settings
@@ -39,7 +39,7 @@ export async function updateBrowserSettings(controller: Controller, request: Upd
 		}

 		// Update global state with new settings
-		controller.stateManager.setGlobalState("browserSettings", newBrowserSettings)
+		controller.cacheService.setGlobalState("browserSettings", newBrowserSettings)

 		// Update task browser settings if task exists
 		if (controller.task) {
@@ -1,7 +1,7 @@
 import { getFileMentionFromPath } from "@/core/mentions"
 import { WebviewProvider } from "@/core/webview"
 import { singleFileDiagnosticsToProblemsString } from "@/integrations/diagnostics"
-import { telemetryService } from "@/services/telemetry"
+import { telemetryService } from "@/services/posthog/PostHogClientProvider"
 import { CommandContext, Empty } from "@/shared/proto/index.cline"
 import { Controller } from "../index"
 import { sendAddToInputEventToClient } from "../ui/subscribeToAddToInput"
@@ -1,6 +1,6 @@
 import { getFileMentionFromPath } from "@/core/mentions"
 import { HostProvider } from "@/hosts/host-provider"
-import { telemetryService } from "@/services/telemetry"
+import { telemetryService } from "@/services/posthog/PostHogClientProvider"
 import { CommandContext, Empty } from "@/shared/proto/index.cline"
 import { ShowMessageType } from "@/shared/proto/index.host"
 import { Controller } from "../index"
@@ -1,6 +1,6 @@
 import { getFileMentionFromPath } from "@/core/mentions"
 import { singleFileDiagnosticsToProblemsString } from "@/integrations/diagnostics"
-import { telemetryService } from "@/services/telemetry"
+import { telemetryService } from "@/services/posthog/PostHogClientProvider"
 import { CommandContext, Empty } from "@/shared/proto/index.cline"
 import { Controller } from "../index"

@@ -1,6 +1,6 @@
 import { getFileMentionFromPath } from "@/core/mentions"
 import { HostProvider } from "@/hosts/host-provider"
-import { telemetryService } from "@/services/telemetry"
+import { telemetryService } from "@/services/posthog/PostHogClientProvider"
 import { CommandContext, Empty } from "@/shared/proto/index.cline"
 import { ShowMessageType } from "@/shared/proto/index.host"
 import { Controller } from "../index"
@@ -1,5 +1,5 @@
 import { openFile as openFileIntegration } from "@integrations/misc/open-file"
-import { telemetryService } from "../../../services/telemetry"
+import { telemetryService } from "../../../services/posthog/PostHogClientProvider"
 import { Empty, StringRequest } from "../../../shared/proto/cline/common"
 import { ensureFocusChainFile, extractFocusChainListFromText } from "../../task/focus-chain/file-utils"
 import { Controller } from ".."
@@ -1,7 +1,7 @@
 import path from "node:path"
+import { telemetryService } from "@services/posthog/PostHogClientProvider"
 import type { ToggleClineRuleRequest } from "@shared/proto/cline/file"
 import { ToggleClineRules } from "@shared/proto/cline/file"
-import { telemetryService } from "@/services/telemetry"
 import type { Controller } from "../index"

 /**
@@ -24,20 +24,13 @@ export async function toggleClineRule(controller: Controller, request: ToggleCli

 	// This is the same core logic as in the original handler
 	if (isGlobal) {
-		const toggles = controller.stateManager.getGlobalStateKey("globalClineRulesToggles")
+		const toggles = controller.cacheService.getGlobalStateKey("globalClineRulesToggles")
 		toggles[rulePath] = enabled
-		controller.stateManager.setGlobalState("globalClineRulesToggles", toggles)
+		controller.cacheService.setGlobalState("globalClineRulesToggles", toggles)
 	} else {
-		const toggles = controller.stateManager.getWorkspaceStateKey("localClineRulesToggles")
+		const toggles = controller.cacheService.getWorkspaceStateKey("localClineRulesToggles")
 		toggles[rulePath] = enabled
-		controller.stateManager.setWorkspaceState("localClineRulesToggles", toggles)
-	}
-
-	// Track rule toggle telemetry with current task context
-	if (controller.task?.ulid) {
-		// Extract just the filename for privacy (no full paths)
-		const ruleFileName = path.basename(rulePath)
-		telemetryService.captureClineRuleToggled(controller.task.ulid, ruleFileName, enabled, isGlobal)
+		controller.cacheService.setWorkspaceState("localClineRulesToggles", toggles)
 	}

 	// Track rule toggle telemetry with current task context
@@ -48,8 +41,8 @@ export async function toggleClineRule(controller: Controller, request: ToggleCli
 	}

 	// Get the current state to return in the response
-	const globalToggles = controller.stateManager.getGlobalStateKey("globalClineRulesToggles")
-	const localToggles = controller.stateManager.getWorkspaceStateKey("localClineRulesToggles")
+	const globalToggles = controller.cacheService.getGlobalStateKey("globalClineRulesToggles")
+	const localToggles = controller.cacheService.getWorkspaceStateKey("localClineRulesToggles")

 	return ToggleClineRules.create({
 		globalClineRulesToggles: { toggles: globalToggles },
@@ -20,12 +20,12 @@ export async function toggleCursorRule(controller: Controller, request: ToggleCu
 	}

