Served Requests
Live
Pane type
Live feed of OpenAI-compatible served requests. Each row surfaces the route, model, latency, and status of a request handled by senkani's local serving endpoint.
What it shows
When senkani is fronting an OpenAI-compatible API, this pane streams every served request as it lands — method and path, the requested model, token counts, latency, and the response status. It is the request-level companion to the aggregate numbers in Analytics.
Keyboard
Open via ⌘K → type the pane name. Close with ⌘W. Focus with ⌘+digit (the pane's position on the canvas).