# AI use cases for Omni Copilot (diegosouzapw/OmniCopilot) Repo: [diegosouzapw/OmniCopilot](https://github.com/diegosouzapw/OmniCopilot) | Use cases: 4 | Page: https://dedupedai.com/use-cases/diegosouzapw-omnicopilot/ A VS Code extension that adds the models from your OmniRoute server to the GitHub Copilot Chat model picker. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Add OmniRoute models to your Copilot Chat picker: https://dedupedai.com/use-cases/diegosouzapw-omnicopilot/add-many-models-to-copilot-chat/ - Point Copilot Chat at a remote OmniRoute server: https://dedupedai.com/use-cases/diegosouzapw-omnicopilot/connect-copilot-to-remote-omniroute/ - Set reasoning effort for thinking models in Chat: https://dedupedai.com/use-cases/diegosouzapw-omnicopilot/set-reasoning-effort-for-thinking-models/ - Configure Codex, Claude Code and Cursor for OmniRoute: https://dedupedai.com/use-cases/diegosouzapw-omnicopilot/configure-coding-clis-for-omniroute/ ## How to add OmniRoute models to your Copilot Chat picker with Omni Copilot Repo: [diegosouzapw/OmniCopilot](https://github.com/diegosouzapw/OmniCopilot) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Install OmniRoute and this extension, then tick the models you want in Copilot Chat. **Who it is for:** A developer who already uses Copilot Chat and wants access to models from other providers without learning a new chat interface. **The problem:** Copilot Chat only offers the models in its own picker, and you want Claude, GPT, Gemini, DeepSeek or Qwen models in the same chat. **The outcome:** Your selected OmniRoute models appear in the Copilot Chat model dropdown and work for chat and agent mode. ### Steps 1. Run `npm install -g omniroute` in a terminal. 2. Run `omniroute` and open the dashboard at http://localhost:20128 to add your providers or use the built-in free ones. 3. In VS Code, search the Extensions view for "OmniRoute" and install the extension. 4. Open Copilot Chat, click the model picker, choose Manage Models, select OmniRoute and tick the models you want. ### Prompt to paste into your agent ```text Using the diegosouzapw/OmniCopilot README, set up the OmniRoute extension for a VS Code install located at . Confirm the OmniRoute server answers at http://localhost:20128 and report the number of models listed in the status-bar or Activity Bar panel. Verify that at least one OmniRoute model appears in the Copilot Chat model picker after Manage Models is used. ``` ### Caveat Inline code completions and embeddings-based features still require GitHub Copilot, so this covers chat and agent mode only. 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/diegosouzapw-omnicopilot/add-many-models-to-copilot-chat/ ## How to point Copilot Chat at a remote OmniRoute server with Omni Copilot Repo: [diegosouzapw/OmniCopilot](https://github.com/diegosouzapw/OmniCopilot) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Use a home server, VPS or tunnel running OmniRoute as the model source for VS Code. **Who it is for:** A developer who runs OmniRoute on another machine and needs the same models in VS Code on a laptop. **The problem:** The OmniRoute server is not on localhost, and the extension needs the correct URL and an API key if the server requires one. **The outcome:** The extension connects to your remote OmniRoute server, the status-bar dot turns to reachable and the models load from that server. ### Steps 1. Click the OmniRoute icon in the Activity Bar, or run `OmniRoute: Manage Connection`. 2. Enter the Server URL, for example http://my-vps:20128. The /v1 suffix is added automatically. 3. If your OmniRoute requires one (REQUIRE_API_KEY), enter the API key. It is stored in the OS keychain. 4. Click Save & Test and check the live model count shown in the panel. ### Prompt to paste into your agent ```text Using the diegosouzapw/OmniCopilot README, configure the extension to use the remote OmniRoute server at . Save the connection and report the live model count shown by Save & Test. Verify that the status-bar dot shows the server as reachable and that the API key is not written into settings.json. ``` ### Caveat The README says the server must be reachable from your VS Code machine, and it does not describe how to set up the tunnel or VPS itself. Risk, credentials: The API key for your OmniRoute server is entered in the extension panel and stored in the OS keychain, so only use a key you are allowed to share with this machine. 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/diegosouzapw-omnicopilot/connect-copilot-to-remote-omniroute/ ## How to set reasoning effort for thinking models in Chat with Omni Copilot Repo: [diegosouzapw/OmniCopilot](https://github.com/diegosouzapw/OmniCopilot) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Control how hard reasoning models think by choosing an effort tier in chat or in settings. **Who it is for:** A developer who uses reasoning models such as GPT-5.x, Claude with thinking or DeepSeek R1 and wants to trade speed for depth. **The problem:** Reasoning models respond at a fixed depth unless you set an effort level, and you want a default when the editor shows no effort control. **The outcome:** Your chosen effort tier is sent to OmniRoute as reasoning_effort for models that support extended thinking. ### Steps 1. Pick a reasoning-capable model in the Copilot Chat model picker. 2. If VS Code shows an effort control next to the model, choose the tier there; the choice is forwarded automatically. 3. If no control is shown, open settings and set `omnicopilot.defaultReasoningEffort` to none, low, medium, high or xhigh. 4. Send a test prompt and confirm the response reflects the chosen level. ### Prompt to paste into your agent ```text Using the diegosouzapw/OmniCopilot README, set omnicopilot.defaultReasoningEffort to in the VS Code settings for . Report which models the setting applies to. Verify that an explicit choice in the chat UI overrides the setting. ``` ### Caveat The default applies only to models the catalog marks as reasoning-capable, so it is ignored for other models. 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/diegosouzapw-omnicopilot/set-reasoning-effort-for-thinking-models/ ## How to configure Codex, Claude Code and Cursor for OmniRoute with Omni Copilot Repo: [diegosouzapw/OmniCopilot](https://github.com/diegosouzapw/OmniCopilot) | Difficulty: Advanced | Time: 30 minutes | Basis: From the README Generate ready-to-use OmniRoute profiles for your coding CLIs from one VS Code command. **Who it is for:** A developer who uses Codex CLI, Claude Code or Cursor and wants all of them to route through the same OmniRoute server. **The problem:** Each coding tool needs its own configuration to reach OmniRoute, and setting them up one by one takes time. **The outcome:** Profiles or tool-native config for the chosen coding tool point at your OmniRoute server. ### Steps 1. Make sure the `omniroute` CLI is installed and reachable at the path set in `omnicopilot.cliPath`. 2. Run the command `OmniRoute: Configure Coding CLI` from the VS Code command palette. 3. Pick the tool, such as Codex CLI or Claude Code, and let the extension generate the profile. 4. Launch the tool with its profile, for example `codex --profile glm52` for Codex CLI or `omniroute launch --profile` for Claude Code. ### Prompt to paste into your agent ```text Using the diegosouzapw/OmniCopilot README, run the Configure Coding CLI flow for on this machine. Report the profile file or launch command it produced. Verify that the generated profile points to the OmniRoute server URL in omnicopilot.baseUrl. ``` ### Caveat The README says the extension drives the omniroute CLI, so that CLI must be installed and working before this command produces anything. 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/diegosouzapw-omnicopilot/configure-coding-clis-for-omniroute/