 	// Update the toggles in workspace state
-	const toggles = controller.stateManager.getWorkspaceStateKey("localCursorRulesToggles")
+	const toggles = controller.cacheService.getWorkspaceStateKey("localCursorRulesToggles")
 	toggles[rulePath] = enabled
-	controller.stateManager.setWorkspaceState("localCursorRulesToggles", toggles)
+	controller.cacheService.setWorkspaceState("localCursorRulesToggles", toggles)

 	// Get the current state to return in the response
-	const cursorToggles = controller.stateManager.getWorkspaceStateKey("localCursorRulesToggles")
+	const cursorToggles = controller.cacheService.getWorkspaceStateKey("localCursorRulesToggles")

 	return ClineRulesToggles.create({
 		toggles: cursorToggles,
@@ -20,9 +20,9 @@ export async function toggleWindsurfRule(controller: Controller, request: Toggle
 	}

 	// Update the toggles
-	const toggles = controller.stateManager.getWorkspaceStateKey("localWindsurfRulesToggles")
+	const toggles = controller.cacheService.getWorkspaceStateKey("localWindsurfRulesToggles")
 	toggles[rulePath] = enabled
-	controller.stateManager.setWorkspaceState("localWindsurfRulesToggles", toggles)
+	controller.cacheService.setWorkspaceState("localWindsurfRulesToggles", toggles)

 	// Return the toggles directly
 	return ClineRulesToggles.create({ toggles: toggles })
@@ -21,18 +21,18 @@ export async function toggleWorkflow(controller: Controller, request: ToggleWork
 	// Update the toggles based on isGlobal flag
 	if (isGlobal) {
 		// Global workflows
-		const toggles = controller.stateManager.getGlobalStateKey("globalWorkflowToggles")
+		const toggles = controller.cacheService.getGlobalStateKey("globalWorkflowToggles")
 		toggles[workflowPath] = enabled
-		controller.stateManager.setGlobalState("globalWorkflowToggles", toggles)
+		controller.cacheService.setGlobalState("globalWorkflowToggles", toggles)
 		await controller.postStateToWebview()

 		// Return the global toggles
 		return ClineRulesToggles.create({ toggles: toggles })
 	} else {
 		// Workspace workflows
-		const toggles = controller.stateManager.getWorkspaceStateKey("workflowToggles")
+		const toggles = controller.cacheService.getWorkspaceStateKey("workflowToggles")
 		toggles[workflowPath] = enabled
-		controller.stateManager.setWorkspaceState("workflowToggles", toggles)
+		controller.cacheService.setWorkspaceState("workflowToggles", toggles)
 		await controller.postStateToWebview()

 		// Return the workspace toggles
@@ -21,13 +21,12 @@ import * as vscode from "vscode"
 import { clineEnvConfig } from "@/config"
 import { HostProvider } from "@/hosts/host-provider"
 import { AuthService } from "@/services/auth/AuthService"
-import { getDistinctId } from "@/services/logging/distinctId"
-import { telemetryService } from "@/services/telemetry"
+import { PostHogClientProvider, telemetryService } from "@/services/posthog/PostHogClientProvider"
 import { ShowMessageType } from "@/shared/proto/host/window"
 import { getLatestAnnouncementId } from "@/utils/announcements"
 import { getCwd, getDesktopDir } from "@/utils/path"
+import { CacheService, PersistenceErrorEvent } from "../storage/CacheService"
 import { ensureMcpServersDirectoryExists, ensureSettingsDirectoryExists, GlobalFileNames } from "../storage/disk"
-import { PersistenceErrorEvent, StateManager } from "../storage/StateManager"
 import { Task } from "../task"
 import { sendMcpMarketplaceCatalogEvent } from "./mcp/subscribeToMcpMarketplaceCatalog"
 import { sendStateUpdate } from "./state/subscribeToState"
@@ -46,7 +45,7 @@ export class Controller {
 	mcpHub: McpHub
 	accountService: ClineAccountService
 	authService: AuthService
-	readonly stateManager: StateManager
+	readonly cacheService: CacheService

 	constructor(
 		readonly context: vscode.ExtensionContext,
@@ -56,34 +55,31 @@ export class Controller {

 		HostProvider.get().logToChannel("ClineProvider instantiated")
 		this.accountService = ClineAccountService.getInstance()
-		this.stateManager = new StateManager(context)
+		this.cacheService = new CacheService(context)
 		this.authService = AuthService.getInstance(this)

 		// Initialize cache service asynchronously - critical for extension functionality
-		this.stateManager
+		this.cacheService
 			.initialize()
 			.then(() => {
 				this.authService.restoreRefreshTokenAndRetrieveAuthInfo()
 			})
 			.catch((error) => {
-				console.error(
-					"[Controller] CRITICAL: Failed to initialize StateManager - extension may not function properly:",
-					error,
-				)
+				console.error("CRITICAL: Failed to initialize CacheService - extension may not function properly:", error)
 			})

