Read my last turn
read_my_last_turnInspect the last LLMxRay turn to get token counts, timing, VRAM fit, and prompt mismatch data. Use it to budget your next call or verify a change helped.
Instructions
The most recent turn seen through LLMxRay, as numbers: prompt tokens and cached share, prefill time and speed, generated tokens and speed, stop reason, prompt make-up (system, tools, history, new message), context requested, VRAM fit, and where the prompt stopped matching the previous turn. Use it to budget the next call or to confirm a change helped. For a verdict across turns use diagnose_my_turns. For what is installed and loaded use list_local_models. Returns text, one fact per line. Explains how to route through 11435 when no turn was seen. client: a substring of the label LLMxRay shows, which is the name you set in X-LLMxRay-Client. On a shared machine the latest turn may be another tool's, so pass your own name. Omit it when you are the only caller. Needs LLMxRay running (npx llmxray) and says so if not. Under a second, from records already kept. No model is called.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| client | No | Part of the client label or id, case-insensitive substring. Omit for the latest turn from any client. |