GitHub Copilot · json
// VS Code: Chat: Manage Language Models → Add Models → Custom Endpoint (chatLanguageModels.json)
[
{
"name": "Intertrace",
"vendor": "customendpoint",
"apiKey": "${input:intertraceRuntimeKey}",
"apiType": "chat-completions",
"models": [
{ "id": "gpt-4o-mini", "name": "GPT-4o mini via Intertrace", "url": "https://intertrace.fly.dev/v1/chat/completions", "toolCalling": true }
]
}
]
// Copilot CLI: itr connect copilot (pre-tool hook)Copilot Chat: a Custom Endpoint model on /v1 with an itr_rt_* key (chat and agent mode). Copilot CLI: itr connect copilot.
+Three steps
- 01
Get a runtime key
Create an itr_rt_* key in Connect. It carries your tenant, so no org headers are needed.
- 02
Point the client at Intertrace
Paste the snippet. Nothing else in your code changes.
- 03
Watch decisions arrive
Every call shows up in Traffic with its verdict and the reason, in monitor mode first.
+What you get
Once it's connected
- Prompts and completions inspected in both directions
- Secrets and credentials kept out of model traffic
- Risky tool use flagged or blocked by policy
- Every request attributed to the agent that made it
+Related
+ The AI watching your AI
Protect your GitHub Copilot agents today.
Start in monitor mode, see every decision, then turn on enforcement when you're ready.