 		// Set up persistence error recovery
-		this.stateManager.onPersistenceError = async ({ error }: PersistenceErrorEvent) => {
-			console.error("[Controller] Cache persistence failed, recovering:", error)
+		this.cacheService.onPersistenceError = async ({ error }: PersistenceErrorEvent) => {
+			console.error("Cache persistence failed, recovering:", error)
 			try {
-				await this.stateManager.reInitialize()
+				await this.cacheService.reInitialize()
 				await this.postStateToWebview()
 				HostProvider.window.showMessage({
 					type: ShowMessageType.WARNING,
 					message: "Saving settings to storage failed.",
 				})
 			} catch (recoveryError) {
-				console.error("[Controller] Cache recovery failed:", recoveryError)
+				console.error("Cache recovery failed:", recoveryError)
 				HostProvider.window.showMessage({
 					type: ShowMessageType.ERROR,
 					message: "Failed to save settings. Please restart the extension.",
@@ -105,7 +101,7 @@ export class Controller {
 	}

 	async getCurrentMode(): Promise<Mode> {
-		return this.stateManager.getGlobalStateKey("mode")
+		return this.cacheService.getGlobalStateKey("mode")
 	}

 	/*
@@ -130,17 +126,17 @@ export class Controller {
 	async handleSignOut() {
 		try {
 			// TODO: update to clineAccountId and then move clineApiKey to a clear function.
-			this.stateManager.setSecret("clineAccountId", undefined)
-			this.stateManager.setGlobalState("userInfo", undefined)
+			this.cacheService.setSecret("clineAccountId", undefined)
+			this.cacheService.setGlobalState("userInfo", undefined)

 			// Update API providers through cache service
-			const apiConfiguration = this.stateManager.getApiConfiguration()
+			const apiConfiguration = this.cacheService.getApiConfiguration()
 			const updatedConfig = {
 				...apiConfiguration,
 				planModeApiProvider: "openrouter" as ApiProvider,
 				actModeApiProvider: "openrouter" as ApiProvider,
 			}
-			this.stateManager.setApiConfiguration(updatedConfig)
+			this.cacheService.setApiConfiguration(updatedConfig)

 			await this.postStateToWebview()
 			HostProvider.window.showMessage({
@@ -156,35 +152,35 @@ export class Controller {
 	}

 	async setUserInfo(info?: UserInfo) {
-		this.stateManager.setGlobalState("userInfo", info)
+		this.cacheService.setGlobalState("userInfo", info)
 	}

 	async initTask(task?: string, images?: string[], files?: string[], historyItem?: HistoryItem) {
 		await this.clearTask() // ensures that an existing task doesn't exist before starting a new one, although this shouldn't be possible since user must clear task before starting a new one

-		const apiConfiguration = this.stateManager.getApiConfiguration()
-		const autoApprovalSettings = this.stateManager.getGlobalStateKey("autoApprovalSettings")
-		const browserSettings = this.stateManager.getGlobalStateKey("browserSettings")
-		const focusChainSettings = this.stateManager.getGlobalStateKey("focusChainSettings")
-		const focusChainFeatureFlagEnabled = this.stateManager.getGlobalStateKey("focusChainFeatureFlagEnabled")
-		const preferredLanguage = this.stateManager.getGlobalStateKey("preferredLanguage")
-		const openaiReasoningEffort = this.stateManager.getGlobalStateKey("openaiReasoningEffort")
-		const mode = this.stateManager.getGlobalStateKey("mode")
-		const shellIntegrationTimeout = this.stateManager.getGlobalStateKey("shellIntegrationTimeout")
-		const terminalReuseEnabled = this.stateManager.getGlobalStateKey("terminalReuseEnabled")
-		const terminalOutputLineLimit = this.stateManager.getGlobalStateKey("terminalOutputLineLimit")
-		const defaultTerminalProfile = this.stateManager.getGlobalStateKey("defaultTerminalProfile")
-		const enableCheckpointsSetting = this.stateManager.getGlobalStateKey("enableCheckpointsSetting")
-		const isNewUser = this.stateManager.getGlobalStateKey("isNewUser")
-		const taskHistory = this.stateManager.getGlobalStateKey("taskHistory")
-		const strictPlanModeEnabled = this.stateManager.getGlobalStateKey("strictPlanModeEnabled")
-		const useAutoCondense = this.stateManager.getGlobalStateKey("useAutoCondense")
+		const apiConfiguration = this.cacheService.getApiConfiguration()
+		const autoApprovalSettings = this.cacheService.getGlobalStateKey("autoApprovalSettings")
+		const browserSettings = this.cacheService.getGlobalStateKey("browserSettings")
+		const focusChainSettings = this.cacheService.getGlobalStateKey("focusChainSettings")
+		const focusChainFeatureFlagEnabled = this.cacheService.getGlobalStateKey("focusChainFeatureFlagEnabled")
+		const preferredLanguage = this.cacheService.getGlobalStateKey("preferredLanguage")
+		const openaiReasoningEffort = this.cacheService.getGlobalStateKey("openaiReasoningEffort")
+		const mode = this.cacheService.getGlobalStateKey("mode")
+		const shellIntegrationTimeout = this.cacheService.getGlobalStateKey("shellIntegrationTimeout")
+		const terminalReuseEnabled = this.cacheService.getGlobalStateKey("terminalReuseEnabled")
+		const terminalOutputLineLimit = this.cacheService.getGlobalStateKey("terminalOutputLineLimit")
+		const defaultTerminalProfile = this.cacheService.getGlobalStateKey("defaultTerminalProfile")
+		const enableCheckpointsSetting = this.cacheService.getGlobalStateKey("enableCheckpointsSetting")
+		const isNewUser = this.cacheService.getGlobalStateKey("isNewUser")
+		const taskHistory = this.cacheService.getGlobalStateKey("taskHistory")
+		const strictPlanModeEnabled = this.cacheService.getGlobalStateKey("strictPlanModeEnabled")
+		const useAutoCondense = this.cacheService.getGlobalStateKey("useAutoCondense")

