# AI use cases for Route VSCODE (yudaprasetya007/routeVSCODE)

Repo: [yudaprasetya007/routeVSCODE](https://github.com/yudaprasetya007/routeVSCODE) | Use cases: 3 | Page: https://dedupedai.com/use-cases/yudaprasetya007-routevscode/

A VSCode extension and local web dashboard that route GitHub Copilot Chat through a local proxy to the 9Router AI gateway, so the active model can be switched without reloading the window.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Switch Copilot Chat models without reloading VSCode: https://dedupedai.com/use-cases/yudaprasetya007-routevscode/switch-copilot-chat-model-without-reload/
- Compare AI model replies and latency side by side: https://dedupedai.com/use-cases/yudaprasetya007-routevscode/compare-model-replies-and-latency/
- Set up the Copilot model connector with one script: https://dedupedai.com/use-cases/yudaprasetya007-routevscode/set-up-connector-with-one-script/

## How to switch Copilot Chat models without reloading VSCode with Route VSCODE

Repo: [yudaprasetya007/routeVSCODE](https://github.com/yudaprasetya007/routeVSCODE) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Route Copilot Chat through a local proxy and change the active AI model in one click.

**Who it is for:** A developer who uses Copilot Chat daily and wants to try Claude, GPT, Gemini or DeepSeek models without editing config files or restarting VSCode.

**The problem:** Changing the model in Copilot Chat normally means editing JSON configuration and reloading the window, which breaks flow.

**The outcome:** Copilot Chat sends requests through the local proxy on port 20129, and the active model can be changed from the dashboard or the status bar while the chat session stays open.

### Steps

1. Install the gateway with `npm install -g 9router`, then start it in a separate terminal with `9router`.
2. Clone the repo with `git clone https://github.com/yudaprasetya007/routeVSCODE.git` and open the folder with `cd routeVSCODE`.
3. Install the extension with `code --install-extension releases/routevscode.model-connector-2.5.0.vsix --force`.
4. Start the dashboard with `npm start` and open http://localhost:5500.
5. In VSCode press Ctrl+Shift+P, run `9Router: Set API Key & Base URL`, enter `http://localhost:20128/v1` and your 9Router API Key.
6. Open Copilot Chat with Ctrl+Alt+I, choose `9Router via Proxy` in the Model Picker, then switch models from the dashboard or the status bar.

### Prompt to paste into your agent

```text
Using the repo yudaprasetya007/routeVSCODE, install the VSCode extension from releases/routevscode.model-connector-2.5.0.vsix and start the dashboard with npm start, then confirm that http://localhost:5500 loads. Set the model to <target model name> from the dashboard and report the active model shown in the status bar; verify that port 20129 is listening before reporting success.
```

### Caveat

The README says a Model Picker reload may be needed after first install, so expect to run Developer: Reload Window once.

Risk, credentials: The 9Router API Key is entered into VSCode settings and forwarded through the local proxy, so keep it out of shared screens, logs and committed files.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/yudaprasetya007-routevscode/switch-copilot-chat-model-without-reload/

## How to compare AI model replies and latency side by side with Route VSCODE

Repo: [yudaprasetya007/routeVSCODE](https://github.com/yudaprasetya007/routeVSCODE) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Send one prompt to several models in the dashboard and measure response latency.

**Who it is for:** A developer or team lead choosing which AI model to use for a coding task and needing evidence from their own prompts.

**The problem:** Picking a model from marketing claims or memory is slow and gives no comparison on real prompts and response time.

**The outcome:** You see replies from different models next to each other with their latency, which helps choose a default model for Copilot Chat.

### Steps

1. Start the gateway with `9router` in one terminal.
2. Start the dashboard with `npm start` in the repo folder.
3. Open http://localhost:5500 in the browser and select two or more models in the dashboard. (inferred, check the README)
4. Enter the same test prompt for every selected model and run the comparison. (inferred, check the README)
5. Read the replies and latency values side by side and note the model that fits your task. (inferred, check the README)

### Prompt to paste into your agent

```text
Using the repo yudaprasetya007/routeVSCODE, start the 9Router gateway and the dashboard with npm start, then run the Live Model Comparison with the prompt <test prompt> on the models <model list>. Report each model's reply length and measured latency, and verify that every selected model returned a response before giving a recommendation.
```

### Caveat

The README lists the comparison feature but does not describe its controls, so the UI steps above are inferred and should be checked against the running dashboard.

Risk, credentials: Each provider call uses the API Key configured in 9Router, so only run comparisons on accounts you are allowed to use.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/yudaprasetya007-routevscode/compare-model-replies-and-latency/

## How to set up the Copilot model connector with one script with Route VSCODE

Repo: [yudaprasetya007/routeVSCODE](https://github.com/yudaprasetya007/routeVSCODE) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Run the platform setup script to install the extension and prepare the connector.

**Who it is for:** A team lead or new developer onboarding several machines to Copilot Chat with 9Router on Windows, Linux or macOS.

**The problem:** Manual install of the gateway, extension and dashboard across machines takes many steps and is easy to get wrong.

**The outcome:** The connector is installed on the machine using the setup script for that platform, ready for the API Key and model selection steps.

### Steps

1. Open a terminal in the folder where you cloned the repo.
2. On Windows, run `scripts\setup.bat` or `npm run setup`.
3. On Linux or macOS, run `chmod +x scripts/setup.sh` and then `./scripts/setup.sh`.
4. Run `9router` in a separate terminal and open http://localhost:20128/dashboard to get your API Key.
5. In VSCode, run `9Router: Set API Key & Base URL` and then choose `9Router via Proxy` in the Copilot Chat Model Picker.

### Prompt to paste into your agent

```text
Using the repo yudaprasetya007/routeVSCODE, run the setup script for this platform (scripts/setup.sh on Linux or macOS, scripts\setup.bat on Windows) and report the output. Verify that the file releases/routevscode.model-connector-2.5.0.vsix was installed into VSCode and that the command `9Router: Status & Info` shows the proxy port 20129.
```

### Caveat

Port 20129 must be free, and the README notes that an older VSCode instance can keep it busy and cause a proxy port conflict.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/yudaprasetya007-routevscode/set-up-connector-with-one-script/