 		const NEW_USER_TASK_COUNT_THRESHOLD = 10

 		// Check if the user has completed enough tasks to no longer be considered a "new user"
 		if (isNewUser && !historyItem && taskHistory && taskHistory.length >= NEW_USER_TASK_COUNT_THRESHOLD) {
-			this.stateManager.setGlobalState("isNewUser", false)
+			this.cacheService.setGlobalState("isNewUser", false)
 			await this.postStateToWebview()
 		}

@@ -193,7 +189,7 @@ export class Controller {
 				...autoApprovalSettings,
 				version: (autoApprovalSettings.version ?? 1) + 1,
 			}
-			this.stateManager.setGlobalState("autoApprovalSettings", updatedAutoApprovalSettings)
+			this.cacheService.setGlobalState("autoApprovalSettings", updatedAutoApprovalSettings)
 		}
 		// Apply remote feature flag gate to focus chain settings
 		const effectiveFocusChainSettings = {
@@ -216,14 +212,14 @@ export class Controller {
 			openaiReasoningEffort,
 			mode,
 			strictPlanModeEnabled ?? true,
-			useAutoCondense ?? false,
+			useAutoCondense ?? true,
 			shellIntegrationTimeout,
 			terminalReuseEnabled ?? true,
 			terminalOutputLineLimit ?? 500,
 			defaultTerminalProfile ?? "default",
 			enableCheckpointsSetting ?? true,
 			await getCwd(getDesktopDir()),
-			this.stateManager,
+			this.cacheService,
 			task,
 			images,
 			files,
@@ -239,7 +235,7 @@ export class Controller {
 	}

 	async updateTelemetrySetting(telemetrySetting: TelemetrySetting) {
-		this.stateManager.setGlobalState("telemetrySetting", telemetrySetting)
+		this.cacheService.setGlobalState("telemetrySetting", telemetrySetting)
 		const isOptedIn = telemetrySetting !== "disabled"
 		telemetryService.updateTelemetryState(isOptedIn)
 		await this.postStateToWebview()
@@ -249,14 +245,14 @@ export class Controller {
 		const didSwitchToActMode = modeToSwitchTo === "act"

 		// Store mode to global state
-		this.stateManager.setGlobalState("mode", modeToSwitchTo)
+		this.cacheService.setGlobalState("mode", modeToSwitchTo)

 		// Capture mode switch telemetry | Capture regardless of if we know the taskId
 		telemetryService.captureModeSwitch(this.task?.ulid ?? "0", modeToSwitchTo)

 		// Update API handler with new mode (buildApiHandler now selects provider based on mode)
 		if (this.task) {
-			const apiConfiguration = this.stateManager.getApiConfiguration()
+			const apiConfiguration = this.cacheService.getApiConfiguration()
 			this.task.api = buildApiHandler({ ...apiConfiguration, ulid: this.task.ulid }, modeToSwitchTo)
 		}

@@ -321,12 +317,12 @@ export class Controller {
 			const clineProvider: ApiProvider = "cline"

 			// Get current settings to determine how to update providers
-			const planActSeparateModelsSetting = this.stateManager.getGlobalStateKey("planActSeparateModelsSetting")
+			const planActSeparateModelsSetting = this.cacheService.getGlobalStateKey("planActSeparateModelsSetting")

 			const currentMode = await this.getCurrentMode()

 			// Get current API configuration from cache
-			const currentApiConfiguration = this.stateManager.getApiConfiguration()
+			const currentApiConfiguration = this.cacheService.getApiConfiguration()

 			const updatedConfig = { ...currentApiConfiguration }

@@ -344,10 +340,10 @@ export class Controller {
 			}

 			// Update the API configuration through cache service
-			this.stateManager.setApiConfiguration(updatedConfig)
+			this.cacheService.setApiConfiguration(updatedConfig)

 			// Mark welcome view as completed since user has successfully logged in
-			this.stateManager.setGlobalState("welcomeViewCompleted", true)
+			this.cacheService.setGlobalState("welcomeViewCompleted", true)

 			if (this.task) {
 				this.task.api = buildApiHandler({ ...updatedConfig, ulid: this.task.ulid }, currentMode)
@@ -388,7 +384,7 @@ export class Controller {
 			}

 			// Store in global state
-			this.stateManager.setGlobalState("mcpMarketplaceCatalog", catalog)
+			this.cacheService.setGlobalState("mcpMarketplaceCatalog", catalog)
 			return catalog
 		} catch (error) {
 			console.error("Failed to fetch MCP marketplace:", error)
@@ -426,7 +422,7 @@ export class Controller {
 			}

 			// Store in global state
-			this.stateManager.setGlobalState("mcpMarketplaceCatalog", catalog)
+			this.cacheService.setGlobalState("mcpMarketplaceCatalog", catalog)
 			return catalog
 		} catch (error) {
 			console.error("Failed to fetch MCP marketplace:", error)
@@ -483,14 +479,14 @@ export class Controller {
 		const currentMode = await this.getCurrentMode()

 		// Update API configuration through cache service
-		const currentApiConfiguration = this.stateManager.getApiConfiguration()
+		const currentApiConfiguration = this.cacheService.getApiConfiguration()
 		const updatedConfig = {
 			...currentApiConfiguration,
 			planModeApiProvider: openrouter,
 			actModeApiProvider: openrouter,
 			openRouterApiKey: apiKey,
 		}
-		this.stateManager.setApiConfiguration(updatedConfig)
+		this.cacheService.setApiConfiguration(updatedConfig)

 		await this.postStateToWebview()
 		if (this.task) {
@@ -541,7 +537,7 @@ export class Controller {
 		taskMetadataFilePath: string
 		apiConversationHistory: Anthropic.MessageParam[]
 	}> {
-		const history = this.stateManager.getGlobalStateKey("taskHistory")
+		const history = this.cacheService.getGlobalStateKey("taskHistory")
 		const historyItem = history.find((item) => item.id === id)
 		if (historyItem) {
 			const taskDirPath = path.join(this.context.globalStorageUri.fsPath, "tasks", id)
@@ -576,9 +572,9 @@ export class Controller {

 	async deleteTaskFromState(id: string) {
 		// Remove the task from history
-		const taskHistory = this.stateManager.getGlobalStateKey("taskHistory")
+		const taskHistory = this.cacheService.getGlobalStateKey("taskHistory")
 		const updatedTaskHistory = taskHistory.filter((task) => task.id !== id)
-		this.stateManager.setGlobalState("taskHistory", updatedTaskHistory)
+		this.cacheService.setGlobalState("taskHistory", updatedTaskHistory)

 		// Notify the webview that the task has been deleted
 		await this.postStateToWebview()
@@ -593,40 +589,40 @@ export class Controller {

 	async getStateToPostToWebview(): Promise<ExtensionState> {
 		// Get API configuration from cache for immediate access
-		const apiConfiguration = this.stateManager.getApiConfiguration()
-		const lastShownAnnouncementId = this.stateManager.getGlobalStateKey("lastShownAnnouncementId")
-		const taskHistory = this.stateManager.getGlobalStateKey("taskHistory")
-		const autoApprovalSettings = this.stateManager.getGlobalStateKey("autoApprovalSettings")
-		const browserSettings = this.stateManager.getGlobalStateKey("browserSettings")
-		const focusChainSettings = this.stateManager.getGlobalStateKey("focusChainSettings")
-		const focusChainFeatureFlagEnabled = this.stateManager.getGlobalStateKey("focusChainFeatureFlagEnabled")
-		const preferredLanguage = this.stateManager.getGlobalStateKey("preferredLanguage")
-		const openaiReasoningEffort = this.stateManager.getGlobalStateKey("openaiReasoningEffort")
-		const mode = this.stateManager.getGlobalStateKey("mode")
-		const strictPlanModeEnabled = this.stateManager.getGlobalStateKey("strictPlanModeEnabled")
-		const useAutoCondense = this.stateManager.getGlobalStateKey("useAutoCondense")
-		const userInfo = this.stateManager.getGlobalStateKey("userInfo")
-		const mcpMarketplaceEnabled = this.stateManager.getGlobalStateKey("mcpMarketplaceEnabled")
-		const mcpDisplayMode = this.stateManager.getGlobalStateKey("mcpDisplayMode")
-		const telemetrySetting = this.stateManager.getGlobalStateKey("telemetrySetting")
-		const planActSeparateModelsSetting = this.stateManager.getGlobalStateKey("planActSeparateModelsSetting")
-		const enableCheckpointsSetting = this.stateManager.getGlobalStateKey("enableCheckpointsSetting")
-		const globalClineRulesToggles = this.stateManager.getGlobalStateKey("globalClineRulesToggles")
-		const globalWorkflowToggles = this.stateManager.getGlobalStateKey("globalWorkflowToggles")
-		const shellIntegrationTimeout = this.stateManager.getGlobalStateKey("shellIntegrationTimeout")
-		const terminalReuseEnabled = this.stateManager.getGlobalStateKey("terminalReuseEnabled")
-		const defaultTerminalProfile = this.stateManager.getGlobalStateKey("defaultTerminalProfile")
-		const isNewUser = this.stateManager.getGlobalStateKey("isNewUser")
+		const apiConfiguration = this.cacheService.getApiConfiguration()
+		const lastShownAnnouncementId = this.cacheService.getGlobalStateKey("lastShownAnnouncementId")
+		const taskHistory = this.cacheService.getGlobalStateKey("taskHistory")
+		const autoApprovalSettings = this.cacheService.getGlobalStateKey("autoApprovalSettings")
+		const browserSettings = this.cacheService.getGlobalStateKey("browserSettings")
+		const focusChainSettings = this.cacheService.getGlobalStateKey("focusChainSettings")
+		const focusChainFeatureFlagEnabled = this.cacheService.getGlobalStateKey("focusChainFeatureFlagEnabled")
+		const preferredLanguage = this.cacheService.getGlobalStateKey("preferredLanguage")
+		const openaiReasoningEffort = this.cacheService.getGlobalStateKey("openaiReasoningEffort")
+		const mode = this.cacheService.getGlobalStateKey("mode")
+		const strictPlanModeEnabled = this.cacheService.getGlobalStateKey("strictPlanModeEnabled")
+		const useAutoCondense = this.cacheService.getGlobalStateKey("useAutoCondense")
+		const userInfo = this.cacheService.getGlobalStateKey("userInfo")
+		const mcpMarketplaceEnabled = this.cacheService.getGlobalStateKey("mcpMarketplaceEnabled")
+		const mcpDisplayMode = this.cacheService.getGlobalStateKey("mcpDisplayMode")
+		const telemetrySetting = this.cacheService.getGlobalStateKey("telemetrySetting")
+		const planActSeparateModelsSetting = this.cacheService.getGlobalStateKey("planActSeparateModelsSetting")
+		const enableCheckpointsSetting = this.cacheService.getGlobalStateKey("enableCheckpointsSetting")
+		const globalClineRulesToggles = this.cacheService.getGlobalStateKey("globalClineRulesToggles")
+		const globalWorkflowToggles = this.cacheService.getGlobalStateKey("globalWorkflowToggles")
+		const shellIntegrationTimeout = this.cacheService.getGlobalStateKey("shellIntegrationTimeout")
+		const terminalReuseEnabled = this.cacheService.getGlobalStateKey("terminalReuseEnabled")
+		const defaultTerminalProfile = this.cacheService.getGlobalStateKey("defaultTerminalProfile")
+		const isNewUser = this.cacheService.getGlobalStateKey("isNewUser")
 		const welcomeViewCompleted = Boolean(
-			this.stateManager.getGlobalStateKey("welcomeViewCompleted") || this.authService.getInfo()?.user?.uid,
+			this.cacheService.getGlobalStateKey("welcomeViewCompleted") || this.authService.getInfo()?.user?.uid,
 		)
-		const customPrompt = this.stateManager.getGlobalStateKey("customPrompt")
-		const mcpResponsesCollapsed = this.stateManager.getGlobalStateKey("mcpResponsesCollapsed")
-		const terminalOutputLineLimit = this.stateManager.getGlobalStateKey("terminalOutputLineLimit")
-		const localClineRulesToggles = this.stateManager.getWorkspaceStateKey("localClineRulesToggles")
-		const localWindsurfRulesToggles = this.stateManager.getWorkspaceStateKey("localWindsurfRulesToggles")
-		const localCursorRulesToggles = this.stateManager.getWorkspaceStateKey("localCursorRulesToggles")
-		const workflowToggles = this.stateManager.getWorkspaceStateKey("workflowToggles")
+		const customPrompt = this.cacheService.getGlobalStateKey("customPrompt")
+		const mcpResponsesCollapsed = this.cacheService.getGlobalStateKey("mcpResponsesCollapsed")
+		const terminalOutputLineLimit = this.cacheService.getGlobalStateKey("terminalOutputLineLimit")
+		const localClineRulesToggles = this.cacheService.getWorkspaceStateKey("localClineRulesToggles")
+		const localWindsurfRulesToggles = this.cacheService.getWorkspaceStateKey("localWindsurfRulesToggles")
+		const localCursorRulesToggles = this.cacheService.getWorkspaceStateKey("localCursorRulesToggles")
+		const workflowToggles = this.cacheService.getWorkspaceStateKey("workflowToggles")

 		const currentTaskItem = this.task?.taskId ? (taskHistory || []).find((item) => item.id === this.task?.taskId) : undefined
 		const checkpointTrackerErrorMessage = this.task?.taskState.checkpointTrackerErrorMessage
@@ -640,7 +636,7 @@ export class Controller {
 		const latestAnnouncementId = getLatestAnnouncementId(this.context)
 		const shouldShowAnnouncement = lastShownAnnouncementId !== latestAnnouncementId
 		const platform = process.platform as Platform
-		const distinctId = getDistinctId()
+		const distinctId = PostHogClientProvider.getInstance().distinctId
 		const version = this.context.extension?.packageJSON?.version ?? ""
 		const uriScheme = vscode.env.uriScheme

@@ -714,14 +710,14 @@ export class Controller {
 	*/

 	async updateTaskHistory(item: HistoryItem): Promise<HistoryItem[]> {
-		const history = this.stateManager.getGlobalStateKey("taskHistory")
+		const history = this.cacheService.getGlobalStateKey("taskHistory")
 		const existingItemIndex = history.findIndex((h) => h.id === item.id)
 		if (existingItemIndex !== -1) {
 			history[existingItemIndex] = item
 		} else {
 			history.push(item)
 		}
-		this.stateManager.setGlobalState("taskHistory", history)
+		this.cacheService.setGlobalState("taskHistory", history)
 		return history
 	}
 }
@@ -19,8 +19,19 @@ export async function addRemoteMcpServer(controller: Controller, request: AddRem
 			throw new Error("Server URL is required")
 		}

-		// Call the McpHub method to add the remote server
-		const servers = await controller.mcpHub?.addRemoteServer(request.serverName, request.serverUrl)
+		// Optional inputs for first-class transport setup
+		const transportType = request.transportType || undefined
+		const headers = request.headers && Object.keys(request.headers).length > 0 ? request.headers : undefined
+		const timeout = typeof request.timeout === "number" && request.timeout > 0 ? request.timeout : undefined
+
+		// Call the McpHub method to add the remote server with transport details
+		const servers = await controller.mcpHub?.addRemoteServer(
+			request.serverName,
+			request.serverUrl,
+			transportType,
+			headers,
+			timeout,
+		)

 		const protoServers = convertMcpServersToProtoMcpServers(servers)

@@ -1,5 +1,6 @@
 import axios from "axios"
-import { SapAiCoreModelsRequest, SapAiCoreModelsResponse } from "@/shared/proto/cline/models"
+import { StringArray } from "@/shared/proto/cline/common"
+import { SapAiCoreModelsRequest } from "@/shared/proto/cline/models"
 import { Controller } from ".."

 interface Token {
@@ -35,19 +36,15 @@ async function getToken(clientId: string, clientSecret: string, tokenUrl: string
 }

 /**
- * Fetches model names and orchestration availability from SAP AI Core deployments
+ * Fetches model names from SAP AI Core deployments
 * @param accessToken Access token for authentication
 * @param baseUrl SAP AI Core base URL
 * @param resourceGroup SAP AI Core resource group
- * @returns Promise<{modelNames: string[], orchestrationAvailable: boolean}> Model names and orchestration availability
+ * @returns Promise<string[]> Array of model names from running deployments
 */
-async function fetchAiCoreModelsAndOrchestration(
-	accessToken: string,
-	baseUrl: string,
-	resourceGroup: string,
-): Promise<{ modelNames: string[]; orchestrationAvailable: boolean }> {
+async function fetchAiCoreModelNames(accessToken: string, baseUrl: string, resourceGroup: string): Promise<string[]> {
 	if (!accessToken) {
-		return { modelNames: ["ai-core-not-configured"], orchestrationAvailable: false }
+		return ["ai-core-not-configured"]
 	}

 	const headers = {
@@ -63,14 +60,8 @@ async function fetchAiCoreModelsAndOrchestration(
 		const response = await axios.get(url, { headers })
 		const deployments = response.data.resources

-		// Filter running deployments
-		const runningDeployments = deployments.filter((deployment: any) => deployment.targetStatus === "RUNNING")
-
-		// Check for orchestration deployment
-		const orchestrationAvailable = runningDeployments.some((deployment: any) => deployment.scenarioId === "orchestration")
-
-		// Extract model names from deployments
-		const modelNames = runningDeployments
+		return deployments
+			.filter((deployment: any) => deployment.targetStatus === "RUNNING")
 			.map((deployment: any) => {
 				const model = deployment.details?.resources?.backend_details?.model
 				if (!model?.name || !model?.version) {
@@ -79,8 +70,6 @@ async function fetchAiCoreModelsAndOrchestration(
 				return `${model.name}:${model.version}`
 			})
 			.filter((modelName: string | null) => modelName !== null)
-
-		return { modelNames, orchestrationAvailable }
 	} catch (error) {
 		console.error("Error fetching deployments:", error)
 		throw new Error("Failed to fetch deployments")
@@ -88,45 +77,29 @@ async function fetchAiCoreModelsAndOrchestration(
 }

 /**
- * Fetches available models from SAP AI Core deployments and orchestration availability
+ * Fetches available models from SAP AI Core deployments
 * @param controller The controller instance
 * @param request The request containing SAP AI Core configuration
- * @returns SapAiCoreModelsResponse with model names and orchestration availability
+ * @returns StringArray of model names
 */
-export async function getSapAiCoreModels(
-	controller: Controller,
-	request: SapAiCoreModelsRequest,
-): Promise<SapAiCoreModelsResponse> {
+export async function getSapAiCoreModels(controller: Controller, request: SapAiCoreModelsRequest): Promise<StringArray> {
 	try {
 		// Check if required configuration is provided
 		if (!request.clientId || !request.clientSecret || !request.baseUrl) {
-			// Return empty response if configuration is incomplete
-			return SapAiCoreModelsResponse.create({
-				modelNames: [],
-				orchestrationAvailable: false,
-			})
+			// Return empty array if configuration is incomplete
+			return StringArray.create({ values: [] })
 		}

-		// Direct authentication and model/orchestration fetching
+		// Direct authentication and model name fetching
 		const token = await getToken(request.clientId, request.clientSecret, request.tokenUrl)
-		const { modelNames, orchestrationAvailable } = await fetchAiCoreModelsAndOrchestration(
-			token.access_token,
-			request.baseUrl,
-			request.resourceGroup,
-		)
+		const modelNames = await fetchAiCoreModelNames(token.access_token, request.baseUrl, request.resourceGroup)

 		// Extract base model names (without version) and sort
-		const baseModelNames = modelNames.map((modelName: string) => modelName.split(":")[0].toLowerCase()).sort()
+		const baseModelNames = modelNames.map((modelName) => modelName.split(":")[0].toLowerCase()).sort()

-		return SapAiCoreModelsResponse.create({
-			modelNames: baseModelNames,
-			orchestrationAvailable,
-		})
+		return StringArray.create({ values: baseModelNames })
 	} catch (error) {
 		console.error("Error fetching SAP AI Core models:", error)
-		return SapAiCoreModelsResponse.create({
-			modelNames: [],
-			orchestrationAvailable: false,
-		})
+		return StringArray.create({ values: [] })
 	}
 }
@@ -22,7 +22,7 @@ export async function refreshBasetenModels(
 	const basetenModelsFilePath = path.join(await ensureCacheDirectoryExists(controller), GlobalFileNames.basetenModels)

 	// Get the Baseten API key from the controller's state
-	const basetenApiKey = controller.stateManager.getSecretKey("basetenApiKey")
+	const basetenApiKey = controller.cacheService.getSecretKey("basetenApiKey")

 	const models: Record<string, Partial<OpenRouterModelInfo>> = {}
 	try {
@@ -5,7 +5,7 @@ import { fileExistsAtPath } from "@utils/fs"
 import axios from "axios"
 import fs from "fs/promises"
 import path from "path"
-import { telemetryService } from "@/services/telemetry"
+import { telemetryService } from "@/services/posthog/PostHogClientProvider"
 import { groqModels } from "../../../shared/api"
 import { Controller } from ".."

@@ -18,7 +18,7 @@ import { Controller } from ".."
 export async function refreshGroqModels(controller: Controller, _request: EmptyRequest): Promise<OpenRouterCompatibleModelInfo> {
 	const groqModelsFilePath = path.join(await ensureCacheDirectoryExists(controller), GlobalFileNames.groqModels)

-	const groqApiKey = controller.stateManager.getSecretKey("groqApiKey")
+	const groqApiKey = controller.cacheService.getSecretKey("groqApiKey")

 	let models: Record<string, Partial<OpenRouterModelInfo>> = {}
 	try {
@@ -110,12 +110,6 @@ export async function refreshOpenRouterModels(

 				switch (rawModel.id) {
 					case "anthropic/claude-sonnet-4":
-						// NOTE: we artificially restrict the context window to 200k to keep costs low for users, and have a :1m model variant created below for users that want to use the full 1m.
-						modelInfo.contextWindow = 200_000
-						modelInfo.supportsPromptCache = true
-						modelInfo.cacheWritesPrice = 3.75
-						modelInfo.cacheReadsPrice = 0.3
-						break
 					case "anthropic/claude-3-7-sonnet":
 					case "anthropic/claude-3-7-sonnet:beta":
 					case "anthropic/claude-3.7-sonnet":
@@ -189,10 +183,6 @@ export async function refreshOpenRouterModels(
 						modelInfo.maxTokens = 8_192 // 128000 breaks context window truncation
 						modelInfo.contextWindow = 272_000 // openrouter reports 400k but the input limit is actually 400k-128k
 						break
-					case "x-ai/grok-code-fast-1":
-						modelInfo.supportsPromptCache = true
-						modelInfo.cacheReadsPrice = 0.02
-						break
 					default:
 						if (rawModel.id.startsWith("openai/")) {
 							modelInfo.cacheReadsPrice = parsePrice(rawModel.pricing?.input_cache_read)
@@ -19,7 +19,7 @@ export async function refreshRequestyModels(controller: Controller, _: EmptyRequ

 	const models: Record<string, OpenRouterModelInfo> = {}
 	try {
-		const apiKey = controller.stateManager.getSecretKey("requestyApiKey")
+		const apiKey = controller.cacheService.getSecretKey("requestyApiKey")
 		const headers = {
 			Authorization: `Bearer ${apiKey}`,
 		}
@@ -24,7 +24,7 @@ export async function updateApiConfigurationProto(
 		const appApiConfiguration = convertProtoToApiConfiguration(request.apiConfiguration)

 		// Update the API configuration in storage
-		controller.stateManager.setApiConfiguration(appApiConfiguration)
+		controller.cacheService.setApiConfiguration(appApiConfiguration)

 		// Update the task's API handler if there's an active task
 		if (controller.task) {
--- a/Show More
+++ b/Show More